Apparatus and method for measuring multiple blood parameters by artificial intelligence

Abstract

The invention relates to a device and a method for measuring a plurality of blood parameters by artificial intelligence. The invention provides for: exciting blood with electromagnetic radiation of a plurality of determined wavelengths; receiving analog information about a plurality of electromagnetic and / or optical responses of the blood, the plurality of electromagnetic and / or optical responses comprising electromagnetic radiation backscattered or diffused by the blood; converting the analog electromagnetic and / or optical response information into digital electromagnetic and / or optical response data; processing the digital electromagnetic and / or optical response data and an actual temperature value of the blood by means of a neural network; determining a value of each parameter as a result of the processing; determining a plurality of ratios of optical counts; providing the plurality of ratios and the temperature value as input to the neural network; processing the plurality of ratios by the neural network taking into account a plurality of data in previous measurements of blood parameters made during a previous training; providing the value of each parameter as output of the neural network. The device can be coupled to a test tube or directly to a tube of an extracorporeal blood circuit.

Description

Technical Field

[0001] This invention relates to an apparatus and method for measuring multiple blood parameters using artificial intelligence.

[0002] The apparatus and method according to the invention enable the measurement of parameters in an extracorporeal blood circuit.

[0003] The present invention also relates to the use of the device and equipment including the device.

[0004] This invention can be applied to monitor blood parameters during treatments that require extracorporeal blood circulation, such as hemodialysis, plasma exchange, extracorporeal respiratory support (ECMO), preservation of transplanted organs, and cancer treatment. Background Technology

[0005] The probe is known to measure multiple blood parameters in an extracorporeal blood circuit.

[0006] This type of probe is known from international patent application WO 2010136962A1 filed in the applicant's name in 2010. Such a probe includes a housing for containing a catheter for blood flowing in an extracorporeal circuit, a transmitting device and a device for detecting electromagnetic radiation, and a control unit to which the transmitting and detecting devices are connected. The control unit calculates the value of the blood parameters by means of a correlation between a reference value and a ratio obtained from the light intensity value of the detected radiation; this correlation utilizes a complex mathematical formula.

[0007] The probe of WO 2010136962A1 has several drawbacks; in particular, the complex mathematical formulas used cannot guarantee optimal accuracy of the measurement parameters. Another drawback is the inaccuracy of measurements when the blood catheter attached to the probe is changed to a different formulation; these different catheters may have different stiffness and different colors (due to chemical additives used in their manufacture) compared to the previous catheter (more or less rigid), but the probe does not have the necessary accuracy to account for these differences. Therefore, the applicant points out that the measurement accuracy and speed of parameter measurement of the probe of WO 2010136962A1 can be improved and improvements have been made accordingly.

[0008] The purpose of this invention

[0009] Therefore, the main objective of this invention is to provide an apparatus for measuring multiple blood parameters that overcomes the disadvantages associated with the prior art described above.

[0010] The object of this invention is to provide a device for measuring multiple blood parameters that does not require calibration by the end user before use.

[0011] Another objective of this invention is to provide a method for measuring multiple blood parameters so that end users do not need to perform any calibration before measurement.

[0012] An additional object of the present invention is to provide an apparatus and method for rapidly, efficiently and reliably measuring multiple blood parameters.

[0013] The present invention also aims to provide a device capable of autonomously and with high accuracy measuring multiple blood parameters throughout the entire measurement range of each parameter.

[0014] These and other objectives are achieved by means of the apparatus, the use of the apparatus, the device, and one or more methods as described below and in accordance with the following aspects. Summary of the Invention

[0015] Various aspects of the invention are described herein. Such an aspect may be combined with another aspect when one aspect refers to one or more elements, steps, or operations introduced by the other aspect by means of specific relevance to one or more other aspects and / or by wording such as “the” or “the”.

[0016] The present invention provides an apparatus (probe) for measuring multiple blood parameters, the apparatus being equipped with a control unit that enables the apparatus to measure the parameters based on multiple data points from previous measurements of the parameters taken during prior training.

[0017] The control unit enables the device to be intelligent and is responsible for performing measurements autonomously. To achieve this, the control unit incorporates an coded computational model (using program code) derived from multiple data points derived from previous measurements of blood parameters taken during prior training. Essentially, the device learns from previous training and is therefore immediately ready for clinical use without requiring prior calibration by the end user.

[0018] After a series of devices have been trained, a methodology (e.g., a model coded in firmware and / or one or more algorithms) is developed that enables subsequent devices to be used with simple calibrations, such as those performed by the device manufacturer in a laboratory. The end user only needs to use the device after connecting it to a tubular element (test tube) or a tube connected to an extracorporeal blood circuit, without having to perform any calibration.

[0019] Each device preferably stores two types of information: the first type of information is common to devices produced after the learning and relates to the “computation mechanism” of parameter values ​​via a neural network (this type of information is preferably encoded in the device’s firmware); the second type of information can vary for each device, for example due to the variability of hardware, components and their specific geometric location within the device’s housing (this type of information is preferably stored in the device’s memory).

[0020] The numbering of this invention is as follows.

[0021] Device for measuring multiple blood parameters

[0022] 1. A device for measuring multiple blood parameters using artificial intelligence, the device comprising:

[0023] - At least one excitation element is configured to excite blood, particularly blood flow, with electromagnetic radiation of multiple defined wavelengths.

[0024] - At least one electromagnetic radiation detection component, particularly at least one photodetector, is configured to detect multiple electromagnetic responses of blood, particularly optical responses, said multiple electromagnetic responses including electromagnetic radiation, particularly light, reflected or diffused by the blood after excitation by the excitation component in the operating state of the device.

[0025] 2. A device for measuring multiple blood parameters using artificial intelligence, the device comprising:

[0026] - At least one excitation element is configured to excite blood flow at multiple defined wavelengths.

[0027] - At least one photodetector is configured to detect multiple electromagnetic and / or optical responses of blood, said multiple electromagnetic and / or optical responses including light reflected or diffused by the blood after being excited by the excitation element in the operating state of the device.

[0028] 3. According to aspect 1 or 2, wherein the device further includes a control unit configured to perform the following operations:

[0029] During the excitation step, at least one excitation element is commanded to excite the blood with electromagnetic radiation of multiple defined wavelengths.

[0030] o Receives analog information relating to multiple electromagnetic and / or optical responses of blood, including electromagnetic radiation reflected or diffused by blood, particularly light.

[0031] o Convert analog information of electromagnetic and / or optical response into digital data of electromagnetic and / or optical response.

[0032] o The electromagnetic and / or optical response digital data, along with the actual temperature value of the blood, are processed by one or more neural networks.

[0033] o is the result of processing operations of one or more neural networks, determining the value of each of multiple blood parameters.

[0034] 4. According to aspect 3, the control unit is configured to process the electromagnetic and / or optical response digital data and the actual temperature value of the blood via one or more neural networks and determine the value of each of the plurality of blood parameters by means of:

[0035] o Define multiple ratios, each defined between a value indicating the amount of radiation reflected or diffused by blood due to excitation of a defined wavelength and a value indicating the amount of radiation reflected or diffused by blood due to excitation of another defined wavelength.

[0036] o serves as input to one or more neural networks, providing the multiple ratios and temperature values.

[0037] o The multiple ratios are processed by using one or more neural networks that consider multiple data points from previous measurements of the blood parameters taken during previous training.

[0038] o, as the output of one or more neural networks, provides the value of each of the multiple blood parameters.

[0039] 5. According to any of the foregoing aspects, wherein the device includes a temperature sensor configured to measure the actual temperature of the blood.

[0040] 6. According to any of the foregoing aspects, wherein the device is configured to simultaneously measure multiple blood parameters via artificial intelligence.

[0041] 7. According to any of the foregoing aspects, wherein the control unit is configured to detect the value of each of the plurality of blood parameters that the artificial intelligence believes corresponds to a previously determined ratio based on the plurality of data from previous measurements.

[0042] 8. According to any of the foregoing aspects, wherein the device includes firmware and the control unit includes artificial intelligence information, such as one or more matrices available from the one or more neural networks, the artificial intelligence information being encoded in the firmware and enabling the computation of the plurality of parameters by the one or more neural networks.

[0043] The information encoded in the firmware is "the same for all devices".

[0044] 9. According to any of the foregoing aspects, wherein the device includes a memory, and a control unit is configured to provide reference values ​​for a first parameter to be measured and a second parameter to be measured as input to one or more neural networks, the reference values ​​preferably being acquired and stored in the memory of the device during a calibration step prior to using the device, the memory thus including information relating to the reference values.

[0045] 10. According to any of the foregoing aspects, wherein the device includes a memory that includes one or more pieces of information uniquely associated with the calibration steps of the device, such as one or more matrices that can be used by the one or more neural networks.

[0046] 11. According to any of the foregoing aspects, wherein the device calibration steps are performed by the manufacturer of the device.

[0047] 12. According to any of the foregoing aspects, wherein the calibration steps are not performed by the end user of the device.

[0048] 13. According to any of the foregoing aspects, wherein the calibration step is not performed during or before the use of the device.

[0049] The information and / or reference parameters stored in the device's memory are specific to each manufactured device and take into account variability between devices (due to, for example, variability in hardware, components, and even infinitesimal geometric positions within the device's housing), and provide a robust starting point for the measurement of oxygen saturation and hematocrit expected in the calibrated state.

[0050] 14. According to any of the foregoing aspects, wherein the control unit includes a microprocessor, and the information is encoded in the firmware of the microprocessor.

[0051] 15. According to any of the foregoing aspects, wherein the device is configured to measure blood oxygen saturation (SatO2), hematocrit (Hct), and optionally also to measure hemoglobin content (Hb) by means of artificial intelligence.

[0052] 16. According to any of the foregoing aspects, wherein the control unit is configured to control the at least one or both excitation elements during an excitation step involving exciting blood flow one wavelength at a time.

[0053] 17. According to any of the foregoing aspects, wherein the apparatus includes a plurality of excitation elements, and the control unit is configured to control the plurality of excitation elements during an excitation step to activate the plurality of excitation elements according to a determined time sequence.

[0054] 18. According to any of the foregoing aspects, wherein the at least one excitation element is configured to excite blood flow at least at the following wavelengths: 660 nm, 805 nm, 1450 nm and at least one between 525 nm, 940 nm and 1050 nm.

[0055] 19. According to any of the foregoing aspects, wherein the at least one excitation element is configured to excite blood flow at at least the following wavelengths: 660 nm, 805 nm, 1450 nm and at least two of the wavelengths between 525 nm, 940 nm and 1050 nm.

[0056] 20. According to any of the foregoing aspects, wherein the at least one excitation element is configured to excite blood flow at at least the following wavelengths: 660 nm, 805 nm, 1450 nm, 525 nm, 940 nm and 1050 nm.

[0057] 21. According to any of the foregoing aspects, wherein the device comprises: a first excitation member configured to excite blood flow at least at a first wavelength, particularly at a first plurality of wavelengths; and a second excitation member configured to excite blood flow at least at a second wavelength, particularly at a second plurality of wavelengths.

[0058] 22. According to aspect 21, wherein the control unit is configured to preferably alternately activate the first excitation member and the second excitation member to preferably alternately excite blood flow at a first wavelength or a first plurality of wavelengths and at a second wavelength or a second plurality of wavelengths.

[0059] 23. The aspect according to any of the foregoing aspects, wherein the device includes a first excitation member and a second excitation member.

[0060] 24. According to aspect 23, wherein the first excitation member and the second excitation member are configured to excite blood at corresponding plurality of different wavelengths.

[0061] 25. According to aspect 23 or 24, wherein the first excitation member is configured to excite blood flow at wavelengths of 525 nm, 940 nm, and optionally 1050 nm.

[0062] 26. According to aspect 23 or 24 or 25, wherein the second excitation element is configured to excite blood flow at wavelengths of 660 nm, 805 nm, and 1450 nm.

[0063] 27. According to any of the foregoing aspects, wherein each excitation member comprises a plurality of LED elements configured to emit light radiation of the wavelength, particularly a plurality of LED elements equal in number to the wavelength at which each LED is configured to operate.

[0064] 28. According to any one of aspects 23 to 27, wherein the first excitation member and the second excitation member are arranged in the housing.

[0065] 29. According to any one of aspects 23 to 28, wherein the first excitation member and the second excitation member are arranged side by side.

[0066] 30. According to any of the foregoing aspects, wherein the device includes a first electromagnetic radiation detection component and a second electromagnetic radiation detection component, each electromagnetic radiation detection component being configured to detect a plurality of electromagnetic and / or optical responses of blood, particularly detecting a plurality of electromagnetic and / or optical responses of blood at different wavelengths.

[0067] 31. According to any of the foregoing aspects, wherein the device includes a first photodetector and a second photodetector, each photodetector being configured to detect a plurality of electromagnetic and / or optical responses of blood, particularly detecting a plurality of electromagnetic and / or optical responses of blood at different wavelengths.

[0068] 32. According to aspect 31, wherein the first photodetector and the second photodetector are arranged inside the housing.

[0069] 33. According to aspect 31 or 32, wherein the first photodetector and the second photodetector are arranged side by side.

[0070] 34. According to aspect 31 or 32 or 33, wherein the first photodetector and the second photodetector are configured to detect blood responses at corresponding plurality of different wavelengths.

[0071] 35. According to any one of aspects 31 to 34, wherein the first photodetector is configured to detect the light response of blood when excited at the following wavelengths: 660 nm, 805 nm, 525 nm, 1050 nm, and 940 nm.

[0072] 36. According to any one of aspects 31 to 35, wherein the second photodetector is configured to detect the light response of blood when excited at wavelengths of 805 nm and 1450 nm.

[0073] 37. According to any of the foregoing aspects, the device includes a housing in which the at least one or each excitation element, the at least one or each electromagnetic radiation detection element, and the control unit are housed.

[0074] 37 of 2. According to any of the foregoing aspects, wherein the device, in particular the housing, includes a coupling portion configured to allow coupling of the device with the container.

[0075] 37 of three. According to aspects 37 and 37 of two, wherein the coupling portion is connected to or engaged with the housing and / or integrated with the housing.

[0076] 37 of four. According to the aspect described in 37 of two or three, wherein the coupling portion is configured to allow coupling of the housing to the container.

[0077] 37 of 5. According to any of the foregoing aspects, wherein the device, in particular the housing, is substantially miniature.

[0078] 37 of 6. According to any of the foregoing aspects, wherein the device, in particular the housing, has one or more feature dimensions (e.g., width, height, and length) less than 100 mm, preferably each feature dimension less than 100 mm.

[0079] 37 of six. According to any of the foregoing aspects, wherein the device does not include a screen.

[0080] Streaming information

[0081] 38. According to any of the foregoing aspects, wherein the control unit is configured to take into account blood flow-related values, particularly the volumetric flow rate of blood, when measuring oxygen saturation and / or hematocrit.

[0082] 39. According to any of the foregoing aspects, wherein the control unit is configured to take into account the operation of blood flow-related values ​​by correcting the measured values ​​of oxygen saturation and / or hematocrit in the measurement of oxygen saturation and / or hematocrit of blood flow.

[0083] 40. According to any of the foregoing aspects, wherein the control unit is configured to preferably make the value of each of the plurality of blood parameters available at the same time.

[0084] Implementation method for test tubes

[0085] 41. According to any of the foregoing aspects, wherein the device includes a coupling portion connected to the housing and including at least one coupling element, the coupling portion being configured to present:

[0086] o is coupled configuration, wherein the coupled configuration is coupled to a container by means of at least one coupling element, the container being capable of containing blood and / or allowing blood to flow therein.

[0087] o Decoupled configuration, where the decoupled configuration is not coupled to the container.

[0088] 42. According to aspect 41, wherein the at least one coupling element is magnetic and configured to allow magnetic coupling with the container.

[0089] 43. According to any of the foregoing aspects, the device includes a first coupling element and a second coupling element, the first coupling element and the second coupling element being arranged at opposite longitudinal portions of the device and configured to couple with corresponding magnetic elements located at respective longitudinal portions or ends of the container.

[0090] 44. According to any of the foregoing aspects, wherein each coupling element is magnetic and configured to allow magnetic coupling with the container.

[0091] Implementation methods for pipes

[0092] 45. According to any of the foregoing aspects, wherein the device is associated with a container, such as a tube, into which blood can flow in during operation, the device being associated with the container.

[0093] 46. ​​According to any of the foregoing aspects, wherein the control unit is configured to perform the following operations:

[0094] - Inspect the type of container, especially the type of pipe.

[0095] - Based on the detected container type, especially the tube type, prepare to perform measurements.

[0096] 47. According to aspect 46, wherein the control unit is configured to prepare for measurement based on the type of the detected container or tube by adapting the measurement mode of one or more parameters to operation with respect to the type of the detected container or tube.

[0097] 48. According to aspect 46 or 47, wherein the control unit is configured to detect the type of container or tube and prepare for measurement based on the detected type of container or tube prior to operation of exciting blood flow at a plurality of defined wavelengths.

[0098] 49. According to aspect 46 or 47 or 48, wherein the control unit is configured to detect the color of the container, in particular the color of the tube.

[0099] 50. According to any one of aspects 46 to 49, wherein the control unit is configured to perform an operation to prepare for measurement based on the detected type or color of a container or tube by selecting a determined matrix from a plurality of matrices available from a neural network.

[0100] 51. According to aspect 50, wherein the control unit is configured to select a determined matrix from a plurality of matrices available from a neural network by querying a memory storing information relating to the plurality of matrices.

[0101] 52. According to any of the foregoing aspects, wherein the device includes a housing, a cover element movable relative to the housing, and a base adapted to receive a portion of a tube, particularly an extracorporeal blood circuit, wherein, in an operational state of the device, blood flows into the container, and the cover element is configured to operate at least between the following configurations:

[0102] - Operational configuration, in which it flattens the relative surfaces of the container housed at the base.

[0103] - Rest configuration.

[0104] 53. According to aspect 52, wherein the covering element is movable by rotation relative to the housing.

[0105] 54. According to aspect 52 or 53, the covering element includes a compression element for compressing a container housed at the base in an operational configuration of the covering element.

[0106] 55. According to aspect 54, wherein the compression element is configured to determine a reduction of the fluid passage cross-section of the container by between 9% and 17%.

[0107] 56. According to aspect 55, wherein the reduction in the cross-sectional area of ​​the fluid channel occurs at a length between 15 mm and 30 mm or equal to one of these values.

[0108] 57. According to any one of aspects 52 to 56, wherein the compression element includes opposing curved ends and a flat portion defined between the ends, the flat portion being configured to define a flat reading area at the surface of the container, particularly at the upper surface and / or the lower surface of the container.

[0109] 58. According to any one of aspects 52 to 57, wherein the device includes at least one constraint element configured to maintain the covering element in an operational configuration.

[0110] 59. According to any one of aspects 52 to 58, wherein the device includes two constraint elements configured to maintain the covering element in an operational configuration, the two constraint elements being opposite to each other.

[0111] 60. According to any one of aspects 52 to 59, wherein the covering element is hinged to the housing at a hinged portion, and the at least one restraining element is opposite to the hinged portion.

[0112] 61. According to any one of aspects 52 to 60, wherein the device includes a sensor configured to verify the configuration (preferably position) of the covering element, particularly verifying that the covering element is in an operational configuration (preferably in a closed position), and a control unit configured to obtain information via the sensor regarding the configuration (preferably position) undertaken by the covering element.

[0113] 62. According to any one of aspects 52 to 61, wherein the control unit is configured to prevent the measurement of parameters when the covering element is in a resting configuration (preferably in an open position).

[0114] 63. According to any one of aspects 52 to 62, wherein the control unit is configured to allow the measurement of parameters only when the covering element is in an operating configuration (preferably in the closed position).

[0115] 64. According to any one of aspects 52 to 63, wherein the covering element comprises a body and a compression element configured to oscillate relative to the body.

[0116] 65. According to aspect 64, wherein the compression element is tilted relative to the body.

[0117] 66. According to any one of aspects 54 to 65, wherein the covering element drags the compression element in a rotating manner.

[0118] 67. According to aspect 64 or 65 or 66, wherein the compression element is configured to describe an angle different from the angle described by the body of the covering element.

[0119] 68. According to any one of aspects 64 to 67, wherein the compression element is configured to rotate at an angle different from the rotation angle of the covering element body.

[0120] 69. According to any one of aspects 64 to 68, wherein the covering element includes a pin operatively arranged between the body and the compression element, the compression element being configured to oscillate relative to the body by means of the pin.

[0121] use

[0122] 70. Use of the apparatus according to any of the foregoing apparatus aspects for measuring, in particular simultaneously measuring, multiple blood parameters.

[0123] 71. According to any one of aspects 70, wherein the simultaneous measurement of the plurality of blood parameters is performed by means of artificial intelligence.

[0124] 72. According to aspect 70 or 71, wherein it is used in an extracorporeal blood circuit.

[0125] 73. The aspect described in aspect 70, 71 or 72, wherein the use does not involve any initial calibration of the device by the end user.

[0126] 74. According to any one of aspects 70 to 73, wherein the use provides measurement of multiple parameters by means of artificial intelligence, in particular by means of one or more neural networks.

[0127] 75. According to any one of aspects 70 to 74, wherein the plurality of blood parameters are used to measure the flow within a test tube connected to an extracorporeal blood circuit.

[0128] 76. According to any one of aspects 70 to 75, wherein the plurality of blood parameters are measured using a tube provided at a portion of an extracorporeal blood circuit.

[0129] Components

[0130] 77. A component comprising:

[0131] - The apparatus according to any of the foregoing apparatus aspects

[0132] - A container capable of containing blood and / or configured to allow blood to flow in the container, preferably a test tube, tube, or fitting for an extracorporeal blood circuit.

[0133] equipment

[0134] 78. An apparatus comprising:

[0135] - The apparatus according to any of the foregoing apparatus aspects

[0136] - Medical machines, such as cardiopulmonary bypass machines or extracorporeal membrane oxygenation (ECMO) machines.

[0137] A user interface, such as a display device, is operatively connected to or can be connected to the device and is configured to make the measured values ​​of the plurality of blood parameters available.

[0138] Methods for measuring multiple blood parameters

[0139] 79. A method for measuring multiple blood parameters using artificial intelligence, the method comprising the following steps:

[0140] - Excite the blood, especially blood flow, with electromagnetic radiation of multiple defined wavelengths.

[0141] - Detect multiple electromagnetic responses of blood, especially optical responses. These multiple electromagnetic responses include electromagnetic radiation reflected or diffused by the blood, particularly light.

[0142] - Receive analog information about multiple electromagnetic and / or optical responses of blood, including light reflected or diffused by the blood.

[0143] - Convert analog information of electromagnetic and / or optical response into digital data of electromagnetic and / or optical response.

[0144] - The electromagnetic and / or optical response digital data, along with the actual blood temperature value, are processed by one or more neural networks.

[0145] - As a result of processing operations of one or more neural networks, determine the value of each of the multiple blood parameters.

[0146] 80. A method for measuring multiple blood parameters using artificial intelligence, the method comprising the following steps:

[0147] - Excite blood flow at multiple defined wavelengths,

[0148] - Detect multiple electromagnetic and / or optical responses of blood, including light reflected or diffused by the blood.

[0149] - Receive analog information about multiple electromagnetic and / or optical responses of blood, including light reflected or diffused by the blood.

[0150] - Convert analog light response information into digital light response data.

[0151] - The light response digital data and actual blood temperature values ​​are processed by one or more neural networks.

[0152] - As a result of processing operations of one or more neural networks, determine the value of each of the multiple blood parameters.

[0153] 81. The aspect according to aspect 79 or 80, wherein the step of processing the electromagnetic and / or optical response digital data and the actual temperature value of the blood by one or more neural networks and determining the value of each of the plurality of blood parameters includes:

[0154] o Define multiple ratios, each defined between a value indicating the amount of radiation reflected or diffused by blood due to excitation of a defined wavelength and a value indicating the amount of radiation reflected or diffused by blood due to excitation of another defined wavelength.

[0155] o serves as input to one or more neural networks, providing the multiple ratios.

[0156] o The multiple ratios are processed by using one or more neural networks that consider multiple data points from previous measurements of the blood parameters taken during previous training.

[0157] o, as the output of one or more neural networks, provides the value of each of the multiple blood parameters.

[0158] 82. According to aspect 79, 80 or 81, the method comprises: arranging the apparatus according to any of the foregoing apparatus aspects, and performing the method by means of said apparatus.

[0159] 83. According to any one of aspects 79 to 82, wherein the method is performed by means of an apparatus according to any one of the foregoing apparatus aspects.

[0160] 84. According to any one of aspects 79 to 83, wherein the method comprises: preferably detecting the actual temperature value of the blood by means of a temperature sensor housed within the device.

[0161] 85. According to any one of aspects 79 to 84, wherein the method is a method for simultaneously measuring multiple blood parameters by means of artificial intelligence.

[0162] 86. According to any one of aspects 79 to 85, wherein the method includes the step of simultaneously making the measured values ​​of the plurality of blood parameters available.

[0163] 87. According to any one of aspects 79 to 86, wherein the step of processing the plurality of ratios by means of one or more neural networks considering a plurality of data from previous measurements of the blood parameters performed during previous training comprises: detecting the value of each of the plurality of blood parameters that the artificial intelligence considers to correspond to a previously determined ratio based on the plurality of data from the previous measurements.

[0164] 88. According to any one of aspects 79 to 87, wherein the method further comprises: providing reference values ​​for a first parameter to be measured and reference values ​​for a second parameter to be measured as input to one or more neural networks, the reference values ​​being acquired and stored in the device during a calibration step prior to using the device.

[0165] 89. According to aspect 87 or 88, wherein the step of detecting the value of each of the plurality of blood parameters that the artificial intelligence considers to correspond to a previously determined ratio based on the plurality of data from previous measurements includes: processing the data and / or information by means of a mathematical matrix model, preferably by means of one or more matrices of weights and biases.

[0166] 90. According to any one of aspects 79 to 89, wherein the step of stimulating blood flow at a plurality of defined wavelengths comprises: activating a plurality of stimulating elements according to a defined time sequence.

[0167] 91. According to aspect 90, wherein the step of activating a plurality of excitation elements according to a determined time sequence comprises: alternately activating a first excitation element and a second excitation element.

[0168] 92. According to any one of aspects 79 to 91, wherein the step of detecting multiple blood electromagnetic responses includes:

[0169] - Multiple electromagnetic and / or optical responses of blood are detected using an initial photodetector.

[0170] - Multiple electromagnetic and / or optical responses of the blood are detected by means of a second photodetector.

[0171] 93. According to any one of aspects 79 to 92, wherein blood stimulation is performed in the device operating state, in which blood flows into a container associated with the device.

[0172] 94. According to any one of aspects 79 to 93, wherein the container associated with the device is a test tube, particularly associated with or arranged in an extracorporeal blood circuit.

[0173] 95. According to any one of aspects 79 to 94, wherein the container associated with the device is a tube or tube portion of an extracorporeal blood circuit.

[0174] 96. According to any one of aspects 79 to 95, wherein the method comprises the step of: preferably at the same time making the value of each of the plurality of blood parameters available on a medium that can be queried by an operator, for example, on a screen of a machine associated with the apparatus configured to perform the method for measuring the plurality of blood parameters by artificial intelligence.

[0175] Streaming information

[0176] 97. According to any one of aspects 79 to 96, wherein the method comprises the step of taking into account blood flow-related values, particularly the volumetric flow rate of blood, when measuring oxygen saturation and / or hematocrit.

[0177] 98. According to any one of aspects 79 to 97, wherein the step of considering blood flow-related values ​​when measuring oxygen saturation and / or hematocrit includes: correcting the measured values ​​of oxygen saturation and / or hematocrit based on blood flow.

[0178] Detect the type (color) of the container.

[0179] 99. According to any one of aspects 79 to 98, wherein the method further comprises the step of:

[0180] - Inspect the type of container, especially the type of pipe.

[0181] - To adapt the measurement pattern of one or more parameters to the type of tube being detected;

[0182] Preferably, the step of detecting the container type, particularly the tube type, includes detecting the color of the container, particularly the color of the tube.

[0183] 100. According to aspect 99, wherein the method includes a step of preparing a control unit of the apparatus for measurement based on the detected tube type, the step including a step of adapting the measurement pattern of one or more parameters to the detected tube type.

[0184] 101. According to aspect 99 or 100, wherein the step of detecting the type of container, particularly the type of tube, is performed while physiological saline or a fluid other than blood is flowing in the container.

[0185] 102. According to aspect 99 or 100 or 101, wherein the step of detecting the container type, particularly the tube type, is performed prior to the step of stimulating blood flow at multiple defined wavelengths.

[0186] 103. According to any one of aspects 99 to 102, wherein the step of adapting the measurement pattern of one or more parameters to the type of tube detected includes the step of selecting a determined matrix from a plurality of matrices available from a neural network.

[0187] 104. According to aspect 103, wherein the step of selecting a determined matrix from a plurality of matrices available from a neural network includes querying a memory storing information relating to the plurality of matrices.

[0188] 105. According to aspect 104, wherein the memory is the memory of an apparatus configured to implement the method.

[0189] Connection between device and container

[0190] 106. According to any one of aspects 79 to 105, wherein the method includes the step of associating the device with a container, for example, with a tubular element such as a test tube or a tube such as an extracorporeal blood circuit.

[0191] 107. According to aspect 106, wherein the step of associating the device with the container includes relatively restraining the device and the container.

[0192] 108. According to aspect 107, the steps of relatively restraining the device and the container include:

[0193] - For example, the device and container are magnetically confined by means of one or more magnetic coupling elements; and / or

[0194] - For example, the device and container are mechanically restrained by means of at least one mechanical restraint element.

[0195] 109. According to aspect 108, the step of mechanically restraining the device and container includes engaging the covering element relative to the housing of the device by means of at least one restraining element, particularly by means of two restraining elements opposite to each other.

[0196] 110. According to aspect 108 or 109, wherein the step of mechanically restraining the device and container includes moving, in particular rotating, the covering element close to the housing of the device.

[0197] 111. The aspect according to any one of aspects 79 to 110, wherein the method includes flattening the opposing surfaces of a container associated with the device, the step being performed before arousing blood flow at a plurality of defined wavelengths.

[0198] 112. According to aspect 111, wherein the step of flattening the relative surfaces of the container associated with the device includes: compressing the tubing of the extracorporeal blood circuit.

[0199] 113. According to aspect 111 or 112, wherein the step of flattening the relative surfaces of the container associated with the device is performed after the step of associating the device with the container.

[0200] 114. According to any one of aspects 79 to 113, wherein the method further comprises the step of compressing a portion of a container in which blood flows or is capable of flowing.

[0201] 115. According to aspect 114, wherein the step of compressing a portion of the container determines a reduction in the cross-sectional area of ​​the fluid passage of the container by between 9% and 17%.

[0202] 116. According to aspect 115, wherein the reduction in the cross-sectional area of ​​the fluid channel occurs at a length between 15 mm and 30 mm or equal to one of these values.

[0203] 117. According to aspect 114 or 115 or 116, wherein the step of compressing a portion of the container in which blood flows or is capable of flowing is performed prior to the step of determining the value of each of the plurality of blood parameters as a result of a processing operation of one or more neural networks, particularly prior to the step of stimulating the blood.

[0204] 118. According to any one of aspects 79 to 117, wherein the method includes the step of oscillating a compression element relative to a container in which blood flows or is capable of flowing.

[0205] 119. According to aspect 118, wherein the step of swinging the compression element relative to the container is performed during the step of moving, in particular rotating, the proximity cover element relative to the housing of the device.

[0206] 120. According to aspect 118 or 119, wherein the step of swinging the compression element relative to the container is achieved by swinging the tilting compression element.

[0207] 121. According to aspect 118 or 119 or 120, wherein the step of oscillating the compression element involves gradually and / or gently compressing the container.

[0208] Other aspects

[0209] 122. According to any of the foregoing aspects, wherein each ratio is a ratio of optical counts performed at the corresponding wavelength.

[0210] 123. According to any of the foregoing aspects, wherein one or more neural networks take into account multiple data of previous measurements of the blood parameter taken during previous training by means of at least one matrix, in particular at least one matrix of weights and biases.

[0211] 124. According to any of the foregoing aspects, wherein the container in which blood flows is of a disposable type.

[0212] 125. According to any of the foregoing aspects, wherein the device is configured to measure at least two blood parameters by means of artificial intelligence.

[0213] 126. According to aspect 125, wherein the at least two blood parameters are blood oxygen saturation and blood hematocrit.

[0214] 127. According to any of the foregoing aspects, wherein the device is configured to measure at least three blood parameters.

[0215] 128. According to aspect 125 or 126 or 127, wherein the device is configured to directly measure the at least two blood parameters by artificial intelligence, and to measure a third blood parameter as a parameter derived from the measurement of at least one of the two parameters.

[0216] 129. According to aspect 127 or 128, wherein the third parameter is hemoglobin content or concentration.

[0217] 130. According to any of the foregoing aspects, wherein the device is configured to measure four blood parameters.

[0218] 131. According to aspect 130, wherein the four blood parameters are: blood oxygen saturation, hematocrit, hemoglobin content or concentration, and blood temperature.

[0219] 132. According to any of the foregoing aspects, wherein the device is configured to be associated with a test tube and has no relative rotating parts to allow engagement between the test tube and the device.

[0220] 133. According to any one of aspects 31 to 132, wherein the first photodetector comprises a silicon photodiode (or a Si photodiode).

[0221] 134. According to any one of aspects 31 to 133, wherein the second photodetector comprises an indium, gallium, and arsenic photodiode (or an InGaAs photodiode).

[0222] 135. According to any of the foregoing aspects, wherein artificial intelligence is capable of measuring (directly or indirectly) the following parameters: blood oxygen saturation (SatO2), hematocrit (Hct), and hemoglobin (Hb).

[0223] 136. According to any of the foregoing aspects, wherein the measurement of the plurality of parameters is performed in the following manner:

[0224] o Directly measure the percentage value of blood oxygen saturation, i.e., SatO2 [%].

[0225] o Directly measure the hematocrit value, i.e., Hct[%],

[0226] o Direct measurement of blood temperature, i.e., Temp. [°C],

[0227] o Indirectly (derived) the hemoglobin content in the blood, that is, its concentration Hb [g / dl].

[0228] 137. According to any of the foregoing aspects, wherein the measurement of the plurality of parameters is performed in the following manner:

[0229] o This method uses artificial intelligence to directly measure the percentage value of blood oxygen saturation, i.e., SatO2 [%].

[0230] o The hematocrit value, i.e., Hct [%], can be directly measured using artificial intelligence.

[0231] o Use a temperature sensor to directly measure blood temperature, i.e., Temp. [°C].

[0232] o Indirectly measure the hemoglobin content in blood, i.e., its concentration, Hb [g / dl], through artificial intelligence.

[0233] 138. According to any of the foregoing aspects, wherein the measurement of the parameter is performed by means of the same measurement operation or session.

[0234] 139. According to any of the foregoing aspects, wherein the computational model implemented by one or more neural networks is a mathematical matrix model.

[0235] Machine learning methods

[0236] 140. A machine learning method based on one or more neural networks, comprising the following steps:

[0237] - Provide machine learning equipment, a step which includes coupling multiple devices to corresponding containers arranged along an extracorporeal blood circuit and / or a portion thereof.

[0238] - Perform one or more training rounds, during which desired blood parameters (hematocrit, oxygen saturation, temperature, and optional hemoglobin) are measured as blood flows through the container.

[0239] - Develop a computational method configured to allow the computation of one or more of the parameters using artificial intelligence.

[0240] 141. According to aspect 140, wherein the machine learning method is capable of including steps 1) to 7) as described in the corresponding portion of the following detailed description.

[0241] 142. According to aspect 140 or 141, wherein the machine learning method is implemented according to the machine learning settings as described in the corresponding part in the following detailed description.

[0242] Conventions and limitations

[0243] Note that in the following detailed description, corresponding parts / components / elements are indicated by the same reference numerals. The drawings can illustrate the subject matter of the invention by non-scaled representation; therefore, the parts / components / elements shown in the drawings and relating to the subject matter of the invention may be for illustrative purposes only. In the context of this disclosure, unless specifically indicated otherwise, the use of terms such as “above,” “upper,” “on top,” “below,” “lower,” “at the bottom,” “side,” “lateral,” “transverse,” “laterally,” “inner,” “internal,” “outer,” “external,” “horizontal,” “horizontal,” “vertical,” “front,” “frontal,” “rear,” “rearward,” “right,” “left,” similar terms, and variations thereof refer to at least one spatial orientation (see, for example, one or more in the drawings) that the object of the invention can take in its use state. Unless otherwise specifically stated, the terms “state” or “configuration” may be used interchangeably in the context of this disclosure. Unless otherwise specifically stated, the expressions “upstream,” “downstream,” and similar or derived expressions refer to the arrangement of a part / component / element relative to the direction of fluid flow along a fluid line or loop or relative to the displacement of the loop of said element in a defined line or branch.

[0244] In the context of this disclosure, one or more of the following limitations / conventions apply where appropriate, unless otherwise stated and / or unless the context excludes this (e.g., for technical reasons):

[0245] - The device is configured to measure several parameters, including oxygen saturation (i.e., SatO2), hematocrit (i.e., Hct), blood temperature, and optionally hemoglobin content (i.e., Hb).

[0246] - The device is preferably a probe;

[0247] - The device is preferably configured to measure the multiple parameters simultaneously;

[0248] - "Simultaneous measurement" means "measurement by means of the same measurement operation or session", and in particular it means "measurement of the multiple blood parameters by means of the same measurement operation or session, making the measured values ​​of the multiple blood parameters available at the same time".

[0249] - The device is configured to measure:

[0250] o The percentage value of blood oxygen saturation, i.e., SatO2 [%],

[0251] o Hematocrit value, i.e., Hct[%],

[0252] o Blood temperature, i.e., Temp. [°C],

[0253] Alternatively, the hemoglobin content or concentration in the blood, i.e., Hb [g / dl],

[0254] Among them, the blood oxygen saturation, blood hematocrit, and, where applicable, the blood hemoglobin content or concentration are measured by artificial intelligence, while the blood temperature is measured using a temperature sensor.

[0255] - Multiple blood parameters measured by artificial intelligence can include "at least two blood parameters" (i.e., SatO2, Hct), more specifically "three blood parameters" (i.e., SatO2, Hct and Hb), or even more specifically "exclusive three blood parameters" (i.e., exclusive SatO2, Hct and Hb).

[0256] - The device is configured to measure multiple parameters in the following manner:

[0257] o This method uses artificial intelligence to directly measure the percentage value of blood oxygen saturation, i.e., SatO2 [%].

[0258] o The hematocrit value, i.e., Hct [%], can be directly measured using artificial intelligence.

[0259] o Preferably, a temperature sensor is used to directly measure the blood temperature, i.e., Temp. [°C].

[0260] o Indirect measurement (derived from direct measurement performed by artificial intelligence) of the blood's hemoglobin content, i.e., its concentration Hb [g / dl]; note that the hemoglobin content is a parameter derived from direct measurement of hematocrit values;

[0261] - Regarding direct measurement, the device is configured to measure parameters within the corresponding range with high accuracy, namely:

[0262] o For hematocrit levels between 13% and 55%

[0263] o For blood oxygen saturation of 35% to 99.9%,

[0264] o For blood temperatures between 9°C and 42°C.

[0265] "Reflected electromagnetic radiation" or "reflected light" refers to electromagnetic radiation or light that returns to the photodetector after being excited by the blood, having passed through a medium (blood) and thus been partially absorbed. It corresponds to the optical count read by the photodetector (photodiode). "Electromagnetic radiation" can also be simply referred to as "radiation."

[0266] - "Light" refers to the radiation in the visible part of the electromagnetic spectrum;

[0267] - Each "optical count" is a measurement indicating the signal (electromagnetic radiation) detected by a photodetector (photodiode) after excitation by electromagnetic radiation of a defined wavelength; optical counts are used to determine or calculate ratios and Figure 12 In Chinese, this is called "counting".

[0268] If necessary, particularly when the foregoing aspects use one or more expressions covered by one or more conventions or limitations, one or more of the conventions and limitations may be included in one or more of the aspects. Attached Figure Description

[0269] To better understand the present invention and its advantages, some embodiments are described below by way of example rather than limitation with reference to the accompanying drawings, in which:

[0270] Figure 1 An apparatus for measuring multiple blood parameters according to a first embodiment of the present invention is shown; the apparatus is shown as being coupled to a test tube;

[0271] Figure 1A It shows Figure 1 The device as viewed from below;

[0272] Figure 2 It shows Figure 1 An exploded view of the apparatus and test tube (the magnetic coupling element of the test tube is also shown in the exploded view), in which half of the housing of the apparatus has been removed to show the apparatus components housed inside the housing.

[0273] Figure 3 It shows Figure 2 The apparatus and test tube are in a coupled state to show the positioning of the various internal components of the apparatus in the operating state;

[0274] Figure 4 A front perspective view of an apparatus for measuring multiple blood parameters according to a second embodiment of the present invention is shown, along with an exploded view of the tubing; the covering element of the apparatus is in a resting configuration (open covering element).

[0275] Figure 5 It shows Figure 4 The device in which the tube is joined at a suitable base;

[0276] Figure 5A It shows Figure 5 The device and tube in the picture, wherein the half shell of the device housing has been removed to show the device components housed inside the housing and the positioning of the components in the operating state;

[0277] Figure 6 Show Figure 4The rear perspective view of the device shows the tube engaging at the base and the cover element in an operational configuration (closed cover element).

[0278] Figure 6A It shows Figure 6 A side view of the device shows how the covering element flattens the relative surfaces of the tube housed in the base; flattening is achieved by compressing the tube.

[0279] Figure 7 It shows Figure 4 Exploded view of the device and tubes;

[0280] Figure 8A It shows Figure 1 The device (shown in the upper right corner of the extracorporeal blood circuit) and Figure 4 The device (shown in the lower right corner of the extracorporeal blood circuit) and the device may be used clinically in the operating room, where they can be used in conjunction with a cardiopulmonary bypass machine;

[0281] Figure 8B It shows Figure 1 The device (shown in the upper right corner of the extracorporeal blood circuit) and Figure 4 The device (shown in the lower right corner of the extracorporeal blood circuit) is another possible clinical use of both in the intensive care unit, where the device can be used in conjunction with an extracorporeal membrane oxygenation (ECMO) machine.

[0282] Figure 9 A laboratory setup for achieving automated learning via the device according to the invention is shown;

[0283] Figure 10 A hematocrit calibration curve (Hct%) for calibrating the device according to the invention at a fixed saturation value in the laboratory is shown; the wording on the horizontal axis indicates the ratio of the optical count (in the numerator) detected by the InGaAs photodiode due to excitation at a wavelength of 805 nm to the optical count (in the denominator) detected by the InGaAs photodiode due to excitation at a wavelength of 1450 nm.

[0284] Figure 11 A saturation calibration curve (Sat%) at a fixed hematocrit value is shown for calibrating the device according to the invention in the laboratory; the wording on the horizontal axis indicates the ratio of the optical count (at the numerator) detected by the Si (silicon) photodiode due to excitation at a wavelength of 805 nm to the ratio of the optical count (at the denominator) detected by the silicon photodiode due to excitation at a wavelength of 660 nm.

[0285] Figure 12 The structure of a multilayer perceptron neural network is illustrated by way of example, which is a possible structure of one or more neural networks that can be implemented in the device according to the invention.

[0286] Figure 13 It shows that it can be made by Figure 12 Possible computational methods for implementing neural networks to measure the values ​​of blood parameters output by the neural network;

[0287] Figure 14 It shows Figure 12 The activation function of neurons in a neural network;

[0288] Figure 15 The tube is shown relative to Figure 6A The configuration of the extrusion profile; it shows in more detail how the cover element compresses the tube, resulting in a smooth transition between the uncompressed portion of the tube and the central portion of the tube, which is compressed at the base to obtain a flat reading area;

[0289] Figure 16 It shows Figures 4 to 7 and Figure 15 An alternative cover element is shown; the compression element of this alternative cover element is configured to oscillate relative to the body of the cover element itself. The oscillating compression element is shown as partially retracting from its base realized in the body of the cover element;

[0290] Figure 17 A cross-section of a variant of the device according to the second embodiment is shown, wherein the covering element presents an angular position with the oscillating compression element positioned close to the tube;

[0291] Figure 18 Shown in cross section Figure 17 The device in which the covering element has been removed Figure 17 The angular position of the tube is further rotated towards the tube, and the oscillating compression element compresses the tube. Detailed Implementation

[0292] Device for measuring multiple blood parameters

[0293] The apparatus according to the invention is generally indicated by the numerals 1 and 1' in the figures. Apparatus 1 and 1' are configured to measure a plurality of blood parameters, particularly the following parameters: oxygen saturation (i.e., SatO2), hematocrit (i.e., Hct), blood temperature, and optionally, hemoglobin content (i.e., Hb). Preferably, apparatus 1 and 1' are configured to measure these parameters according to the following mode: measuring oxygen saturation and hematocrit by means of artificial intelligence, measuring temperature by means of a temperature sensor, and measuring hematocrit in a derived manner, particularly by means of a value derived from the hematocrit; details of the calculation of parameters by means of artificial intelligence are described below.

[0294] Devices 1 and 1' are configured to be associated with, and in particular coupled to, containers 25 and 25', in which blood can flow; containers 25 and 25' are preferably conduits. Containers 25 and 25' typically have a tubular shape and are therefore provided with a fluid channel cross-section in which blood can flow. For example, the container may be a test tube 25 in fluid communication with an extracorporeal blood circuit, or a tube (or part of a tube) 25' of an extracorporeal blood circuit. Devices 1 and 1' are according to a first embodiment designed to be coupled to a tubular container (e.g., test tube 25) (devices indicated by reference numeral 1, see attached figures). Figures 1 to 3 ) and a second embodiment according to a tube (or tube portion) 25' designed to be coupled to an extracorporeal blood circuit (the device indicated by reference numeral 1', see also) Figures 4 to 7 and Figure 15 The embodiments described and depicted herein are obviously not identical; other embodiments may be considered. As detailed below, devices 1, 1' and containers 25, 25' are configured to be coupled to each other and to interact functionally. Containers 25, 25', which come into contact with blood during use, are disposable elements, while devices 1, 1' are reusable to perform additional parameter measurements. In particular, containers 25, 25' are the only disposable elements in the assembly comprising devices 1, 1' and containers 25, 25'. Common features between the first and second embodiments are described herein, while their differences are detailed below.

[0295] Devices 1 and 1' include a housing 2. Housing 2 has an internal volume that houses the components including the control unit 3. Housing 2 has a small size, which provides compactness to devices 1 and 1'. It should also be noted that housing 2 can be assembled; in particular, housing 2 can include two parts 2a and 2b, which are assembled together in the operating state of devices 1 and 1'. As shown in the figures, the assembleable parts can be half-shells 2a and 2b; the half-shells are preferably substantially symmetrical to each other.

[0296] Devices 1 and 1' include at least one excitation element 4 or 5 configured to excite blood flow with electromagnetic radiation of a plurality of defined wavelengths. The electromagnetic radiation is intended to elicit a photoresponse in the blood; in this regard, see the wavelengths described below. In the operating state of devices 1 and 1', wherein at least one excitation element 4 or 5 excites the blood, and the blood responds to the excitation by reflecting and diffusing electromagnetic radiation including radiation of visible wavelengths (light). The wavelengths are selected such that the blood responds to these wavelengths with a significant photoresponse.

[0297] The wavelengths that can be excited by blood are as follows:

[0298] - 660 nm was chosen because most of the absorption of oxyhemoglobin occurs at this wavelength, meaning the difference in absorption between the oxygenated and non-oxygenated or reduced forms of hemoglobin is greatest at this wavelength.

[0299] - 805 nm, this wavelength was chosen because of the isoabsorption point of hemoglobin (i.e., where the absorption of oxyhemoglobin and deoxyhemoglobin is equal).

[0300] - 1450 nm, this wavelength was chosen because there is more water absorption at this wavelength (used to measure hematocrit).

[0301] - 940 nm, this wavelength was chosen because it is at which maximum diffusion occurs on water and maximum absorption occurs on blood with high hematocrit (it is used in conjunction with wavelengths of 525 nm, 1450 nm and 805 nm for detecting the following states of device operation: presence of blood in the container, presence of saline, absence of the container).

[0302] - 525 nm, this wavelength was chosen because there is maximum absorption from blood at this wavelength (used to determine whether the device "sees" blood).

[0303] - Optionally, 1050 nm, this wavelength is chosen for possible hemoglobin variations.

[0304] - Optionally, 1550 nm is chosen to improve the accuracy of hematocrit measurements for Hct% values ​​below 40%, because there are greater dynamic variations in optical counting at this wavelength.

[0305] Wavelength should be understood as falling within a defined range near the values ​​mentioned above, for example as follows:

[0306] o 660±10 nm,

[0307] o 805±5 nm,

[0308] o 1450±30 nm,

[0309] o 940±10 nm,

[0310] o 525±10 nm,

[0311] o 1050±10 nm,

[0312] o 1550 nm±10 nm.

[0313] As shown in the attached figures, the devices 1 and 1' include: a first excitation member 4 configured to excite blood flow at at least a first plurality of wavelengths; and a second excitation member 5 configured to excite blood flow at a second plurality of wavelengths. The first excitation member 4 and the second excitation member 5 are arranged within the housing 2, and in particular, the first excitation member 4 and the second excitation member 5 are arranged side by side.

[0314] Advantageously, by means of one or more excitation elements 4, 5, the devices 1, 1' can excite blood with radiation from the visible region (excitation at 600 nm) to the infrared to “interrogate” the blood flowing in the containers 25, 25' associated with the devices 1, 1' at these electromagnetic wavelengths and obtain appropriate responses for calculating multiple parameters.

[0315] In the embodiments shown herein, the first excitation element 4 is configured to excite blood flow at wavelengths of 525 nm, 940 nm, and optionally 1050 nm; and the second excitation element 5 is configured to excite blood flow at wavelengths of 660 nm, 805 nm, and 1450 nm. More specifically, each excitation element 4, 5 includes a plurality of individual LED elements (not shown in the figures), which are configured to emit light radiation at corresponding wavelengths between the wavelengths. In particular, each excitation element 4, 5 includes a plurality of individual LED elements equal in number to the wavelengths at which the excitation element is configured to emit light.

[0316] In the embodiments disclosed herein, the first excitation element includes a tri-color LED element 4 configured to excite blood flow at 525 nm, 940 nm, and optionally 1050 nm (a first plurality of wavelengths); and the second excitation element includes a multi-wavelength LED element 5 configured to excite blood flow at 660 nm, 805 nm, and 1450 nm (a second plurality of wavelengths). Each excitation element 4, 5 includes a chip on which individual LED elements are mounted; the tri-color LED element 4 has three LED elements mounted to emit electromagnetic radiation at wavelengths of 525 nm, 940 nm, and 1050 nm, and the multi-wavelength LED element 5 has at least three LED elements mounted to emit electromagnetic radiation at wavelengths of 660 nm, 805 nm, and 1450 nm. Optionally, the multi-wavelength LED element 5 also has a fourth LED element mounted to also emit electromagnetic radiation at a wavelength of 1550 nm; this LED element can be used to improve the accuracy of hematocrit measurements, particularly for hematocrit values ​​below 40%.

[0317] Individual LED elements can be activated (turned on) by control unit 3 in the following time-controlled manner: sequentially turned on at a frequency of approximately 20 pulses per second every 100 μs, and then turned off for 50 ms. The LED elements are turned on one at a time, and within 1 second, each LED element (each light source) sends 20 optical count measurements. Preferably, all LED elements are turned on at the same frequency. During this time, these measurements are averaged for each individual LED element, and the ratio of optical counts (as will be seen below) is calculated and used to calculate the parameters. The applicant notes that such timing allows for a good signal-to-noise ratio, which is beneficial for the parameter measurements to be performed. Obviously, other timings that allow for a good signal-to-noise ratio and / or optimal parameter measurements can be used.

[0318] To protect each excitation element 4, 5, the devices 1, 1' can provide appropriate excitation element protection windows 6, 7. Each excitation element protection window 6, 7 is designed to protect the corresponding excitation element 4, 5 from electromagnetic waves having frequencies different from those that the corresponding excitation element 4, 5 can emit; the devices 1, 1' shown in the figures have a first excitation element protection window 6 and a second excitation element protection window 7 designed to protect the first excitation element 4 and the second excitation element 5 respectively (see Figure 1). Figure 2 and Figure 7 The protective windows 6 and 7 of the activating components face the corresponding activating components 4 and 5, such that during use, they are arranged between the corresponding activating components 4 and 5 and the blood inflow containers 25 and 25' (see...). Figure 3Each excitation element window 6, 7 may be made of a material configured to propagate radiation at a frequency that the respective excitation elements 4, 5 are configured to emit; for example, each excitation element window 6, 7 may be made of COP (cyclic olefin polymer).

[0319] Devices 1 and 1' further include at least one electromagnetic radiation detection element 8 and 9, configured to detect multiple electromagnetic blood responses, including electromagnetic radiation or light reflected or diffused by blood. Upon excitation by one or more excitation elements 4 and 5, electromagnetic radiation (including light responses) is reflected or diffused from the blood during the operation of the devices.

[0320] More specifically, as shown in the accompanying drawings, devices 1, 1' include a first electromagnetic radiation detection element 8 and a second electromagnetic radiation detection element 9. In the embodiments described herein, each electromagnetic radiation detection element is in the form of a photodetector 8, 9; therefore, the electromagnetic radiation detection element as a photodetector (photodiode) is described below. It should be understood that devices 1, 1' may include one or more electromagnetic radiation detection elements different from photodetectors 8, 9.

[0321] Therefore, devices 1 and 1' include a first photodetector 8 and a second photodetector 9, each of which is configured to detect multiple blood light responses. The first photodetector 8 and the second photodetector 9 are arranged within housing 2, specifically side by side.

[0322] The first photodetector 8 and the second photodetector 9 are configured to detect the blood response at corresponding multiple different wavelengths. Preferably, the first photodetector 8 is configured to detect the blood's light response when excited at the following wavelengths: 660 nm, 805 nm, 525 nm, 1050 nm, and 940 nm. As for the second photodetector 9, the second photodetector 9 is preferably configured to detect the blood's light response when excited at the following wavelengths: 805 nm and 1450 nm.

[0323] In the embodiments disclosed herein, the first photodetector is preferably a Si (silicon) type photodiode 8, that is, it is a silicon photodiode, and the second photodetector is preferably an InGaAs (indium gallium arsenide) type photodiode 9, that is, it is a semiconductor composed of indium, gallium and arsenic that is generally sensitive to electromagnetic radiation bands between 600 nm and 2600 nm.

[0324] In operation, each photodiode 8, 9 converts the received electromagnetic radiation into an electrical signal (current), which is then converted into a voltage via a transimpedance converter. This voltage is amplified by an analog-to-digital converter (ADC, part of control unit 3), which detects a number between 0 and 4096 corresponding to the detected light count. As will be seen in more detail below, the control unit 3 uses these optical counts to calculate a ratio. (See Appendix...) Figure 10 and Figure 11 The ratio of optical counts is shown as "ratio".

[0325] To protect each photodetector 8, 9, devices 1, 1' may provide corresponding photodetector protection windows 10, 11. Each photodetector protection window 10, 11 is designed to protect the corresponding photodetector 8, 9 from electromagnetic waves with frequencies different from those detectable by the photodetector 8, 9; devices 1, 1' shown in the figures have a first photodetector protection window 10 and a second photodetector protection window 11, designed to protect the first photodetector 8 and the second photodetector 9 respectively (see Figure 1). Figure 2 and Figure 7 The photodetector protection windows 10 and 11 face the corresponding photodetectors 8 and 9, such that during use, they are arranged between the corresponding photodetectors 8 and 9 and the blood inflow containers 25 and 25' (see...). Figure 5A Each photodetector protection window 10, 11 may be configured in material to transmit radiation at the frequency that the corresponding photodetectors 8, 9 are configured to detect; for example, each photodetector protection window 10, 11 may be a COP (cyclic olefin polymer), i.e., the same material as the protection windows 6, 7 of the excitation element.

[0326] Devices 1 and 1' include a temperature sensor 12 housed within a housing 2 and configured to detect the temperature of blood. Specifically, the temperature sensor 12 is configured to detect the temperature of blood inside the container. To facilitate easy detection of the temperature of blood contained in containers 25 and 25', the temperature sensor is preferably arranged near a coupling portion of devices 1 and 1', which is configured to couple with containers 25 and 25'. Even more specifically, the temperature sensor 12 is positioned near the coupling portion such that it faces containers 25 and 25' within the coupled configuration of devices 1 and 1'. The temperature sensor is preferably an infrared temperature sensor 12.

[0327] To protect the temperature sensor 12, devices 1, 1' may provide a temperature sensor protection window 13. The temperature sensor protection window 13 is designed to protect the temperature sensor 12 from electromagnetic waves having frequencies different from those that the temperature sensor 12 can detect. The temperature sensor protection window 13 faces the temperature sensor 12 such that, during use, the temperature sensor protection window 13 is positioned between the temperature sensor 12 and the blood inflow containers 25, 25' (see [reference]). Figure 3 and Figure 5A In embodiments where the temperature sensor 12 is infrared type, the temperature sensor protection window 13 may be made of a material configured to transmit radiation in the infrared frequency; for example, the temperature sensor protection window 13 may be made of zinc sulfide (ZnS).

[0328] The housing 2 includes at least one hole 14, which is adapted to face the containers 25, 25' into which blood flows when the devices 1, 1' are in the operating state. Excitation components and electromagnetic radiation detection components face this hole or corresponding hole, such that they can respectively excite the blood and receive an excitation response from the blood. Furthermore, a temperature sensor preferably faces the container so that it can measure the temperature of the blood. The opening 14 of each component 4, 5, 8, 9 and the opening of the temperature sensor 12 can be provided (see [reference]). Figure 4 According to the embodiment shown, electromagnetic radiation detection components 8 and 9 are arranged between excitation components 4 and 5 and temperature sensor 12. Furthermore, as shown, excitation components 4 and 5, electromagnetic radiation detection components 8 and 9, and temperature sensor 12 can be arranged along the same longitudinal direction. Such features related to the structural arrangement of excitation components 4 and 5, electromagnetic radiation detection components 8 and 9, and temperature sensor 12 increase the compactness of devices 1 and 1'.

[0329] The following describes the structural and functional differences between the device 1 according to the first embodiment and the device 1' according to the second embodiment, and then describes the operating logic of the control unit 3 of the devices 1 and 1'. The functional differences relate to the mode of engagement between the devices 1 and 1' and the containers (test tube 25 and tube 25', respectively) to which they are configured to be coupled.

[0330] First embodiment of the apparatus (an apparatus that can be associated with a test tube)

[0331] A first embodiment of the device 1 is envisioned to operate on a test tube 25, into which blood circulation from an extracorporeal blood circuit flows during measurement. The test tube 25 has a flat surface, particularly a flat top surface, which defines a flat reading area necessary for measurement accuracy; see [link to related document]. Figure 2 .

[0332] The housing 2 also has an opening 15 adapted to allow connection to a cable 16; the cable 16 allows digital data processed by the control unit 3 to be transmitted to medical devices 90', 90'' and / or display device 91. The cable 16 also enables power supply to the device 1. As shown in the figures, the cable 16 may have a stress-relieving element 16a, which is capable of preventing or minimizing stress at the portion where the cable 16 passes through the housing 2. The housing 2 has at least one gripping portion 2c, which allows the device 1 to be easily gripped and handled; as shown in the figures, the gripping portion may be in the form of a pair of grooves 2c defined on opposite sides of the housing 2.

[0333] Geometrically, the box 2 has a length L, a width T, and a height H; the width T is preferably smaller than the length L and the height H. The box 2 preferably has a configuration such that the necessary components of the device 1' are accommodated within it with the smallest possible volume. As shown in the figures, the height H can vary along the length L; therefore, the box 2 can have a minimum height H1 and a maximum height H2, which can be defined at corresponding opposite ends as the length L of the box 2. The length L, measured along the main direction of the container, can be between 40 mm and 80 mm. The width T, measured orthogonally to the length L, can be between 15 mm and 50 mm. The height H, measured orthogonally to the length L and the width T, can be between 30 mm and 80 mm. Essentially, the device 1 has dimensions such that it is substantially pocket-sized. As a non-limiting consideration, it should be noted that in a preferred version of the first embodiment, the length L can be 65 mm, the maximum height H2 can be 58 mm, and the width L can be 35 mm. In the first embodiment, the volume of the box 2 defines the volume of the device 1; the volume of the device 1 can be within the volume calculated according to the extreme values ​​of the aforementioned size ranges. In particular, in a possible implementation, the volume of device 1' can be between 20,000 mm. 3 With 400,000mm 3 Between, preferably between 50,000 mm 3 With 200,000 mm 3 Between, more specifically between 75,000 mm 3 With 175,000 mm 3 Between, or even more specifically between 90,000 mm 3 With 150,000 mm 3 between.

[0334] The device 1 includes a coupling portion 17 associated with a housing 2. Referring to the orientation of the device 1 shown in the accompanying drawings, the coupling portion 17 is connected to the housing 2 at a lower portion of the housing 2. The coupling portion 17 may extend parallel to the length L of the housing 2 between two opposing longitudinal ends. The coupling portion 17 may be integral with the housing 2. The coupling portion 17 includes a base 17a, which is sized to accommodate a container 25' (particularly a test tube) for blood. The base may take the form of a recess 17a extending in the longitudinal direction of the extension of the coupling portion 17. As shown in the accompanying drawings, the coupling portion 17 may take the form of a skirt extending from the lower portion of the housing 2 to define the base 17a; the skirt has opposing walls 17b, 17c, and the base 17a is defined between the opposing walls 17b, 17c. Since the measurement is optical, it is advantageous to shield the photosensitive area from external light components as much as possible; for this purpose, the walls are configured to shield light and reduce the possibility of glare or direct light affecting the measurement. Each wall 17b, 17c may be integral with its corresponding half-shell. Each wall 17b, 17c may also include one or more structural elements 17d, which may be in the form of recesses and / or ribs, configured to allow explicit coupling between the container 25 and the device 1, and additionally or alternatively to lighten (for recesses) or reinforce (for ribs) the walls 17b, 17c that define the recesses and / or ribs thereon. Preferably, the walls 17b, 17c provide the recesses / ribs 17d with the dual function of lightening / reinforcing the walls 17b, 17c that they define thereon; and allowing explicit coupling between the device 1 and the defined container 25, which may in turn have a corresponding structural element 25a. This allows the container, such as test tube 25, to be inverted between the arterial probe and the venous probe; in other words, this allows the device 1 (arterial probe) described herein to be uniquely coupled to the arterial test tube due to the corresponding recess / rib presented by the arterial test tube, thereby preventing the venous test tube from coupling to the arterial probe.

[0335] The coupling portion 17 includes at least one coupling element 17e, 17f, which allows the device 1 to be arranged in a coupled configuration (e.g., Figure 1 and Figure 3 (As shown in the figures) and decoupled configurations, in which the housing 25 is coupled to the device 1, and in which the housing 25 is decoupled from the device 1. Measurement of blood parameters is performed in the coupled configuration, in which the container 25 is housed at the base 17a. As shown in the figures, the coupling portion 17 may include at least a first coupling element 17e and a second coupling element 17f. The first coupling element 17e and the second coupling element 17f may be longitudinally opposite each other (see Figure 17a). Figure 2The first coupling element 17e and the second coupling element 17f are configured to couple with corresponding coupling elements 25b and 25c of the container 25. Providing two coupling elements 17e and 17f arranged in opposite positions allows for greater safety and stability in the coupling between the device 1 and the container 25. The first coupling element 17e and the second coupling element 27f can be of the same type; Figures 1 to 3 The magnetic coupling elements are shown. Each coupling element includes a corresponding magnet 25b, 25c configured to couple to container 25 (see [reference]). Figure 2 The corresponding magnets 17e and 17f of the container; note that the magnets 25b and 25c of the container are housed at the corresponding positions 25d and 25e. (As from...) Figure 2 As can be seen, the magnets 17e and 17f of device 1 and the magnets 25b and 25c of container 25 can both extend laterally on the storage plane. The following alternative embodiments are not excluded, in which at least one of the two coupling elements 17e and 17f is not magnetic, but rather, for example, mechanical.

[0336] Device 1 may also include an additional temperature sensor, which may preferably be a thermistor; this additional temperature sensor, not shown in the drawings relating to this first embodiment, may be arranged below the electromagnetic radiation detection element 9. The additional temperature sensor is configured to measure the temperature of the electromagnetic radiation detection element 9 (photodiode InGaAs) in such a way that the temperature of the electromagnetic radiation detection element 9 can be corrected for changes in optical responsiveness. The additional temperature sensor is in contact with the electromagnetic radiation detection element and the area confined thereon.

[0337] Second embodiment of the device (a device that can be associated with a pipe)

[0338] A second embodiment of device 1' is conceived to operate directly on a portion of an extracorporeal blood circuit tube into which blood flows during measurement.

[0339] Device 1' includes cover elements 18, 18' movable relative to housing 2 and base 19. As previously mentioned, housing 2 is the portion providing a housing for excitation components 4, 5, electromagnetic radiation detection components 8, 9, and control unit 3. In addition to the two half-shells 2a, 2b, housing 2 of device 1' may also have a base portion 2d adapted to connect the two half-shells 2a, 2b by means of a constraint element 2e (e.g., a threaded element). Base 19 is defined at the coupling portion of housing 2 and adapted to accommodate a portion of tube 25' housing an extracorporeal blood circuit. Cover elements 18, 18' are configured at least in the operating configuration (closed configuration of cover elements, see...). Figure 6 and Figure 6A ) and rest configuration (overlay element open configuration, see Figure 5 and5A In operation, in the operating configuration, the covering elements 18 and 18' flatten the opposing surfaces of the tube 25' housed in the base 19, and the corresponding positions of the covering elements 18 and 18' relative to the housing 2 correspond to the resting configuration. Essentially, the covering elements are closing elements capable of moving between a closed position and an open position. For example... Figure 5 and Figure 6 As shown, the covering elements 18 and 18' are hinged to the housing 2 at the hinge portion 20 of the device 1 and can be moved by rotation relative to the housing 2, thus determining the transition between positions corresponding to the resting configuration and the operating configuration. The covering elements 18 and 18' can be rotated relative to the housing 2 by angles α, α', and α''; angles α, α', and α'' can be defined by the angle defined by the body 18b of the covering elements 18 and 18' and the horizontal plane (see [reference]). Figure 5 , Figure 17 and Figure 18 The box 2 and the covering elements 18, 18' can present the same covering area in a plane, particularly a polygonal covering area, especially a quadrilateral covering area; in the figures, both the box 2 and the covering elements 18, 18' present a substantially square covering area in a plane (see figure). Figures 4 to 7 and Figure 15 This configuration ensures the compactness of the device and minimizes its coverage area. Further structural and geometric details are as follows.

[0340] In this second embodiment, it is important that, during measurement, the upper and lower surfaces of tube 25' are at least partially flat to ensure proper operation of device 1', and most importantly, to ensure measurement repeatability and accuracy; to achieve this, the base and cover elements 18, 18' in which tube 25' is mounted are designed such that a "rectangular" tube cross-section / shape is obtained by flattening the surface of tube 25' (see...). Figure 6A (Note that this flattening is not necessary for test tube 25, as it includes a flat surface defining the flat reading area; see also...) Figure 2 During measurement, a flat reading area allows the emission cone of electromagnetic radiation from individual LED elements to enter the tube as far as possible without interacting with the wall and altering its transmittance.

[0341] Cover elements 18, 18' include a compression element 18a for compressing a portion of the tube 25' housed therein in an operating configuration. The compression element 18a engages with the body 18b of the cover elements 18, 18'. The compression element 18a compresses the tube 25' at the measuring area to flatten the reading area. Essentially, when the tube portion 25' is inserted into the base 19 and the cover elements 18, 18' are closed, the tube portion 25' is compressed by the compression element 18a, thereby creating two parallel flat surfaces: one flat surface contacts the cover elements 18, 18', and the other flat surface contacts the bottom of the base 19 (see [link to documentation]). Figure 6A The compression element 18a has a geometry designed to minimize deformation of a portion of the tube 25' so as not to significantly alter blood flow and thus avoid the risk of hemolysis caused by abrupt changes in the precise portion through which blood flows. For this purpose, it is conceivable that the compression element 18a could be implemented from the circular shape of the tube (defined at the uncompressed portions 25b', 25c' of the tube, see...) Figure 15 (to a rectangular shape (defined at the compressed portion 25a' of tube 25', see...) Figure 6A The smooth transition of the device 1' aims to achieve minimal possible deformation, minimizing or even eliminating the effects of mechanical trauma (e.g., due to sudden cross-sectional contraction) experienced by cellular components, particularly erythrocytes, during in vitro flow. Such mechanical trauma can lead to cell lysis or various forms of sublethal damage, including alterations in cell morphology and deformability, release of certain cellular components, and shortened cell lifespan. Damage may be caused by direct contact with a solid surface or by physical forces applied to the cells. The extent of the latter damage depends on the magnitude of the shear stress exposed to the cells (particularly erythrocytes), rather than the nature of the flow conditions (whether laminar or turbulent). The conceived implementation of the device 1' ensures that it does not trigger damage, i.e., it remains in the "sub-hemolytic" zone (with shear stresses well below 100 Pa) under operating hydrodynamic conditions, i.e., in a region where the interaction effects of materials only in contact with the blood surface dominate. To this end, a defined geometry is provided for the compression element 18a, which allows for gentle compression of the tube 25'; essentially, the compression element 18a compresses the central portion 25a' of the tube 25' (the portion of the tube 25' misaligned at the base 19) to obtain a flat reading area and defines a smooth transition between the uncompressed portions of the tubes 25b' and 25c' that define the central compressed portion 25a'; in this regard, see Figure 15 The image shows a section of tube 25' joined to the base 19 and partially compressed. Figure 15The diagram illustrates how compression of tube 25' occurs at its upper surface to obtain a flat reading area; the flattened surfaces are both the upper and lower surfaces of the tube. To ensure optimal flattening of tube 25' without impairing blood properties (avoiding hemolysis), the compression element 18a includes a flattened portion 18a' defined between opposing curved portions (particularly ends 18a'', 18a'''), which may exhibit similar or analogous extensions; the flattened portion 18a' is adapted to produce a flat reading area. The flattened portion 18a' is substantially straight and may have a length L18 and a depth F; the depth F may correspond to the compressed core (or extruded core, i.e., the difference between the diameter D1 of the undeformed tube and the diameter or equivalent diameter D2 of the deformed tube). The depth F may be 2 mm. The length L18 is preferably between 10 mm and 50 mm, particularly between 12 mm and 45 mm. Figure 15 In the embodiment shown, the length L18 is 30 mm; in another embodiment, the length L18 may be 15 mm. The tube 25' has a diameter D1 (undeformed diameter), a diameter or equivalent diameter D2 (compressed diameter), and a thickness T1 (wall thickness). Compression of the central portion 25a' of the tube 25' by the compression element 18a results in a reduction of the cross-sectional area of ​​the blood passage by between 9% and 17% (caused by the reduction in the diameter of the tube 25' at length L18). For example, if the tube 25' has an undeformed diameter D1 of 14.3 mm, the reduction in the cross-sectional area of ​​the blood passage could correspond to approximately 14% compression of the tube, where the corresponding compressed equivalent diameter D2 of the tube 25' (D2 can be defined as the compressed equivalent diameter because the shape of the tube after compression is no longer circular) is 12.3 mm. It should be noted that in Figure 15 In this embodiment, the diameter D1 of tube 25' is equal to 9 / 16'' (a dimension in inches, corresponding to approximately 14.3 mm), the thickness T1 is equal to 3 / 32'' (a dimension in inches, corresponding to approximately 2.38 mm), and the equivalent diameter D2 is approximately 12.3 mm; therefore, the compressed body of tube 25' is approximately 2 mm (the difference between the undeformed diameter and the deformed diameter, as described above, is approximately 14%). Figure 6A and Figure 15 The compression effect visible in the figure serves a dual purpose: locking the relative position between the device 1' and the tube 25'; and creating a substantially flat or horizontal surface for performing measurements on this surface. As shown in the figures, the compression element may include a protrusion 18a extending along the main longitudinal direction and having the aforementioned profile.

[0342] The device 1' may further include a closing portion 21, which engages with the housing 2 to hold the covering elements 18, 18' in an operational configuration (closed position). The closing portion 21 may be integral with the covering elements 18, 18' and / or may have opposing operating ends 21a, 21b. Each operating end 21a, 21b is provided with a base, preferably defined on the outer side of the operating end 21a, 21b; the base may be a groove, for example, a groove with a curved profile. The closing portion 21 may extend longitudinally parallel to the compression element 18a. In the illustrated embodiment (see...), Figure 5 and Figure 5A In this configuration, the closing portion 21 is integral and has opposing operating ends 21a and 21b connected by an intermediate portion 21c. The closing portion 21 is easy to clean because it has no hard-to-access and / or hard-to-clean recesses.

[0343] The device 1' preferably includes at least one constraint element 22, 23 configured to hold the cover elements 18, 18' in an operational configuration; substantially, the constraint elements 22, 23 allow the cover elements 18, 18' to remain closed when they are in the operational configuration (during parameter measurement). As shown in the figures, the device 1' preferably includes two constraint elements 22, 23 configured to hold the cover elements 18, 18' in an operational configuration. The constraint elements 22, 23 engage with the housing 2 near the upper surface of the housing 2 and at corresponding positions 2f defined on the housing 2. The two constraint elements 22, 23 are opposite each other to ensure stable and symmetrical closure; furthermore, the symmetry of the closure helps ensure that the defined measurement surface at the reading area is flat. To achieve stable closure of the cover elements 18, 18', the constraint elements 22, 23 are preferably opposite the hinge portion 20. As shown in the accompanying drawings, each constraint element 22, 23 may provide a movable element 22a, 23a having, for example, a curved head (e.g., at least partially spherical); when closed, each movable element 22a, 23a may move via the opposing operating ends 21a, 21b of the closing portion 21; such movement determines engagement of the constraint elements 22, 23 with their respective bases. This engagement is preferably determined by accommodating the curved heads 22a, 23a of each constraint element 22, 23 at curved recesses in the corresponding operating ends 21a, 21b of the closing portion. The movement of the constraint elements 22, 23 preferably occurs as mutual movement away from each other. Each movable element 22a, 23a may move at least in the direction defining the constraint with the closing portion 21 (external direction, moving away from each other), and in particular, each movable element 22a, 23a may move in multiple directions, preferably substantially in each direction. The movable elements 22a and 23a are essentially sealed; therefore, providing closure of the covering elements 18 and 18' by means of the essentially sealed movable elements 22a and 23a and by means of the easily cleanable closing portion 21 not only ensures a stable closure but also guarantees a high degree of cleanability of the device 1'; this is obviously advantageous from a hygienic point of view.

[0344] The housing 2 also has a device 24 (preferably a connector) for connection to a cable 16; the cable 16 enables the transmission of digital data processed by the control unit 3 to medical devices 90', 90'' and / or display device 91. The cable 16 also provides power to the device 1'. As shown in the figures, the device 24 for connection may be located near the hinge portion 20, particularly on the side of the housing 2 and below the hinge portion 20.

[0345] Device 1' may also include an additional temperature sensor 12', which is preferably a thermistor (see [link]). Figure 7An additional temperature sensor 12' is configured to measure the temperature of the electromagnetic radiation detection element 9 to monitor the temperature of the electromagnetic radiation detection element 9 (InGaAs photodiode) in order to correct for changes in optical responsiveness to temperature. The additional temperature sensor 12' is in contact with the electromagnetic radiation detection element 9 and the area confined thereto.

[0346] Geometrically, device 1' has a length L, a width T, and at least one height, specifically a minimum height H1 and a maximum height H2; in the illustrated embodiment, the width T is substantially equal to the length L (essentially a square outline). The width T and length L are dimensions relating to the housing 2, while the heights H1 and H2 are dimensions defined by the fit between the housing 2 and the covering elements 18, 18'. The housing 2 preferably has a configuration such that the necessary components of device 1' can be accommodated therein with the smallest possible volume. As shown in the figures, the heights H1 and H2 of device 1' are functions of the configuration presented by the covering elements 18, 18'; therefore, the housing 2 can present a minimum height H1 (height of the covering elements in the operating configuration) corresponding to the use state of device 1' and a maximum height H2 (height of the covering elements in the resting configuration) corresponding to the resting state of device 1'. The length L can be between 40 mm and 80 mm. The width T, measured orthogonally to the length L, can be between 40 mm and 85 mm. The minimum height H1, measured orthogonally to the length L and width T, can be between 30 mm and 60 mm. Essentially, the device 1' has dimensions that make it substantially compact. As a non-limiting observation, it should be noted that in a preferred version of the second embodiment, the length L can be 64 mm, the minimum height H1 can be 44 mm, and the width L can be 67 mm; the length L and width T are similar values, and the box 3 can be substantially square in shape (see [reference]). Figures 4 to 7 In the second embodiment, the volume of device 1' is defined by the housing 2 and the covering elements 18, 18'; in the volumes described below, the volume of device 1' calculated using the minimum height value H1 as the height value will be referenced. The volume of device 1' may include the volume calculated based on the extreme values ​​of the aforementioned size range. In particular, in a possible embodiment, the volume of device 1' may be between 48,000 mm. 3 With 408,000mm 3 Between, preferably between 75,000 mm 3 With 330,000 mm 3 Between, more specifically between 120,000 mm 3 With 260,000 mm 3 Between, or even more specifically between 150,000 mm 3 With 220,000 mm 3Between. The above quadrilateral configuration, especially the basic square configuration, is the smallest configuration containing the physical dimensions of the components (including constraint elements 22, 23 and closed portion 21).

[0347] The advantage of this implementation is that it avoids the use of components that increase the cost of using device 1', namely, test tube 25; in addition, by directly coupling device 1' to tube 25' of the extracorporeal blood circuit, device 1' allows monitoring of blood parameters "on the go," that is, when the medical procedure has started.

[0348] Figure 16 , Figure 17 and Figure 18 It shows that according to Figures 4 to 7 and Figure 15 The cover element 18 is an alternative variant of the cover element 18 shown. According to this variant, the cover element 18' provides a compression element 18o, which is configured to oscillate relative to the body 18b of the cover element 18' (causing the compression element to tilt). In addition to the oscillation capability, the compression element 18o can have the same characteristics as the previously described compression element 18a, particularly the same configuration, and therefore can have portions 18a', 18a'', 18a''' (see...). Figure 16 ).

[0349] The development of the oscillating compression element 180 requires achieving the smoothest possible blood channel cross-section. By providing the possibility of compressing the adaptable tube 25', the oscillating compression element 180 enables increased repeatability of measurements that are essentially optical, and should be completely unaffected by the non-fixed and repeatable positioning of the tube 25' in front of the previously described optical component protective window.

[0350] In order to allow the compression element 18o to oscillate, the cover element 18' includes a pin 18c, which is received within a corresponding base 18d defined on the body 18b. Figure 16 , Figure 17 and Figure 18 A base 18d with a shape opposite to the circular outline of pin 18c is shown. As shown in these figures, pin 18c can be integrally formed with the oscillating compression element 18o; in alternative embodiments, they can form two separate but connected components. Figure 16 , Figure 17 and Figure 18 As shown, in order to retain pin 18c, base 18d can substantially define the undercut; for the assembly of compression element 18o to body 18b, pin 18c can be inserted into base 18d (see...). Figure 16Clearly, a kinematic device (e.g., a cam or parallelogram kinematics) can be provided instead of pin 18c to allow oscillation of the compression element 18o relative to the body 18b or to allow oscillation of the entire cover element 19' relative to the housing 25'. The oscillating compression element 18o is rotatedly pulled by the body 18b of the cover element 18'. Although rotated by the cover element 18', the compression element 18o can present an angular position according to angles β', β'' different from those of the cover element 18' due to pin 18c. In particular, the two rotational configurations of the cover element 18' are... Figure 17 and Figure 18 As can be seen, the body of the covering element 18' is positioned according to corresponding angles α', α'', while the compression element 18' presents corresponding and different angles β', β''. Although the angles β', β'' described by the compression element 18o are different from the angles α, α', α'' described by the body 18b of the covering element 18', they are still related to it because certain angular positions of the covering element 18' correspond to the corresponding angular positions of the compression element 18o. The device 1' can be specified that the body 18b of the covering element 18' rotates relative to the hinge portion 20 according to a first rotation direction (e.g., clockwise), and the compression element 18o rotates according to the first rotation direction and a second rotation direction opposite to the first rotation direction (e.g., counterclockwise); this is possible because the compression element 18o is tilted and is therefore configured to oscillate about the pin 18c to adapt its rotation direction to the relative position between the covering element 18' and the tube 25'.

[0351] Continue closing the cover element 18' in the direction of housing 2, and the compression element 18o from it does not compress the tube 25' (see Figure 17 The configuration is changed to one in which the compression element 18o contacts and oscillates with the tube 25' and then gradually rotates as the angles α, α', α'' decrease. Therefore, according to this variant, it is advantageous to imagine that the compression element 18o gradually adapts to the configuration of the tube 25' and gently compresses the central portion 25a' of the tube 25' in a manner that does not significantly alter the blood flow within the tube 25'. Figure 18 The diagram shows the configuration of the cover element 18' before it is fully closed on the housing 2; in this figure, it can be seen that the central portion 25a' of the tube is not yet fully compressed, and therefore the reading area is not yet flat. Thus, despite the fact that the cover element 18' is simply hinged to the housing 2, the compression element 18o can be approached in an almost parallel manner.

[0352] Control unit of the device

[0353] Devices 1 and 1' also include a control unit 3. The logic and characteristics of the control unit 3 described below are common to both embodiments of devices 1 and 1'. The control unit 3 is housed within a housing 2.

[0354] Due to the training described below, the control unit 3 preferably enables devices 1, 1' to perform parameter measurements without the need for initial calibration. Furthermore, the control unit 3 preferably enables devices 1, 1' to perform measurements without any interaction with external processing or computing units; thus, the processing of information and data for measuring multiple blood parameters is performed autonomously by devices 1, 1'. In this way, an external database is not required for devices 1, 1'; devices 1, 1' provide all the components for performing measurements of the parameters of interest within the housing 2. With the aid of the control unit 3, devices 1, 1' can perform parameter measurements based on multiple data points from previous measurements of blood parameters performed during previous training. This is possible because the control unit 3 can provide an coded computational model. Preferably, prior to supplying the devices 1, 1' discussed, training is performed in a laboratory (e.g., by the supplier of devices 1, 1' based on an end-user request) on a series of devices 1L, 1L' to be trained. As will be discussed further below, the previous training induces learning, particularly machine learning, which the control unit 3 considers when measuring parameters during clinical use. Each device 1, 1' produced after a certain number of devices 1L, 1L' have been calibrated in the laboratory (this aspect will be detailed below) so that the end user of device 1, 1' has an instrument ready for immediate use. Because there is no initial calibration, device 1, 1' is particularly suitable for use in emergency situations. Examples of emergency situations are those requiring treatment with extracorporeal membrane oxygenation (ECMO or extracorporeal membrane oxygenation machine), i.e., cardiac circulatory support, such as in patients with cardiac arrest or lung trauma, in the most acute and other untreatable stages of Covid-19 disease (Coronavirus disease 19 caused by the SARS-CoV-2 virus, also referred to below as "Covid").

[0355] In operation, the control unit 3 is configured to perform at least the following operations:

[0356] o During the excitation step, excitation components 4 and 5 are controlled to excite blood flow using electromagnetic radiation of multiple defined wavelengths.

[0357] o Receives analog information related to multiple electromagnetic and / or optical responses of blood (read by electromagnetic radiation detection components 8, 9), including electromagnetic radiation reflected or diffused by blood, particularly light.

[0358] o Convert analog information of electromagnetic and / or optical response into digital data of electromagnetic and / or optical response.

[0359] o Processing digital electromagnetic and / or optical response data and actual blood temperature values ​​via one or more neural networks (NNs)

[0360] o As a result of processing operations using one or more neural networks (NNs), the value of each of the multiple blood parameters is determined.

[0361] To perform these operations, the control unit 3 is operatively connected to the excitation components 4 and 5 and the electromagnetic radiation detection components 8 and 9.

[0362] Moving on to higher-level details regarding the processing and measurement of parameters by devices 1 and 1', it is indicated that control unit 3 is configured to:

[0363] o Determine multiple ratios (optical counting ratios).

[0364] o serves as input to one or more neural networks (NNs), providing multiple ratios and temperature values.

[0365] o This method utilizes one or more neural networks (NNs) to process multiple ratios by considering multiple data points from previous measurements of blood parameters taken during prior training (laboratory training).

[0366] o, as the output of one or more neural networks (NN), provides the value of each of the multiple blood parameters.

[0367] Each ratio is defined between the amount of radiation reflected or diffused by blood due to excitation at a defined wavelength (a count calculated based on the radiation received by the photodiode) and the amount of radiation reflected or diffused by blood due to excitation at another defined wavelength (a count calculated based on the radiation received by the same photodiode). For example, Figure 10 The x-axis of the graph shows the "ratio 805InGaAs / 1450", which is the ratio of the optical count to the radiation read from the InGaAs photodiode 9 at excitation radiation at 805 nm (back reflection radiation) (the numerator of the ratio) and the radiation read from the same InGaAs photodiode 9 at excitation radiation at 1450 nm (back reflection radiation). To provide another example, Figure 11 The horizontal axis of the graph indicates the "ratio 805 / 660", which is the ratio of the optical count to the radiation (back reflection radiation) read from the excitation radiation of the silicon photodiode 8 at 805 nm (the numerator of the ratio) and the radiation (back reflection radiation) read from the excitation radiation of the same silicon photodiode 8 at 660 nm.

[0368] Basically, the control unit 3 receives the actual blood temperature value and analog electromagnetic and / or optical response information from photodetectors 8 and 9 as input, processes it based on prior training, and measures parameter values. The actual blood temperature value is measured by temperature sensor 12, which detects the temperature of the blood flowing into containers 25 and 25'. The temperature value input is useful because, as temperature changes, the excitation element exhibits different electromagnetic radiation emission states, and the blood's response to the excitation electromagnetic radiation changes as a function of temperature.

[0369] The control unit 3 is configured to control a plurality of excitation elements 4, 5 during an excitation step, which includes activating the plurality of excitation elements 4, 5 according to a specified time sequence. For example, the control unit 3 can activate the plurality of excitation elements 4, 5 one at a time according to the following time sequence, such that blood is excited: activating the LED element that causes excitation at 660 nm, then activating the LED element that causes excitation at 805 nm; then activating the LED element that causes excitation at 1450 nm; and finally activating the LED element that causes excitation at 1550 nm; and also activating other LED elements at 525 nm, 940 nm, and 1050 nm. Essentially, it should be understood that following the specific time sequence described above is not necessary for the measurement of the plurality of parameters and is therefore not limited in any way; thus, the control unit 3 can operate by exciting blood according to other excitation sequences.

[0370] Preferably, the control unit 3 is configured to alternately activate the first excitation element 4 and the second excitation element 5 to alternately excite blood flow at a first wavelength or a first plurality of wavelengths selected from a first plurality of wavelengths (525 nm, 940 nm, optionally 1050 nm) and at a second wavelength or a second plurality of wavelengths selected from a second plurality of wavelengths (660 nm, 805 nm, 1450 nm). Preferably, the control unit 3 is configured to alternately activate the first excitation element 4 and the second excitation element 5 to alternately excite blood flow at the first plurality of wavelengths and the second plurality of wavelengths.

[0371] The control unit 3 is configured to control at least one or two excitation elements 4, 5 during the excitation step, in which the blood flow is excited one wavelength at a time.

[0372] More specifically, the control unit 3 is configured to activate (turn on) each LED element in a timed manner, such that within a given reference time unit (e.g., 1 second), there are dozens of measurements of the optical count of transmission for each LED element (each light source). Specifically, the control unit 3 is configured to activate each LED element in a timed manner according to the previously described timing, such that there are 20 measurements of the optical count of transmission for each LED element within 1 second. As the number of measurements within a given time unit increases, the influence of noise on the measurement has a smaller weight (the acquired measurements can be averaged), and therefore the accuracy of the measurement improves because the data used is statistically more reliable.

[0373] In essence, the control unit 3 constitutes a component of the device 1, 1' equipped with artificial intelligence (based on machine learning as described below) and is configured to detect the value of each parameter that the artificial intelligence considers to correspond to a previously determined ratio based on multiple data from previous measurements.

[0374] Specifically, the control unit 3 includes artificial intelligence information, such as one or more matrices that can be used by the one or more neural networks. The artificial intelligence information is encoded in its firmware and enables the computation of multiple parameters by means of one or more neural networks NN and by means of a given computational model.

[0375] In addition to the information encoded in the firmware, the control unit 3 is also configured to provide reference values ​​for a first parameter (oxygen saturation) to be measured and a second parameter (hematocrit) to be measured as input to one or more neural networks. These reference values ​​are acquired during a calibration step prior to use of devices 1, 1' and stored in the device's memory (e.g., EEPROM memory); the memory may be part of the control unit 3. Such calibration prior to use of devices 1, 1' may be performed by the manufacturer of devices 1, 1', for example, in a laboratory; in any case, calibration is not performed by the end user.

[0376] For each device 1, 1' produced, the information encoded in the firmware, especially the artificial intelligence information, is the same, while the aforementioned information stored in memory can vary between devices 1, 1' because it takes into account the variability of each individual device 1, 1' by means of calibration performed in the laboratory, which can be related to factors such as the variability of hardware, components, and their specific, even infinitesimal, geometric positions within the device's housing.

[0377] When measuring oxygen saturation and / or hematocrit, the control unit 3 can also be configured to take into account values ​​related to blood flow, particularly volumetric blood flow rate. As described below, the control unit 3 can perform this operation by correcting the measured values ​​of oxygen saturation and / or hematocrit based on blood flow.

[0378] In terms of components, control unit 3 may include at least a microprocessor (MP) and an analog-to-digital converter (ADC). The microprocessor (MP) can determine and supervise the execution of the aforementioned operations, and the ADC performs the operation of converting analog information into digital data. Artificial intelligence information is encoded in the firmware of the microprocessor (MP). Control unit 3 may include the previously mentioned memory, such as EEPROM memory.

[0379] Control unit 3 may also include an analog “AFE” front end (AFE chip), i.e., a system that integrates the analog technology required to achieve optimal interfacing with the analog-to-digital converter. This interfacing fundamentally involves adapting the analog signal captured by the sensor (photodetector) to the functional specifications of the analog-to-digital converter regarding amplitude dynamics (amplification) and frequency bandwidth (anti-aliasing filtering), i.e., the principles governing the sampling of the analog signal. In fact, the analog front end performs complex analog signal processing generally referred to as “conditioning,” much of which is strictly dependent on the application and nature of the sensor (photodetector).

[0380] The control unit 3 may also include at least one printed circuit board assembly PCB1. Essentially, the printed circuit board assembly PCB1 is a board filled with, i.e., on which certain electronic components are arranged, enabling the assembly to perform its intended function or multiple functions. As shown in the figures, the control unit 3 may include a first printed circuit board PCB1 for a microprocessor MP and a second printed circuit board PCB2 for an analog front end. Figure 7 As shown, constraint elements 2e, particularly threaded elements, can be provided to fix the printed circuit board assembly PCB1, excitation components 4 and 5, and electromagnetic radiation detection components 8 and 9.

[0381] The values ​​of oxygen saturation and hematocrit are calculated by the artificial intelligence of devices 1 and 1' at essentially the same time; therefore, the measurement of these parameters is essentially instantaneous. Furthermore, output parameters (hematocrit, saturation, hemoglobin) are provided simultaneously by devices 1 and 1' via control unit 3; temperature data measured without artificial intelligence assistance is also synchronized with other parameters and output together. Thus, the end user of devices 1 and 1' has access to all parameters measured by the simultaneously available devices 1 and 1', and in particular, these parameters can be displayed on a user interface such as display device 91, operatively connected to or operable to devices 1 and 1'. The parameters can be made available at a certain rhythm (e.g., every second, every 5 seconds, every 10 seconds) or continuously and additionally or alternatively on demand (e.g., at the request of medical machines 90', 90'').

[0382] In a second embodiment of device 1', the device can be associated with pipe 25', and control unit 1 is configured to perform the following operations:

[0383] - The type of the 25' detection tube.

[0384] - Prepare for measurement based on the detected type of tube 25'.

[0385] Among the potentially different properties of tubes 25', it is important to note their color or hue, as this can alter the blood's response to electromagnetic excitation. Tubes 25' are typically plasticized polyvinyl chloride (PVC), or at least based on plasticized PVC, and are not completely transparent. Furthermore, the sterilization process that tubes 25' may undergo before use can also lead to changes in their color or hue. It should be remembered that if the actual color or hue of the tube 25' on which measurements are taken is not properly taken into account, the blood response received by the electromagnetic radiation detection element will be incorrect (e.g., because devices 1, 1' may expect a transparent container, while the tube is not actually a transparent container, thus modifying the electromagnetic response "recorded" by the electromagnetic radiation detection element), and therefore the measurement of the expected parameters will be unreliable.

[0386] Then, the detection of tube 25' type involves the detection of the color or hue of tube 25; then the control unit 3 prepares itself for measurement, for example, by adapting the measurement mode of one or more parameters to the detected container or tube 25' type, based on the detected color or hue of tube 25'.

[0387] The color or hue of tube 25' is detected before blood is stimulated, specifically before blood flows into tube 25'. When the color or hue of tube 25' is detected, a fluid other than saline or blood is preferably introduced into tube 25'.

[0388] The control unit 3 is configured to perform a measurement preparation operation based on the detected color or hue of the tube 25' by selecting a given matrix from multiple matrices available to the neural network NN; each matrix corresponds to a given color or hue of the tube 25'. This selection operation can be performed by querying the memory of the devices 1 and 1', which stores information related to the multiple matrices.

[0389] The technical features disclosed herein that relate to the function of apparatus 1, 1' or its parts / components / elements, particularly to the operation of control unit 3, are applicable in the context of their corresponding use in the apparatus or method steps described below.

[0390] Machine learning setup based on one or more neural networks

[0391] The learning was conducted through extensive in vitro laboratory testing, i.e., using in vitro blood prepared and circulated in setting 50, wherein the states of the blood and environment were altered to simulate virtually all possible states that the device 1 according to the invention might undergo in clinical use (see [link to documentation]). Figure 9 The simulated states include blood temperature, blood flow rate, ambient temperature, blood oxygen saturation, and hematocrit. The following describes the testing and training of the apparatus in a laboratory to determine the settings 50 for the automated learning model. During the learning tests performed, the environmental states remained unchanged; therefore, measurements were obtained at room temperature. However, it should be noted that, in general, the ambient temperature can be changed; this requires the use of settings 50 within an environmental chamber.

[0392] Set 50 in Figure 9 The diagram shows and includes two circuits through which extracorporeal blood circulates. More specifically, there is a blood preparation circuit 51 and a main blood circuit 52, in which blood suitably prepared by means of the blood preparation circuit 51 circulates to perform parameter measurements. Figure 9 The loops 51 and 52 are depicted differently using corresponding and different lines. This is mainly in... Figure 9 The main blood circuit 52 (which is shown in the upper part) is illustrated in the upper part. Figure 9 (extending to the lower part of the figure on the left), while Figure 9 The lower part shows the blood preparation circuit 51. In the blood preparation circuit 51 and the main blood circuit 52, blood is circulated through corresponding processing components 53, 54; in particular, for this purpose, the arrangement shown provides a main centrifugal pump 54 for the main blood circuit 52 and a secondary centrifugal pump 53 for the blood preparation circuit 51.

[0393] The blood preparation circuit 51 allows blood to be prepared under desired conditions. For this purpose, a blood oxygenator 55 and a plasma filter 56 are arranged along the blood preparation circuit 51.

[0394] The plasma filter 56 is a component whose function is to extract plasma from blood, allowing the blood to be "concentrated" to increase the hematocrit value. The plasma filter 56 is connected to the extracted plasma discharge container 57, into which the plasma removed by the plasma filter 56 is poured. Plasma removal occurs due to the pressure gradient established between the blood preparation circuit 51 and the extracted plasma discharge container 57; to interrupt removal, the line connecting the plasma filter 56 and the extracted plasma discharge container 57 is shut off.

[0395] Regarding the blood oxygenator 55, it is a component of the setup 50 that functions in the blood preparation circuit 51 as equivalent to the human lungs; as described below, it is configured to oxygenate the blood, remove carbon dioxide, and also heat or cool the blood. For this purpose, the blood oxygenator 55 includes a heat exchanger and is connected to a thermostatic bath 58. The setup 50 also includes a water pump 59, which is configured to circulate water between the thermostatic bath 58 and the blood oxygenator 55. The thermostatic bath 58 is configured to heat or cool the water, which circulates in the heat exchanger within the blood oxygenator 55 by means of the water pump 59, thus the thermostatic bath 58 cools or heats the blood to a desired temperature. To change the saturation state of the blood, and particularly the oxygen saturation state, the blood oxygenator 55 is connected to a gas mixer 60, which is upstream connected to an oxygen tank 61, a nitrogen tank 62, and a carbon dioxide tank 63. The gas mixer 60 is configured to mix gases from the three tanks 61, 62, and 63 just described in different proportions. Figure 9 As shown, the tanks can take the form of cylinders 61, 62, 63 configured to deliver the corresponding gas to the gas mixer 60.

[0396] The blood preparation circuit 51 and the main blood circuit 52 share a common element including a blood container 64, which in... Figure 9 The image is shown as a blood bag. Blood container 64 acts as a reservoir from which blood is drawn by auxiliary centrifugal pump 53, and because the blood preparation circuit is a closed loop, it returns properly prepared blood to the reservoir. Blood container 64 is connected to isotonic solution source 65, which is configured to provide isotonic solution. Since isotonic solution does not contain red blood cells, its supply to blood container 64 allows the blood contained therein to be diluted. The isotonic solution (also referred to as saline) enters the main blood circuit 52 by gravity and performs the opposite action to that performed by plasma filter 56. Blood container 64 can be fed properly prepared blood from the blood preparation circuit 51 just described into the main blood circuit 52 by means of main centrifugal pump 54.

[0397] Configuration 50 also provides multiple devices 1L, 1L' (where "L" stands for learning, indicating that these devices undergo automatic learning) along the main blood circuit 52, which are associated with corresponding containers 25, 25' of the aforementioned type. More specifically, device 1L is of the type corresponding to the first embodiment (and associated with the corresponding test tube 25), while device 1L' is of the type corresponding to the second embodiment (and associated with tube 25'). The difference from devices 1, 1' is that devices 1L, 1L' undergo machine learning to develop artificial intelligence (computation methods, firmware, related logic, and code) that will then be implemented in devices 1, 1', which are already equipped with artificial intelligence and only require simple calibration in the laboratory before they can be delivered and used. The containers associated with devices 1L, 1L' are test tubes 25 and tubes 25' arranged along the main blood circuit 52, respectively. Tubes 25' have different formulations (and therefore typically different colors) and are connected by means of connecting elements 77 (see See...). Figure 9 The color and / or hue of the individual fitting 25' depends on the chemical formulation of the tube material and / or the tube sterilization process. Multiple devices 1L' can be configured to connect to tube sections of the same type (i.e., the same formulation and the same color or hue); in this case, a single tube of the same color or hue can be configured instead of an individual fitting. It is advantageous for device 1L' to learn to recognize and differentiate tubes of different types, colors, and / or hues to provide accurate measurement of parameters; artificial intelligence derived from machine learning provides device 1' with the necessary information to prepare it to recognize tubes of different types, colors, and / or hues and adjust measurements accordingly. The test tubes 25 and fittings 25' coupled to devices 1L and 1L' respectively are of disposable type. Figure 9 The setting 50 allows the probe to learn the behavior of different tube types. For learning experiments, tubes 25' of the same color can be set simultaneously (i.e., in the same learning session or round) to collect more statistically valid data; subsequently, the tube type can be changed (replacing tube 25' with tubes of other different colors) and more data can be collected, etc., to have a large history of instances for training the neural network.

[0398] Therefore, the devices 1L, 1L' provided by setting 50 are photoelectric probes configured to excite blood and detect the associated electromagnetic and / or optical responses; their photoelectric excitation unit (excitation element) and their electromagnetic and / or optical response detection element (electromagnetic radiation detection element) are similar to those described in the corresponding embodiments of previously referenced devices 1, 1'. Essentially, the devices 1L, 1L' provided are of the type previously described, except that they lack an algorithm capable of autonomously measuring blood parameters in clinical use, as this algorithm is precisely developed through the training described herein undergone by devices 1L, 1L'. More specifically, devices 1L, 1L' and devices 1, 1' differ in their calibration coefficients, as described below. After preparation of the devices 1L, 1L' by means of learning, which is precisely performed through learning in the laboratory, devices 1L, 1L' will be configured to calculate parameter values ​​using an appropriately trained neural network for all operating states expected to occur during the clinical use of devices 1, 1'. Reiterating, this learning / calibration is performed in the laboratory, i.e., prior to the clinical use of devices 1, 1'. Figure 9 As shown, there can be two test tubes and corresponding devices 1L, and three devices 1L'; it should be understood that more than two devices 1L and corresponding test tubes, and / or two or more than three devices 1L', can be provided. In embodiments, at least five devices 1L and at least five devices 1L' can be provided. As the number of devices 1L and 1L' increases, the amount of "raw" data collected also increases, and greater variability between devices is included.

[0399] During the learning process, the devices 1L and 1L' "question" the blood by emitting electromagnetic radiation of different wavelengths and detect the response in the electromagnetic radiation by deriving calibration curves as described below (in particular, at least one calibration curve for hematocrit at a fixed oxygen saturation value and at least one calibration curve for oxygen saturation at a fixed hematocrit value).

[0400] Setting 50 also includes a blood flow meter 66 and a temperature detector 67 along the main blood circuit 52; the temperature detector 67 serves as a temperature verification and reference instrument.

[0401] Blood flow meter 66 is configured to measure the blood flow rate in the main blood circuit 52. Blood flow meter 66 can also measure the blood flow rate downstream of the main centrifugal pump 54. Figure 9 In the diagram, blood flow meter 66 is shown connected to the main centrifugal pump 54.

[0402] Temperature detector 67 is configured to measure the temperature of blood, preferably near a container coupled to the corresponding device. Figure 9In the figure, temperature detector 67 is shown in the form of a digital thermometer, which has a temperature sensor immersed in blood and is arranged upstream and near the container coupled to the devices 1L, 1L'.

[0403] The main blood circuit 52 also includes a blood sampling point 68 and a reference blood analyzer 69. The blood sampling point 68 is a point in the circuit where an in vitro blood sample is collected; the collected sample is analyzed by the reference blood analyzer 69, which is a reference instrument to which the "raw" measurements (and associated "raw" data) of parameters obtained from multiple devices 1L, 1L' are referenced. The reference blood analyzer 69 is a clinically accepted reference instrument and therefore provides parameter measurements with the necessary accuracy. Essentially, the reference blood analyzer 69 provides reference values ​​for parameters under the specific conditions in which the measurement is performed (actual blood temperature and, for example, blood oxygenation). In the performed tests, the blood reference analyzer 69 measures at least the blood oxygen saturation value, the blood hemoglobin concentration, and the hematocrit value. Figure 9 The blood reference analyzer shown is a laboratory blood chemistry analyzer 69.

[0404] use Figure 9 The setting is 50, and then the previously indicated state is changed, and for each change, the electromagnetic radiation response generated by the excitation of blood is acquired. Thus, the ratio between optical counts is acquired, and a calibration curve is generated; the acquired curve is digitized by means of components built into devices 1L, 1L'.

[0405] In this way, analog information of the electromagnetic and / or optical response of blood to a given change in state is transformed into processable digital data. The values ​​of the parameters corresponding to the changed state, the analog information, and the corresponding digital data are correlated with the values ​​of the parameters (oxygen saturation and hematocrit in the performed test) measured by a reference blood analyzer. By extensively simulating every possible state that may occur in clinical use, thousands of associated parameter / digitalized curve data are obtained for each of the states set in the laboratory, covering all states for the parameters (oxygen saturation and hematocrit) that you want to measure with your device 1, 1'.

[0406] The setup also includes a data collector 70 and a data processor 71. The data collector 70 is connected to multiple devices 1L, 1L' to collect data from the devices 1L, 1L'; the collected data is digital data related to the electromagnetic and / or optical response of blood. For example... Figure 9 As shown, in order to collect data, the data collector 70 may have a plurality of input terminals corresponding in number to the devices 1L, 1L' of the setup 50, and at least one output terminal for connection to the computer 71. The data collector 70 is essentially an electronic instrument; Figure 9The data collector used in the experiment shown is a multiplexer 70. After collecting the data, the data collector 70 transmits the data to the processor, which then... Figure 9 The diagram shows a personal computer 71. The computer 71 collects "raw" data from devices 1L, 1L' for all operating states intended to be tested; this "raw" data constitutes a dataset for training a neural network.

[0407] Configuration 50 may also provide an external archive 72, which is connected to computer 71 and configured to store data received from computer 71. Essentially, the external archive is an electronic archive 72, which can be remote and used for storing data.

[0408] The setup 50 for implementing training has been described; now, a machine learning method based on a neural network (NN) is described.

[0409] Machine learning methods based on one or more neural networks

[0410] Such as by means of Figure 9 The settings mentioned herein allow for discrete steps of changing the state of temperature, oxygen saturation, and hematocrit, as well as each of multiple combinations of these parameters, within all expected measurement ranges (13% to 55% for hematocrit, 35% to 99.9% for blood oxygen saturation, and 9°C to 42°C for blood temperature). The process of learning and designing a device for correctly measuring Sat% and Hct% is accomplished by performing the following steps.

[0411] 1) Perform gain and intensity settings for individual LED elements, i.e., maximize the optical count of each individual LED element at the extreme values ​​of the measurement range of Hct% and Sat%. Gain is the ability of a photodiode to convert a light signal into a current signal, while the optical count is an indicative measurement of the signal transmitted through the tube and detected by the photodiode. The maximum count value is approximately 4000; beyond this value, the signal saturates and therefore no longer indicates the measurement. Therefore, in extreme measurement conditions (i.e., for measurements of parameters at the end of their measurement range), it is necessary to set the count to avoid exceeding this maximum threshold.

[0412] 2) The calibration curve for Hct% was constructed using a "best-fit" technique, exhibiting a fourth-order curve representing the ratio of the optical counts of electromagnetic radiation read from an InGaAs photodiode 9 at an excitation of 805 nm to the optical counts of electromagnetic radiation read from the same photodiode 9 at an excitation of 1450 nm, obtained relative to a reference instrument. Blood oxygen saturation (Sat%) was kept constant at 80%, blood temperature was maintained at 37°C, and hematocrit values ​​increased in 3 percentage point increments from 12 Hct% to 55 Hct% (see [reference]). Figure 10 ; Ratio = count 805 / count 1450). Figure 10 Each point indicated on the graph corresponds to the measurement taken.

[0413] 3) Then, the calibration curve for blood oxygen saturation (Sat%) was constructed using the "best fit" technique. This curve is a third-order curve representing the ratio of the optical count of electromagnetic radiation read from an excitation at 805 nm by a silicon photodiode 8 to the optical count of electromagnetic radiation read from an excitation at 660 nm by the same photodiode 8. The hematocrit (Hct%) was kept constant at 15%, the blood temperature was maintained at 37°C, and the Sat% increments were made in steps of 5 points within the range of 35% to 98% (see [link to relevant documentation]). Figure 11 ; Ratio = count 805 / count 660). Figure 11 Each point indicated on the graph corresponds to the measurement taken.

[0414] 4) Then, continue to construct the temperature calibration curve (the linear relationship between the fluid temperature detected by the device and the fluid temperature of the reference instrument under data acquisition conditions at an ambient temperature of 24±2°C).

[0415] 5) In this step, artificial intelligence using a neural network (NN) of the type described below is used to create a weight matrix to accurately calculate Sat% and Hct% including their interdependencies. This step requires acquiring a dataset for each tube or test tube the device will operate on. The dataset is acquired by setting the Hct% and blood temperature and scanning the Sat% value for each established Hct%; scans are performed by changing the blood state to obtain Sat% values ​​across its entire range, and this process is repeated for each Hct% value across its entire range. Depending on the method used, after setting a specific blood temperature, a specific value of Hct% is kept fixed, and a scan is performed across the entire measurement range of Sat%; then, at the same blood temperature, the value of Hct% is changed, and Sat% is scanned again to cover the entire measurement range of Hct%. Next, another blood temperature is set, and the above two scans of Hct% and Sat% are repeated. The aim is to substantially cover all possible values ​​of Sat% and Hct% within the desired temperature range, i.e., to cover all values ​​of the parameters of the blood temperature of interest, Hct%, and Sat% within their respective ranges. The method for achieving this objective has just been described and has proven advantageous; it should be understood that other methods can achieve the same objective in other ways (e.g., by setting the temperature after the value of Hct% or by using another sequence of settings and variations of parameters blood temperature, Hct%, and Sat%).

[0416] 6) In this step, artificial intelligence is used to calculate the correlation between Hct% and Sat%; this step can be performed using the same neural network NN used in step 5) or another neural network (second neural network) with essentially the same structure.

[0417] 7) In this step, artificial intelligence is used to calculate the correlation between Hct% and blood temperature. This step can be performed using the same neural network as in step 5) or another neural network (a third neural network) with essentially the same structure.

[0418] Preferably, only one neural network NN is used during learning. If higher accuracy is desired, two additional neural networks, namely a second neural network and a third neural network, can be combined to improve the results from the output of the first neural network (the neural network in step 5).

[0419] Each neural network preferably has the following structure and computation method.

[0420] In the tests performed, the following were selected: Figure 12The diagram illustrates a multilayer perceptron neural network (MLP or multilayer perceptron). A multilayer perceptron neural network (NN) is an artificial neural network model that maps an input dataset to an appropriate output dataset. Furthermore, such a neural network NN is feedforward type, meaning it is an artificial neural network where the connections between nodes do not form loops. It should be understood that different types of machine learning neural networks can be chosen depending on the desired machine learning approach; the type of neural network chosen will be described below with reference to a tested application involving the direct measurement of oxygen saturation and hematocrit parameters using artificial intelligence. Obviously, the following modifications are applicable to the measurement of one or more other blood parameters.

[0421] Figure 12 The neural network NN presents an input or input layer L0 with six neurons, a first layer L1 with twelve fully connected neurons, a second layer L2 with ten fully connected neurons, and a third layer L3 with two fully connected neurons. The two neurons of this final layer L3, which constitutes the output layer or output, correspond to the output values ​​of the neural network, namely: the Sat% value and the Hct% value. Regardless of the number of neurons in the output layer L3, the other layers L0, L1, and L2 may present different numbers of neurons and / or layers than described herein, depending on the specific optimization performed for the chosen neural network model. The number of neurons in each layer may be constrained in part by the computational power of the microprocessor MP of the control unit 3 of the devices 1L and 1L'. All neurons in the network are S-shaped activated; the activation of a neuron corresponds to the activation of the neuron and the operation of its information transfer function (in Figure 14 The moment shown in the figure and referred to below as sigmoid is when it enables the transmission of incoming stimulus information.

[0422] The following describes the input data (input data) of the neural network NN; see [link to relevant documentation]. Figure 12 Two of the six neurons in the input layer L0 correspond to the Sat% and Hct% values ​​measured by devices 1L and 1L' (respectively...). Figure 12 Sat% in IN and Hct% IN Three of the six neurons correspond to ratios of 805 / 660, 805 / 1450, 805 / 1550, or alternatively 940 / 1050; the 805 / 1550 ratio is used to improve the measurement accuracy of Hct%, while the 940 / 1050 ratio is used because both the 805 / 1550 and 940 / 1050 ratios exhibit good dynamic variation across the entire measurement range of Sat% at a wavelength of 1050 nm. The other neuron in layer L0 corresponds to the blood temperature value detected by temperature detector 67. Figure 12 T in IN)correspond.

[0423] Input parameters are scaled to normalize their magnitude to prevent very large values ​​from being weighted more heavily than smaller values ​​in the neural network, and also to allow for more efficient training of the network. Essentially, based on the collected training set, the minimum and maximum values ​​of each parameter input to the network are computed, and these minimum and maximum values ​​are normalized before being passed to the network, and then denormalized to obtain the output data. These values ​​must be rescaled before being passed to the network in this way: Normalized value = (Collected value - Minimum) / (Maximum - Minimum). Similarly, the values ​​output from the network must be rescaled in this way to obtain the actual values: Denormalized value = Value * (Maximum - Minimum) + Minimum.

[0424] The neural network (NN) is then able to calculate the Sat% and Hct% values ​​(output data) of the blood flowing into the container based on the input data mentioned above. In the selected and tested neural network, this calculation is performed as follows, enabling the measurements taken by the device.

[0425] The calculation method used is Figure 13 The following formula is shown and involves the symbol *, where the symbol * indicates a scalar product:

[0426] (Formula 1)

[0427] (Formula 2)

[0428] In Formula 1, the following should also be specified:

[0429] - w i = weight i

[0430] - b i = bias i

[0431] - “wi” and “bi” are matrices of weights and biases, respectively; the weights and biases are calibration coefficients.

[0432] By providing matrices, the computational model is a mathematical matrix model.

[0433] For Formula 2, specifying a out It is the output of each neuron, and therefore also the output of the inner layers L1 and L2.

[0434] In more detail:

[0435] - For the first layer L1:

[0436] a1 = x_input * w1 + b1

[0437] z1 = sigmoid(a1)

[0438] - For the second L2 layer:

[0439] a2 = z1 * w2 + b2

[0440] z2 = sigmoid(a2)

[0441] - For the third layer L3:

[0442] a3 = z2 * w3 + b3

[0443] z3 = sigmoid(a3)

[0444] Output = z3

[0445] There are two neurons in the output layer L3, one of which has Sat% as its output and the other has Hct% as its output, which are the desired output parameters related to blood circulation in the container to which the device is connected.

[0446] It should also be noted that:

[0447] - The range of "i" is from 1 to N.

[0448] - "N" is the number of nodes (neurons) in each layer of the neural network.

[0449] - "x_input" is a vector of input values / parameters (containing a vector of parameters related to optical counting and blood temperature).

[0450] - The letters “a”, “b”, and “w” are derived from the learning stage.

[0451] - "g(z)" is the activation function of the neuron and Figure 14 It is shown in the middle.

[0452] The learning process uses example measurements to optimize the values ​​of the weight and bias matrices, resulting in weight and bias matrices for each layer. Therefore, w1 and b1 are the weight and bias matrices for the first layer (L1), w2 and b2 are the weight and bias matrices for the second layer (L2), and w3 and b3 are the weight and bias matrices for the third layer (L3). Optimization, i.e., finding the “optimal” values ​​of weight and bias, means finding the values ​​of weight and bias that minimize the cost function, which represents the error between the actual measured values ​​and the network’s predictions.

[0453] Algorithm execution implemented in devices 1 and 1' Figure 13The instructions are shown. Thousands of training epochs were run (one epoch corresponds to a complete cycle of all examples), with an average batch size of 4 examples per batch. In the tests performed, the learning performance reached 4*10-1. 5 In each round, the adaptive learning rate starts at a value of 0.001 to avoid overfitting. It should be noted that the learning rate is one of several parameters set during the learning phase of the neural network; it modifies the optimizer steps. An optimizer called "Adam" is used, which is a derivative of the gradient method. In neural network terminology:

[0454] - Rounds = Forward and backward passes of all training examples. A round describes how many times the algorithm sees the entire dataset. Therefore, a round is completed each time the algorithm sees all samples in the dataset.

[0455] - Batch size = Number of training examples in the forward channel / Number of training examples in the backward channel. The larger the batch size, the more memory space is required.

[0456] - Number of iterations = Number of channels, number of instances used per channel [batch size]. One channel = one forward channel + one backward channel (forward and backward channels are not counted as two separate channels).

[0457] For less detailed information on machine learning, please refer to the literature on neural network theory.

[0458] For each link in the network, there exists a function transposed into C language code within the microprocessor MP, called the sigmoid function, which is the mathematical function connecting neurons (sublayer). The input to each neuron in the network is multiplied by the network parameter matrix, and the result is passed to the sigmoid function using the above formula. The result of the sigmoid function represents the intermediate output of each layer or the input to the neurons in the next layer.

[0459] During the learning process, a non-linear cost function (mean absolute error) was chosen, which was modified to double-weight the examples at low Sat% and Hct% (which suffer from higher percentage errors).

[0460] The final output of a neural network (NN) model is represented by a set of parameters, namely a matrix w of weights and biases. i and b i Essentially, the neural network model learns through extensive laboratory testing and measurement which values ​​of the two blood parameters (Sat% and Hct%) are appropriate as weights and biases of the output matrix w for the input vector x_input. i and b iThe optimal value is then determined. The mathematical model of the multilayer perceptron network is then implemented in C code within the microprocessor MP of devices 1 and 1'.

[0461] In summary, the procedure is as follows: Select a neural network model, that is, limit the number of layers, the number of neurons in each layer, and the activation function of the neurons.

[0462] The program continues the learning process, using an exemplary measurement and optimization matrix w of weights and biases. i and b i The value of . For each layer, there is a matrix w with weights and biases. i and b i Therefore, w1 and b1 are the weight and bias matrices for the first layer, w2 and b2 are the weight and bias matrices for the second layer, and w3 and b3 are the weight and bias matrices for the third layer (and so on if additional layers are provided). "Optimization" or "optimal values" means finding those weight and bias values ​​that minimize the cost function, which represents the error between the actual and predicted measurements performed by the network. After defining x_input, i.e., a vector containing the ratio from optical counts or parameters directly from optical counts and blood temperature, the algorithm implemented in the device executes... Figure 13 The operations shown are described above.

[0463] The developed computational methods, as a result of machine learning, are essentially algorithms encoded and implemented in the microprocessor MP of the device to perform the measurement of blood parameters. The computational methods and therefore algorithms are preferably encoded in program code, particularly C code, for execution by the microprocessor during the clinical use of the devices 1, 1'. Implementation of the computational methods and algorithms in the microprocessor MP of the devices 1, 1' makes the devices 1, 1' according to the invention independent in clinical use; all calculations required for measuring blood parameters are performed by a control unit built into the device and can be transmitted via serial cable to a medical machine interfaced therewith, which only uses the measured "complete data" (i.e., data ready for use by medical personnel) without performing calculations.

[0464] Devices 1 and 1' contain all the information needed to perform parameter measurements. The firmware code is written in such a way that for each of the two electromagnetic wavelength ratios calculated by acquiring the relative intensity of devices 1 and 1', along with the blood temperature value also measured by the devices, becomes an input parameter to the model. Each device 1 and 1' is then programmed so that a matrix containing weights and biases is stored (in EEPROM memory), while the algorithm based on the calculation method is written (encoded) into the firmware.

[0465] It has been verified that the neural model of the device trained in this way has the ability to measure / estimate the output value of Sat% with an accuracy of ±6% across the entire measurement range and for all states, and the ability to measure / estimate the output value of Hct% with an accuracy of ±3% across the entire measurement range and for all operating states; this accuracy is achieved using a matrix that includes weights and biases (derived from the neural network model based on what the device learns during the learning phase).

[0466] More details about neural networks

[0467] Neural networks are constructed based on the following assumptions. Three neural networks are described below; the device is referred to as a "probe". Each network has the same number of neurons in the input layer L0 as the number of input values ​​and the same number of neurons in the output layer L3 as the number of output values.

[0468]

[0469] Below is a reference photodiode used to read the optical count:

[0470] - Optical counting ratio 805 / 660: Si photodiode,

[0471] - Optical counting ratio 805 / 1450: InGaAs photodiode,

[0472] - Optical counting ratio 940 / 1050: Si photodiode,

[0473] - 660 Optical Counting: Si Photodiode,

[0474] - Optical counting of 805: Si photodiode,

[0475] - 805 Optical Counter: InGaAs Photodiode

[0476] - Optical counting from 1450: InGaAs photodiode,

[0477] - Optical count from 1550: InGaAs photodiode.

[0478] The first neural network has six neurons in the input layer L0 and two neurons in the output layer L3. As indicated above, the values ​​of Hct% and Sat% at the outputs of the two calibration curves are two of the six input parameters of the neural network. As previously mentioned, the first neural network described above (see also...) Figure 12This is sufficient to achieve the desired accuracy in measuring the parameters Sat% and Hct%; in this case, the artificial intelligence of devices 1 and 1' provides a single neural network NN. However, if this is insufficient and / or higher accuracy is desired, a second and third neural network can also be used, or the number of neural networks may be equal to two or greater than three.

[0479]

[0480] The second neural network has: two neurons in the input layer L0 (corresponding to the input values ​​of the calculated Sat% and Hct% outputs from the first neural network); and two neurons in the output layer L3 (corresponding to the detected Sat% and Hct% output values).

[0481]

[0482] The third neural network has: two neurons in the input layer L0 (corresponding to the input values ​​of the Sat% and Hct% outputs calculated by the second neural network and the blood temperature); and two neurons in the output layer L3 (corresponding to the detected Sat% and Hct% output values).

[0483] When developing / designing a neural network and identifying the coefficients / weights of the computation matrix, the network's input / output is as follows.

[0484]

[0485] Therefore, when using multiple neural networks, the structure of the neural networks is the same, except for the number of neurons in the input layer L0 and the corresponding input values, which vary depending on the type of network to be designed. The output data calculated by the neural network through artificial intelligence are the Sat% and Hct% values ​​for each neural network, while the Hb (hemoglobin) value is calculated mathematically because it is derived from the hematocrit value of erythrocytes. The Hb value can be calculated according to the following formula (relative to a reference blood analyzer 69): Hb (g / dL) = Hct% / approximately 3.

[0486] Preparation (calibration) of the device after training.

[0487] Each device 1, 1' produced after training the aforementioned devices 1L, 1L' is equipped with firmware that takes into account the aforementioned algorithm, and is therefore equipped with artificial intelligence functions.

[0488] For each of these devices 1 and 1', only two curves are acquired: a fixed Sat% calibration curve and a fixed Hct% calibration curve, without having to perform the full training described above. Therefore, in the laboratory, it is necessary to acquire these two curves so that the probe has all the necessary inputs to provide the desired output. These can be viewed as curves that allow the probe to provide initial saturation and hematocrit, which the probe uses together with the light count ratio for each measurement as input (see [reference]). Figure 12 (Two neurons in the L0 input layer are dedicated to these two input values). The two calibration curves above are similar to... Figure 10 The curve shown (hematocrit calibration curve) and Figure 11 Saturation calibration curves. Artificial intelligence allows for the calibration of devices 1 and 1' based on these two calibration curves; the devices are then ready for measurement of multiple parameters.

[0489] In other words, each device 1, 1' manufactured after training probes 1L, 1L' is calibrated in the laboratory (using the aforementioned calibration curves), so that the end user of device 1, 1' does not need to perform calibration and thus has instruments ready for immediate use. This calibration in the laboratory is relatively fast (e.g., tens of minutes or hours); essentially, as mentioned above, two calibration curves are preferably acquired at a blood temperature of 37°C, so that device 1, 1' has all the necessary inputs to output the desired parameter values. Essentially, this step of acquiring only two curves serves as the sole calibration operation for each newly manufactured probe and allows for consideration of variability between probes (hardware, component variability and their geometry, even infinitesimals within the probe housing), providing a robust starting point for the expected Sat% and Hct% measurements in the calibrated state.

[0490] Identify the correlation between the type (color / hue) of the tubes associated with the device according to the second embodiment.

[0491] The aim is to use LED elements with wavelengths of 525 nm and 940 nm to identify tube type correlations associated with device 1'. Optical counts of these wavelengths are obtained by having saline solution in tube 25' (i.e., before blood flows into the tube), and then the factors to be used (coefficients of the neural network NN, i.e., weights and biases, which are as many as the number of neurons) are determined.

[0492] Different hues of the tubes affect the optical counts detected at these wavelengths. Each tube 25' is identified based on a mathematical relationship between these two optical counts.

[0493] Identify the correlation with blood flow

[0494] To identify the correlation between saturation and blood flow, the optical count of a 940 nm wavelength LED element is used as a function of flow rate. Blood flow rate is preferably the volumetric flow rate of blood flowing into the extracorporeal blood circuit and thus into tube 25', and can be measured in liters per minute. Essentially, since the optical count of the 940 nm wavelength LED element is correlated with Sat% (Sat%), compensation for this correlation is required. The count caused by excitation of the 940 nm wavelength LED element is affected by both blood flow and saturation; in order to use these counts for flow detection, it must be ensured that the count is independent of saturation.

[0495] By introducing an additional LED excitation element with a wavelength of 1050 nm (varying with Sat%) mounted on the same excitation element as the 940 nm LED element (first excitation element) and then detected by the same photodiode (first photodetector), a "second" saturation (the ratio of the count for 940 nm excitation to the count for 1050 nm excitation) is obtained to compensate for the variation in the 940 nm wavelength LED element and thus make it immune to saturation dependence for flux detection.

[0496] Therefore, the obtained flow information is used to develop algorithms for correcting Sat% and Hct% based on blood flow.

[0497] Clinical use of the device

[0498] The present invention also relates to the use of the previously described devices 1, 1'. These devices 1, 1' are used to measure multiple blood parameters; these parameters are of the type described above.

[0499] The device does not require initial calibration and therefore does not include initial calibration. This use is preferably clinical, wherein devices 1, 1' can be used in conjunction with medical machines 90', 90' (e.g., cardiopulmonary bypass machine 90' ​​or extracorporeal membrane oxygenation (ECMO) machine 90' ​​or other machines). Due to training, the device does not require any initial calibration and is therefore ready to use.

[0500] Figure 8A and Figure 8B The corresponding device 100 and the possible clinical uses of the devices 1, 1' according to the invention are shown. More specifically, Figure 8A The clinical use of devices 1, 1' in an operating room is illustrated, wherein devices 1, 1' are used in conjunction with a cardiopulmonary bypass machine 90', and devices 1, 1' are connected to the cardiopulmonary bypass machine 90'. As for... Figure 8BIt illustrates the clinical use of the device in an intensive care unit, wherein devices 1, 1' are used in conjunction with an extracorporeal membrane oxygenation (ECMO) machine 90', and devices 1, 1' are connected to the ECMO machine 90'. An example of intensive care where the device 1 according to the invention can be suitably used is intensive care due to Covid, in which case monitoring one or more parameters related to the presence or concentration of oxygen in the blood may be crucial.

[0501] The measured parameter values ​​are available to the responsible medical personnel, for example, at the user interface of the medical machines 90' and 90''. The parameter values ​​can be provided to the medical machines 90' and 90'' continuously or rhythmically, and additionally or alternatively, according to their requirements.

[0502] Clearly, device 1 is suitable for clinical use other than those described herein, particularly in combination with any additional medical device and / or for use in any treatment or range requiring extracorporeal blood circulation.

[0503] equipment

[0504] The present invention also relates to a device 100, comprising devices 1, 1' of the type described above and medical machines 90', 90''. Devices 1, 1' are configured to cooperate and interact with medical machines 90', 90''.

[0505] Medical devices 90', 90'' may be cardiopulmonary bypass machines 90' or extracorporeal membrane oxygenation (ECMO) machines 90' or other medical devices. Medical devices 90', 90'' may include a user interface configured to make parameter values ​​measured by devices 1, 1' available. The user interface may include a display device 91, 91', such as a screen 91, for displaying the values. The display device 91 is operatively connected to or can be connected to devices 1, 1'. The display device 91 may be part of the medical device, or associated with or connected to the medical device. Figure 8A and Figure 8B The image shows both the device 1 according to the first embodiment and the device 1' according to the second embodiment; Figure 8A In the middle, they are respectively connected to screen 91 integrated in medical machines 90' and 90'' and screen 91' capable of displaying physiological parameters, while Figure 8B In this context, they are connected to the same screen 91 integrated in the medical machine 90', 90''. Alternatively, the user interface may make the parameter values ​​available or, in another way, transmit the parameter values ​​to medical personnel.

[0506] Device 100 includes an extracorporeal blood circuit 92 configured to circulate blood. The extracorporeal blood circuit 92 connects medical devices 90', 90'' to a patient; according to a first embodiment, a test tube can be displaced along the circuit associated with device 1. Figure 8A , Figure 8B Each of these also illustrates a device 1' directly associated with the extracorporeal blood circuit 92 according to the second embodiment. Essentially, devices 1, 1' can constitute accessories to medical devices 90', 90'', which functionally act as sensors designed to measure multiple parameters of the blood circulating in the extracorporeal blood circuit 92.

[0507] Methods for measuring multiple blood parameters

[0508] The present invention also relates to a method for measuring multiple blood parameters of the type described above. Preferably, the method is performed using the aforementioned apparatus 1, 1'.

[0509] The method includes at least the following steps:

[0510] - Using electromagnetic radiation of multiple defined wavelengths to stimulate blood flow.

[0511] - Detect multiple electromagnetic responses of blood, especially optical responses. These multiple electromagnetic responses include electromagnetic radiation reflected or diffused by the blood, particularly light.

[0512] - Receive analog information about multiple electromagnetic and / or optical responses of blood, including light reflected or diffused by the blood.

[0513] - Convert analog information of electromagnetic and / or optical response into digital data of electromagnetic and / or optical response.

[0514] - The electromagnetic and / or optical response digital data, along with the actual temperature value of the blood, are processed through one or more neural networks (NNs).

[0515] - As a result of processing operations performed by one or more neural networks (NNs), the value of each of the multiple blood parameters is determined.

[0516] The latter two steps involve the following steps:

[0517] o Define multiple ratios, each defined between a value indicating the amount of radiation reflected or diffused by blood due to excitation of a defined wavelength and a value indicating the amount of radiation reflected or diffused by blood due to excitation of another defined wavelength.

[0518] o serves as input to one or more neural networks (NNNs), providing the multiple ratios and temperature values.

[0519] o The multiple ratios are processed by using one or more neural networks (NNs) that consider multiple data points from previous measurements of the blood parameters taken during previous training.

[0520] o serves as the output of one or more neural networks NN, providing the value of each of the plurality of blood parameters.

[0521] This method can provide one or more steps corresponding to the operations described above regarding the control unit.

[0522] This method involves measuring blood oxygen saturation, hematocrit, and hemoglobin using artificial intelligence. Oxygen saturation and hematocrit are measured directly using the aforementioned artificial intelligence, while hemoglobin is measured indirectly, i.e., as a value derived from the hematocrit.

[0523] The method also provides, preferably by means of a suitable temperature sensor 12, to measure the actual temperature of the blood; this temperature constitutes both the input parameters for one or more neural networks and the output parameters of the device, such that the output parameters of the device are available and viewable by the end user of the device on a suitable display device.

[0524] This method may include steps that consider values ​​related to blood flow rate, particularly the volumetric flow rate of blood, when measuring blood oxygen saturation and / or hematocrit. This step may involve correcting the measured values ​​of oxygen saturation and / or hematocrit based on blood flow rate.

[0525] Before exciting blood flow with electromagnetic radiation of multiple defined wavelengths, the method includes the step of coupling devices 1, 1' to corresponding containers 25, 25'.

[0526] Specific method steps for the first embodiment of the device

[0527] The step of coupling device 1 to test tube 25 can be performed by coupling one or more coupling elements 17e, 17f of device 1 to one or more corresponding coupling elements 25b, 25c of test tube 25.

[0528] Specific method steps for the second embodiment of the device

[0529] The step of coupling device 1' to container 25' can be performed by accommodating a portion of the tube 25' of the extracorporeal blood circuit at the base 19 of the housing 2 of device 1' and bringing the covering elements 18, 18' into an operational configuration (closing the covering elements 18, 18' on the housing 2). This step involves moving the covering elements 18, 18' closer to the displaced constraint elements 22, 23 on the housing until engagement is established between the movable elements 22a, 23a and the corresponding bases defined on the opposing operational ends 21a, 21b of the closed portion 21 of the covering elements 18, 18'.

[0530] The closure of the covering elements 18, 18' results in the compression of the central portion 25a' of the tube 25' through which blood flows and the flattening of the opposing surfaces of the portions of the tube 25' that engage at the base 19 due to the compression of these surfaces (see [link]). Figure 6A The compression step resulted in a reduction of the blood channel cross-section of the 25' tube by 9% to 17% for lengths between 15 mm and 30 mm or equal to one of these values.

[0531] In an embodiment providing an oscillating compression element 18o, the step of closing the covering element 18' includes oscillating the compression element 18o relative to the body 18b of the covering element 18', and thus oscillating the compression element 18o relative to the blood flow tube 25'. Such a closing step includes gradually and smoothly compressing the tube 25', thereby smoothly changing the blood flow within the tube 25'.

[0532] This method enables the detection of the type of tube 25'. The step of detecting the tube type 25' is performed before the step of exciting blood flow at multiple defined wavelengths. The method can prepare the control unit 3 of device 1 for measurement based on the detected tube type 25'. The latter step may involve adapting the measurement pattern of one or more parameters to the detected tube type 25'. Preferably, the step of detecting the tube type 25' includes detecting the color of the tube. The step of detecting the type of tube 25' is performed while a fluid other than physiological saline or blood is flowing in the container. Preferably, the step of adapting the measurement pattern of one or more parameters to the detected tube type 25' includes selecting a defined matrix from multiple matrices that can be used by a neural network (each matrix may correspond to a specific color or hue of the tube). This selection may be performed via a query memory (EEPROM memory) storing information related to the multiple matrices.

[0533] Examples of possible modifications

[0534] This invention can be modified and / or further improved.

[0535] For example, devices 1 and 1', particularly device 1' according to the second embodiment, may be equipped with a display device, such as a monitor, on which blood parameters are displayed. Preliminary calculations of such blood parameters can be performed assuming a standard tube (i.e., the tube of the most commonly used color or hue) is coupled to device 1'. Device 1' can provide the possibility that the type of tube 25' actually coupled to device 1' (particularly the type of tube 25' in terms of color or hue; for example, input 1 might be required for a "blue" tube, input 2 for a "yellow" tube, etc.) exists on the display device as input, allowing device 1' to automatically load the coefficient matrix of the associated neural network and recalculate the blood parameters to take into account the tube actually coupled to device 1'. Visualization support and this interactive possibility make "on-the-go" measurement options more advantageous and faster.

[0536] According to the second embodiment, the device 1' may be equipped with sensors for verifying the position of the cover elements 18, 18', particularly for verifying that the cover elements 18, 18' are in the closed position (operational configuration). The control unit 3 may be provided such that parameter measurements can only be performed after verifying that the cover elements 18, 18' are correctly in the closed position.

[0537] The aforementioned control unit 3 provides a possible implementation of the artificial intelligence according to the present invention, which the applicant has verified to be particularly efficient; however, possible modifications / improvements or other implementations are not excluded. Similarly, different neural networks can be used to implement the artificial intelligence features of the present invention.

[0538] Further modifications may be conceived depending on specific needs or contingencies related to the implementation of the invention.

[0539] Other advantages and conclusions

[0540] In summary, the main advantages of this invention are as follows:

[0541] - Parameter measurements can be performed without the user having to perform any calibration on devices 1 and 1'; essentially, in clinical use, the user has devices 1 and 1' ready to use immediately because they contain all the information needed to measure the blood parameters of interest.

[0542] - Devices 1 and 1' are autonomous in terms of measurement, that is, they do not depend on other instruments outside of devices 1 and 1' to perform parameter measurements; external instruments may only be used to make the measured parameter values ​​available.

[0543] - Measurements performed by artificial intelligence are reliable across the entire measurement range of the parameters; more specifically, measurements performed by artificial intelligence show an accuracy of ±6% across the entire measurement range of the parameter Sat% and for all operating states, and an accuracy of ±3% across the entire measurement range of the parameter Hct% and for all operating states.

[0544] - Measurements are performed using compact, space-saving, and lightweight devices 1, 1' with appropriately miniaturized components.

[0545] The protection granted by this disclosure extends to each element, component, and / or step of the invention that is equivalent to the claimed element, component, and / or step. Therefore, according to the invention, each element, component, and / or step of the product / method can be replaced by an equivalent element, component, and / or step (hereinafter referred to as "equivalent"); such equivalents may have existed on the date of this patent document or subsequent conceived / developed application or priority claim.

Claims

1. A device for measuring multiple blood parameters using artificial intelligence, comprising: - At least one excitation element is configured to excite blood by electromagnetic radiation of multiple defined wavelengths; - At least one electromagnetic radiation detection component is configured to detect multiple electromagnetic responses of blood, the multiple electromagnetic responses including electromagnetic radiation reflected or diffused by the blood when the excitation component is excited by the blood in the operating state of the device. - The control unit is configured to perform the following operations: During the excitation step, the at least one excitation element is commanded to excite the blood through electromagnetic radiation of multiple defined wavelengths. o Receives analog information regarding multiple electromagnetic and / or optical responses of blood, said multiple electromagnetic and / or optical responses including electromagnetic radiation reflected or diffused by the blood. o Convert analog information of electromagnetic and / or optical response into digital data of electromagnetic and / or optical response; o The electromagnetic and / or optical response digital data, along with the actual temperature value of the blood, are processed by one or more neural networks. o As a result of the processing operations of the one or more neural networks, determine the value of each of the plurality of blood parameters. The control unit is configured to process the electromagnetic and / or optical response digital data and the actual temperature value of the blood via one or more neural networks and determine the value of each of the plurality of blood parameters by: o Define multiple ratios, each ratio being defined between a value indicating the amount of radiation reflected or diffused by blood due to excitation of a defined wavelength and a value indicating the amount of radiation reflected or diffused by blood due to excitation of another defined wavelength. o serves as input to one or more neural networks, providing the plurality of ratios and the temperature value. o The multiple ratios are processed by one or more neural networks by considering multiple data points of previous measurements of the blood parameters performed during previous training. o provides the value of each of the plurality of blood parameters as the output of the one or more neural networks. The device further includes: - A housing, wherein at least one or each of the excitation components, the control unit and the electromagnetic radiation detection component are housed within the housing; - A coupling portion, configured to allow coupling of the device to a container in which the blood can flow, the coupling portion being connected to the housing.

2. The apparatus according to claim 1, wherein, The control unit is configured to detect the value of each of the plurality of blood parameters that the artificial intelligence believes corresponds to a predetermined ratio based on the plurality of previously measured data.

3. The apparatus of claim 1, further comprising firmware, and the control unit including artificial intelligence information encoded in the firmware and adapted to enable the calculation of the plurality of parameters via one or more neural networks.

4. The apparatus of claim 1, further comprising a memory, wherein the control unit is configured to provide reference values ​​for a first parameter to be measured and a second parameter to be measured as input to the one or more neural networks, the reference values ​​being acquired and stored in the memory of the apparatus during a calibration step prior to use of the apparatus, the memory thus including information about the reference values.

5. The apparatus according to claim 1, wherein, The device is configured to measure oxygen saturation (SatO2) and hematocrit (Hct) using artificial intelligence.

6. The apparatus according to claim 1, wherein, The control unit is configured to command at least one or both of the excitation elements during an excitation step, which is set to excite blood flow at one wavelength at a time.

7. The apparatus according to claim 1, wherein, The at least one excitation element is configured to excite blood flow at at least the following wavelengths: 660 nm, 805 nm, 1450 nm, and at least one of 525 nm, 940 nm, and 1050 nm.

8. The apparatus according to claim 1, comprising: A first excitation element configured to excite blood flow at at least a first plurality of wavelengths; A second excitation element is configured to excite blood flow at a second plurality of wavelengths, and the control unit is configured to alternately activate the first excitation element and the second excitation element to alternately excite blood flow at the first plurality of wavelengths and at the second plurality of wavelengths.

9. The apparatus according to claim 1, wherein, The device is pocket-sized.

10. The apparatus of claim 1, wherein the apparatus is associated with a container in which blood can flow, and in an operational state, the apparatus is associated with the container. The control unit is configured to perform the following operations: - Detect the type of container. - Based on the type of container detected, prepare to perform a measurement.

11. The apparatus of claim 1, wherein the apparatus is associated with a tube, the control unit being configured to detect the color of the tube and perform the following operations: preparing for a measurement based on the detected color of the tube by selecting a determined matrix from a plurality of matrices that can be used by the neural network.

12. The device of claim 1, comprising a cover element movable relative to the housing and a base adapted to receive a container, wherein blood flows in the container in an operating state of the device, the cover element being configured to operate at least between the following configurations: - Operational configuration in which the covering element flattens the opposing surfaces of the container housed in the base. - Rest configuration.

13. The apparatus according to claim 12, wherein, The covering element includes a compression element adapted to compress the container housed at the base in an operating configuration of the covering element.

14. The apparatus according to claim 13, wherein, The compression element is configured to determine a reduction in the cross-sectional area of ​​the fluid passage of the container housed at the base, ranging from 9% to 17%.

15. The apparatus according to claim 13 or 14, wherein, The covering element includes a body, and the compression element is configured to oscillate relative to the body.

16. The device of claim 1, further comprising a temperature sensor housed within the housing of the device and configured to measure the actual temperature of the blood.

17. The apparatus according to claim 1, wherein, The coupling portion is integral with the box body.

18. The apparatus according to claim 1, wherein, The so-called stimulation of blood refers to stimulating blood flow.

19. The apparatus according to claim 1, wherein, The at least one electromagnetic radiation detection component is at least one photodetector.

20. The apparatus according to claim 1, wherein, The multiple electromagnetic responses are multiple optical responses.

21. The apparatus according to claim 1, wherein, The electromagnetic radiation mentioned is light.

22. The apparatus according to claim 3, wherein, The artificial intelligence information is one or more matrices that can be used by the one or more neural networks.

23. The apparatus according to claim 5, wherein, The device is also configured to measure the content of hemoglobin, or Hb.

24. The apparatus according to claim 9, wherein, The box is miniature.

25. The apparatus according to claim 10, wherein, The container is a tube.

26. The apparatus according to claim 12, wherein, The container is part of a tube.

27. Use of the apparatus according to any one of claims 1 to 26 for measuring multiple blood parameters by means of artificial intelligence.

28. An apparatus comprising: - The apparatus according to any one of claims 1 to 26, - Medical machines - A user interface that is operatively connected to or capable of being connected to the device and configured to provide measurements of the plurality of blood parameters.

29. The device according to claim 28, wherein, The medical machine in question is a cardiopulmonary bypass machine.

30. The device according to claim 28, wherein, The user interface is a display device.

31. The device according to claim 29, wherein, The cardiopulmonary resuscitation machine is an extracorporeal membrane oxygenation (ECMO) machine.

32. A method for measuring multiple blood parameters using artificial intelligence, the method comprising the following steps: - Excite the blood through electromagnetic radiation of multiple defined wavelengths, - Detect multiple electromagnetic responses in blood, said multiple electromagnetic responses including electromagnetic radiation reflected or diffused by the blood. - Receive analog information regarding the plurality of electromagnetic and / or optical responses of blood, the plurality of electromagnetic and / or optical responses including light reflected or diffused by blood. - Convert analog information of electromagnetic and / or optical response into digital data of electromagnetic and / or optical response. - The electromagnetic and / or optical response digital data, along with the actual blood temperature value, are processed by one or more neural networks. - As a result of the processing operations of the one or more neural networks, determine the value of each of the plurality of blood parameters. The step of processing the electromagnetic and / or optical response digital data and the actual temperature value of the blood by the one or more neural networks, and determining the value of each of the plurality of blood parameters, includes: o Define multiple ratios, each ratio being defined between a value indicating the amount of radiation reflected or diffused by blood due to excitation of a defined wavelength and a value indicating the amount of radiation reflected or diffused by blood due to excitation of another defined wavelength. o serves as input to one or more neural networks, providing the plurality of ratios and the temperature value. o The multiple ratios are processed by one or more neural networks by considering multiple data points of previous measurements of the blood parameters performed during previous training. o provides the value of each of the plurality of blood parameters as the output of the one or more neural networks.

33. The method of claim 32, further comprising the step of compressing a portion of a container in which blood flows or is capable of flowing, the step of compressing a portion of the container comprising: The fluid passage cross-section of the container is determined by a reduction between 9% and 17%.

34. The method of claim 32, further comprising the step of oscillating the compression element relative to a container in which blood flows or is capable of flowing.

35. The method according to any one of claims 32 to 34, wherein, The method is performed by means of the apparatus according to any one of claims 1 to 26.

36. The method according to any one of claims 32 to 34, comprising the following steps: - Provide an apparatus according to any one of claims 1 to 26, - The device is coupled to the container prior to the step of exciting the blood with electromagnetic radiation of multiple defined wavelengths.

37. The method according to any one of claims 32 to 34, comprising the step of detecting the actual temperature value of the blood by means of a temperature sensor housed inside the housing of the device according to any one of claims 1 to 26.

38. The method according to claim 32, wherein, The so-called stimulation of blood refers to stimulating blood flow.

39. The method according to claim 32, wherein, The multiple electromagnetic responses are multiple optical responses.

40. The method according to claim 32, wherein, The electromagnetic radiation mentioned is light.

Images