Computer-implemented method for monitoring a transcutaneous sensor for measuring the partial pressure of one or more blood gases in a patient - Patent Application 20070122997

Abstract

According to a first aspect of the present invention, a computer-implemented method for monitoring a transcutaneous sensor configured to measure the partial pressure of one or more blood gases in a patient is presented. The method includes determining a response time parameter of the transcutaneous sensor (step S1). The method further includes determining whether the sensor's partial pressure measurement capability is sufficient based on the determined response time parameter (step S2). The method can detect not only an increase in the sensor's response time due to a dried membrane, which may occur after several days of use with the sensor, but also sensor degradation, which may occur only after several years of use.

Description

[Technical Field]

[0001] The present invention relates to a computer-implemented method of monitoring a transcutaneous sensor configured to measure the partial pressure of one or more blood gases in a patient, a computer program, a non-transitory program storage medium storing such a program, a transcutaneous blood gas monitor for transcutaneously monitoring one or more blood gases in a patient, and uses of the results of determining the response time parameters of the transcutaneous sensor. [Background technology]

[0002] Transcutaneous monitoring is a method for use in patients who require continuous, noninvasive monitoring of oxygenation and ventilation. Sensors applied to the body can detect and measure blood gases diffusing through the skin. Specifically, transcutaneous monitoring is a useful and widely used tool for noninvasively monitoring a patient's oxygenation (tcpO2) and ventilation (tcpCO2) status. It provides real-time vital information, allowing immediate action to be taken when needed to improve patient safety and comfort. One exemplary transcutaneous monitor from Radiometer Medical ApS is the TCM5 FLEX transcutaneous monitor, a compact, convenient solution that provides accurate and continuous measurement of oxygenation (tcpO2) and ventilation (tcpCO2) status in neonatal, pediatric, and adult patients in the intensive care unit (ICU).

[0003] Such transcutaneous monitors typically include a transcutaneous electrochemical sensor configured to measure a patient's partial pressure blood gases. Such sensors occasionally require membrane reformation, i.e., replacement of the membrane used within the sensor. Currently, the membrane reformation interval for sensors is typically fixed at a specific time period, e.g., 28 days, because the risk of the sensor membrane drying out is significantly increased or too high after this 28-day period. If the sensor membrane dries out, the measurement becomes inaccurate.

[0004] During research and development, the inventors of the present invention identified a need to extend the membrane reformation interval beyond the current fixed time period. The inventors also identified a need to detect sensors that have dried out for any reason before the fixed time period has passed, as well as a need to detect sensors whose performance has deteriorated over time and with use, resulting in response times that are too long.

[0005] It is therefore desirable to provide improved monitoring of transcutaneous sensors configured to measure the partial pressure of one or more blood gases in a patient, which is achieved by the present invention, as described in more detail hereinafter.

[0006] Aspects, embodiments, examples, and exemplary steps of the invention are disclosed below. Features of different embodiments, examples, and examples of the invention may be combined in accordance with the invention where technically suitable and feasible. Summary of the Invention [Problem to be solved by the invention]

[0007] As noted above, it would be desirable to provide improved monitoring of transcutaneous sensors configured to measure the partial pressure of one or more blood gases in a patient. [Means for solving the problem]

[0008] This is achieved by the subject matter of the independent claims, further embodiments are incorporated in the dependent claims and in the following description and figures. Technical terms are used in accordance with their common meaning. Where a specific meaning is conveyed to a particular term, a definition of the term is provided below in the context in which the term is used.

[0009] According to a first aspect of the present invention, a computer-implemented method for monitoring a transcutaneous sensor configured to measure the partial pressure of one or more blood gases in a patient is presented. The method includes determining a response time parameter of the transcutaneous sensor (step S1). The method further includes determining whether the partial pressure measurement capability of the sensor is sufficient based on the determined response time parameter (step S2).

[0010] As will become clear from the present disclosure, the proposed method uses the results of response time determination during sensor monitoring. The method requires that a response time parameter be determined in step S1, and this result is then used to determine whether the sensor's ability to measure partial pressures of blood gases is sufficient, i.e., appropriate and / or acceptable. Different possibilities are disclosed for determining whether the sensor's ability is sufficient, such as, for example, comparing the measured response time of an individual sensor with a response time threshold. Thus, step S2 of the presented method can be considered as an evaluation of the sensor's partial pressure measurement ability. In particular, the evaluation of the response time parameter is performed to determine whether the sensor's ability to measure partial gas pressures is sufficient, appropriate, and / or acceptable. As will be understood by the skilled reader, in the context of the present invention, the term "sufficient" is used synonymously with the terms "adequate" and "acceptable." Different possibilities are disclosed hereinafter for determining whether the sensor's ability is sufficient, such as, for example, comparing the measured response time with a response time threshold. Thus, generally, in step S2, the method determines whether the determined response time parameter satisfies or meets a sufficiency criterion, i.e., an acceptance criterion. This sufficiency criterion, i.e., an acceptance criterion, may preferably be predefined. Thus, as will be appreciated by the skilled reader, in step S2, it is determined—by the computer-implemented method—whether the partial pressure measurement capability of the sensor is deemed acceptable / acceptable based on the determined response time parameter. Thus, step S2 may be understood to determine whether the partial pressure measurement capability of the sensor is sufficient based on the determined response time parameter, thereby determining whether the determined response time parameter satisfies or meets the sufficiency criterion, i.e., an acceptance criterion.

[0011] As will be described in more detail in specific embodiments hereinafter, determining whether the sensor's performance is sufficient may include or be embodied as determining whether sensor membrane reforming, sensor replacement, or sensor maintenance should be initiated. In other words, in the above embodiment, the method determines in step S2 whether membrane reforming, sensor replacement, or sensor maintenance is required based on the response time parameter determined in step S1. This will be described in more detail in the context of specific embodiments hereinafter.

[0012] As will be explained in detail hereinafter, the presented method can detect not only an increase in sensor response time due to a dried membrane, which can occur after several days of use with the sensor, but also sensor degradation, which can occur only after several years of use. This may be less than several years, depending on the sensor's use and configuration. For example, the glass surface of the sensor may no longer be suitable after several years. Therefore, in addition to measures to regenerate the sensor, the sensor can also be repaired or regenerated by using hydrofluoric acid on the glass to restore the glass surface. Therefore, in addition to detecting the need for regeneration, the presented method can also detect the need for sensor replacement or maintenance. As previously mentioned, this extends to repairing, regenerating, repairing, or revitalizing the glass surface of a transcutaneous sensor. In general, the present method can detect any type of sensor condition that inhibits or alters the sensor's ability to measure blood gas partial pressure, and this change in ability can be detected based on evaluating the response time parameter determined in step S1 in step S2.

[0013] It should be noted that different response time parameters can be used for the determination performed in step S1. For example, the response time parameter determined in step S1 can be a response time value, particularly an absolute value. In the context of the present invention, and unless otherwise stated, response time is understood as the so-called 10% to 90% response time, i.e., the time required by the sensor to detect a change from a first partial gas pressure to a second partial gas pressure, where 10% and 90% refer to the time difference between detecting 10% and 90% of the difference between the first and second partial gas pressures. This can also be related to the time constant τ described herein; see, for example, the description of FIG. 4. The response time is not necessarily 10% to 90% response time; in other embodiments, it can be, for example, 20% to 80% response time, 5% to 95% response time, or any other percentage selected on the response curve. Those skilled in the art will recognize the (10% to 90% or other) response time parameters. Furthermore, the skilled reader will recognize that the (10% to 90% or other) response time can be computationally converted to a time constant τ, known by the skilled reader as the time constant of the exponential or biexponential response of a transcutaneous sensor to a suddenly changing gas pressure. Thus, consistent with the skilled reader's understanding, response time as used herein preferably refers to the x% to y% response time, e.g., the 10% to 90% response time, or the time constant τ. This is explained in more detail hereinafter.

[0014] Furthermore, the response time parameter determined in step S1 may also be embodied as a trend parameter that indicates the time evolution of the response time of the transcutaneous sensor. A non-limiting example of such a trend parameter is the time derivative of the measurement curve of the blood gas partial pressure values ​​measured by the monitored sensor over time. This can be seen in and will be further clarified in the context of Figures 2 and 3. Furthermore, other examples of the response time parameter to be determined in step S1 may be used.

[0015] Furthermore, method step S1 "determining a response time parameter" may be embodied as calculating a response time parameter and / or measuring a response time parameter, as will be clarified hereinafter in the context of specific embodiments. It should be noted that step S1 of determining a response time parameter extends to any calculation using a two-point model, which also extends to, for example, the use of regression analysis, as will be explained in more detail hereinafter. In another embodiment, such determination of step S1 is embodied as prediction of a response time parameter using a predictive maintenance module, for example, by using an artificial intelligence module and / or machine learning.

[0016] The presented method can be performed, for example, by a transcutaneous blood gas monitor and can be repeated periodically, for example, every 24 hours, every 12 hours, every 8 hours, etc. Thus, the method of monitoring a transcutaneous sensor can be considered as a method of performing a continuous quality check of a transcutaneous sensor. Furthermore, the presented method of monitoring a transcutaneous sensor can be considered as a method of calibrating a transcutaneous sensor or can be part of a calibration method for calibrating said transcutaneous sensor.

[0017] Furthermore, in the context of the present invention, the term "transcutaneous sensor" shall be understood as any type of sensor configured for non-invasively measuring the partial pressure of one or more blood gases in a human being in / on the skin of a patient.

[0018] It should be noted that the presented method can be used for several different types of transcutaneous sensors. In particular, the presented method can be used with electrochemical transcutaneous sensors for measuring the partial pressure of one or more blood gases in a patient, particularly electrochemical transcutaneous STOW-SEVERINGHAUS type CO2 sensors, amperometric O2 sensors, as well as other sensors. Furthermore, the presented method can also be applied to transcutaneous sensors using optical sensor technology. The operating principles of optical sensors may differ from those of electrochemical sensors described herein. However, the response time can still be useful for determining some conditions of the sensor.

[0019] As will be understood by the skilled reader, response times should generally be measured at the same temperature to be comparable. Alternatively, response times at different temperatures can be converted to a standard temperature by a known conversion function and thus made comparable. In other words, a prerequisite for making a meaningful comparison is that the response times are measured at the same temperature, e.g., set by the user to 42°C, or that the response times at different temperatures are converted to make them comparable. This temperature is usually set for the entire measurement period. The monitor can be set to maintain this temperature between uses or to go into standby mode where the temperature is reduced when not in use.

[0020] As will be appreciated by the skilled reader, by implementing response time parameter determination in a monitoring algorithm as proposed herein, notifications regarding membrane reformation, sensor replacement, or sensor maintenance can be based on actual sensor conditions, which typically allows for membrane reformation intervals that are significantly longer than the fixed number of days, e.g., 28 days, used in the prior art.

[0021] This novel method of monitoring transdermal sensors offers certain advantages. First, the membrane reformation interval can be extended beyond the fixed time period of the prior art. Currently, membrane reformation is one of the biggest drawbacks for customers using transdermal monitoring. Furthermore, the presented method can detect if the sensor has dried out for any reason before the fixed time period has elapsed. Furthermore, it can detect if the sensor's performance has deteriorated over time and due to use, resulting in an excessively long sensor response time.

[0022] As previously explained, the current membrane reformation interval of 28 days is a number determined by a safety margin. Equivalent or better safety can be provided by periodically or constantly monitoring the sensor's response time, as proposed herein. This is particularly important for CO2 sensors, such as those shown in and described in the context of FIG. 2. For CO2 sensors, response time is closely correlated with the occurrence of erroneous readings at steady state. The data in FIG. 3 show that sensor behavior can suddenly change, resulting in less accurate partial blood gas measurements from the sensor. This occurs, for example, when the sensor membrane dries out and is correlated with a change in response time. Such a correlation is explained by the fact that electrolytes applied to the inner membrane of a transcutaneous sensor slowly evaporate, resulting in a more concentrated electrolyte. The phenomenon associated with increased response time versus electrolyte concentration is utilized in certain embodiments of the present invention. The use of such correlations and / or phenomena to detect a dry transcutaneous sensor therefore provides improved monitoring of the sensor.

[0023] It should be noted that the methods presented herein are applicable to sensors that are calibrated to both a single gas concentration and two different gas concentrations. According to another exemplary embodiment of the present invention, the response time parameter is indicative of the response time of the sensor in measuring the partial pressure of one or more blood gases of the patient.

[0024] According to another exemplary embodiment of the present invention, step S2 of determining whether the partial pressure measurement capability of the sensor is sufficient includes determining whether membrane reformation of the transcutaneous sensor should be initiated, such determination being based on the previously determined response time parameter.

[0025] Certain transcutaneous sensors for measuring blood gases include a membrane. In particular, transcutaneous CO2 sensors are electrochemical sensors. In this case, the membrane is provided in an electrolyte, which can evaporate. This evaporation can change the membrane's properties, and unless additional electrolyte is added, the membrane can begin to dry out. This process, however, can cause a change in the sensor's ability to measure the patient's blood gas partial pressure. Therefore, in the presented embodiment, the membrane reformation interval can be extended beyond the currently used fixed time period used in the prior art, and a sensor that has dried out for any reason before the currently used fixed time period can be detected. Preferably, in step S2, it is determined whether the sensor's partial pressure measurement capability is sufficient based on the determined response time parameter, thereby determining whether the determined response time parameter satisfies or meets the sufficiency criterion, i.e., the acceptance criterion.

[0026] According to another exemplary embodiment of the present invention, the step S2 of determining whether the partial pressure measurement capability of the sensor is sufficient includes determining whether replacement or maintenance of the transcutaneous sensor due to degradation should be initiated, wherein said replacement or maintenance decision is based on the determined response time parameter.

[0027] In certain embodiments, the transcutaneous sensor may be repaired or regenerated by, for example, using hydrofluoric acid on the glass to restore the sensor's glass surface. Other repair or regeneration means may be used as well. Thus, after determining that the sensor requires replacement or maintenance, a signal or alert may be generated to a user or monitor to perform the presented method of replacing, repairing, regenerating, or servicing the sensor, or reactivating the sensor's glass surface. Further details regarding such signals are described hereinafter in the context of further embodiments. Preferably, in step S2, it is determined whether the sensor's partial pressure measurement capability is sufficient based on the determined response time parameter, thereby determining whether the determined response time parameter satisfies or meets a sufficiency criterion, i.e., an acceptance criterion.

[0028] According to another exemplary embodiment of the present invention, the response time parameter determined in step S1 is a response time value, and the method comprises the step of comparing the determined value of the response time with a response time threshold value.

[0029] As previously mentioned, the response time value may be a 10% to 90% response time value or a value of the time constant τ of the underlying exponential or biexponential response of the transcutaneous sensor; see, for example, FIG. 4 and its accompanying description. As the skilled reader will appreciate, a specific absolute value of the response time, as opposed to a relative value, is measured, determined, and / or used in the context of the present invention. In other words, this embodiment details that the response time value is measured and / or calculated and compared to the response time threshold value. The result of this comparison then defines whether the monitoring method concludes that the sensor requires membrane regeneration, replacement, and / or maintenance.

[0030] It should be noted that the response time threshold as used herein can be embodied in different ways. For example, the response time threshold can depend on the initial response time of the sensor. This means that the response time measured immediately after membrane reformation of the sensor is used to set or define this response time threshold, e.g., double or triple the initial response time, or multiply it by any other factor set by the user or the system. Thus, the individual response time of a particular sensor can be measured and / or calculated, and the threshold can be set accordingly. In other words, the threshold can be set individually for each sensor, e.g., to a value twice the response time measured after membrane reformation. In another example, the response time threshold can be calculated or determined by adding a predetermined amount of time to the response time measured after membrane reformation. Furthermore, in certain embodiments, a predetermined threshold can be used. For example, the response time threshold can be set to a specific predetermined time period, e.g., 30 seconds, 40 seconds, 50 seconds, or 60 seconds. As will be appreciated by the skilled reader, many different ways of using predefined or individually set thresholds can be used in the context of the present invention.

[0031] According to another exemplary embodiment, the method includes generating a control signal configured to cause membrane reformation of the sensor or to cause replacement or maintenance of the sensor if the determined value of the response time exceeds a response time threshold.

[0032] Such a control signal enables the device to perform this monitoring method to deactivate the sensor function and / or to alert the user that membrane reformation, replacement, and / or maintenance is required. The control signal is thus generated when it is determined or resolved that membrane reformation is required, i.e., when the determined response time of the sensor exceeds or is longer than the response time threshold. In one example, the response time of the sensor is 54 seconds and the response time threshold is 50 seconds. In this case, membrane reformation is required and a corresponding signal or alert is generated.

[0033] According to another exemplary embodiment of the present invention, the response time parameter determined in step S1 is a trend parameter indicative of the time evolution of the response time of the transcutaneous sensor, and the method further comprises a step (step S3b) of comparing the determined trend parameter with a trend threshold value for the time evolution of the response time of the transcutaneous sensor.

[0034] As will be explained in detail in the context of certain embodiments, for example, the first and / or second time derivative of the measurement curve as shown in any of Figures 2 to 4 can be used for the trend parameter. Furthermore, the trend threshold used in step S3b in a preferred embodiment is a set threshold of the first or second time derivative of said measurement curve as shown in Figures 2 to 4.

[0035] FIG. 2 shows partial CO2 pressure values ​​measured by a monitored sensor when exposed to significant changes in gas pressure. For example, if the slope of the partial blood gas pressure measured by the sensor over time, i.e., the first time derivative, is too low in the first curve portion where the pressure increases, this can be used as a criterion for triggering the control signal. This first curve portion can be within a time period of 50 to 300 seconds. As can be seen from FIG. 2, the slope of the partial blood gas pressure curve over time decreases in the first curve portion from day 10 to day 50 of sensor use.

[0036] In further exemplary embodiments of the invention, the control signal is configured to prevent further use of the sensor by the operator, for example, by deactivating the sensor, and / or the control signal is configured to alert the operator regarding the need for membrane regeneration, replacement, or maintenance of the sensor.

[0037] Thus, a device performing the methods described herein, e.g., a transcutaneous blood gas monitor, may generate a control signal for sensor deactivation such that the user can no longer use the transcutaneous sensor for blood gas measurements. Furthermore, an operator or user may be alerted by a visual or audible signal (e.g., via the user interface of the transcutaneous blood gas monitor) that the sensor requires remembranation, replacement, or maintenance.

[0038] According to an exemplary embodiment of the present invention, the method includes a step (S4b) of generating a control signal configured to cause membrane reformation of the sensor or to cause replacement or maintenance of the sensor if the determined trend parameter deviates from the trend parameter by at least a predetermined minimum amount.

[0039] Such control signals may trigger automatic re-membrane formation of the sensor, or automatic replacement of the sensor, or automatic maintenance of the sensor, freeing the user from these tasks. According to another exemplary embodiment of the present invention, the method further includes measuring blood gas partial pressure values ​​over time with a sensor, and the determined trend parameter is embodied as one or more time derivatives of a measurement curve of the blood gas partial pressure values ​​measured over time.

[0040] In a preferred embodiment, the first and / or second time derivatives can be determined in this computer-implemented method. Such a measurement curve of the blood gas partial pressure values ​​measured over time is shown in the non-limiting example of FIG. 2. As can be seen from FIG. 2 and described in detail hereinafter, depending on the age of the sensor and / or the age of the membrane on the sensor (i.e., the length of time the membrane has been used with the sensor), the slope of the measurement curve when the sensor is exposed to pressure changes decreases with increasing time, from 10 days to 50 days, as shown in the exemplary measurement in FIG. 2. Therefore, the first time derivative of this measurement curve can be used by the presented method to detect that the sensor's membrane needs reconditioning, replacement, or maintenance. For example, if the first time derivative is not steep enough / too low within a specific time period of the measurement curve, e.g., 50 to 300 seconds, the method can detect that membrane reconditioning is required. In other words, in this embodiment, the trend parameter is the time derivative of the measured partial blood gas pressure over time. A decrease in the slope of the curve shown in Figure 2, for example, indicates a bad or old sensor. In other words, the method can perform a so-called "slope test," which is then used by the presented method for membrane reformation decision-making.

[0041] According to another exemplary embodiment of the present invention, the response time parameter determined in step S1 is a response time value over a time period, preferably at least several days. Furthermore, the determined response time value describes a response time measurement curve of the response time values ​​of the sensor over said time period. Furthermore, the determined trend parameter is a time derivative of the response time measurement curve.

[0042] In other words, in this embodiment, the trend parameter is the time derivative of the measurement curve, such as that shown in FIG. 3. The inventors of the present invention have confirmed that a strong increase in the slope, i.e., first derivative, of the curve shown indicates a phase change of the membrane. In the non-limiting example shown in FIG. 3, the strong increase in the first time derivative / slope of the curve shown in FIG. 3 occurs around day 36. Therefore, if the absolute value of the slope / first time derivative increases above a certain threshold, the presented method can determine that the sensor's partial pressure measurement capability is no longer sufficient. The certain threshold value of the first time derivative is therefore used as the trend threshold in this embodiment. Furthermore, in another example, the value of the second time derivative can be used as the trend threshold, and the determination of sensor capability can be based on a comparison of the value of the second time derivative with the trend threshold. As will be apparent to the skilled reader, in this embodiment, the method compares the determined trend parameter, i.e., the first or second time derivative, with a trend threshold for the time evolution of the response time of the transcutaneous sensor, i.e., a set threshold for the first or second time derivative, as described herein as step S3b.

[0043] Thus, in the presented method, the membrane reformation interval can be extended beyond the fixed time period used in the prior art, which improves one of the biggest drawbacks for customers using transdermal monitoring.

[0044] In accordance with another exemplary embodiment of the present invention, the method includes determining whether the sensor at the start of the monitoring method is inside a calibration chamber, preferably the calibration chamber of a transcutaneous blood gas monitor.

[0045] In certain applications, it may be useful to know whether the sensor to be monitored is currently inside the calibration chamber. In a preferred embodiment, the angle of the calibration chamber door may be used to indicate whether the sensor is inside the chamber. Since the door in this embodiment opens a little further to accommodate the sensor, the angle of the calibration chamber door may be used for such an indication.

[0046] According to another exemplary embodiment of the present invention, the method includes the step of ensuring that the sensor is exposed to a minimal amount of gas pressure change during the monitoring method. In certain embodiments, this can be ensured by using a calibration chamber into which calibration gas is flushed by the device performing the monitoring method. For example, the transcutaneous blood gas monitor described herein can cause calibration gas to be delivered from a calibration gas reservoir into the calibration chamber; see, for example, FIG. 5. In a particular, non-limiting embodiment, an exhaust tube can be present between the calibration chamber and the atmosphere. Thus, when flow from the calibration gas reservoir is closed, the air inside the calibration chamber is slowly exchanged with the atmosphere by simple diffusion. The inventors of the present invention have determined this exchange rate. Preferably, the monitoring method proposed herein can usually only be requested more than 30 minutes after the previous successful monitoring; therefore, the change in gas pressure should usually be sufficient to determine the response time. However, there may be some special cases / occasions in which the previously described scenario does not apply, for example, if the sensor temperature is changed less than 30 minutes after monitoring / calibration.

[0047] Furthermore, ensuring that the sensor is exposed to a minimum amount of gas pressure change during the monitoring method can also be performed by looking at the monitoring curve when the monitoring is finished: determining the difference between the initial gas pressure value, which should be the minimum, and the final gas pressure value, which should be the maximum, and checking whether it is at least a certain desired amount of gas pressure change.

[0048] As previously described, the monitoring method proposed herein may be performed by a transcutaneous monitor comprising a transcutaneous sensor, a calibration chamber, and a calibration gas reservoir. In this embodiment, the method includes flushing calibration gas from the calibration gas reservoir into the calibration chamber, in which the transcutaneous sensor is placed for monitoring the sensor.

[0049] According to another exemplary embodiment of the present invention, step S1 of determining the response time parameter includes providing sensor data and / or data related to the sensor as input data to a predictive maintenance module. Such data may be considered monitoring data. Such a predictive maintenance module may be embodied as an artificial intelligence module and / or modules trained by machine learning. The method of this embodiment may further include predicting, by the predictive maintenance module, the response time of the transcutaneous sensor. Furthermore, in step S2, the predicted response time of the transcutaneous sensor is used to determine whether the partial pressure measurement capability of the sensor is sufficient, in particular, whether membrane regeneration of the transcutaneous sensor or replacement or maintenance of the sensor is or will be required.

[0050] Such a predictive maintenance module may therefore predict values ​​of the measurement curves shown, for example, in Figures 2 and 3. In other words, instead of measuring partial blood gas pressures as performed in Figure 2 and / or measuring / determining response times over membrane age as performed in Figure 3, such measurement curves may be predicted by the predictive maintenance module. These predicted response time values ​​of the transcutaneous sensor may then be used to make a decision in step S2 as to whether the sensor's partial pressure measurement capability is still sufficient or will be sufficient at a future time point. Preferably, in step S2, it is determined whether the sensor's partial pressure measurement capability is sufficient based on the determined response time parameters, thereby determining whether the determined response time parameters meet or satisfy sufficiency criteria, i.e., acceptance criteria.

[0051] In general, an artificial intelligence module is an entity that processes one or more inputs into one or more outputs, typically using an internal processing chain with a set of free parameters. The internal processing chain may be structured into interconnected layers that are successively traversed when moving from input to output. Many artificial intelligence modules are structured to process inputs with high dimensionality into outputs with much lower dimensionality. A common task of an artificial intelligence module is to classify data into one or more categories. Such modules are called "intelligent" because they can be "trained." A module may be trained using a record of training data. The training data record includes training input data and corresponding training output data. The training output data of a training data record is the expected result produced by the module when given the training input data of the same record of training data as input. The deviation between this expected result and the actual result produced by the module is observed and evaluated by a "loss function." This loss function is used as feedback to adjust the parameters of the module's internal processing chain. For example, the parameters may be adjusted with an optimization objective that minimizes the value of a loss function that occurs when all training input data is fed to the module and the results are compared to the corresponding training output data. The result of this training is that, given a relatively small number of records of training data as "ground truth," the module is enabled to successfully perform its job on a large number of records of input data that are orders of magnitude higher. In the context of this embodiment, neural networks, convolutional neural networks, and generative adversarial networks may be used.

[0052] According to another exemplary embodiment of the present invention, the method is applied to a transcutaneous electrochemical sensor for measuring the partial pressure of one or more blood gases in a patient. While it will be explained hereinafter that optical sensors can also be monitored using the present invention, this particular embodiment relates to electrochemical sensors. In particular, electrochemical sensors are often used to measure the partial pressure of CO in a patient. The effects of membrane drying can be avoided or reduced for electrochemical sensors, as detailed previously. The membrane reformation interval can be extended beyond the fixed time period used by the prior art. Furthermore, the presented method can detect that an electrochemical sensor has dried out for any reason before the fixed time period used in the prior art has elapsed.

[0053] According to another aspect of the present invention, there is provided a program which, when executed on or loaded onto a computer, causes the computer to carry out the method steps of the methods disclosed herein.

[0054] The program may be part of a computer program, but it may also be an entire program on its own. For example, the program may be used to update an already existing computer program to incorporate the present invention.

[0055] According to another aspect of the present invention, a non-transitory program storage medium storing such a program is presented. The computer readable medium may be considered as a storage medium such as for example a data storage device, a USB stick, a CD, a DVD, a hard disk or any other medium on which a program as described above may be stored.

[0056] In accordance with another exemplary embodiment of the present invention, a transcutaneous blood gas monitor for transcutaneously monitoring one or more blood gases in a patient is presented. The monitor includes a transcutaneous sensor, preferably a transcutaneous electrochemical sensor, configured to measure the partial pressure of one or more blood gases in the patient. The monitor further includes control circuitry configured to determine a response time parameter of the transcutaneous sensor during monitoring of the transcutaneous sensor. Furthermore, the control circuitry is configured to determine whether the sensor's partial pressure measurement capability is sufficient based on the determined response time parameter.

[0057] A specific, non-limiting example of such a blood gas monitor is depicted in Figure 5 and described in more detail hereinafter. Preferably, the control circuit is configured to determine whether the partial pressure measurement capability of the sensor is sufficient based on the determined response time parameter, and thereby to determine whether the determined response time parameter meets or satisfies a sufficiency criterion, i.e., an acceptance criterion.

[0058] In accordance with another exemplary embodiment of the present invention, a transcutaneous blood gas monitor includes a calibration chamber and a calibration gas reservoir configured for flushing calibration gas from the calibration gas reservoir into the calibration chamber for calibrating the transcutaneous sensor.

[0059] In certain embodiments, the transcutaneous blood gas monitor is configured to ensure that the sensor is exposed to a minimal amount of gas pressure change during the monitoring procedure. According to another aspect of the present invention, a use of the results of determining a response time parameter of a transcutaneous sensor configured to measure the partial pressure of one or more blood gases in a patient is presented for sensor monitoring. In particular, this can be used to determine the need for membrane reformation of the transcutaneous sensor or the need to replace the sensor due to degradation. Preferably, the results are used in or by a transcutaneous blood gas monitor, computer-implemented method, program, and / or computer. It should be noted that the results of determining the response time parameter of the transcutaneous sensor are preferably data that can be used as input for such a transcutaneous blood gas monitor, computer-implemented method, program, and / or computer. Thus, the disclosed uses are to be understood as technical uses of the data generated by said determinations, and not as mental acts.

[0060] According to an exemplary embodiment of the present invention, a transcutaneous blood gas monitor is configured to perform the methods as presented herein periodically, for example, every 24 hours, every 12 hours, every 8 hours, etc.

[0061] The present invention will now be described with reference to the accompanying drawings, which provide a description of the background art and depict specific embodiments of the invention, however, the scope of the invention is not limited to the specific features disclosed in the context of the drawings. [Brief explanation of the drawings]

[0062] [Figure 1] FIG. 1 illustrates generally a flow diagram of a computer-implemented method for monitoring a transcutaneous sensor, according to an embodiment of the present invention. [Figure 2] FIG. 1 shows four measurement curves of partial CO pressure over time that may be used in one or more embodiments of the present invention. [Figure 3] FIG. 10 is a schematic diagram illustrating a measurement curve of response time of a transcutaneous sensor over membrane age, which may be used in one or more embodiments of the present invention. [Figure 4]FIG. 10 is a schematic illustration of a theoretical response curve of a transcutaneous sensor for measuring the partial pressure of one or more blood gases in a patient when exposed to a pressure change, which may be used in one or more embodiments of the present invention. [Figure 5] FIG. 1 is a schematic diagram of a transcutaneous blood gas monitor for transcutaneously monitoring one or more blood gases of a patient, in accordance with one embodiment of the present invention. [Figure 6] FIG. 1 illustrates generally a flow diagram of a computer-implemented method for monitoring a transcutaneous sensor, according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0063] FIG. 1 shows a schematic flow diagram of a computer-implemented method for monitoring a transcutaneous sensor configured to measure the partial pressure of one or more blood gases in a patient. Preferred blood gases are oxygen and carbon dioxide, although other blood gases may also be measured. As previously described, the presented method shown in FIG. 1 can be applied to transcutaneous electrochemical sensors, but the method is also applicable to transcutaneous sensors that measure the partial pressure of a patient's blood gases using optical techniques. The method shown in FIG. 1 includes a step S1 in which a response time parameter of the transcutaneous sensor is determined. The response time parameter may be one or more absolute values ​​of the sensor's response time, but may also be a trend parameter, such as the first or second derivative of the measurement curve shown in FIGS. 2 and 3. Furthermore, in a second step S2, the method determines whether the sensor's partial pressure measurement capability is sufficient, adequate, or acceptable based on the previously determined response time parameter. As the skilled reader will appreciate, in the context of the present invention, the term "sufficient" is used synonymously with the terms "adequate" and "acceptable." For example, different possibilities are disclosed for determining whether the sensor's capabilities are sufficient, such as comparing the measured response time with a response time threshold. Thus, generally, the method, in step S2, determines whether the determined response time parameter satisfies or meets a sufficiency criterion, i.e., an acceptance criterion. This sufficiency criterion, i.e., an acceptance criterion, may preferably be predefined. Thus, as will be appreciated by the skilled reader, in step S2, it is determined whether the sensor's partial pressure measurement capability is deemed acceptable / acceptable—by a computer-implemented method—based on the determined response time parameter. Thus, step S2 should be understood as determining whether the sensor's partial pressure measurement capability is sufficient based on the determined response time parameter, thereby determining whether the determined response time parameter satisfies or meets the sufficiency criterion, i.e., an acceptance criterion. The method shown in FIG. 1 can be performed, for example, by a control circuit, a processor, or a computer.Such control circuitry, processor, or computer may be included by the transcutaneous blood gas monitor 500 shown in the non-limiting example of FIG.

[0064] FIG. 2 shows a measurement curve of a transcutaneous sensor for measuring the partial pressure of carbon dioxide (CO2) over time. As can be seen from FIG. 2, four different measurements were performed on days 10, 36, 40, and 50. The number of days indicates the age of the membrane used on the sensor. In each measurement, the sensor was exposed to external gas pressure. As can be seen from FIG. 2, the slope of each curve is significantly different for the sensor measured on day 10 of use compared to the sensor measured on day 50 of use. Therefore, in an exemplary embodiment, the slope of this measurement curve, i.e., the first time derivative of the mathematical function describing the depicted curve, can be used as a criterion for determining whether the sensor's partial pressure measurement capability is sufficient in step S2 of FIG. 1. A decrease in the slope of the curve shown in FIG. 2 indicates a bad or old sensor. This can then be used by the presented method for decision-making, e.g., for membrane regeneration. In other words, according to certain embodiments of the present invention, the first and / or second time derivatives of the measurement curve as shown in FIG. 2 can be used for the trend parameters described herein. Furthermore, in a preferred embodiment, the trend threshold used in step S3b is a set threshold of the first and / or second time derivative of the measurement curve shown in FIG.

[0065] FIG. 3 shows the so-called 10% to 90% response time calculated over multiple days. The calculation of the response time is explained in detail in the context of FIG. 4. As can be seen from FIG. 3, a strong increase in the slope of the illustrated curve, i.e., the first derivative, indicates a phase change in the membrane's properties. In the example of FIG. 3, the strong increase occurs at approximately 36 days of membrane age. Thus, the method presented herein can detect the need for membrane reformation, which occurs only after 36 days, not after the 28 days currently used in the prior art as a fixed interval for membrane reformation. In this case, an embodiment of the presented method determines, as a response time parameter in step S1, one or more values ​​of the first and / or second time derivative as trend parameters of the response time curve over time shown in FIG. 3. The determined first and / or second time derivatives are then compared to a trend threshold, as described herein as step S3b. The trend threshold may be a predetermined value of the first and / or second time derivative. Thus, for example, if the absolute value of the slope / first time derivative increases above a certain threshold, as in the case of the curve in Figure 3, at approximately day 36, the presented method may determine that the partial pressure measurement capability of the sensor is no longer sufficient.

[0066] This example makes clear that the method proposed herein can extend the membrane reformation interval beyond the known prior art period. Furthermore, the proposed method can detect a sensor that has dried out for some reason before the prior art time period has elapsed. Furthermore, the proposed method can detect a sensor whose performance has deteriorated over time and with use, resulting in a response time that is too long. In such cases, the method described in the context of FIG. 3 can generate a control signal that indicates that replacement or maintenance of the transcutaneous sensor due to degradation should be initiated.

[0067] FIG. 4 shows the theoretical response curve of a transcutaneous sensor to changes in gas pressure using the model parameters listed in FIG. 4. The two points used to calculate the response time in the two-point prediction are also shown in FIG. 4. The method presented herein takes advantage of the fact that a transcutaneous sensor has a bi-exponential or exponential response to a sudden change in gas pressure, p(t)=(p end -p(0))(1-e (-t / τ) )+p(0), the time constant (τ) in the exponential response is:

[0068]

number

[0069] where p end is the steady-state value of the gas pressure in the exponential function, and p(t1) and p(t2) are the gas pressures of the exponential function at time points t1 and t2 as illustrated in FIG. 4. Furthermore, the skilled reader will recognize that this time constant τ can be converted by calculation into the so-called 10% to 90% response time. In the context of the present invention, and unless otherwise stated, response time shall be understood as the so-called 10% to 90% response time, i.e., the time required by the sensor to detect a change from a first partial gas pressure to a second partial gas pressure, where 10% and 90% refer to the time difference between detecting 10% and 90% of the difference between the first and second partial gas pressures. This may also be related to the time constant τ described herein; see, for example, the description of FIG. 4. The response time is not necessarily 10% to 90% response time, but in other embodiments may be, for example, 20% to 80% response time, 5% to 95% response time, or any other percentage selected on the response curve.

[0070] FIG. 5 schematically illustrates a transcutaneous blood gas monitor 500 for transcutaneously monitoring one or more blood gases in a patient. Monitor 500 includes a transcutaneous sensor 501 configured to measure the partial pressure of one or more blood gases in the patient. Monitor 500 also includes control circuitry 502 configured to determine a response time parameter of the transcutaneous sensor during monitoring of sensor 501. Control circuitry 502 is also configured to determine whether the partial pressure measurement capability of sensor 501 is sufficient, appropriate, or acceptable based on the determined response time parameter. Monitor 500 includes a calibration chamber 503 into which a calibration gas can be flushed from a calibration gas reservoir 504. Calibration gas 505, when flushed into calibration chamber 503 through conduit 506, ensures that sensor 501 is exposed to minimal gas pressure changes during a monitoring method performed by monitor 500. Control circuitry 502 is connected to calibration gas reservoir 504 via electrical connection 507 to initiate flushing. Furthermore, the control circuit 502 is connected to the sensor 501 via a connection 508 so that measurements made by the sensor 501 can be transmitted from the sensor 501 to the control circuit 502 .

[0071] FIG. 6 illustrates a computer-implemented method for monitoring a transcutaneous sensor according to another embodiment of the present invention. In step S1, a response time parameter of the transcutaneous sensor is determined. In the embodiment of FIG. 6, a value, preferably an absolute value, of the 10% to 90% response time is determined. Furthermore, in step S3a, the determined value of the 10% to 90% response time is compared to a response time threshold. As previously described in detail, the threshold may be predefined, for example, a specific amount of time, such as 50 seconds. However, the threshold may also be embodied as a value calculated based on the response time measured when the sensor is re-formed. For example, the threshold may be set to 1.5 times the value of the response time measured after re-formation of the individual sensor. Other possibilities are previously disclosed. Furthermore, in the method of FIG. 6, the determined value of the response time is compared to a response time threshold in step S3a. Furthermore, based on the comparison in step S3a, it is determined in step S2 whether the sensor's partial pressure measurement capability is sufficient. In other words, this determination is based on a comparison of the response value with a threshold value at / within step S3a. In particular, depending on the comparison of the response time determined in step S3a with the threshold value, it can be determined that membrane reformation is necessary. For example, if the response time exceeds the threshold value, the method determines that membrane reformation should be initiated. Therefore, a control signal for triggering membrane reformation is generated in step S4a.

[0072] The described embodiments also relate to a computer-implemented method of monitoring a transcutaneous sensor configured to measure the partial pressure of one or more blood gases in a patient, a computer program, a non-transitory program storage medium storing such a program, a transcutaneous blood gas monitor for transcutaneously monitoring one or more blood gases in a patient, and uses of the results of determining the response time parameter of the transcutaneous sensor. Synergistic effects may result from different combinations of the embodiments, which may not be described in detail.

[0073] Furthermore, it should be noted that all embodiments of the present invention relating to methods may be carried out in the order of steps as described, but this need not be the only or required order of steps of the method. The methods presented herein may be carried out using a different order of the disclosed steps without departing from the respective method embodiment, unless expressly stated to the contrary hereinafter.

[0074] When an indefinite or definite article, such as "a," "an," or "the," is used to refer to a singular noun, it includes a plural of that noun unless specifically stated otherwise. The term "about" or "approximately" in the context of the present invention refers to an interval of precision that a person skilled in the art would understand to still ensure the technical effect of the feature in question. This term typically indicates a deviation of ±20%, preferably ±15%, more preferably ±10%, and even more preferably ±5% from the indicated numerical value.

[0075] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. Within the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude a plurality. A single processor or other unit may fulfill the functions of several items or steps recited in a claim. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be advantageously used. A computer program may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, provided together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless communication systems. Any reference signs in the claims should not be construed as limiting the scope of the claims.

Claims

1. 1. A computer-implemented method for monitoring a transcutaneous sensor configured to measure partial pressures of one or more blood gases in a patient, comprising: determining a response time parameter of the transcutaneous sensor (step S1); determining whether the partial pressure measurement capability of the sensor is sufficient based on the determined response time parameter (step S2); 11. A computer-implemented method comprising:

2. 10. The method of claim 1, wherein the response time parameter is indicative of a response time of the sensor in measuring the partial pressure of the one or more blood gases of the patient.

3. 3. The method of claim 1, wherein the step S2 of determining whether the partial pressure measurement capability of the sensor is sufficient comprises determining whether membrane reformation of the transcutaneous sensor should be initiated based on the determined response time parameter.

4. 4. The method according to claim 1, wherein the step S2 of determining whether the partial pressure measurement capability of the sensor is sufficient comprises determining whether replacement or maintenance of the transcutaneous sensor due to deterioration should be initiated based on the determined response time parameter.

5. 5. The method according to claim 1, wherein the response time parameter determined in step S1 is a value of the response time, and the method further comprises the step of comparing the determined value of the response time with a response time threshold (step S3a).

6. 6. The method of claim 5, further comprising generating (step S4a) a control signal configured to cause membrane reformation of the sensor or to cause replacement or maintenance of the sensor if the determined value of the response time exceeds the response time threshold.

7. The response time parameter determined in step S1 is a trend parameter that indicates the time evolution of the response time of the transcutaneous sensor, and the method further comprises:

7. The method according to claim 1, further comprising the step (S3b) of comparing the determined trend parameter with a trend threshold for the time evolution of the response time of the transcutaneous sensor.

8. 8. The method of claim 7, further comprising the step (S4b) of generating a control signal configured to cause membrane reformation of the sensor or to cause replacement or maintenance of the sensor if the determined trend parameter deviates from the trend by at least a predetermined minimum amount.

9. The method further includes measuring blood gas partial pressure values ​​over time with the sensor; 9. The method according to claim 7 or 8, wherein the determined trend parameter is one or more time derivatives, in particular a first time derivative and / or a second time derivative, of a measurement curve of the blood gas partial pressure values ​​measured over time.

10. the response time parameters determined in step S1 include values ​​of the response time over a period of time, preferably at least a number of days; the determined values ​​of the response time describe a response time measurement curve of the response time values ​​of the sensor over the time period; 10. The method according to any one of claims 7 to 9, wherein the determined trend parameter is the time derivative of the response time measurement curve.

11. The step S1 of determining the response time parameters comprises: providing data of and / or related to said sensors as input data to a predictive maintenance module; predicting, by the predictive maintenance module, the response time of the transcutaneous sensor; 11. The method according to claim 1, wherein in step S2, the predicted response time of the transcutaneous sensor is used to determine whether the partial pressure measurement capability of the sensor is sufficient, in particular whether membrane regeneration of the transcutaneous sensor or replacement or maintenance of the sensor is necessary.

12. 12. The method of claim 1, wherein the method is applied to a transcutaneous electrochemical sensor for measuring the partial pressure of one or more blood gases in a patient.

13. the sensor is exposed to a pressure change from a first partial gas pressure to a second partial gas pressure during a monitoring method; 13. The method according to any one of claims 1 to 12, wherein the first and / or second partial gas pressures are known.

14. A program which, when executed on or loaded onto a computer, causes the computer to carry out the method steps of the method according to any one of claims 1 to 13.

15. A non-transitory program storage medium storing the program according to claim 14.

16. A transcutaneous blood gas monitor (500) for transcutaneously monitoring one or more blood gases in a patient, comprising: a transcutaneous sensor, preferably a transcutaneous electrochemical sensor (501), configured to measure the partial pressure of one or more blood gases of the patient; a control circuit (502) that, during monitoring of the transcutaneous sensor, - determining the response time parameters of said transcutaneous sensor It is configured for determining whether the partial pressure measurement capability of the sensor is sufficient based on the determined response time parameter; a control circuit (502) configured for A transcutaneous blood gas monitor (500) comprising:

17. The monitor a calibration chamber (503); a calibration gas reservoir (504) containing a calibration gas (505); Furthermore, 17. The transcutaneous blood gas monitor of claim 16, wherein the transcutaneous blood gas monitor is configured to flush calibration gas from the calibration gas reservoir into the calibration chamber for calibrating the transcutaneous sensor.

18. Use of the results of determining the response time parameters of a transcutaneous sensor configured to measure the partial pressure of one or more blood gases of a patient for monitoring the sensor, in particular for determining the need for membrane reformation of the transcutaneous sensor or the need to replace the sensor due to deterioration.

Images