Monitoring for tremor and sweating attacks

Abstract

A patient monitoring method includes receiving (103, 109) input data indicative of a patient's tremor attacks 52 and sweat attacks 54, recording (105, 111) the respective time points at which the tremor attacks and sweat attacks occur, and generating (115, 117) an output based on the alternating pattern of tremor attacks and sweat attacks from each recorded time point of tremor and / or seizures. Also disclosed are computer program products for implementing such methods and monitoring systems for implementing such methods.

Description

Technical Field

[0001] The present invention relates to a computer-implemented method for monitoring a patient's tremor attacks and sweating attacks.

[0002] The present invention further relates to a computer program product for implementing such a method on a monitoring system, and a monitoring system for implementing such a method.

Background Art

[0003] A febrile patient is defined as a patient whose core body temperature (CBT) exceeds the normal range due to an elevated body temperature set point. Fever is caused by many medical conditions, ranging from mild to life-threatening. These include, among others, viral infections such as the common cold, urinary tract infections, meningitis, malaria, appendicitis, bacterial infections, and parasitic infections. Non-infectious causes include, among others, vasculitis, deep vein thrombosis, drug side effects, cancer, etc. Fever is thought to be beneficial to the host in the survival of bacterial infections and is regulated, in particular, by the body's thermoregulation method in which sweating and tremors play a major role.

[0004] In US Patent Application Publication No. 2018 / 0242850, it is disclosed that from the monitoring of a patient's body temperature, a plethysmographic parameter is obtained, thereby determining the core body temperature, and from there, characterizing the user's symptoms such as fever.

[0005] In International Patent Publication WO2017 / 172837A1, a system, method, and device for detecting changes or the absence of changes in a patient's endogenous set point body temperature are disclosed by using the heat transfer parameters or energy consumption of a device that provides controlled hypothermia, normothermia, or hyperthermia. When the body's core body temperature falls below the threshold zone, a series of coordinated responses such as, among others, surface vasoconstriction, tremors, and metabolic heat generation occur. When the body's core body temperature exceeds the threshold zone, a series of coordinated reactions including, among others, surface vasodilation and sweating occur.

[0006] Patient CBT exhibits different time-dependent behaviors depending on the nature of the illness. For example, infection-related fever is caused by an increase in settling point due to cytokines released into the bloodstream by circulating white blood cells. However, as the source of infection, i.e., the activation of the host immune system, decreases, the concentration of cytokines in the bloodstream decreases, and hypothalamic suppression decreases. This leads to a lower settling point, resulting in sweating and a CBT pattern that exhibits cyclical behavior of fever episodes over the long term. Long-term monitored CBT, also known as a fever curve, can provide medical professionals such as clinicians and nurses with diagnostic information.

[0007] In high-priority situations in hospitals, particularly in intensive care units (ICUs), CBT is measured continuously. This is done using invasive methods. In less urgent situations, especially in general wards, it is preferable to avoid invasive methods due to infection risks. Since a reliable, continuous, and non-invasive method for measuring CBT has not been established, CBT is usually measured only once to three times a day through spot checks. As a result, it is not possible to reconstruct the fever curve. [Overview of the project] [Problems that the invention aims to solve]

[0008] The present invention aims to provide a non-invasive method for monitoring patients.

[0009] The present invention further aims to provide a computer program product for performing such a method on a monitoring system, and a monitoring system for monitoring a patient that performs such a method. [Means for solving the problem]

[0010] The present invention is defined by the independent claims. Dependent claims define advantageous embodiments. A surrogate fever curve and / or other information used by healthcare professionals to draw conclusions about a patient is output. This output, based on tremor and sweating episodes, is used by healthcare professionals to evaluate in order to obtain information relevant to the diagnosis of the progression of the patient's fever. The diagnostic information helps healthcare professionals recognize the type of patient's condition, for example, when defining a medication plan for the patient, or when evaluating the effectiveness of a medication plan that has been implemented, for example, by monitoring changes in the surrogate fever curve after medication.

[0011] According to one embodiment, a computer-aided method for monitoring the progression of a patient's fever is provided. This computer-aided method uses a processor device to perform the following steps: receive input data indicating the patient's tremor episodes and sweating episodes as indicators of the progression of the patient's fever over a certain time interval; record the time points at which the tremor episodes and sweating episodes occurred; and generate an output (for example, an output indicating the progression of the patient's fever) from each recorded time point of the tremor episodes and / or sweating episodes based on the alternating pattern of the tremor episodes and sweating episodes.

[0012] Embodiments of the present invention are based on the insight that the detection of tremor and sweating episodes in a patient or other entity at different points in time during the monitoring period (i.e., the time intervals described above) can be interpreted as an indicator of changes in the patient's CBT (i.e., progression or change in the patient's fever state) without the need to record the patient's actual CBT. In some embodiments, a surrogate fever curve for the patient is constructed by recording the times when these tremor and sweating episodes occurred. Such a fever curve is considered a surrogate fever curve because it is based on inferences of changes in the patient's CBT from the aforementioned detection of tremor and sweating episodes, rather than on actual CBT measurements.

[0013] In one embodiment, the computer implementation further performs the step of using a processor device to determine the periodicity of the alternating pattern of detected tremor and sweating episodes based on their occurrence at different points in time within a given time interval. Based on this, a medical professional identifies the type of fever from the determined periodicity of the alternating pattern. For example, by identifying the type of fever based on the elapsed time between subsequent tremor episodes, between subsequent sweating episodes, and / or between a tremor episode and a subsequent sweating episode (and vice versa), additional diagnostic information is extracted from the surrogate fever curve and presented to the medical professional, for example, to assist the medical professional in effectively treating the patient's condition.

[0014] Such moments are recorded by the user manually generating input data, such as confirmation signals, during the occurrence of a patient's tremor or sweating episode. However, in a particularly advantageous embodiment, the step of receiving input data includes receiving patient monitoring data from a sensor device that monitors the patient's tremor and sweating as an indicator of the progression of the patient's fever over a time interval, and processing the received patient monitoring data to detect tremor and sweating episodes and recording the respective moments in time when the detected tremor and sweating episodes occurred in the patient monitoring data, thereby eliminating the need for manual input for monitoring the patient.

[0015] The computerized method may further include the steps of using a processor to determine at least one of the duration and intensity of each of the tremor episodes and sweating episodes, and optionally, calculating an index of fever intensity from the determined at least one of the duration and intensity of each of the tremor episodes and sweating episodes. This provides valuable insights into the patient's ability to resist fever caused, for example, by infection, as expressed as the trend of the severity of such episodes over time and / or duration.

[0016] In a further improved version, patient monitoring data includes information about the patient's thermal insulation, and the above computer implementation method further performs a step of using a processor device to determine at least one of the duration and severity of tremor attacks and sweating attacks, respectively, as a function of the patient's thermal insulation information. For example, whether the patient is covered with one or more blankets and / or wearing a certain amount of clothing affects the severity and duration, so detecting these external influences allows for a more accurate assessment of the true nature of the tremor attack or sweating attack.

[0017] In certain embodiments, the computer implementation method further performs the steps of using a processor device to determine the tremor frequency of each tremor episode and, based on the determined tremor frequency, determining whether the tremor episode is an indicator of a patient's body temperature change due to illness. This is based on the insight that the tremor frequency caused by fever differs from the frequencies of other involuntary tremors such as shivering. This further ensures that the tremor episodes included in the surrogate fever curve are indeed related to the patient's CBT changes caused by fever.

[0018] Preferably, sweating episodes are identified based on the patient's sweating rate, as this is a particularly accurate way to determine such sweating episodes. For example, the computer implementation method further performs the steps of: determining the patient's baseline sweating rate from patient monitoring data received during a tremor episode using a processor device; and detecting sweating episodes by detecting the patient's actual sweating rate in the received patient monitoring data that exceeds the baseline sweating rate by a defined amount. This is particularly advantageous because it provides a baseline of sweating rate unique to the patient, based on the insight that the patient's sweating rate is usually minimal during a tremor episode. Thus, by comparing the actual sweating rate with this baseline rate, a significant sweating rate for the patient can be detected, making the detection method robust to differences in sweating rates among patients.

[0019] Alternatively, the computer implementation method may further include the steps of using a processor device to compare the patient's actual sweat rate with a defined sweat rate threshold, and to detect a sweating episode when the actual sweat rate exceeds the defined sweat rate threshold, thereby ensuring that the detected sweat rate is sufficiently high, so that the detection is associated with a decrease in the patient's CBT, i.e., a genuine sweating episode indicating the patient's thermoregulation.

[0020] In a further embodiment, the computer implementation method further performs the steps of using a processor device to determine the signal intensity of signals associated with tremor attacks over a time interval; determining the total amount of sweat produced by the patient during sweating attacks over a time interval; determining the patient's sweating rate over a time interval from the determined total amount of sweat produced by the patient; calculating the ratio of the determined signal intensity to the determined sweating rate; and including the calculated ratio in the output. This ratio can be used to reconstruct a surrogate fever curve that enables prediction of, for example, the severity of fever and the effectiveness of drug response.

[0021] The patient monitoring data further includes core body temperature data relating to the patient's core body temperature measured over time intervals using the core body temperature sensor of the sensor device, and the above computer implementation method may further perform a step of including the patient's core body temperature data in the output using a processor device. This makes it possible to determine, for example, the lag between the occurrence of a tremor or sweating episode and the accompanying change in the patient's CBT monitored by the core body temperature sensor, from which the patient's thermoregulatory ability can be derived. Furthermore, CBT measurements help distinguish between tremor episodes caused by fever (which raise the patient's CBT) and tremor episodes caused by the patient being cold (which do not lead to an increase in the patient's body temperature setpoint). This can be used, for example, to verify whether a tremor episode is reliably associated with the onset of a fever episode, thereby further improving the accuracy of patient monitoring. Furthermore, including CBT information over a finite time period, such as a period containing several fever cycles, can be used for calibration or training of a surrogate fever curve by the processor device. For example, CBT data can be used as ground truth for training artificial intelligence or machine learning algorithms. Therefore, such calibration or training leads to the generation of surrogate fever curves that can accurately estimate actual CBT. Such CBT information is collected when the patient is continuously monitored in an intensive care setting, for example, during spot checks or invasive procedures.

[0022] In another embodiment, the computer implementation further includes, using a processor device, receiving auxiliary information at time intervals via a communication interface device, wherein the auxiliary information includes at least one of the ambient temperature to which the patient is exposed and the patient's activity level; determining, based on the actual auxiliary information at the time of the tremor or sweating episode, whether it is a reliable indicator of the patient's body temperature change due to the illness; and including the tremor or sweating episode in a step of generating an output only if it is determined that the tremor or sweating episode is a reliable indicator of the progression of the patient's fever. This makes it possible to exclude tremor or sweating episodes caused by factors other than fever from the surrogate fever curve and improve the accuracy of the surrogate fever curve.

[0023] In another embodiment, a computer program product is provided that includes a computer-readable storage medium in which computer-readable program instructions are embodied. When the computer-readable program instructions are executed on a processor device of a patient monitoring system, the processor device is instructed to carry out any of the methods of the embodiments described herein. Such a computer program product can be used to configure a monitoring system so that the methods according to embodiments of the present invention can be carried out.

[0024] According to yet another aspect, a monitoring system for monitoring a patient is provided. The monitoring system includes a processor device that receives input data indicating the patient's shivering episodes and sweating episodes as an indicator of the progression of the patient's fever over a period of time. The monitoring system further includes any of the computer program products described herein, and the processor device executes computer-readable program instructions. Thus, such a monitoring system can generate a proxy fever curve of the patient from the patient's shivering episodes and sweating episodes captured in the patient monitoring data provided by the sensor device without collecting CBT information. The monitoring system provides an output (e.g., an output including information related to the proxy fever curve and / or a diagnosis obtained from the shivering and sweating episodes) to a user interface based on the proxy fever curve, whereby the output can be evaluated, for example, by a medical expert at the user interface or the output can be stored in a data storage architecture such as an electronic patient record for retrieval by a medical expert at an appropriate time.

[0025] The monitoring system further includes a communication interface device that receives input data in the form of patient monitoring data from a sensor device that monitors shivering and sweating as an indicator of the progression of the patient's fever and transfers the patient monitoring data to the processor device. The monitoring system optionally includes the sensor device described above, whereby the patient is monitored without the need for manual intervention. Thus, as described above, a complete solution for monitoring the progression of the patient's fever based on monitoring the patient's shivering and sweating episodes is provided. The sensor device includes at least one of a camera, a sensor pad integrated into the bed, a wearable sensor including a sweat sensor, and a motion sensor that detects shivering. Preferably, the sensor device includes a wearable sensor.

Brief Description of the Drawings

[0026] Embodiments of the present invention will be described as non-limiting examples in more detail and with reference to the accompanying drawings.

[0027] [Figure 1] FIG. 1 schematically shows a monitoring system according to an embodiment. [Figure 2] FIG. 2 schematically shows an example of a fever curve (y-axis is core body temperature, x-axis is time). [Figure 3] FIG. 3 schematically shows in more detail an aspect of the monitoring system of FIG. 1. [Figure 4] FIG. 4 shows a flowchart of a fever progression monitoring method according to an embodiment. [Figure 5] FIG. 5 shows a graph for explaining the construction of a surrogate fever curve according to an example embodiment. [Figure 6] FIG. 6 shows a graph for explaining the construction of a surrogate fever curve according to another example embodiment. [Figure 7] FIG. 7 shows a graph for explaining the construction of a surrogate fever curve according to yet another example embodiment. [Figure 8] FIG. 8 shows a flowchart of an aspect of the fever progression monitoring method according to an embodiment. [Figure 9] FIG. 9 is a graph showing several fever index curves (y-axis is the reconstructed core body temperature index, x-axis is time).

Mode for Carrying Out the Invention

[0028] It should be understood that the figures are merely schematic and not drawn to scale. Also, it should be understood that the same reference numbers are used throughout the figures to indicate the same or similar parts.

[0029] Figure 1 schematically shows a configuration for monitoring the progression of fever in patient 1 using a monitoring system 10. The monitoring system 10 typically includes a data processing architecture 30 (e.g., a computer system, a server system, etc.), which includes a communication interface device 32 that communicates with a processor device 34. The communication interface device 32 includes any number of appropriate data communication interfaces, such as one or more P2P communication interfaces, such as a Bluetooth® interface, one or more wireless communication interfaces, such as a Wi-Fi® interface, and one or more wired communication interfaces, such as an Ethernet® interface, for connecting the data processing architecture 30 to a local area network or the internet, etc. The processor device 34 includes one or more processing elements, such as one or more processors or processor cores, that process patient monitoring data provided by the sensor device 20.

[0030] The sensor device 20 (which may form part of the monitoring system 10) typically provides patient monitoring data so that the processor device 34 can detect tremor episodes 52 and sweating episodes 54 of patient 1 during monitoring, in order to construct a surrogate fever curve 50 for patient 1 schematically shown in Figure 2. This will be described in more detail below. The patient monitoring data is typically provided to the data processing architecture 30 via one or more data communication links between the sensor device 20 and the communication interface device 32. The communication interface 32 transfers the received patient monitoring data to the processor device 34. To provide patient monitoring data that allows the processor device 34 to derive tremor and sweating episodes of patient 1, the sensor device 20 includes one or more sensors for this purpose.

[0031] For example, the sensor device 20 includes a camera 21 directed at patient 1. The camera 21 detects, for example, patient tremors by detecting patient movement in the image provided by the camera 21, and also detects sweating by changing the reflection of light due to the formation of sweat droplets on exposed areas of the patient's skin, such as the patient's forehead, which are detected in the image provided by the camera 21. The sensor device 20 includes a wearable sensor 22 attached to the patient's skin that provides the necessary patient monitoring data. Figure 3 shows an example embodiment of such a wearable sensor 22. Figure 3 shows a wearable sensor 22 that includes a motion sensor 221 such as an EMG or ECG sensor or accelerometer that can detect patient movement (e.g., tremors), a sweat sensor 222 that can detect sweating in the area of ​​the patient's skin to which the wearable sensor 22 is attached, and optionally at least one additional sensor 223 that provides additional sensor data, as will be described in more detail below.

[0032] The sweat sensor 222 measures sweat parameters indirectly by measuring sweat flow rate or sweat volume after a defined collection time, or by measuring, for example, skin conduction. If both motion sensor 221 and sweat sensor 222 are included, the wearable sensor 22 must be placed on a part of the patient's body where both tremor and sweating can be reliably measured, such as the patient's chest or neck. The sensor device 20 includes a sensor 23 integrated into bedding, for example, a mattress 3 on which patient 1 sleeps, to detect patient movement while patient 1 is in bed. Tremor can be detected from this patient movement. A suitable combination of such sensors 21, 22, and 23 can be arranged. In a preferred embodiment, the sensor device 20 includes at least a wearable sensor 22.

[0033] The data processing architecture 30 may further be communicatively coupled to one or more user interfaces 41, 42. These user interfaces display the results of processing patient monitoring data by the processor device 34 (e.g., a surrogate fever curve 50). For this purpose, the processor device 34 typically generates an output based on this processing result, for example, containing the processing result and information derived therefrom. This output is transmitted to specific user interfaces 41, 42 via a communication interface device 32. For example, user interface 41 is a mobile communication device, including an app for visualizing the processing results of the processor device 34, which can be used by healthcare professionals such as nurses and doctors to assess the fever of patient 1. User interface 42 is a user terminal, such as a personal computer, from which healthcare professionals can receive processing results from the processor device 34. Alternatively, the processor device may further store the processing results in a data storage arrangement 43, for example a network-connected database, which stores patient monitoring data, such as an electronic patient record, so that the processing results can be accessed at any appropriate time using user interface 41 or 42. Other suitable architectures will be apparent to those skilled in the art.

[0034] In another embodiment (not shown), the sensor device 20 is omitted, and the processor device 34 can instead receive manually generated input data using an input device such as a remote controller, an electronic communication device such as a smartphone, for example, by patient 1 or a medical professional such as a nurse or doctor, so that the person operating such an input device can signal the occurrence of a tremor attack 52 or a sweating attack 54 of patient 1 using that input device, so that the processor device only needs to record the time when such input is received in order to construct a surrogate fever curve 50.

[0035] The monitoring system 10 implements one or more embodiments of Method 100 of the present invention. A flowchart of Method 100 is shown in Figure 4. Method 100 begins with step 101. In step 101, for example, a sensor device 20, if present, is enabled and provides the aforementioned patient monitoring data to the processor device 34 via the communication interface device 32. In step 103, the processor device 34 processes the patient monitoring data received from the sensor device 20 to determine whether it can detect a tremor episode 52 of patient 1 within the patient monitoring data. This processing is performed continuously or periodically. That is, the patient monitoring data is processed continuously or sampled periodically, such as once every 1 to 5 minutes, for processing by the processor device 34. If no tremor is detected, the processor device 34 continues to search for a tremor episode 52 of patient 1 in the received patient monitoring data. However, if the processor device 34 detects the occurrence of a tremor episode 52, the method proceeds to step 105. In step 105, the processor device records the time when the tremor seizure 52 was detected, for example, as derived from patient monitoring data provided by the sensor device 20, or as derived from manually generated input data indicating the tremor seizure 52. This time is expressed in any appropriate format, for example, the elapsed time since the start of patient monitoring, the actual time, etc.

[0036] Method 100 proceeds to step 107, in which the processor device 34 determines the baseline sweating rate of patient 1 during a tremor episode 52. This is based on the insight that during such a tremor episode 52, patient 1's CBT, i.e., body temperature setpoint, is elevated, which typically corresponds to minimal associated sweating. Thus, determining the sweating rate during such a tremor episode 52 provides a reliable baseline for determining patient 1's subsequent sweating episodes 54, because patient 1's actual sweating episodes 54 will have a significantly higher sweating rate than the baseline sweating rate. Determining such a baseline sweating rate has the advantage that a patient-specific baseline sweating rate is defined, thus eliminating the need to consider different sweating rates for each patient to reliably detect patient 1's sweating episodes. However, in alternative embodiments, the detection of such a baseline sweating rate may be omitted. In this case, patient 1's sweating episodes 54 can be detected using a defined sweating rate threshold. The sweating rate threshold may be general, sex-specific, or specific to the location of the wearable sensor 22 on the patient's body.

[0037] In step 109, the processor device 34 processes the patient monitoring data received from the sensor device 20 to determine whether a sweating episode 54 of patient 1 can be detected in the patient monitoring data. This processing is performed continuously or periodically. That is, the patient monitoring data is processed continuously or sampled periodically, such as once every 1 to 5 minutes, for processing by the processor device 34. For example, the processor device 34 determines the actual sweating rate of patient 1 and compares this actual sweating rate with the sweating baseline rate determined in step 107. If the actual sweating rate exceeds the sweating baseline rate by a defined amount (for example, a defined multiple such as 4 to 6 times), it determines that a sweating episode 54 has occurred.

[0038] Alternatively, the processor device 34 may compare the actual sweat rate with a defined sweat rate threshold and determine that a sweating episode 54 has occurred if the actual sweat rate exceeds the defined threshold, and confirm that the sweat rate is sufficiently high (for example, above 0.7 nL / min for the sweat glands) to determine that the sweating episode 54 has occurred with sufficient reliability. Such a sweat rate can be determined, for example, by using the wearable sensor 22 to determine the actual sweat rate and parameters related to changes in the sweat rate, such as skin conductance, or by using the camera 21 to determine, for example, changes in reflected light from camera images and deriving the sweat rate from these changes.

[0039] If no sweating episode 54 is detected, the processor device 34 continues to search for the sweating episode 54 of patient 1 in the received patient monitoring data in step 109. However, if the processor device 34 detects the occurrence of a sweating episode, for example, in the patient monitoring data provided by the sensor device 20, or from manually generated input data that flags the sweating episode 54, the method proceeds to step 111, in which the processor device 34 records the time at which the sweating episode 54 was detected. This time is expressed in any appropriate format, for example, the elapsed time since the start of monitoring of patient 1, the elapsed time since a previously detected tremor episode 52, or the actual time.

[0040] As shown in step 113, recording continues at the time when tremor attacks 52 and sweating attacks 54 are detected. In this case, method 100 returns to step 103, and the processor device 34 processes the patient monitoring data to detect the next tremor attack 52, or waits for manual flagging of such attacks as described above. Method 100 may instead proceed to step 115, in which the processor device 34 constructs a surrogate fever curve 50 for patient 1 from the recorded time when tremor attacks 52 and sweating attacks 54 occurred in patient 1. To avoid concern, the construction of the surrogate fever curve 50 is performed after monitoring patient 1 at regular time intervals, or in parallel with monitoring patient 1 over those time intervals. The processor device 34 constructs the surrogate fever curve 50 based on the alternating pattern of tremor attacks 52 and sweating attacks 54 and the periodicity of this alternating pattern.

[0041] For example, as schematically shown in Figure 5, the processor device 34 receives an instruction for the onset of a tremor episode 52 at T=t1, for example from the sensor device 20 or by manual input as described above. The tremor episode 52 ends at T=t2. The graph above shows the intensity (in arbitrary units) (Y-axis) of the tremor episode 52 and the sweating episode 54 as a function of time (X-axis). The processor device 34 further receives an instruction for the onset of a sweating episode 54 at T=t3, for example from the sensor device 20 or by manual input as described above. The sweating episode 54 ends at T=t4. The processor device 34 further receives an instruction for the onset of a further tremor episode 52 at T=t5, for example from the sensor device 20 or by manual input as described above. The further tremor episode 52 ends at T=t4. The processor device 34 constructs a surrogate fever curve 50 from the point in time when the tremor attacks 52 and sweating attacks 54 began (i.e., t1, t3, and t3), without considering the duration of each attack. This generates the resulting surrogate fever curve 50, which has CBT, or more precisely, the projected change of CBT (Y axis), as a function of time (X axis), as shown in Figure 5. As can be seen from this curve, the occurrence of each tremor attack 52 is interpreted as an instantaneous rise in CBT, and the occurrence of each sweating attack is interpreted as an instantaneous decrease in CBT. Of course, alternative approaches are also possible, such as fitting a sine curve based on the recorded timing of the occurrence of the tremor attacks 52 and sweating attacks 54. The processor device 34 then generates output based on the constructed surrogate fever curve 50 for, for example, transmission to the user interface 41 or 42 and / or storage in the data storage architecture 43, in step 117. Method 100 then terminates in step 119.

[0042] In the improved version, when constructing the surrogate fever curve 50 in step 115, the processor device 34 takes into account the duration of each tremor episode 52 and sweating episode 54. This is shown in Figure 6, and at the start of each tremor episode 52, the processor device 34 assumes a gradual increase, such as a linear increase in the patient's CBT, until the end of the tremor episode 52. Thereafter, the CBT is assumed to remain constant until the start of the subsequent sweating episode 54. At that point, the processor device 34 assumes a gradual decrease, such as a linear increase in the patient's CBT, until the end of the sweating episode 54, in its construction of the surrogate fever curve 50. Again, as an alternative, a sine curve can be fitted based on the start and end values ​​(times) of the start and end points of each tremor episode 52 and sweating episode 54.

[0043] As shown in Figure 7, in a further improved version, the processor device 34 constructs a surrogate fever curve 50 that takes into account both the duration and intensity of tremor attacks 52 and sweating attacks 54. In this approach, if patient 1 is sweating heavily, i.e., has a high sweat rate, the reproducible approximation of patient 1's CBT decreases faster than if patient 1 is sweating lightly, i.e., has a low sweat rate. As described above, a sweating attack 52 is detected when the actual sweat rate exceeds the sweating baseline rate or threshold 55. Similarly, if patient 1 has severe tremors, the reproducible approximation of patient 1's CBT increases faster than if patient 1 has light tremors. The intensity of tremor attacks is determined using power spectral density analysis, as will be explained in more detail below. Since the intensity levels of tremor attacks 52 or sweating attacks 54 change over time, the construction of the surrogate fever curve 50 becomes an integral, as shown in equation (1), rather than a binary on / off approach.

number

[0044] In this equation, t is time, T0 is body temperature at t=0 (which is measured, estimated, or a default value), and c1 and c2 are parameters that depend on the patient and environment (e.g., consider the thermal insulation of patient 1; see below), and may also depend on the intensity of tremor and sweating. If independent CBT measurements are not available, default values ​​are used for T0, c1, and c2. However, if such independent CBT measurements become available, T0 can be determined using these measurements. If multiple independent CBT measurements become available over a period of time (e.g., through continuous or spot-check CBT measurements over a period of time during which tremor attacks 52 and sweating attacks 54 occur), c1 and c2 can also be estimated for a particular patient, environment, and tremor / sweating attack intensity level during the CBT measurements. This serves as calibration for the construction of the surrogate fever curve 50 by the processor device 34 after the CBT measurements have stopped. Therefore, in this embodiment, a surrogate fever curve 50 can be provided on the Y axis of the graph, which shows the surrogate fever curve 50 as a function of time on the X axis of the graph, and the estimated absolute value of the patient's CBT can be provided on the Y axis of the graph.

[0045] In a preferred embodiment, the processor device 34 generates information to support the treatment of the patient by healthcare professionals, such as determining the type of fever from the recorded time points in which the detected tremor attacks 52 and sweating attacks 54 of patient 1 occurred, in addition to or instead of generating the surrogate fever curve 50, and includes this information in the output generated in step 117, for example, in addition to the surrogate fever curve 50, or without including the actual surrogate fever curve 50, as information derived from the surrogate fever curve 50, to provide healthcare professionals with additional insights into the underlying symptoms of patient 1. This will be illustrated in more detail with reference to Figure 8, which schematically shows a decision tree deployed by the processor device 34 to determine the type of fever from the recorded time points. The decision tree begins in step 151, and then in step 153, the periodicity of the surrogate fever curve 50 is determined by the processor device 34, for example, in step 153, by determining the elapsed time between consecutive tremor attacks 52 separated by sweating attacks 54, or the elapsed time between consecutive sweating attacks 54 separated by tremor attacks 52 from the recorded time points. If this periodicity is less than approximately 24 hours, as determined in step 155, the processor unit 34 determines that the type of heat generation is ripple heat, as expressed in conclusion 171.

[0046] On the other hand, if this periodicity is determined to be approximately 24 hours, the processor device 34 determines that the type of fever is daily fever. Next, in step 157, the processor device 34 further evaluates the time elapsed from the tremor attack 52 to the subsequent sweating attack 54 to determine the patient's physical ability to fight daily fever. Normally, if the patient's immune system is functioning normally, the duration of the CBT or fever rise is within a few hours, during which time the patient's immune system attacks the surge of parasites. Therefore, in step 157, if the processor device 34 concludes that the duration of the CBT rise corresponds to proper functioning of the immune system, the processor device 34 concludes that the fever is "normal" daily fever, as expressed in conclusion 172. On the other hand, in step 157, if the processor device 34 concludes that the duration of the CBT rise exceeds a threshold indicating a decline in the immune system, the processor device 34 concludes that the fever is daily fever of a weakened patient 1, as expressed in conclusion 173.

[0047] Naturally, the assessment of the patient's immune system status is optional, in which case the determination of the elapsed time between the tremor episode 52 and the subsequent sweating episode 54 is omitted from this assessment. Therefore, the recording of the time of onset of the sweating episode 54 is omitted, and the evaluation of the surrogate fever curve 50 is based solely on the elapsed time between consecutive tremor episodes 52 (as long as these tremor episodes are separated by sweating episodes 54). Similarly, the recording of the time of onset of the tremor episode 52 is omitted, and the evaluation of the surrogate fever curve 50 is based solely on the elapsed time between consecutive sweating episodes 54 (as long as these sweating episodes are separated by tremor episodes 52).

[0048] In step 155, if the processor unit 34 determines that the fever cycle of patient 1 clearly exceeds 24 hours, the processor unit 34 concludes that this fever is another type of fever, such as tertian fever, quartian fever, relapsing fever, or wave fever, as expressed in conclusion 174. To distinguish between such further types of fever, the processor unit 34 may implement an additional decision tree (not shown).

[0049] As described above, in at least some embodiments, in which patient monitoring data is collected using the sensor device 20 and a surrogate fever curve 50 is constructed from it, additional sensors (such as additional sensors 223) are used for several reasons. For example, the sweat sensor 222 of the wearable sensor 22 further determines the concentration of a substance of interest (such as cytokines or lactates) in the secreted sweat. The processor device 34 uses this to further determine the cause of the fever, the severity of the disease, and / or the effectiveness of medication to combat the disease. This information provides healthcare professionals with useful insights into how to treat patient 1, for example, by different dosages, different drug doses, or administering different medications. Further additional sensors, preferably integrated into one or more wearable sensors 22 but not necessarily, provide physiological monitoring data such as heart rate, respiratory rate, blood pressure, and peripheral oxygen saturation. Including this sensor data in the output generated by the processor device 34 further enhances the diagnostic potential of this output.

[0050] The sensor device 20 may further include one or more sensors that provide auxiliary information to the processor device 34, such as one or more motion sensors that detect an increase in the patient's activity (such as sports activity or strenuous activity like climbing stairs) that may cause sweating episodes, rather than a decrease in the patient's body temperature setpoint due to fever, a heart rate monitor, a blood pressure sensor, etc. This auxiliary information allows the processor device 34 to distinguish between tremor episodes 52 and sweating episodes 54 caused by fever, or the occurrence of such episodes for different reasons. Environmental sensors (such as ambient temperature sensors) can be used to determine whether the onset of a tremor or sweating episode is caused by environmental factors such as low or high ambient temperature, rather than by illness. The processor device 34 uses this auxiliary information to determine whether a tremor episode 52 or sweating episode 54 is a reliable indicator of a change in the patient's body temperature caused by illness. As a result, the processor device 34 includes only the time points of such tremor episodes 52 or sweating episodes 54 in the surrogate fever curve 50 if it determines that the tremor episodes 52 or sweating episodes 54 are reliable indicators of changes in patient 1's body temperature caused by the illness, and not by other factors as indicated by the supplementary information.

[0051] In yet another embodiment, the sensor device 20 further includes a CBT sensor, which may be an additional sensor 223 within the wearable sensor 22, or a separate (wearable) sensor. Including CBT information in the patient monitoring data allows for more information to be obtained from the point in time when tremor episodes 52 and / or sweating episodes 54 occur. Typically, CBT increases with tremors and decreases with sweating, but there is a certain lag time between the occurrence of such tremor or sweating episodes and the accompanying change in CBT. This lag time can be used to gain insights into the patient's thermoregulatory ability. Furthermore, the CBT information is used to calibrate the construction of a surrogate fever curve 50 by the processor device 34. For example, it is used as ground truth for training artificial intelligence or machine learning algorithms used by the processor device 34 to construct the surrogate fever curve 50.

[0052] Another reason to add CBT measurements is to distinguish between tremors caused by an elevated setpoint (leading to fever) and tremors caused by patient 1 becoming too cold (having a normal setpoint). This is particularly useful when establishing the onset of a fever period. One simple way to distinguish between these two possibilities is to perform a single CBT measurement whenever a tremor is detected for an appropriate period (e.g., 10 minutes). If the cause is an elevated setpoint, the temperature will have already risen, but if the body is cold, it will fall.

[0053] As is well known, fever is an increase in body temperature during infection. However, the underlying mechanism of this fever is more complex and involves a host response to the infection. The immune system is activated by the source of infection, releasing chemokines into the body, leading to activation of cyclooxygenase (COX), resulting in stimulation of the "heat-gaining thermoeffector" (i.e., tremor) and suppression of the "heat-loss thermoeffector" (i.e., sweating). Usually, only core body temperature is measured, and apart from the aforementioned impractical clinical integration, it only provides information about the elevation of the patient's body temperature setpoint. Therefore, in a preferred embodiment, the construction of the surrogate fever curve 50 further includes determining the patient's tremor rate and sweat rate to provide the surrogate fever curve 50 with an additional layer of diagnostically relevant information. This is, for example, to provide information about the host response to the source of infection, i.e., the immune response. As mentioned above, in addition to or alternative to measuring patient 1's CBT to determine the lag between tremor and sweating episodes and the induced changes in the patient's CBT, such host responses can be calculated from several parameters, including the change in time between consecutive tremor episodes 52, the change in time between consecutive sweating episodes 54, the change in time between tremor episode 52 and the subsequent sweating episode 54, and the intensity and duration of such tremor episodes 52 and sweating episodes 54. The intensity of the sweating episodes 54 is based on the sweating rate determined by the sensor device 20. The intensity of the tremor episodes 52 is determined based on Fourier analysis and / or spectral power analysis of the tremor data provided by the sensor device 20. This serves several purposes. First, the analysis of such tremor data provides a measurement of the tremor frequency of patient 1. This allows the processor device to distinguish between unintentional muscle movements, such as age-related tremors, and tremors resulting from an elevated setpoint compared to patient 1's actual CBT. For example, hand tremors caused by Parkinson's disease can reach up to 9 Hz, with the amplitude of this tremor and the acceleration amplitude being 19 cm and 20 m / s², respectively. 2It may reach this level. During fever or hyperthyroidism, the frequency rises to a maximum of 14 Hz, so that fever-related tremors can be distinguished from other types of tremors, and the processor device 34 can, for example, use a bandpass filter or highpass filter with an appropriate cutoff frequency (e.g., 10 Hz) to discard tremor attacks 52 caused by such other types of tremors and consider only tremor attacks 52 caused by fever in the construction of the surrogate fever curve 50.

[0054] Next, a surrogate fever curve can be constructed using the ratio of the signal intensity of the tremor signal generated by the sensor device 20 to the total amount of sweat or the rate of sweating over time monitored at the patient monitoring time interval, so as to predict the severity of fever and the effectiveness of the treatment response.

[0055] In the first step, a fast Fourier analysis (e.g., amplitude or power spectral signal analysis) of the oscillation signal is performed to determine the intensity of the tremor. The power spectral density (PSD) of the tremor signal (PSD_Shivering) represents the power present in the signal as a function of frequency per unit frequency. Power spectral density is usually expressed in watts per Hertz (W / Hz). Next, the total power present in the signal over the relevant frequency range (e.g., 10–20 Hz or 5–15 Hz) is calculated.

[0056] In the second step, the ratio of tremor signal intensity to sweat rate (nL / s) is determined, and the fever index is calculated according to Equations 2 and 3 below. Such a fever index is either the index at a given time (Equation 2) or the time integral index (Equation 3), i.e., the area under the fever index curve shown in Figure 9. Integrating the fever index over time to calculate the cumulative fever index (Equation 2), this time integral index provides clinical information related to the intensity of fever episodes or fever intervals in a given time frame of clinical interest. Another option is to calculate the first derivative of the fever index curve. This provides information about fever dynamics, such as the rate of fever onset or the rate of fever recovery.

number

number

[0057] This ratio is calculated assuming that the onset and development of fever are usually proportional to and directly related to tremor, while fever is inversely proportional to the rate of sweating, decreasing with sweating. This is schematically shown in Figure 9. Three fever index curves are shown, ranging from a normal or reference value of 5, below the upper threshold of normal (7), to a strong fever value of 6, exceeding the critical threshold of 8, as indicated by tremor attacks 52, and then returning to normal or reference value of 5 (indicated by sweating attacks 54).

[0058] From the surrogate heat index curves A to C, the time constant τ up or τ down It is possible to determine or derive τ. For example, τ up τ is defined as the time it takes for the surrogate heating curve 50 to pass the critical threshold 8, starting from a reference value of 5. down This is defined as the time it takes for the surrogate fever curve 50 to pass the upper limit threshold 7 from a fever value of 6. Alternatively, τ down This time constant may be defined as the time it takes for the fever to decrease to 67% of its maximum value, similar to the calculation of the decay time of electrical components such as capacitors. Thus, these time constants carry clinical information about the rate at which fever develops and subsides, such as after drug administration. The surrogate fever curve shown in Figure 9 can be visualized in user interface 41 or user interface 42, for example, to provide direct feedback to healthcare professionals about the response to treatment, or to enable clinical decision-making support regarding the effectiveness of an intervention or drug.

[0059] In one embodiment, the determination results of patient 1's tremor intensity and sweat rate are scaled by the processor device 34 based on available information regarding patient 1's thermal insulation. For example, during a tremor attack 52, patient 1 can stay warm by wearing more clothes or adding blankets, which can suppress the intensity of the tremor attack 52. Similarly, during a sweating attack 54, patient 1 can cool down by removing clothes or blankets, which can suppress the rate of sweating. To this end, the sensor device 20 provides information about the patient's thermal insulation so that the processor device 20 can determine at least one of the duration and severity of the tremor attack 52 and sweating attack 54, respectively, as a function of the information about the patient's thermal insulation, as described above. Such information is provided in an appropriate manner. For example, the presence of some blankets or clothing, and / or the thickness of the blankets or clothing, is determined from image data provided by the camera 21. Alternatively, such information may be generated using a wearable sensor 22 by providing one or more measurements of skin temperature, pressure, and ambient light, for example. In particular, the pressure of the blanket against the skin and ambient light, i.e., light passing through blankets and clothing, are unrelated to core body temperature and are particularly useful parameters to monitor for the purposes described above.

[0060] Embodiments of the present invention provide clinical insights into the body's thermoregulatory capacity to, for example, provide insights into the effectiveness of administered drugs, the severity of a disease, or the cause of fever. Such clinical insights are useful in various therapeutic settings, such as hospital, hospital-to-home, or home use, helping to find the appropriate drug, dosage, and timing. For example, the clinical information provided by the processor device 34 helps determine whether antibiotics are necessary to treat patient 1's condition, thereby reducing the risk of unnecessary administration of such antibiotics (which is undesirable in the sense that it increases antibiotic resistance). However, it should be understood that the use of the present invention is not limited to medical applications and may be used to obtain insights into the body's thermoregulatory characteristics of any patient (e.g., human or non-human) in general. In this context, the term "patient" as used in this application is intended to apply to all patients whose CBT is monitored in accordance with the teachings of this application and should not be construed as being limited to persons suffering from a disease.

[0061] The above embodiments of Method 100, executed by the processor device 34, are realized by computer-readable program instructions embodied in a computer-readable storage medium. When the computer-readable program instructions are executed by the processor device 34 of the computing device 30, for example, in a patient monitoring terminal, the processor device 34 is made to implement any embodiment of Method 100. For this purpose, any suitable computer-readable storage medium is used, such as an optically readable medium such as a CD, DVD, or Blu-Ray® disc, a magnetically readable medium such as a hard disk, or an electronic data storage device such as a Memory Stick. The computer-readable storage medium is a medium accessible via a network such as the Internet, thereby allowing the computer-readable program instructions to be accessed via the network. For example, the computer-readable storage medium may be a network-attached storage device, a storage area network, or cloud storage. The computer-readable storage medium may also be an Internet-accessible service from which the computer-readable program instructions can be obtained. In some embodiments, at least a portion of the computer-readable program instructions are incorporated into the processor device 34 in hardware form.

[0062] The embodiments described above are illustrative, not limiting, of the invention, and it should be noted that those skilled in the art can design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference numerals in parentheses should not be construed as limiting the claims. The word “includes” does not exclude the existence of elements or steps other than those enumerated in the claims. A singular element does not exclude the existence of multiple elements. The invention can be implemented by hardware comprising several different elements. In a device claim that enumerates several means, some of these means can be embodied by the exact same hardware item. Means described in mutually different dependent claims can be advantageously combined.

Claims

1. 1. A patient monitoring system for monitoring the progression of fever in a subject, comprising: receiving patient monitoring data from a sensor device monitoring tremors and sweating of the patient as an indication of a progression of the patient's fever over a time interval; processing the received patient monitoring data to detect tremor attacks and sweat attacks and record the time points at which the tremor attacks and the sweat attacks occurred, respectively; 1. A patient monitoring system including a processor device, the processor device further comprising: and constructing a surrogate fever curve from each of the recorded time points of the tremor attacks and the sweat attacks based on an alternating pattern of the tremor attacks and the sweat attacks for use in monitoring the progression of the subject's fever.

2. The processor device includes: determining a periodicity of the alternating pattern of the detected tremor and sweating attacks based on their respective occurrences at different times during the time interval; The patient monitoring system of claim 1 , further comprising: a step of: determining a type of fever from the determined periodicity of the alternating pattern;

3. The processor device includes:

3. A patient monitoring system according to claim 1 or 2, which determines at least one of the duration and intensity of each of the tremor and sweating attacks.

4. the patient monitoring data includes information regarding the degree of insulation of the patient; The processor device includes:

4. The patient monitoring system of claim 3, further comprising: determining at least one of a duration and a severity of each of the tremor and sweat attacks as a function of the information regarding the degree of insulation of the patient.

5. The processor device includes:

5. The patient monitoring system of claim 1, wherein the tremor frequency of each tremor episode is determined.

6. The processor device includes:

6. The patient monitoring system of claim 1, further comprising: a patient monitoring system for determining whether a sweat episode occurs based on a sweat rate of the patient.

7. The processor device includes: determining a sweat baseline rate for the patient from the patient monitoring data received during a tremor attack; 7. The patient monitoring system of claim 6, further comprising: detecting a sweat episode by detecting, within the received patient monitoring data, an actual sweat rate of the patient that exceeds the sweat baseline rate by a defined amount.

8. The processor device includes: Comparing the patient's actual sweat rate with a defined sweat rate threshold; 8. The patient monitoring system of claim 6 or 7, wherein a sweat episode is detected when the actual sweat rate exceeds the defined sweat rate threshold.

9. The processor device includes: determining a signal strength of a signal associated with a tremor attack over the time interval; determining a total amount of sweat produced by the subject during the sweat bout over the time interval; determining a sweat rate of the subject over the time interval from the determined total amount of sweat produced by the subject; Calculating a ratio between the determined signal strength and the determined sweat rate; 9. A patient monitoring system according to claim 6, which outputs the calculated ratio.

10. 10. The patient monitoring system of claim 1, wherein the patient monitoring data further includes core body temperature data relating to a core body temperature of the patient measured over the time interval using a core body temperature sensor of the sensor device, and the processor device outputs the core body temperature data.

11. The processor device includes: receiving, by a communications interface device, auxiliary information during the time interval, the auxiliary information including at least one of an ambient temperature to which the patient is exposed and a measurement of an activity level of the patient; determining whether a tremor attack or a sweat attack is a reliable indicator of a change in the patient's body temperature due to illness based on actual auxiliary information at the time of the tremor attack or the sweat attack; 11. The patient monitoring system of claim 1, wherein the patient monitoring system outputs a tremor or sweating attack only if the tremor or sweating attack is determined to be a reliable indicator of the progression of the patient's fever.

12. 12. The patient monitoring system of claim 11, further comprising a communication interface device configured to receive input data in the form of patient monitoring data from a sensor device monitoring tremor and sweating of the patient as an indication of a progression of the patient's fever and to transfer the patient monitoring data to the processor device, the patient monitoring system optionally including the sensor device.

13. A computer readable storage medium having computer readable program instructions embodied thereon, the computer readable program instructions, when executed by a processor unit of a patient monitoring system according to any one of claims 1 to 12, causing the processor unit to: receiving said patient monitoring data from said sensor device monitoring said patient's tremors and sweating as indicators of the progression of the patient's fever over said time interval; processing the received patient monitoring data to detect tremor attacks and sweat attacks and record the time points at which the tremor attacks and the sweat attacks occur, respectively; constructing a surrogate fever curve from the recorded time points of the tremor attacks and the sweat attacks based on an alternating pattern of the tremor attacks and the sweat attacks for use in monitoring the progression of the subject's fever; 16. A computer readable storage medium for implementing a patient monitoring method, comprising:

Images