Monitoring of tremor and sweating episodes

Abstract

A patient monitoring method comprises receiving (103, 109) input data indicative of chills episodes (52) and sweating episodes (54) of a patient; recording (105, 111) respective time points at which said chills episodes and sweating episodes occur; and generating (115, 117) an output based on an alternating pattern of chills episodes and sweating episodes from the recorded respective time points of the respective chills and / or sweating episodes. A computer program product for implementing such a method and a monitoring system (10) arranged to implement such a method are also disclosed.

Description

Technical Field

[0001] The present invention relates to a computer-implemented method for monitoring episodes of trembling and sweating in patients.

[0002] The present invention also relates to a computer program product for implementing this method on a monitoring system, and a monitoring system configured to implement this method. Background Technology

[0003] Fever in patients is defined as a core body temperature (CBT) above the normal range due to an elevated temperature set point. Fever can be caused by a wide range of medical conditions, from mild to life-threatening. These include viral, bacterial, and parasitic infections such as the common cold, urinary tract infections, meningitis, malaria, and appendicitis. Non-infectious causes include vasculitis, deep vein thrombosis, drug side effects, and cancer. Fever is believed to be beneficial for the host's survival in bacterial infections and is regulated by the body's thermoregulation mechanisms, among which sweating and shivering play particularly important roles.

[0004] US 2018 / 0242850 discloses obtaining perfusion parameters from patient temperature monitoring to determine core body temperature, which can characterize user conditions such as fever.

[0005] WO 2017 / 172837A1 discloses a system, method, and apparatus for detecting changes or the absence of changes in a patient's intrinsic set point temperature using heat transfer parameters or energy consumption from a device that provides controlled low temperature, normal body temperature, or high temperature. When the body's core temperature deviates below a threshold range, a series of coordinated responses occur, including surface vasoconstriction, shivering, and metabolic thermogenesis. When the body's core temperature deviates above a threshold range, a series of coordinated responses occur, including surface vasodilation and sweating.

[0006] Depending on the nature of the medical condition, a patient's CBT may exhibit different time-dependent behaviors. For example, infection-related fever is caused by an increase in the set point due to cytokines released by circulating white blood cells in the bloodstream. However, when the source of infection decreases, or in other words, when the activation of the host immune system is reduced, the concentration of cytokines in the bloodstream decreases, leading to decreased inhibition in the hypothalamus. This results in a lower set point, and therefore sweating reaches a lower set point, thus leading to a CBT that exhibits a periodic behavior of fever episodes over time. Long-term monitored CBT, also known as a fever curve, can provide diagnostic information to medical professionals such as clinicians or nurses.

[0007] In high-sensitivity hospital environments, particularly in intensive care units (ICUs), CBT can be measured continuously. This is done via invasive measurement. In low-sensitivity environments, especially in general wards, invasive techniques are avoided, for example, due to the risk of infection. Because there is no reliable, continuous, non-invasive technique for measuring CBT, CBT is measured on a random basis, typically only once or three times per day. Therefore, the fever curve cannot be reconstructed. Summary of the Invention

[0008] This invention seeks to provide a non-invasive method for patient monitoring.

[0009] The present invention also seeks to provide a computer program product for implementing this method on a monitoring system, and a monitoring system for monitoring patients, said monitoring system being configured to implement this method.

[0010] This invention is defined by the independent claims. Dependent claims define advantageous embodiments. The output may be an alternative fever curve and / or other information that can be used by healthcare professionals to draw conclusions about the patient. Output based on shivering and sweating episodes can be used by medical professionals to obtain diagnostically relevant information about the progression of a patient's fever, which, for example, can help medical professionals identify the type of a patient's medical condition, define a patient's medication regimen, or assess the effectiveness of an applied medication regimen, for example, by monitoring changes in the alternative fever curve after administration.

[0011] According to an embodiment, a computer-implemented method for monitoring the progression of a patient's fever is provided. The computer-implemented method includes, using a processor device, receiving input data indicating shivering episodes and sweating episodes of the patient as indicators of the patient's fever progression over a time interval; recording the corresponding time points of the shivering episodes and sweating episodes; and generating output, for example, an output indicating the patient's fever progression, based on the alternation pattern of shivering episodes and / or sweating episodes from the recorded corresponding time points of the corresponding shivering and / or sweating episodes.

[0012] Embodiments of the present invention are based on the understanding that the detection of shivering and sweating episodes in a patient (e.g., the patient or any other person) at different time points during a monitoring period (i.e., time interval) can be interpreted as an indicator of changes in the patient's CBT (i.e., the progression or change of the patient's fever state), without necessarily recording the patient's actual CBT. In some embodiments, by recording the time points at which these shivering and sweating episodes occur, an alternative fever curve for the patient can be constructed. Such a fever curve can be considered an alternative fever curve because it is not based on actual CBT measurements, but rather on inferences about changes in the patient's CBT based on the aforementioned detection of shivering and sweating episodes.

[0013] In an embodiment, the computer-implemented method further includes using the processor device to determine the periodicity of the alternation pattern of detected tremor and sweating episodes based on their corresponding occurrence at different points in time during the time interval. Based on this, healthcare professionals can identify the type of fever according to the determined periodicity of the alternation pattern. By identifying the type of fever (e.g., based on the elapsed time between subsequent tremor episodes, between subsequent sweating episodes, and / or between a tremor episode and a subsequent sweating episode, or vice versa), additional diagnostic information can be extracted from the alternative fever curve and presented to medical professionals, for example, to help them effectively manage a patient's medical condition.

[0014] Such time points can be recorded by the user manually generating input data (e.g., confirmation signals, etc.) during an episode of shivering or sweating in the patient. However, in a particularly advantageous embodiment, receiving the input data includes receiving patient monitoring data from a sensor device for monitoring the patient's shivering and sweating as an indicator of the patient's fever progression during the time interval; and processing the received patient monitoring data to detect the shivering and sweating episodes, and recording the corresponding time points of the detected shivering and sweating episodes in the patient monitoring data, thus eliminating the need for manual input to monitor the patient.

[0015] The computer-implemented method may further include using the processor device to determine at least one of the duration and intensity of each shivering episode and sweating episode; and optionally, calculating an indication of fever intensity based on at least one of the determined duration and intensity of each shivering episode and sweating episode. This can provide valuable insights into a patient's ability to resist fever, for example, when caused by infection, as indicated by the trend of the severity and / or duration of such episodes over time.

[0016] In another improvement, the patient monitoring data may include information related to the patient's level of thermal insulation, and the computer-implemented method may further include using the processor device to determine at least one of the duration and severity of each shivering episode and sweating episode based on the information related to the patient's level of thermal insulation. For example, whether the patient is covered with one or more blankets and / or wearing a certain amount of clothing may affect the severity and duration, making the detection of these external influences possible for a more accurate assessment of the true nature of the shivering or sweating episode.

[0017] In a particular embodiment, the computer-implemented method further includes using the processor device to determine the frequency of each tremor episode; and based on the determined tremor frequency, determining whether the tremor episode is an indicator of disease-induced changes in body temperature (CBT) in the patient. This is based on the understanding that the frequency of tremors caused by fever episodes differs from the frequency of other involuntary trembling-like body movements (e.g., tremors), thereby further ensuring that tremor episodes included in the surrogate fever curve are truly correlated with changes in the patient's CBT caused by the fever episode.

[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-implemented method may further include using the processor device to determine the patient's baseline sweating rate based on patient monitoring data received during a shivering episode; and detecting a sweating episode by detecting that the patient's actual sweating rate in the received patient monitoring data exceeds the baseline sweating rate—a defined amount. This is particularly advantageous because it provides a patient-specific baseline for the sweating rate based on the understanding that the patient's sweating rate is typically minimal during a shivering episode, allowing any sweating rate significant to the patient to be detected by comparing the actual sweating rate to this baseline (sweat) rate, thus making the detection method robust to different sweating rates between patients.

[0019] Alternatively or additionally, the computer-implemented method may include using the processor device to compare the patient’s actual sweating rate with a defined sweating rate threshold; and detecting a sweating episode when the actual sweating rate exceeds the defined sweating rate threshold (to ensure that the detected sweating rate is high enough), such that the detection can be associated with a true sweating episode indicating a decrease in the patient’s CBT (i.e., the patient’s fever subsides).

[0020] In another embodiment, the computer-implemented method further includes using the processor device to determine the signal strength of a signal associated with a shivering episode during the time interval; determining the total amount of sweat produced by the patient during the sweating episode within the time interval; determining the patient's sweating rate during the time interval based on the determined total amount of sweat produced by the patient; calculating the ratio of the determined signal strength to the determined sweating rate; and including the calculated ratio in the output. This ratio can be used to reconstruct an alternative fever profile to enable prediction, for example, of the severity of fever and the effectiveness of drug response.

[0021] The patient monitoring data may further include core body temperature data related to the patient's core body temperature measured by the core body temperature sensor of the sensor device within the time interval, wherein the computer-implemented method may further include including the patient's core body temperature data in the output using the processor device. For example, this allows determining the lag between the occurrence of shivering or sweating episodes and the relevant changes in the patient's CBT monitored by the core body temperature sensor, from which the patient's thermoregulation capacity can be derived. Furthermore, CBT measurements can help distinguish between shivering episodes caused by a fever episode (where the fever episode leads to an increase in the patient's CBT) and shivering episodes caused by a cold (where the shivering episode will not lead to an increase in the patient's temperature set point). For example, this can be used to verify whether shivering episodes can be reliably associated with the onset of a fever episode, thereby further improving the accuracy of patient monitoring. Moreover, including CBT information within a limited time frame (e.g., a time period covering several fever cycles) can be used to calibrate or train the processor device to construct alternative fever curves. For example, CBT data can be used as basic facts for training artificial intelligence or machine learning algorithms. Therefore, such calibration or training can lead to the generation of alternative fever curves, in which the actual CBT can be accurately estimated. For example, this CBT information can be collected during random sampling or when continuously monitoring patients in an intensive care setting (e.g., during invasive surgery).

[0022] In another embodiment, the computer-implemented method further includes, using the processor device, receiving auxiliary information via the communication interface device during the time interval, the auxiliary information including at least one of a measurement 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 point of the shivering or sweating episode, whether the shivering or sweating episode is a reliable indicator of disease-induced changes in the patient's body temperature; and including the shivering or sweating episode in the output only if the shivering or sweating episode is determined to be a reliable indicator of the progression of the patient's fever. This helps to exclude shivering or sweating episodes caused by factors other than fever from the surrogate fever curve, thereby improving the accuracy of the surrogate fever curve.

[0023] According to another aspect, a computer program product is provided, comprising a computer-readable storage medium having computer-readable program instructions that, when executed on a processor device of a patient monitoring system, cause the processor device to implement the methods of any of the embodiments described herein. Such a computer program product can be used to configure a monitoring system such that it can implement the methods according to embodiments of the invention.

[0024] According to another aspect, a monitoring system for monitoring a patient is provided, the monitoring system including a processor device arranged to receive input data indicating shivering and sweating episodes of the patient as indicators of the patient's fever progression over a time interval, wherein the monitoring system further includes a computer program product of any of the embodiments described herein, and the processor device is arranged to execute the computer-readable program instructions. This monitoring system is capable of generating alternative fever curves for the patient without having to collect CBT information from shivering and sweating episodes captured from patient monitoring data provided by sensor devices, wherein the monitoring system can provide a user interface with output based on the alternative fever curves, such as output including alternative fever curves and / or diagnostically relevant information derived from shivering and sweating episodes, such that the output can be evaluated at the user interface, for example, by a medical professional, or the output can be stored in a data storage architecture such as an electronic patient record for retrieval by a medical professional at any suitable point in time.

[0025] The monitoring system may further include a communication interface device arranged to receive input data in the form of patient monitoring data from sensor devices for monitoring shivering and sweating as indicators of the patient's fever progression, and to forward the patient monitoring data to the processor device. The monitoring system optionally includes the sensor devices to enable patient monitoring without manual intervention, thereby providing a complete solution for monitoring the progression of a patient's fever based on the monitoring of shivering and sweating episodes as described above. The sensor devices may include at least one of a camera, a sensor pad for integration into the bed, a wearable sensor including a sweat sensor and a motion sensor for detecting shivering, and preferably, the sensor devices include wearable sensors. Attached Figure Description

[0026] With reference to the accompanying drawings, embodiments of the invention will be described in detail by way of non-limiting examples, wherein:

[0027] Figure 1 A monitoring system according to an embodiment is schematically depicted;

[0028] Figure 2 An example fever curve is schematically depicted (core body temperature on the y-axis and time on the x-axis);

[0029] Figure 3 A more detailed, schematic depiction Figure 1 One aspect of the monitoring system;

[0030] Figure 4 A flowchart of a fever progression monitoring method according to an embodiment is shown;

[0031] Figure 5 A graph illustrating the construction of an alternative fever curve according to an example embodiment is depicted;

[0032] Figure 6 A graph illustrating the construction of an alternative fever curve according to another example embodiment is depicted;

[0033] Figure 7 A graph illustrating the construction of an alternative fever curve according to yet another example embodiment is depicted;

[0034] Figure 8 A flowchart of one aspect of the fever progression monitoring method according to an embodiment is shown; and

[0035] Figure 9 It is a graph depicting several fever index curves (the reconstructed core body temperature index is on the y-axis, and time is on the x-axis). Detailed Implementation

[0036] It should be understood that these figures are schematic only and are not to scale. It should also be understood that the same reference numerals are used in the figures to indicate the same or similar parts.

[0037] Figure 1 An apparatus for monitoring the progression of fever in patient 1 using a monitoring system 10 is schematically depicted. The monitoring system 10 typically includes a data processing architecture 30, such as a computer system, server system, etc., which includes a communication interface device 32 that communicates with a processor device 34. The communication interface device 32 may include any suitable number of data communication interfaces, such as one or more P2P communication interfaces (e.g., Bluetooth interfaces), one or more wireless communication interfaces (e.g., WiFi interfaces), or one or more wired communication interfaces (e.g., Ethernet interfaces), for connecting the data processing architecture 30 to a local area network, the Internet, etc. The processor device 34 may include one or more processing elements, such as one or more processors, processor cores, etc., arranged to process patient monitoring data provided by the sensor device 20.

[0038] Sensor devices 20, which can form part of monitoring system 10, are typically arranged to provide patient monitoring data that allows processor device 34 to detect tremor episodes 52 and sweating episodes 54 of the monitored patient 1, so that processor device 34 can construct a system for monitoring patient 1 such as... Figure 2An alternative fever curve 50 is schematically depicted. This will be explained in further detail below. 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, which forwards the received patient monitoring data to the processor device 34. In order to provide patient monitoring data from which the processor device 34 can derive patient monitoring data of the patient 1's shivering and sweating episodes, the sensor device 20 may include one or more sensors for this purpose.

[0039] For example, sensor device 20 may include a camera 21 aimed at patient 1 to detect patient trembling, for example by detecting patient movement in an image provided by camera 21, and to detect sweating, for example by detecting changes in light reflection caused by the formation of sweat droplets on exposed parts of the patient's skin (e.g., the patient's forehead) in an image provided by camera 21. Sensor device 20 may include a wearable sensor 22 that can be attached to the patient's skin to provide the required patient monitoring data. Figure 3 An example embodiment of such a wearable sensor 22 is shown, which depicts a wearable sensor 22 including a motion sensor 221 that can detect patient movement (e.g., trembling), a sweat sensor 222 that can detect sweat generated in an area of ​​the patient's skin to which the wearable sensor 22 is attached, and at least one additional sensor 223 optionally used to provide additional sensor data, as will be explained in further detail below.

[0040] The sweat sensor 222 can be arranged to measure sweat flow rate or sweat volume after a defined collection time, or alternatively, it can be arranged to indirectly measure sweat parameters, for example, by measuring skin conductivity. When both motion sensor 221 and sweat sensor 222 are included, the wearable sensor 22 should be placed on a portion of the patient's body capable of reliably measuring both shivering and sweating, such as on the patient's chest or neck. The sensor device 20 may include a sensor 23 for integration into bedding (e.g., a mattress 3 on which the patient 1 lies) to detect patient movement while the patient 1 is in bed, from which shivering can be detected. Any suitable combination of such sensors 21, 22, and 23 can be deployed. In a preferred embodiment, the sensor device 20 includes at least the wearable sensor 22.

[0041] The data processing architecture 30 can also be communicatively coupled to one or more user interfaces 41, 42, on which the processing results of patient monitoring data processing performed by the processor device 34 can be displayed, for example, an alternative fever curve 50. For this purpose, the processor device 34 typically generates output based on the processing results, such as information including the processing results or derived from them, which can be forwarded via the communication interface device 32 to a specific user interface 41, 42. For example, user interface 41 can be a mobile communication device including an app for visualizing the processing results of the processor device 34, which can be used by medical professionals such as nurses or doctors to assess the fever of patient 1. User interface 42 can be a user terminal such as a personal computer, through which medical professionals can receive the processing results from the processor device 34. Alternatively or additionally, the processor device can be arranged to store the processing results in a data storage device 43 (e.g., a network-connected database storing patient monitoring data (e.g., electronic medical records, etc.)) such that the processing results can be accessed at any suitable time, for example, using user interface 41 or 42. Other suitable architectures will be apparent to those skilled in the art.

[0042] In an alternative embodiment (not shown), the sensor device 20 may be omitted, and the processor device 34 may instead be arranged to receive input data manually generated, for example, by the patient 1 or by a medical caregiver such as a nurse or doctor using an input device such as a remote control, an electronic communication device such as a smartphone, so that the person operating such an input device can use the input device to signal the occurrence of the patient 1's tremor episode 52 or sweating episode 54, so that the processor device only needs to record the time points when such input has been received to construct an alternative fever curve 50.

[0043] Monitoring system 10 is arranged to implement one or more embodiments of the method 100 of the present invention, the flowchart of which is shown in Figure 4As shown in the diagram. Method 100 begins at operation 101, where, for example, sensor device 20 (if present) is activated and provides the previously described patient monitoring data to processor device 34 via communication interface device 32. In operation 103, processor device 34 processes the patient monitoring data received from sensor device 20 to determine whether a tremor episode 52 of patient 1 can be detected in the patient monitoring data. This processing can be performed continuously or periodically; that is, the patient monitoring data can be processed on a continuous basis or can be sampled periodically, for example, every 1-5 minutes, for processing by processor device 34. If no tremor is detected, processor device 34 continues to search for tremor episode 52 of patient 1 in the received patient monitoring data. However, if processor device 34 detects the occurrence of such a tremor episode 52, the method proceeds to operation 105, where the processor device records the time point at which the tremor episode 52 was detected, for example, as derived from the patient monitoring data provided by sensor device 20 or as derived from manually generated input data that marks the tremor episode 52. This time point can be represented in any suitable format, such as the amount of time elapsed since the start of patient monitoring, or the actual time of day.

[0044] Method 100 can proceed to operation 107, in which the processor device 34 determines the baseline sweating rate of patient 1 during a shivering episode 52. This is based on the understanding that during such a shivering episode 52, patient 1's CBT (i.e., temperature set point) is increasing, which is generally equal to the minimum associated sweating. Therefore, determining the sweating rate during such a shivering episode 52 provides a reliable baseline for determining subsequent sweating episodes 54 of patient 1, since the actual sweating episode 54 of patient 1 will result in a sweating rate significantly higher than the baseline sweating rate. Determining such a baseline sweating rate has the advantage of defining a patient-specific sweating rate baseline, making it unnecessary to consider the different sweating rates of different patients in order to reliably detect sweating episodes of patient 1. However, in alternative embodiments, the detection of this baseline sweating rate can be omitted, in which case a defined sweating rate threshold can be used to detect sweating episodes 54 of patient 1, which can be general, gender-specific, specific to the location of the wearable sensor 22 on the patient's body, etc.

[0045] In operation 109, processor device 34 processes patient monitoring data received from sensor device 20 to determine whether a sweating episode 54 of patient 1 can be detected in the patient monitoring data. This processing can be continuous or periodic; that is, the patient monitoring data can be processed on a continuous basis or can be sampled periodically, for example, every 1 to 5 minutes, for processing by processor device 34. For example, processor device 34 can determine the actual sweating rate of patient 1 and compare this actual sweating rate with a baseline sweating rate determined in operation 107, and if the actual sweating rate exceeds a defined amount of the baseline sweating rate (e.g., a defined factor, such as factor 4-6), then it is determined that a sweating episode 54 is occurring.

[0046] Alternatively or additionally, the processor device 34 may compare the actual sweat rate with a defined sweat rate threshold, and determine that a sweating episode 54 is occurring if the actual sweat rate exceeds the defined threshold to ensure that the sweat rate is high enough (e.g., above 0.7 nL / min for sweat glands) to determine with sufficiently high confidence that a sweating episode 54 is occurring. This sweat rate can be determined using the wearable sensor 22, for example by determining the actual sweat rate or parameters associated with changes in the sweat rate (e.g., skin conductance), or by utilizing the camera 21, for example by determining changes in reflected light from a camera image and deriving the sweat rate based on those changes.

[0047] If no sweating episode 54 is detected, in operation 109, the processor device 34 continues to search for sweating episode 54 of patient 1 in the received patient monitoring data. However, if the processor device 34 detects the occurrence of such a sweating episode, for example, in the patient monitoring data provided by the sensor device 20 or in the patient monitoring data derived from manually generated input data marked with sweating episode 54, the method proceeds to operation 111, in which the processor device 34 records the time point at which sweating episode 54 was detected. This time point can be represented in any suitable format, for example, as the amount of time elapsed since monitoring of patient 1 began, as the amount of time elapsed since a previously detected shivering episode 52, as the actual time of day, etc.

[0048] As indicated in operation 113, the time points of tremor episodes 52 and sweating episodes 54 can continue to be recorded. In this case, method 100 returns to operation 103, in which the processor device 34 processes the patient monitoring data to detect the next tremor episode 52, or alternatively waits for the manual marking of such an episode as previously explained. Method 100 can alternatively proceed to operation 115, in which the processor device 34 constructs an alternative fever curve 50 for patient 1 based on the recorded time points of the corresponding tremor episodes 52 and sweating episodes 54. It should be noted that, to avoid doubt, the construction of the alternative fever curve 50 can be performed after monitoring patient 1 at a certain time interval, or alternatively, the construction of the alternative fever curve 50 can be performed in parallel with the monitoring of patient 1 within that time interval. The processor device 34 can construct the alternative fever curve 50 based on the alternation pattern of tremor episodes 52 and sweating episodes 54 and the periodicity of the alternation pattern.

[0049] For example, such as Figure 5 As schematically depicted, processor device 34 can receive, for example, an indication from sensor device 20 or via manual input as previously described that a tremor episode 52 begins at T = t1 and terminates at T = t2. The graph above shows the intensity (au) (y-axis) of the tremor episode 52 and the sweating episode 54 as a function of time (x-axis). Processor device 34 also receives, for example, an indication from sensor device 20 or via manual input as previously described that a sweating episode 54 begins at T = t3 and terminates at T = t4. Processor device 34 also receives, for example, an indication from sensor device 20 or via manual input as previously described that another tremor episode 52 begins at T = t5 and terminates at T = t4. Processor device 34 can construct an alternative fever curve 50 based on the start times of the tremor episode 52 and the sweating episode 54 (i.e., t1, t3, and t5), regardless of the duration of each episode, which produces... Figure 5 The resulting alternative fever curve 50 is shown, where the CBT, or more precisely, the projected change of the CBT (y-axis), is a function of time (x-axis). From this curve, it can be seen that the onset of each shivering episode 52 is interpreted as an instantaneous rise in CBT, while the onset of each sweating episode is interpreted as an instantaneous fall in CBT. Of course, alternative methods (e.g., fitting a sine curve based on the recorded start times of the corresponding shivering episode 52 and sweating episode 54) are also feasible. The processor device 34 then generates an output in operation 117 based on the thus constructed alternative fever curve 50, for example, for transmission to user interfaces 41 or 42 and / or for storage in data storage architecture 43, after which method 100 terminates in operation 119.

[0050] In the improved scheme, when constructing the alternative fever curve 50 in operation 115, the processor device 34 can consider the duration of each of the shivering episode 52 and the sweating episode 54. This in Figure 6 As shown, at the onset of each tremor episode 52, the processor device 34 assumes a gradual increase (e.g., a linear increase) in the patient's CBT until the end of this tremor episode 52, after which the CBT is assumed to be constant until the onset of a subsequent sweating episode 54. At this point in time, the processor device 34 assumes a gradual decrease (e.g., a linear increase) in the patient's CBT in the construction of its alternative fever curve 50 until the end of such a sweating episode 54. Again, as an alternative, a sine curve can be fitted based on the start and end values ​​(in time) of the corresponding start and end points of the tremor episode 52 and the sweating episode 54.

[0051] In another improvement, such as Figure 7 As shown, the processor device 34 can consider both the duration and intensity of tremor episodes 52 and sweating episodes 54 when constructing the alternative fever curve 50. In this method, when patient 1 sweats profusely (i.e., with a high sweating rate), the reproducible approximation of patient 1's CBT decreases faster than when patient 1 sweats only slightly (i.e., with a low sweating rate). As mentioned above, sweating episodes 52 can be detected when the actual sweating rate exceeds the baseline sweating rate or threshold 55. Similarly, when patient 1 trembles violently, the reproducible approximation of patient 1's CBT increases faster than when patient 1 trembles only slightly. The intensity of tremor episodes can be determined using power spectral density analysis, which will be explained in more detail below. Since the intensity level of tremor episodes 52 or sweating episodes 54 can vary over time, rather than... Figure 5 The binary on / off method in the construction of the alternative fever curve 50 in the middle, therefore it becomes an integral as expressed in equation (1):

[0052]

[0053] In this equation, t is time, T0 is the temperature at t=0, which can be measured, estimated, or may be a default value, while c1 and c2 are patient- and environment-dependent parameters (e.g., considering the insulation level of patient 1, see below), and may even depend on the intensity of shivering and sweating, respectively. If no independent CBT measurement is available, T0, c1, and c2 can use default values. However, if such an independent CBT measurement becomes available, it can be used to determine T0. If multiple independent CBT measurements become available over a period of time, for example, by continuous or spot-checking CBT measurements during the time interval in which shivering episode 52 and sweating episode 54 occur, c1 and c2 can also be estimated for a specific patient, environment, and shivering / sweating episode intensity level during the CBT measurement. Once the CBT measurement has stopped, this can be used as a calibration by the processor device 34 for the alternative fever curve 50. Therefore, in this embodiment, an alternative fever curve 50 may be provided, which includes an estimated absolute value of the patient's CBT on the y-axis of the graph as a function of time on the x-axis of the graph, the graph depicting the alternative fever curve 50.

[0054] In a preferred embodiment, processor device 34 generates information to assist healthcare professionals in managing the patient, including determining the type of fever based on recorded time points of occurrence of the detected shivering episode 52 and sweating episode 54 of patient 1, for example, in addition to generating an alternative fever curve 50 or instead of generating an alternative fever curve 50, and including this information in the output generated in operation 117, for example, in addition to the alternative fever curve 50, or as information derived from the alternative fever curve 50 without including the actual alternative fever curve 50, to provide medical professionals with additional insights into the potential condition of patient 1. This is achieved by means of Figure 8 To explain in more detail, Figure 8 A decision tree, which can be deployed by processor device 34 to determine the type of fever from recorded time points, is schematically depicted. The decision tree begins in operation 151, followed by operation 153 where processor device 34 determines the periodicity of an alternative fever curve 50, for example, by determining the elapsed time between consecutive shivering episodes 52 separated by sweating episodes 54 or between consecutive sweating episodes 54 separated by shivering episodes 52, based on the recorded time points. If the periodicity is less than approximately 24 hours, as determined in operation 155, then processor device 34 determines that the type of fever is a remissionary fever, as symbolized by conclusion 171.

[0055] On the other hand, if the period is determined to be approximately 24 hours, the processor device 34 determines that the fever is a common fever. The processor device 34 can then further evaluate the time elapsed between the shivering episode 52 and the subsequent sweating episode 54 in operation 157 to determine the patient's body's ability to combat a common fever. Typically, when the patient's immune system is functioning normally, the duration of a CBT elevation or fever should not exceed a few hours, during which time a parasite outbreak triggers the patient's immune system. Therefore, when the processor device 34 determines in operation 157 that the duration of the CBT elevation corresponds to an appropriate functional immune system, the processor device 34 can determine that the fever is a "normal" common fever, as indicated by conclusion 172; while if the processor device 34 determines in operation 157 that the duration of the CBT elevation exceeds a threshold indicating immune system impairment, the processor device 34 can determine that the fever is a common fever of the debilitated patient 1, as indicated by conclusion 173.

[0056] Of course, the assessment of the patient's immune system status is optional. In this case, the determination of the elapsed time between the shivering episode 52 and the subsequent sweating episode 54 can be omitted from the assessment. Therefore, the recording of the time point of occurrence of the sweating episode 54 can be omitted, and the assessment of the alternative fever curve 50 can be based solely on the elapsed time between consecutive shivering episodes 52, provided that these shivering episodes are separated by the sweating episodes 54. Similarly, the recording of the time point of occurrence of the shivering episode 52 can be omitted, and the alternative fever curve 50 can be assessed solely based on the elapsed time between consecutive sweating episodes 54, provided that these sweating episodes are separated by the shivering episodes 52.

[0057] If processor device 34 determines in operation 155 that patient 1's fever cycle significantly exceeds 24 hours, processor device 34 can infer that the fever is another type of fever symbolized by conclusion 174, such as tertian fever, quartan fever, relapsing fever, undulant fever, etc. Another decision tree (not shown) can be implemented by processor device 34 to distinguish such another type of fever.

[0058] In at least some embodiments where sensor device 20 is used to collect patient monitoring data to construct an alternative fever curve 50 as described above, additional sensors (e.g., additional sensor 223) may be used for a variety of reasons. For example, the sweat sensor 222 of wearable sensor 22 may also be configured to determine the concentration of an analyte of interest (e.g., cytokines or lactate) in secreted sweat, which may be used by processor device 34 to further determine the cause of the fever, the severity of the illness, and / or the efficacy of the administered medication against the illness. This information can provide healthcare professionals with useful insights into how to manage patient 1, such as by administering different drug doses, different medications, etc. Additional additional sensors, preferably but not necessarily integrated into one or more wearable sensors 22, may provide physiological monitoring data, such as heart rate, respiratory rate, blood pressure, peripheral oxygen saturation, etc. This sensor data may also be included in the output generated by processor device 34 to further enhance the diagnostic potential of the output.

[0059] The sensor device 20 may also include one or more additional sensors (e.g., one or more motion sensors, heart rate monitors, blood pressure sensors, etc.) that provide auxiliary information to the processor device 34, allowing the processor device 34 to distinguish between shivering episodes 52 caused by fever and sweating episodes 54, or the occurrence of such episodes for different reasons, to detect increased patient activity (e.g., physical activity, strenuous activity such as climbing stairs, etc.). This may result in sweating episodes triggered by activity, rather than a decrease in the patient's temperature set point caused by fever. Environmental sensors (e.g., ambient temperature sensors, etc.) may be deployed to determine whether the shivering or sweating episodes are caused by environmental factors (e.g., low or high ambient temperatures) rather than by illness. Using the auxiliary information, the processor device 34 can determine whether the shivering episode 52 or the sweating episode 54 is a reliable indicator of the body temperature change caused by the patient 1's illness, such that when the processor device 34 determines that the shivering episode 52 or the sweating episode 54 is a reliable indicator of the body temperature change caused by the patient 1's illness and is unlikely to be caused by other factors (as indicated by the auxiliary information), the processor device 34 will only include the time point of such shivering episode 52 or sweating episode 54 in the alternative fever curve 50.

[0060] In another embodiment, sensor device 20 further includes a CBT sensor, which may be an additional sensor 223 within wearable sensor 22 or a separate (wearable) sensor. Including CBT information in the patient monitoring data allows for the acquisition of even more information from the time points of occurrence of shivering episodes 52 and / or sweating episodes 54. Typically, CBT increases with shivering and decreases with sweating, but there is a lag between the occurrence of such shivering or sweating episodes and the accompanying CBT changes. This lag can be used to understand the patient's thermoregulation ability. Additionally, CBT information can be used to calibrate the construction of the alternative fever curve 50 by processor device 34, for example, as a basis for training artificial intelligence or machine learning algorithms that construct the alternative fever curve 50 by processor device 34.

[0061] Another reason to increase CBT measurements is to differentiate between shivering caused by an elevated set point (leading to fever) and shivering caused by the patient being too cold (having a normal set point). This is especially useful in determining the onset of a fever. A simple way to differentiate between these two possibilities is to perform a CBT measurement when shivering is detected within an appropriate time period (e.g., 10 minutes). If the elevated set point is the cause, the temperature has already risen, while if the body is cold, the temperature has fallen.

[0062] Fever is well known to refer to an increase in body temperature during infection. However, the underlying mechanisms of this fever are more complex and involve the host's response to infection. The immune system is activated by the infectious agent and releases chemokines in the body, leading to the activation of cyclooxygenase (COX), which stimulates "heat-gaining heat effectors" (i.e., shivering) and inhibits "heat-lossing heat effectors" (i.e., sweating). Typically, only core body temperature is measured, and it only provides information about the increase in the patient's temperature set point beyond the aforementioned impractical clinical integration. Therefore, in a preferred embodiment, the construction of the alternative fever curve 50 also includes determining the rate of shivering and sweating of patient 1 to provide an additional layer of diagnostically relevant information to the alternative fever curve 50, as this provides, for example, information about the host's response to the infectious agent (i.e., the immune response). As a supplement or alternative to measuring patient 1's CBT as described above to determine the lag between tremor and sweating episodes and induced changes in the patient's CBT, this host response can be calculated based on multiple parameters, such as the change in the amount of time between consecutive tremor episodes 52, the change in the amount of time between consecutive sweating episodes 54, the change in the amount of time between a tremor episode 52 and a subsequent sweating episode 54, and the intensity and duration of such tremor episodes 52 and sweating episodes 54. The intensity of sweating episodes 54 can be based on the sweating rate determined using sensor device 20. The intensity of tremor episodes 52 can be determined based on Fourier analysis and / or spectral power analysis of the tremor data provided by sensor device 20. This can have several purposes. First, such analysis of the tremor data provides a measurement of the frequency of tremor in patient 1, which allows the processor device to distinguish between unexpected muscle movements (e.g., age-related tremors) and tremors caused by a set point that is elevated compared to patient 1's actual CBT. For example, hand tremors caused by Parkinson's disease can reach as high as 9 Hz, with tremor amplitude and acceleration amplitude reaching 19 cm and 20 m / s, respectively. 2 During fever or hyperthyroidism, the frequency is increased to 14 Hz, thereby allowing differentiation between fever-related tremors and other types of tremors. This allows the processor device 34 to discard tremor episodes 52 caused by such other types of tremors and, for example, to consider only fever-related tremor episodes 52 when constructing the alternative fever curve 50 by using a bandpass or high-pass filter with a suitable cutoff frequency (e.g., 10 Hz).

[0063] Secondly, the ratio of the signal strength of the shivering signal generated by the sensor device 20 to the total amount of sweating or the rate of sweating over time monitored during the patient monitoring interval can be used to construct an alternative fever curve to predict the severity of fever and the effectiveness of medical treatment.

[0064] In the first step, a Fast Fourier Analysis (FFT) of the jittered signal (e.g., amplitude or power spectral density analysis) is performed to determine the intensity of the jitter. The power spectral density (PSD) of the jittered signal (PSD_Shivering) describes the power present in the signal as a function of frequency per unit frequency. Power spectral density is typically expressed in watts per hertz (W / Hz). The total power present in the signal within the relevant frequency range (e.g., 10–20 Hz or 5–15 Hz) is then calculated.

[0065] In the second step, the ratio of shivering signal intensity to sweating rate (nL / s) is determined to calculate the fever index according to Equations 2 and 3 below. This fever index can be a fever index for a given time (Equation 2) or a fever area index for time integration (Equation 3), i.e., as shown below. Figure 9 The area under the fever index curve is shown. If the fever index is integrated over time to calculate the cumulative fever index (Equation 2), this time-integrated index will provide clinical information relating to the intensity of fever onset or fever intervals within a given time window of clinical interest. Alternatively, the first derivative of the fever index curve can be calculated, which will then give information about fever dynamics, such as the speed of fever development or recovery.

[0066]

[0067]

[0068] The reason for calculating this ratio is that the onset and development of fever are usually proportional to and directly related to shivering, while fever can be assumed to be inversely proportional to the rate of sweating and decrease during sweating. This is in... Figure 9 The illustration is shown in the middle. Figure 9 Three fever index curves AC are shown, which progress from a normal or reference value 5 with an upper threshold 7 below this normal value to a high fever value 6 above the critical threshold 8 (as indicated by shivering episode 52) and back to a normal or reference value 5 (as indicated by sweating episode 54).

[0069] Based on the alternative fever index curve AC, the time constant τ can be determined or derived. up or τ down , where, for example, τ up τ is defined as the amount of time taken to replace the fever curve 50 when the reference value 5 passes the critical threshold 8, and τ down It is defined as the amount of time taken for the replacement fever curve 50 to pass through the upper reference threshold 7 from the fever value of 6. Alternatively, τ downThis can be defined as the amount of time it takes for a fever to decrease to 67% of its maximum value, analogous to the calculation of decay time in electrical components such as capacitors. Therefore, these time constants carry clinical information about, for example, how quickly a fever develops and subsides after medication administration. Figure 9 The alternative fever curve shown can be visualized on user interface 41 or user interface 42, for example, to support clinical decision-making regarding the efficacy of interventions or medications, such as to provide direct feedback to healthcare providers on treatment response.

[0070] In an embodiment, the determination of the intensity of shivering and the rate of sweating of patient 1 can be scaled by processor device 34 based on available information regarding patient 1's insulation. For example, patient 1 can wear more clothing or add blankets to stay warm during a shivering episode 52, which can suppress the intensity of the shivering episode 52. Similarly, during a sweating episode 54, patient 1 can remove clothing or blankets to cool down, thereby suppressing his or her sweating rate. For this purpose, sensor device 20 can provide information related to the patient's insulation level to allow processor device 20 to determine at least one of the duration and severity of each shivering episode 52 and sweating episode 54 as described above, based on the information related to the patient's insulation level. Such information can be provided in any suitable manner. For example, the presence of the quantity and / or thickness of blankets or clothing items can be derived from image data provided by camera 21. Alternatively, such information can be generated using wearable sensor 22, for example by providing measurements of one or more of skin temperature, pressure, and ambient light, wherein, in particular, the pressure of the blanket on the skin and the ambient light (i.e., light penetrating the blanket and clothing) are independent of core body temperature and are particularly useful parameters for monitoring for this purpose.

[0071] Embodiments of the present invention can provide clinical insights into the thermoregulatory capacity of Patient 1's body, such as insights into the effectiveness of administered medications, the severity of the illness, or aiding in the diagnosis of the cause of fever. Such clinical insights are useful in many care settings (such as hospitals, hospital-to-home, or home use), where they can help determine the correct medication, dosage, and timing. For example, clinical information provided by processor device 34 can help determine whether antibiotics are needed to manage Patient 1's medical condition, thereby reducing the risk of unnecessary administration of such antibiotics, which is undesirable in the context of developing resistance to such antibiotics. However, it should be understood that the use of the present invention is not limited to medical care applications and can generally be used to gain insights into the thermoregulatory characteristics of any patient's body (e.g., human or non-human). In this context, the term "patient" as used in this application should not be construed as limited to a person suffering from a disease, as the term is intended to apply to any patient whose CBT is monitored in accordance with the teachings of this application.

[0072] The embodiments of method 100 executed by processor device 34 described above can be implemented by computer-readable program instructions implemented on a computer-readable storage medium, which, when executed on the processor device of computing device 30 (e.g., a patient monitoring terminal, etc.), cause processor device 34 to implement any embodiment of method 100. Any suitable computer-readable storage medium can be used for this purpose, such as optically readable media (e.g., CDs, DVDs, or Blu-ray discs), magnetically readable media (such as hard disks), electronic storage devices (e.g., Memory Sticks, etc.). The computer-readable storage medium can be a network-accessible medium (e.g., the Internet), allowing the computer-readable program instructions to be accessed via the network. For example, the computer-readable storage medium can be a network-attached storage device, a storage area network, cloud storage, etc. The computer-readable storage medium can be a network-accessible service from which the computer-readable program instructions can obtain. In some embodiments, at least a portion of the computer-readable program instructions can be included in the processor device 34 in hardware form.

[0073] It should be noted that the embodiments mentioned above are illustrative rather than limiting of the invention, and those skilled in the art will be able to devise many alternative embodiments without departing from the scope of the claims. Any reference numerals placed in parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of other elements or steps besides those listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements. In product claims that enumerate several units, several of these units can be implemented by the same hardware. Measures enumerated in dissimilar dependent claims can be advantageously combined.

Claims

1. A patient monitoring system (10) for monitoring the progression of fever in a subject, comprising a processor device (34) configured to: Patient monitoring data is received from a sensor device (20) used to monitor the patient's shivering and sweating, as an indicator of the patient's fever progression over a time interval; The received patient monitoring data is processed to detect tremor episodes (52) and sweating episodes (54) and to record the corresponding time points at which the tremor episodes and sweating episodes occur; and Alternative fever curves (115, 117) are constructed based on the alternation pattern of tremor and / or sweating episodes at corresponding time points recorded from the corresponding tremor and / or sweating episodes, and these alternative fever curves are used to monitor the fever progression of the subject.

2. The patient monitoring system (10) according to claim 1, wherein, The processor device is configured to: The periodicity of the alternation pattern of the detected tremor episodes (52) and sweating episodes (54) is determined (153) based on their corresponding occurrence at different time points during the time interval; and The type of fever is identified based on the periodicity of the determined alternation pattern.

3. The patient monitoring system (10) according to claim 1 or 2, wherein, The processor device is configured to: Determine at least one of the duration and intensity of each trembling and sweating episode.

4. The patient monitoring system (10) according to claim 3, wherein, The patient monitoring data includes information related to the patient's thermal insulation level, and wherein the processor device is configured to: The duration and severity of each shivering episode and sweating episode are determined based on the information relating to the patient’s thermal insulation.

5. The patient monitoring system (10) according to any one of claims 1-4, wherein, The processor device is configured to: Determine the frequency of each tremor episode (52).

6. The patient monitoring system (10) according to any one of claims 1-5, wherein, The processor device is configured to: Sweating episodes were identified based on the patients’ sweating rates (54).

7. The patient monitoring system (10) according to claim 6, wherein, The processor device is configured to: The baseline sweating rate of the patient (107) was determined based on patient monitoring data received during the shivering episode (52); and Sweating episodes are detected by detecting whether the actual sweating rate of the patient in the received patient monitoring data exceeds the basic sweating rate defined as a certain amount (54).

8. The patient monitoring system (10) according to claim 6 or 7, wherein, The processor device is configured to: The patient's actual sweating rate was compared with a defined sweating rate threshold; and A sweating episode is detected when the actual sweating rate exceeds the defined sweating rate threshold.

9. The patient monitoring system (10) according to any one of claims 6-8, wherein, The processor device is configured to: Determine the signal strength of the signal associated with the tremor episode (52) within the time interval; Determine the total amount of sweat produced by the patient during the sweating episode (54) within the time interval; The patient's sweating rate during the time interval is determined based on the total amount of sweat produced by the patient. Calculate the ratio of the determined signal strength to the determined sweating rate; and Output the calculated ratio.

10. The patient monitoring system (10) according to any one of claims 1-9, wherein, The patient monitoring data also includes core body temperature data related to the patient's core body temperature measured by the core body temperature sensor of the sensor device within the time interval, and wherein the processor device is configured to output the core body temperature data.

11. The patient monitoring system (10) according to any one of claims 1-10, wherein, The processor device is configured to: During the time interval, the auxiliary information is received via a communication interface device, the auxiliary information including at least one of the ambient temperature to which the patient is exposed and a measurement of the patient's activity level; Based on actual auxiliary information at the time points of trembling or sweating episodes, determine whether the trembling or sweating episodes are reliable indicators of disease-induced body temperature changes in the patient; and A tremor or sweating episode is output only when it is determined to be a reliable indicator of the patient's fever progression.

12. The patient monitoring system (10) according to claim 11 further includes a communication interface device (32) arranged to receive input data in the form of patient monitoring data from a sensor device (20) for monitoring the patient's shivering and sweating as an indicator of the patient's fever progression, and to forward the patient monitoring data to the processor device (34).

13. The patient monitoring system (10) according to claim 12, wherein, The monitoring system includes the sensor device.

14. A computer program product comprising a computer-readable storage medium having computer-readable program instructions contained thereon, the computer-readable program instructions causing the processor device to implement a patient monitoring method (100) when executed on a processor device (34) of a patient monitoring system (10) according to any one of claims 1-13, the patient monitoring method comprising: Patient monitoring data is received from the sensor device (20) used to monitor the patient's shivering and sweating as an indicator of the patient's fever progression over time intervals; The received patient monitoring data is processed to detect tremor episodes (52) and sweating episodes (54) and to record the corresponding time points at which the tremor episodes and sweating episodes occur; and Alternative fever curves (115, 117) are constructed based on the alternation pattern of tremor and / or sweating episodes at corresponding time points recorded from the corresponding tremor and / or sweating episodes, and these alternative fever curves are used to monitor the fever progression of the subject.

Images