Sepsis determination program, sepsis determination device, sepsis determination method, and sepsis determination system

Abstract

Provided are a sepsis determination program, a sepsis determination device, a sepsis determination method, and a sepsis determination system that allow for quick auxiliary diagnosis of sepsis. An acceleration pulse wave of a subject person is acquired, information related to the magnitude of the amplitude of the acquired acceleration pulse wave is identified, whether or not the subject person has sepsis is determined on the basis of the identified information related to the magnitude of the amplitude, and the result of determination as to whether or not there is a possibility that the subject person has sepsis is output.

Description

Sepsis determination program, sepsis determination device, sepsis determination method, and sepsis determination system

[0001] The present invention relates to a sepsis determination program, a sepsis determination device, a sepsis determination method, and a sepsis determination system.

[0002] Sepsis is a disease caused by bacteria or viruses (hereinafter simply referred to as bacteria, etc.) in the blood, which damages organs throughout the body. Once the disease develops, symptoms may progress rapidly within a few hours to a day. Therefore, sepsis is a disease that requires early initiation of initial treatment (see, for example, Patent Document 1).

[0003] Japanese Patent Application Laid-Open No. 2022-058359

[0004] Here, the diagnosis of sepsis as described above may be performed using an index (hereinafter simply referred to as the index) such as the SOFA score (Sequential Organ Failure Assessment Score). However, in this case, for example, a blood test or a medical examination by a doctor is required, making it difficult to quickly diagnose sepsis.

[0005] Furthermore, the diagnosis of sepsis as described above may be made, for example, by performing blood culture and then identifying the type of bacteria contained in the blood. However, even in this case, it is difficult to quickly diagnose sepsis because, for example, blood culture takes time.

[0006] Therefore, there is a need for a method that enables early initiation of initial treatment for a patient with sepsis by, for example, quickly carrying out auxiliary diagnosis of sepsis.

[0007] Therefore, an object of the present invention is to provide a sepsis determination program, a sepsis determination device, a sepsis determination method, and a sepsis determination system that enable rapid auxiliary diagnosis of sepsis.

[0008] In order to achieve the above-mentioned object, the sepsis determination program of the present invention causes a computer to execute the following processes: acquire an acceleration pulse wave of a subject; identify information related to the amplitude of the acquired acceleration pulse wave; determine whether or not the subject is suffering from sepsis based on the identified information related to the amplitude; and output a determination result as to whether or not the subject is likely to be suffering from sepsis.

[0009] According to the sepsis determination program, sepsis determination device, sepsis determination method, and sepsis determination system of the present invention, it is possible to quickly perform auxiliary diagnosis of sepsis.

[0010] FIG. 1 is a diagram illustrating a configuration example of a sepsis determination system 10 according to the first embodiment. FIG. 2 is a diagram illustrating a configuration example of an information processing device 1 according to the first embodiment. FIG. 3 is a diagram illustrating an outline of sepsis determination processing according to the first embodiment. FIG. 4 is a diagram illustrating an outline of sepsis determination processing according to the first embodiment. FIG. 5 is a flowchart illustrating sepsis determination processing according to the first embodiment. FIG. 6 is a flowchart illustrating sepsis determination processing according to the first embodiment. FIG. 7 is a flowchart illustrating sepsis determination processing according to the first embodiment. FIG. 8 is a flowchart illustrating sepsis determination processing according to the first embodiment. FIG. 9 is a flowchart illustrating sepsis determination processing according to the first embodiment. FIG. 10 is a flowchart illustrating sepsis determination processing according to the first embodiment. FIG. 11 is a flowchart illustrating sepsis determination processing according to the first embodiment. FIG. 12 is a diagram illustrating sepsis determination processing according to the first embodiment. FIG. 13 is a diagram illustrating sepsis determination processing according to the first embodiment.

[0011] [Configuration Example of Sepsis Determination System 10 According to First Embodiment] First, a description will be given of a configuration example of the sepsis determination system 10 according to the first embodiment. Fig. 1 is a diagram showing a configuration example of the sepsis determination system 10 according to the first embodiment.

[0012] The sepsis determination system 10 includes, for example, an information processing device 1 (hereinafter also referred to as the sepsis determination device 1) and an acceleration plethysmograph 2. The information processing device 1 is connected to the acceleration plethysmograph 2, for example, by wire or wirelessly, and is capable of communicating with the acceleration plethysmograph 2.

[0013] The acceleration plethysmograph 2 generates time-series data (hereinafter also referred to as waveform data) on the acceleration plethysmogram of the subject OB, for example, by continuously measuring the acceleration plethysmogram of the subject OB.

[0014] The information processing device 1 is, for example, a physical machine or a virtual machine, and performs a process (hereinafter also referred to as sepsis determination process) to determine (auxiliary diagnosis) whether or not the subject OB is suffering from sepsis by using waveform data generated by the acceleration plethysmograph 2.

[0015] Specifically, the information processing device 1 in this embodiment acquires, for example, waveform data generated from the acceleration pulse wave of the subject OB from the acceleration plethysmograph 2. Then, the information processing device 1, for example, identifies information regarding the amplitude of the acquired waveform data. The information regarding the amplitude is, for example, the amplitude magnitude (value). Furthermore, the information regarding the amplitude is, for example, information indicating the shape characteristics of the acquired waveform data. Next, the information processing device 1 determines whether the subject OB is suffering from sepsis, for example, based on the identified information regarding the amplitude. Thereafter, the information processing device 1 outputs, for example, a determination result regarding whether the subject OB is likely to be suffering from sepsis.

[0016] That is, the information processing device 1 in this embodiment determines whether or not the subject OB is likely to be suffering from sepsis, for example, based on the measurement results of the accelerated pulse wave of the subject OB.

[0017] As a result, the sepsis determination system 10 in this embodiment can, for example, quickly perform auxiliary diagnosis of sepsis. Specifically, the sepsis determination system 10 can quickly perform auxiliary diagnosis of sepsis even in places where there are no doctors, for example. Therefore, the sepsis determination system 10 can, for example, quickly start initial treatment for a subject OB suffering from sepsis.

[0018] The following description will be given of a case where the sepsis determination system 10 includes one information processing device 1, but the sepsis determination system 10 may include, for example, multiple information processing devices 1. The sepsis determination process may be performed in a distributed manner across, for example, the multiple information processing devices 1.

[0019] Furthermore, the following description will be given assuming that the information processing device 1 is placed adjacent to the acceleration plethysmograph 2, but the information processing device 1 may also be placed, for example, in a different location from the acceleration plethysmograph 2 (for example, a data center not shown).

[0020] [Configuration Example of Information Processing Device 1 in First Embodiment] Next, a description will be given of a configuration example of the information processing device 1. Fig. 2 is a diagram showing a configuration example of the information processing device 1 in the first embodiment.

[0021] 2, the information processing device 1 includes, for example, a CPU 101 which is a processor, a memory 102, a communication device 103, a storage medium 104, and an output device 105. The respective components are connected to each other via a bus 106.

[0022] The storage medium 104 has a program storage area (not shown) that stores, for example, a program 110 for performing sepsis assessment processing.

[0023] The storage medium 104 also includes a storage unit 130 (hereinafter also referred to as an information storage area 130) that stores information used when performing the sepsis assessment process. The storage medium 104 may be, for example, a hard disk drive (HDD) or a solid state drive (SSD).

[0024] The CPU 101 executes, for example, a program 110 loaded from the storage medium 104 into the memory 102 to perform sepsis determination processing.

[0025] The communication device 103 is connected to the acceleration plethysmograph 2 via a wired or wireless connection, for example, and communicates with the acceleration plethysmograph 2 .

[0026] The output device 105 is, for example, a device such as a display, and is a device that outputs the determination result of the sepsis determination process.

[0027] [Outline of Sepsis Determination Processing in First Embodiment] Next, an outline of the sepsis determination processing in the first embodiment will be described. Figures 3 and 4 are diagrams illustrating an outline of the sepsis determination processing in the first embodiment.

[0028] As shown in FIG. 3, the information processing device 1 realizes various functions including, for example, an input receiving unit 111, a pulse wave acquiring unit 112, a feature identifying unit 113, a sepsis determining unit 114, an information generating unit 115, and an information output unit 116.

[0029] 4, the information storage area 130 stores, for example, waveform data 131, morbidity data 132, and output data 133. The waveform data 131 is, for example, time-series data on the accelerated pulse wave of the subject OB. The morbidity data 132 is, for example, data related to the subject OB (e.g., so-called clinical data) including data indicating whether the subject OB has been diagnosed with sepsis (whether the subject OB currently has sepsis). The output data 133 is, for example, data indicating the determination result of the sepsis determination process.

[0030] The input receiving unit 111 receives, for example, an input of an instruction to start a sepsis assessment process for the subject OB (hereinafter also simply referred to as a start instruction).

[0031] For example, when the input receiving unit 111 receives a start instruction, the pulse wave acquiring unit 112 acquires waveform data 131 for the subject OB from the acceleration plethysmograph 2. Then, the pulse wave acquiring unit 112 stores the acquired waveform data 131 in the information storage area 130, for example.

[0032] The feature identifying unit 113 identifies, for example, information relating to the magnitude of the amplitude in the waveform data 131 acquired by the pulse wave acquiring unit 112 .

[0033] Specifically, the feature identification unit 113 identifies, as information related to the amplitude magnitude, the magnitude (value) of each of a plurality of consecutive peaks (hereinafter simply referred to as a plurality of peaks) in the waveform data 131 acquired by the pulse wave acquisition unit 112. The plurality of peaks are, for example, a plurality of consecutive peaks in the waveform data 131 corresponding to a predetermined time period among the waveform data 131 acquired by the pulse wave acquisition unit 112. The predetermined time period may be, for example, a time period of approximately the most recent several tens of seconds to several minutes.

[0034] Furthermore, the feature identifying unit 113 identifies information related to the amplitude magnitude, for example, instead of or in addition to the amplitude magnitude (value) of each of the multiple peaks, the ratio of the amplitude magnitude of each of the multiple peaks (i.e., information indicating the shape characteristics of the waveform data 131 acquired by the pulse wave acquiring unit 112). In this case, the feature identifying unit 113 may identify, for example, the ratio of the amplitude magnitude of each peak to a predetermined reference magnitude as the amplitude magnitude ratio of each of the multiple peaks.

[0035] The sepsis determining unit 114 determines whether or not the subject OB is suffering from sepsis based on, for example, information relating to the magnitude of the amplitude identified by the feature identifying unit 113 .

[0036] Specifically, the sepsis determination unit 114 determines whether or not the subject OB is suffering from sepsis, for example, based on the maximum value of the amplitude of each of multiple consecutive peaks in the waveform data 131 acquired by the pulse wave acquisition unit 112.

[0037] In addition, the sepsis determination unit 114 determines whether the subject OB is suffering from sepsis, for example, based on the ratio of the amplitude of each of multiple consecutive peaks in the waveform data 131 acquired by the pulse wave acquisition unit 112.

[0038] The information generating unit 115 generates output data 133 based on, for example, the determination result by the sepsis determining unit 114. Then, the information generating unit 115 stores the generated output data 133 in the information storage area 130, for example.

[0039] The information output unit 116 outputs, for example, the output data 133 generated by the information generation unit 115 to the output device 105 .

[0040] The input receiving unit 111 may, for example, receive input of morbidity data 132 about the subject OB. The input receiving unit 111 may, for example, store the received input of morbidity data 132 in the information storage area 130. Thereafter, the information generating unit 115 may, for example, generate output data 133 based on both the determination result by the sepsis determining unit 114 and the morbidity data 132 received as input by the input receiving unit 111.

[0041] Furthermore, the information output unit 116 may, for example, transmit (store) the output data 133 generated by the information generation unit 115 to another information processing device (not shown) that can communicate with the information processing device 1 via a network (not shown) such as the Internet.

[0042] [Flowchart of Sepsis Determination Processing in First Embodiment] Next, the sepsis determination processing in the first embodiment will be described. Figures 5 to 11 are flowcharts explaining the sepsis determination processing in the first embodiment. Figures 12 and 13 are diagrams explaining the sepsis determination processing in the first embodiment.

[0043] [Data Reception Processing] First, a description will be given of the process of receiving input of the morbidity data 132 (hereinafter also referred to as data reception processing) in the sepsis diagnosis processing. Fig. 5 is a flowchart illustrating the data reception processing.

[0044] As shown in FIG. 5, the input receiving unit 111 waits until it receives input of the disease data 132 of the subject OB (NO in S11).

[0045] Then, when input of the disease data 132 of the subject OB is accepted (YES in S11), the input accepting unit 111 stores the accepted input disease data 132 in the information storage area 130, for example (S12).

[0046] [Data Acquisition Process] Next, the timing of acquiring the waveform data 131 (hereinafter also referred to as data acquisition process) in the sepsis assessment process will be described. Fig. 6 is a flowchart illustrating the data acquisition process.

[0047] 6, the pulse wave acquisition unit 112 waits until the data acquisition timing (NO in S21). The data acquisition timing may be, for example, the timing when information indicating that waveform data 131 of the subject OB will be acquired is input. Alternatively, the data acquisition timing may be, for example, the timing immediately after the data reception process is performed.

[0048] When the timing for acquiring data arrives (YES in S21), the pulse wave acquiring unit 112 acquires waveform data 131 for the subject OB from, for example, the acceleration plethysmograph 2 (S22).

[0049] Specifically, the pulse wave acquisition unit 112 acquires, for example, waveform data 131 for the subject OB corresponding to a predetermined time period (for example, a time period of approximately the most recent tens of seconds to several minutes) from the acceleration plethysmograph 2.

[0050] Thereafter, the pulse wave acquiring unit 112 stores, for example, the waveform data 131 received in the process of S22 in the information storage area 130 (S23). A specific example of the waveform data 131 will be described below.

[0051] 12 and 13 are examples of waveform data 131. In the waveform data 131 shown in Fig. 12 and 13, the horizontal axis represents time, and the vertical axis represents the magnitude (amplitude) of the acceleration pulse wave.

[0052] The waveform data 131 shown in Fig. 12 (hereinafter also referred to as waveform data 131a) is, for example, waveform data in which peak values ​​of approximately constant values ​​occur regularly (periodically). Specifically, each peak value in the waveform data 131a shown in Fig. 12 is approximately 10,000. In other words, the waveform data 131a shown in Fig. 12 is waveform data having a shape similar to that of waveform data of an electrocardiogram in a normal case, for example.

[0053] 13 (hereinafter also referred to as waveform data 131b) is, for example, waveform data in which non-constant peak values ​​occur irregularly (so-called tooth-shaped waveform data). Specifically, each peak value in the waveform data 131b shown in FIG. 13 is, for example, approximately 500 to 1000. In other words, the waveform data 131b shown in FIG. 13 is waveform data having a shape similar to that of electrocardiogram waveform data in the case of ventricular fibrillation, for example.

[0054] [Main Processing of Sepsis Diagnosis Processing] Next, the main processing of the sepsis diagnosis processing (hereinafter also simply referred to as the main processing) will be described. Figures 7 and 8 are flowcharts illustrating the main processing.

[0055] 7, the feature identification unit 113 waits until the determination timing arrives (NO in S31). The determination timing may be, for example, the timing when information indicating that a determination as to whether the subject OB has sepsis is to be made is input. The data acquisition timing may be, for example, the timing immediately after the data acquisition process is performed.

[0056] Then, when the judgment timing arrives (YES in S31), the feature identification unit 113 identifies, for example, the amplitude magnitude (value) of each of multiple consecutive peaks in the waveform data 131 stored in the information storage area 130 (the waveform data 131 acquired in the data acquisition process) (S32).

[0057] Furthermore, the sepsis determining unit 114 determines whether or not the subject OB is suffering from sepsis based on, for example, the maximum value of the amplitude identified in the process of S32 (S33).

[0058] Thereafter, the information generating unit 115 generates output data 133 based on, for example, the determination result in the process of S33 and the morbidity data 132 stored in the information storage area 130 (morbidity data 132 inputted and accepted in the data accepting process) (S34). The processes of S33 and S34 will be described in detail below.

[0059] 8, the sepsis determination unit 114 determines whether the maximum amplitude value identified in the process of S32 is less than a threshold value (hereinafter also referred to as a first threshold value) (S41). The first threshold value may be, for example, 1000.

[0060] As a result, if it is determined that the maximum value of the amplitude magnitude identified in the processing of S32 is less than the first threshold value (YES in S41), the sepsis determination unit 114 identifies, for example, a specific degree of certainty (hereinafter also referred to as the first degree of certainty) as the degree of certainty that the subject OB is suffering from sepsis (S42).

[0061] On the other hand, if it is determined that the maximum value of the amplitude magnitude identified in the processing of S32 is greater than or equal to the first threshold value (NO in S41), the sepsis determination unit 114 identifies, for example, another probability (hereinafter also referred to as the second probability) that the subject OB is suffering from sepsis, which is lower than the first probability (S44).

[0062] That is, the sepsis determining unit 114 determines whether or not the subject OB is suffering from sepsis, for example, by using the maximum value of the amplitude identified in the process of S32.

[0063] Specifically, for example, if the maximum value of the amplitude magnitude identified in the processing of S32 is less than a first threshold value, the sepsis determination unit 114 identifies a first probability, which is higher than the second probability, as the probability that the subject OB is suffering from sepsis.

[0064] On the other hand, for example, if the maximum value of the amplitude magnitude identified in the processing of S32 is greater than or equal to the first threshold value, the sepsis determination unit 114 identifies a second probability that the subject OB is suffering from sepsis, which is lower than the first probability.

[0065] Then, for example, after the process of S42, the information generating unit 115 generates information indicating the first certainty identified in the process of S42 as the output data 133 (S43).

[0066] Specifically, in this case, the information generating unit 115 generates information such as "high possibility of having sepsis" as the output data 133.

[0067] More specifically, for example, if the morbidity data 132 corresponding to the subject OB is not stored in the information storage area 130, or if the morbidity data 132 indicating that the subject OB is not currently suffering from sepsis is stored in the information storage area 130, the information generating unit 115 generates information such as "highly likely to have suffered from sepsis" as the output data 133. Also, for example, if the morbidity data 132 indicating that the subject OB is currently suffering from sepsis is stored in the information storage area 130, the information generating unit 115 generates information such as "still suffering from sepsis" as the output data 133.

[0068] Furthermore, for example, after the process of S44, the information generating unit 115 generates information indicating the second certainty identified in the process of S44 as the output data 133 (S45).

[0069] Specifically, in this case, the information generating unit 115 generates information such as "there is a low possibility that the patient is suffering from sepsis" as the output data 133.

[0070] More specifically, for example, if the morbidity data 132 corresponding to the subject OB is not stored in the information storage area 130, or if the morbidity data 132 indicating that the subject OB is not currently suffering from sepsis is stored in the information storage area 130, the information generating unit 115 generates information such as "It is unlikely that the subject OB has suffered from sepsis" as the output data 133. Also, for example, if the morbidity data 132 indicating that the subject OB is currently suffering from sepsis is stored in the information storage area 130, the information generating unit 115 generates information such as "It is highly likely that the subject OB has recovered from sepsis" as the output data 133.

[0071] Returning to FIG. 7, the information output unit 116 outputs the output data 133 generated in the process of S34 (the process of S43 or the process of S45) to the output device 105 (S35).

[0072] This enables the information processing device 1 to quickly output a determination result as to whether or not the subject OB is suffering from sepsis, for example.

[0073] Specifically, the maximum amplitude value in the waveform data 131a described in Fig. 12 is, for example, about 10000. Therefore, for example, when the first threshold value is 1000, the information processing device 1 can output a determination result indicating that the subject OB corresponding to the waveform data 131a described in Fig. 12 is unlikely to be suffering from sepsis.

[0074] On the other hand, the maximum amplitude value in the waveform data 131b described in Fig. 13 is, for example, approximately 500 to 1000. Therefore, for example, when the first threshold value is 1000, the information processing device 1 can output a determination result indicating that the subject OB corresponding to the waveform data 131b described in Fig. 13 is highly likely to be suffering from sepsis.

[0075] If it is determined that the maximum amplitude value identified in the process of S32 is equal to or greater than the first threshold value (NO in S41), the sepsis determination unit 114 may determine, for example, whether the maximum amplitude value identified in the process of S32 is less than another threshold value (hereinafter also referred to as a second threshold value) that is greater than the first threshold value. The second threshold value may be, for example, 2000.

[0076] If it is determined that the maximum value of the amplitude magnitude identified in the process of S32 is equal to or greater than the first threshold value and less than the second threshold value, the sepsis determination unit 114 may, for example, identify another degree of certainty that the subject OB is suffering from sepsis (hereinafter also referred to as a third degree of certainty) that is lower than the first degree of certainty and higher than the second degree of certainty. In this case, the sepsis determination unit 114 may then, for example, generate information indicating the identified third degree of certainty as the output data 133.

[0077] That is, the sepsis determination unit 114 may, for example, determine whether or not the subject OB is suffering from sepsis, in addition to determining whether or not there are signs of sepsis.

[0078] Specifically, for example, if it is determined that the maximum value of the amplitude magnitude identified in the processing of S32 is greater than or equal to the first threshold value and less than the second threshold value, and disease data 132 corresponding to the subject OB is not stored in the information storage area 130, or if disease data 132 indicating that the subject OB is not currently suffering from sepsis is stored in the information storage area 130, the information generation unit 115 may generate information such as ``there are signs of sepsis'' as output data 133.

[0079] Furthermore, for example, if it is determined that the maximum value of the amplitude magnitude identified in the processing of S32 is greater than or equal to the first threshold value and less than the second threshold value, and disease data 132 indicating that the subject OB is currently suffering from sepsis is stored in the information storage area 130, the information generation unit 115 may generate information such as "the symptoms of sepsis are alleviating" or "sepsis is being cured" as output data 133.

[0080] That is, the sepsis determination unit 114 may determine, for example, whether or not the subject OB is suffering from sepsis, as well as determine the recovery status of sepsis in the subject OB.

[0081] This enables the information processing device 1 to output, for example, a more detailed determination result as to whether or not the subject OB is suffering from sepsis.

[0082] [Other Main Processing of Sepsis Diagnosis Processing] Next, other main processing of the sepsis diagnosis processing (hereinafter simply referred to as other main processing) will be described. Figures 9 to 11 are flowcharts explaining the other main processing. The other main processing is processing that can be performed, for example, instead of the main processing described in Figures 7 and 8, or together with the main processing described in Figures 7 and 8.

[0083] As shown in FIG. 9, the feature specifying unit 113 waits until the determination timing, for example (NO in S51).

[0084] Then, when the judgment timing arrives (YES in S51), the feature identification unit 113 identifies, for example, the ratio of the amplitude magnitudes of each of multiple consecutively located peaks in the waveform data 131 stored in the information storage area 130 (the waveform data 131 acquired in the data acquisition process) (S52).

[0085] Furthermore, the sepsis determining unit 114 determines whether or not the subject OB is suffering from sepsis based on, for example, the ratio of the amplitudes identified in the process of S52 (S53).

[0086] Thereafter, the information generating unit 115 generates output data 133 based on, for example, the determination result in the process of S53 and the morbidity data 132 stored in the information storage area 130 (morbidity data 132 inputted in the data receiving process) (S54). The processes of S53 and S54 will be described in detail below.

[0087] [Details of processing in S53 and S54] As shown in FIG. 10, the sepsis determination unit 114, for example, identifies one or more peaks (hereinafter also referred to as the first number) that have a small amplitude ratio identified in the processing in S52 from multiple peaks that are consecutively located in the waveform data 131 stored in the information storage area 130 (S61).

[0088] Specifically, the sepsis determining unit 114 identifies a first number of peaks in ascending order of the amplitude ratio identified in the process of S52, for example.

[0089] In addition, the sepsis determination unit 114, for example, identifies one or more peaks (hereinafter also referred to as the second number) from multiple peaks located consecutively in the waveform data 131 stored in the information storage area 130, which have a large ratio of the amplitude magnitude identified in the processing of S52 (S62).

[0090] Specifically, the sepsis determining unit 114 identifies the second number of peaks in descending order of the amplitude ratio identified in the process of S52, for example.

[0091] Then, the sepsis determining unit 114 calculates, for example, a value indicating the ratio of the amplitudes of the first number of peaks identified in the process of S61 (hereinafter also referred to as a first value) (S63).

[0092] Specifically, the sepsis determining unit 114 calculates, as the first value, for example, the average or median of the ratio of the amplitude magnitudes of the first number of peaks identified in the process of S61.

[0093] In addition, if only one peak is identified in the processing of S61, that is, if only the peak with the smallest amplitude is identified in the processing of S61, the sepsis determination unit 114 may, for example, use the ratio of the amplitudes of the peaks identified in the processing of S61 as the first value.

[0094] Furthermore, the sepsis determining unit 114 calculates, for example, a value indicating the ratio of the amplitudes of the second number of peaks identified in the process of S63 (hereinafter also referred to as a second value) (S64).

[0095] Specifically, the sepsis determining unit 114 calculates, as the second value, for example, the average or median of the ratio of the amplitude magnitudes of the second number of peaks identified in the process of S63.

[0096] In addition, if only one peak is identified in the processing of S63, that is, if only the peak with the largest amplitude is identified in the processing of S63, the sepsis determination unit 114 may, for example, use the ratio of the amplitudes of the peaks identified in the processing of S63 as the second value.

[0097] Next, the sepsis determination unit 114 calculates the ratio (hereinafter simply referred to as the ratio) of the second value calculated in the processing of S64 to the first value calculated in the processing of S63, for example, by dividing the second value calculated in the processing of S64 by the first value calculated in the processing of S63 (S65).

[0098] 11, the sepsis determination unit 114 determines whether the ratio calculated in the process of S65 is less than a threshold value (hereinafter also referred to as a third threshold value) (S71). The third threshold value may be, for example, 100.

[0099] As a result, if it is determined that the ratio calculated in the processing of S65 is less than the third threshold value (YES in S71), the sepsis determination unit 114 identifies, for example, a specific probability (hereinafter also referred to as the fourth probability) as the probability that the subject OB is suffering from sepsis (S72).

[0100] On the other hand, if it is determined that the ratio calculated in the processing of S65 is equal to or greater than the third threshold (NO in S71), the sepsis determination unit 114 identifies, for example, another probability (hereinafter also referred to as the fifth probability) that the subject OB is suffering from sepsis, which is lower than the fourth probability (S74).

[0101] That is, the sepsis determination unit 114 determines whether or not the subject OB is suffering from sepsis, for example, by using the ratio calculated in the process of S65.

[0102] Specifically, for example, if the ratio calculated in the processing of S65 is less than the third threshold, the sepsis determination unit 114 identifies a fourth probability, which is higher than the fifth probability, as the probability that the subject OB is suffering from sepsis.

[0103] On the other hand, for example, if the ratio calculated in the processing of S65 is equal to or greater than the third threshold, the sepsis determination unit 114 identifies a fifth probability, which is lower than the fourth probability, as the probability that the subject OB is suffering from sepsis.

[0104] Then, for example, after the process of S72, the information generating unit 115 generates information indicating the fourth probability identified in the process of S72 as the output data 133 (S73).

[0105] Specifically, the information generating unit 115 generates information such as "high possibility of suffering from sepsis" as the output data 133.

[0106] Furthermore, for example, after the process of S74, the information generating unit 115 generates information indicating the fifth degree of certainty identified in the process of S74 as the output data 133 (S75).

[0107] Specifically, the information generating unit 115 generates information such as "there is a low possibility that the patient is suffering from sepsis" as the output data 133.

[0108] Returning to FIG. 9, the information output unit 116 outputs the output data 133 generated in the process of S54 (the process of S73 or the process of S75) to the output device 105 (S55).

[0109] This enables the information processing device 1 to quickly output a determination result as to whether or not the subject OB is suffering from sepsis, for example, as in the case described with reference to Figures 7 and 8.

[0110] Specifically, for example, if the first value in the waveform data 131a described in Fig. 12 is 10000 and the second value is 20, the information processing device 1 calculates 500 as the proportion corresponding to the waveform data 131a described in Fig. 12. Therefore, for example, if the third threshold is 100, the information processing device 1 can output a determination result indicating that the subject OB corresponding to the waveform data 131a described in Fig. 12 is unlikely to be suffering from sepsis.

[0111] On the other hand, if the first value in the waveform data 131b described in Fig. 13 is 500 and the second value is 20, the information processing device 1 calculates 25 as the proportion corresponding to the waveform data 131b described in Fig. 13. Therefore, for example, if the third threshold is 100, the information processing device 1 can output a determination result indicating that the subject OB corresponding to the waveform data 131b described in Fig. 13 is highly likely to be suffering from sepsis.

[0112] In addition, if it is determined that the ratio calculated in the processing of S65 is equal to or greater than the third threshold value (NO in S71), the sepsis determination unit 114 may, for example, determine whether the ratio calculated in the processing of S65 is less than another threshold value (hereinafter also referred to as the fourth threshold value) that is greater than the third threshold value.

[0113] If it is determined that the ratio calculated in the process of S65 is equal to or greater than the third threshold and less than the fourth threshold, the sepsis determination unit 114 may, for example, specify another probability that the subject OB has sepsis (hereinafter also referred to as a sixth probability) that is lower than the fourth probability and higher than the fifth probability. In this case, the sepsis determination unit 114 may then generate, for example, information indicating the specified sixth probability as the output data 133.

[0114] This enables the information processing device 1 to output a more detailed determination result as to whether or not the subject OB is suffering from sepsis, for example, as in the case described with reference to Figures 7 and 8.

[0115] In this manner, the information processing device 1 in this embodiment acquires, for example, waveform data generated from the acceleration pulse wave of the subject OB from the acceleration plethysmograph 2. Then, the information processing device 1 identifies, for example, information related to the amplitude of the acquired waveform data. Next, the information processing device 1 determines whether the subject OB is suffering from sepsis, for example, based on the information related to the identified amplitude. Thereafter, the information processing device 1 outputs, for example, a determination result regarding whether the subject OB is likely to be suffering from sepsis.

[0116] That is, the information processing device 1 in this embodiment determines whether or not the subject OB is likely to be suffering from sepsis, for example, based on the measurement results of the accelerated pulse wave of the subject OB.

[0117] As a result, the sepsis determination system 10 in this embodiment can, for example, quickly perform auxiliary diagnosis of sepsis. Specifically, the sepsis determination system 10 can quickly perform auxiliary diagnosis of sepsis even in places where there are no doctors, for example. Therefore, the sepsis determination system 10 can, for example, quickly start initial treatment for a subject OB suffering from sepsis.

[0118] Furthermore, the sepsis determination system 10 in this embodiment can also determine the recovery status of the subject OB suffering from sepsis, for example, from the measurement results of the accelerated pulse wave of the subject OB. Therefore, the sepsis determination system 10 can be used, for example, to monitor the recovery status of the subject OB suffering from sepsis. In other words, the measurement results by the sepsis determination system 10 can be used, for example, as a surrogate marker for the recovery of the subject OB suffering from sepsis.

[0119] In addition, the sepsis determination system 10 in this embodiment may determine whether or not the subject OB is suffering from sepsis by using, for example, a learning model generated by machine learning.

[0120] 1: Information processing device 2: Acceleration plethysmograph 10: Sepsis determination system 101: CPU 102: Memory 103: Communication device 104: Storage medium 105: Output device 106: Bus 110: Program 111: Input reception unit 112: Pulse wave acquisition unit 113: Feature identification unit 114: Sepsis determination unit 115: Information generation unit 116: Information output unit 130: Information storage area 131: Waveform data 132: Morbidity data 133: Output data OB: Subject

Claims

1. A sepsis determination program that causes a computer to execute the following processes: acquire an accelerated pulse wave of a subject; identify information related to the magnitude of the amplitude of the acquired accelerated pulse wave; determine whether or not the subject is suffering from sepsis based on the identified information related to the magnitude of the amplitude; and output a determination result as to whether or not the subject is likely suffering from sepsis.

2. The sepsis determination program according to claim 1, characterized in that in the determination process, it is determined whether or not the subject is suffering from sepsis based on the maximum value of the amplitude of each of multiple consecutive peaks in the waveform of the accelerated pulse wave.

3. The sepsis determination program of claim 2, wherein the determination process determines whether the maximum value is less than a first threshold value, and if it is determined that the maximum value is less than the first threshold value, determines that the certainty that the subject is suffering from sepsis is a first certainty, and if it is determined that the maximum value is equal to or greater than the first threshold value, determines that the certainty that the subject is suffering from sepsis is a second certainty lower than the first certainty, and the output process outputs information indicating the first certainty as the determination result if it is determined that the certainty that the subject is suffering from sepsis is the first certainty, and outputs information indicating the second certainty as the determination result.

4. The sepsis determination program of claim 3, characterized in that in the determination process, if the maximum value is equal to or greater than the first threshold value, it is determined whether the maximum value is less than a second threshold value; if it is determined that the maximum value is less than the second threshold value, it is determined that the certainty that the subject is suffering from sepsis is a third certainty lower than the first certainty and higher than the second certainty; if it is determined that the maximum value is equal to or greater than the second threshold value, it is determined that the certainty that the subject is suffering from sepsis is the second certainty; and in the output process, if it is determined that the certainty that the subject is suffering from sepsis is the third certainty, information indicating the third certainty is output as the determination result.

5. The sepsis determination program of claim 3, further comprising: causing a computer to execute a process of accepting input of morbidity data indicating whether or not the subject is suffering from sepsis; and in the output process, when it is determined that the certainty that the subject is suffering from sepsis is the first certainty and the morbidity data indicates that the subject is suffering from sepsis, outputting information indicating that the subject may not have recovered as the determination result.

6. The sepsis determination program of claim 3, further comprising: causing a computer to execute a process of accepting input of morbidity data indicating whether or not the subject is suffering from sepsis; and in the output process, when it is determined that the certainty that the subject is suffering from sepsis is the second certainty and the morbidity data indicates that the subject is suffering from sepsis, outputting information indicating that the subject may have recovered as the determination result.

7. The sepsis determination program of claim 4, further comprising: causing a computer to execute a process of accepting input of morbidity data indicating whether or not the subject is suffering from sepsis; and in the output process, when it is determined that the certainty that the subject is suffering from sepsis is the third certainty and the morbidity data indicates that the subject is suffering from sepsis, outputting information indicating that the subject may not have recovered or information indicating that the subject may be recovering as the determination result.

8. The sepsis determination program according to claim 1, characterized in that in the determination process, it is determined whether or not the subject is suffering from sepsis based on the ratio of the amplitudes of multiple consecutive peaks in the waveform of the accelerated pulse wave.

9. In the determining process, a first number of peaks having a small amplitude magnitude ratio are identified from the plurality of peaks, a second number of peaks having a large amplitude magnitude ratio are identified from the plurality of peaks, a first value indicating the amplitude magnitude ratio in the identified first number of peaks is calculated, a second value indicating the amplitude magnitude ratio in the identified second number of peaks is calculated, and whether or not a ratio of the second value to the first value is less than a third threshold is determined, and if the ratio is less than the third threshold, the certainty that the subject is suffering from sepsis is a fourth certainty, and if the ratio is equal to or greater than the third threshold, the certainty that the subject is suffering from sepsis is a fifth certainty lower than the fourth certainty; in the outputting process, if the certainty that the subject is suffering from sepsis is determined to be the fourth certainty, information indicating the fourth certainty is output as the determination result, and if the certainty that the subject is suffering from sepsis is determined to be the fifth certainty, information indicating the fifth certainty is output as the determination result. The sepsis determination program according to claim 8 .

10. A sepsis determination device comprising: a pulse wave acquisition unit that acquires an accelerated pulse wave of a subject; a feature identification unit that identifies information relating to the magnitude of the amplitude of the acquired accelerated pulse wave; a sepsis determination unit that determines whether or not the subject is suffering from sepsis based on the identified information relating to the magnitude of the amplitude; and an information output unit that outputs a determination result as to whether or not the subject is likely to be suffering from sepsis.

11. A method for diagnosing sepsis, characterized in that a computer executes the following processes: acquiring an accelerated pulse wave of a subject; identifying information relating to the magnitude of the amplitude of the acquired accelerated pulse wave; determining whether or not the subject is suffering from sepsis based on the identified information relating to the magnitude of the amplitude; and outputting a determination result as to whether or not the subject is likely to be suffering from sepsis.

12. A sepsis determination system comprising an acceleration plethysmograph that measures an acceleration pulse wave of a subject, and a sepsis determination device capable of communicating with the acceleration plethysmograph, wherein the sepsis determination device acquires the acceleration pulse wave of the subject from the acceleration plethysmograph, identifies information relating to the amplitude of the acquired acceleration pulse wave, determines whether or not the subject is suffering from sepsis based on the identified information relating to the amplitude, and outputs a determination result as to whether or not there is a possibility that the subject is suffering from sepsis.

Images