Predictive systems, electronic devices, and readable storage media for sepsis-associated encephalopathy

Abstract

This invention relates to a prediction system, electronic device, and readable storage medium for sepsis-associated encephalopathy (SEEE). The system includes: a data acquisition module for acquiring measurements of neuron-specific enolase levels, transcranial ultrasound-measured peak systolic velocity of the left middle cerebral artery, and an APACHE II score reflecting disease severity; and a SEEE prediction module for obtaining the risk probability of sepsis-associated encephalopathy in sepsis patients using a pre-built and trained prediction model based on the acquired neuron-specific enolase levels, transcranial ultrasound-measured peak systolic velocity of the left middle cerebral artery, and APACHE II score reflecting disease severity. Compared with existing technologies, this invention can predict the risk of sepsis-associated encephalopathy in patients at an early stage and has good accuracy, simplicity, and practicality.

Description

Technical Field

[0001] This invention relates to the fields of bioinformatics and communication technology, and in particular to a predictive system, electronic device, and readable storage medium for sepsis-associated encephalopathy. Background Technology

[0002] Sepsis is a physiological, pathological, and biochemical disorder caused by infection. A 2017 consensus report published in the prestigious international journal JAMA defines it as a life-threatening organ dysfunction resulting from abnormal host regulation of infection. Brain dysfunction caused by sepsis is called sepsis-associated encephalopathy (SAE), a diffuse brain disorder caused by the systemic inflammatory response to sepsis. It has been reported that SAE occurs in 30-70% of sepsis patients and can manifest as varying degrees of brain dysfunction, ranging from mild delirium to severe coma. SAE severely impacts the prognosis of sepsis patients and is an independent risk factor for mortality; SAE survivors often suffer from varying degrees of acute or chronic autonomic dysfunction, delirium, or cognitive impairment.

[0003] However, there is currently a lack of unified diagnostic criteria for sepsis-associated encephalopathy in clinical practice. Its diagnosis and treatment primarily rely on exclusionary diagnosis; that is, sepsis patients can be diagnosed with sepsis-associated encephalopathy only after ruling out other central nervous system diseases that cause impairment of consciousness and cognition. Furthermore, there is a lack of means for early prediction and intervention. Therefore, there is currently a lack of predictive models capable of identifying high-risk groups for sepsis-associated encephalopathy in its early stages. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art, which lacks a predictive model capable of early identification of high-risk groups for sepsis-associated encephalopathy, and to provide a predictive system, electronic device, and readable storage medium for sepsis-associated encephalopathy.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] A predictive system for sepsis-related encephalopathy, comprising:

[0007] The data acquisition module is used to acquire measurements of neuron-specific enolase indices, transcranial ultrasound measurements of peak systolic velocity in the left middle cerebral artery, and APACHE II scores reflecting disease severity.

[0008] The sepsis-associated encephalopathy prediction module is used to obtain the risk probability of sepsis patients developing sepsis-associated encephalopathy based on the obtained neuron-specific enolase index, the peak systolic velocity index of the left middle cerebral artery measured by transcranial ultrasound, and the APACHE II score reflecting the severity of the disease, through a pre-built and trained prediction model.

[0009] Furthermore, the prediction model is a nodal plot.

[0010] Furthermore, the prediction system is used for early-stage sepsis.

[0011] Furthermore, the early stage of sepsis refers to the period within 0-24 hours after the onset of sepsis.

[0012] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement a method for predicting sepsis-related encephalopathy, the prediction method comprising the following steps:

[0013] S1: Obtain neuron-specific enolase index, transcranial ultrasound measurement of left middle cerebral artery systolic peak velocity index, and APACHE II score reflecting disease severity.

[0014] S2: Based on the obtained neuron-specific enolase index, the transcranial ultrasound measurement of the peak systolic velocity of the left middle cerebral artery, and the APACHE II score reflecting the severity of the disease, the risk probability of sepsis-associated encephalopathy in sepsis patients is obtained through a pre-built and trained predictive model.

[0015] Furthermore, the prediction model is a nodal plot.

[0016] Furthermore, the electronic device is intended for use within 0-24 hours after the onset of sepsis.

[0017] The present invention also provides a computer-readable storage medium storing a computer program, the computer program being executed by a processor, a method for predicting sepsis-related encephalopathy, the prediction method comprising the following steps:

[0018] S1: Obtain neuron-specific enolase index, transcranial ultrasound measurement of left middle cerebral artery systolic peak velocity index, and APACHE II score reflecting disease severity.

[0019] S2: Based on the obtained neuron-specific enolase index, the transcranial ultrasound measurement of the peak systolic velocity of the left middle cerebral artery, and the APACHE II score reflecting the severity of the disease, the risk probability of sepsis-associated encephalopathy in sepsis patients is obtained through a pre-built and trained predictive model.

[0020] Furthermore, the prediction model is a nodal plot.

[0021] Furthermore, the computer-readable storage medium is intended for use within 0-24 hours following the onset of sepsis.

[0022] Compared with the prior art, the present invention has the following advantages:

[0023] (1) The present invention can predict the risk of sepsis-associated encephalopathy in patients with sepsis and has high predictive value.

[0024] (2) The three indicators involved in the method of this invention (neuron-specific enolase NSE, transcranial ultrasound measurement of left middle cerebral artery systolic peak velocity index LVS, and APACHE II score measurement reflecting the severity of the disease) are very easy to obtain clinically in the early stage of sepsis. Therefore, the prediction model has good simplicity and practicality. Attached Figure Description

[0025] Figure 1 This is a schematic diagram of a predictive model for sepsis-related encephalopathy provided in an embodiment of the present invention;

[0026] Figure 2 Calibration curve of a predictive model for sepsis-associated encephalopathy provided in an embodiment of the present invention;

[0027] Figure 3a The original cohort plot of the ROC curve for model validation of a predictive model for sepsis-related encephalopathy provided in this embodiment of the invention;

[0028] Figure 3b The validation cohort diagram of the ROC curve for a predictive model of sepsis-related encephalopathy provided in this embodiment of the invention;

[0029] Figure 4 This is a diagram showing the model usage results of a predictive model for sepsis-related encephalopathy provided in an embodiment of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0031] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0032] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0033] Example 1

[0034] This embodiment provides a predictive system for sepsis-related encephalopathy, including:

[0035] The data acquisition module is used to acquire measurements of neuron-specific enolase indices, transcranial ultrasound measurements of peak systolic velocity in the left middle cerebral artery, and APACHE II scores reflecting disease severity.

[0036] The sepsis-associated encephalopathy prediction module is used to obtain the risk probability of sepsis patients developing sepsis-associated encephalopathy based on the obtained neuron-specific enolase index, the peak systolic velocity index of the left middle cerebral artery measured by transcranial ultrasound, and the APACHE II score reflecting the severity of the disease, through a pre-built and trained prediction model.

[0037] Preferably, the prediction model is a nodal plot.

[0038] Preferably, the prediction system is used within the 0-24 hour range following the onset of sepsis.

[0039] The technical solution of this embodiment is described in detail below:

[0040] This model was constructed using LASSO regression analysis of clinical data from 195 patients with sepsis, generating the following line graph (e.g.) Figure 1The main inclusion indicators included: ① neuron-specific enolase (NSE), ② transcranial ultrasound measurement of peak systolic velocity (LVS) of the left middle cerebral artery, and ③ APACHE II score reflecting the severity of the disease.

[0041] All three indicators mentioned above can be measured at the bedside in the early stages of sepsis. By using this model, the risk probability of a patient developing SAE can be predicted.

[0042] Specifically, this solution consists of the following construction process:

[0043] 1. Model Building

[0044] This prospective study included 195 patients with sepsis, collecting detailed clinical data (age, sex, BMI, APACHE II score, SOFA score, primary cause, underlying diseases, duration of mechanical ventilation, number of days in ICU, number of days in hospital, etc.), laboratory indicators (complete blood count, blood gas analysis, liver and kidney function, electrolytes, coagulation function, tumor markers, cytokines, etc.), transcranial ultrasound measurements of cerebral blood flow parameters (systolic peak velocity VS, end-diastolic velocity VD, mean velocity VM, pulsatility index PI, resistance index RI) of bilateral middle cerebral arteries, and the final clinical outcomes.

[0045] Using LASSO regression analysis, 137 cases were randomly selected as the original cohort (another 58 cases were used as the validation cohort). Three variables were selected and compressed as predictors: NSE, left-sided VS (LVS), and APACHE II score. A noctilinear plot of the model was further constructed (e.g., ...). Figure 1 ).

[0046] 2. Model Validation:

[0047] Calibration curves confirmed that the model's predicted values ​​and actual values ​​have good linear consistency, such as... Figure 2 As shown.

[0048] The model was further applied to the original cohort (n=137) and the validation cohort (n=58) respectively, and ROC curves were plotted. The area under the curve (AUC) was 0.813 (original cohort) and 0.831 (validation cohort) respectively, confirming that the model has high predictive value. Figure 3a and Figure 3b As shown.

[0049] 3. Examples

[0050] Using this model in patients diagnosed with early-stage sepsis (within 24 hours) can predict the risk of developing sepsis-associated encephalopathy (SAE).

[0051] Example: A 69-year-old male was admitted to the hospital for acute cholangitis and diagnosed with sepsis. Upon admission, his serum NSE was measured at 30 ng / ml, his APACHE II score was 25, and his transcranial ultrasound showed a lower lung field (LVS) of 120 cm / s. Then, if... Figure 4 As shown, the individual scores for the three indicators were 50, 35, and 27, respectively, with a total score of 112. The nomogram indicates a probability of SAE > 95% for this patient.

[0052] It should be noted that the sepsis-related encephalopathy prediction model based on the above three indicators in this embodiment can be implemented using currently mature data prediction methods, such as nomograms and deep learning methods, and is not the only limitation. As long as it can make predictions based on the three indicators and trained on a large number of instances, it is acceptable.

[0053] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement a method for predicting sepsis-related encephalopathy, the prediction method including the following steps:

[0054] S1: Obtain neuron-specific enolase index, transcranial ultrasound measurement of left middle cerebral artery systolic peak velocity index, and APACHE II score reflecting disease severity.

[0055] S2: Based on the obtained neuron-specific enolase index, the transcranial ultrasound measurement of the peak systolic velocity of the left middle cerebral artery, and the APACHE II score reflecting the severity of the disease, the risk probability of sepsis-associated encephalopathy in sepsis patients is obtained through a pre-built and trained predictive model.

[0056] Preferably, the prediction model is a nodal plot.

[0057] Preferably, the electronic device is used within 0-24 hours after the onset of sepsis.

[0058] The electronic device of this invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) or loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for device operation. The CPU, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0059] Multiple components in the device are connected to the I / O interface, including: input units such as keyboards and mice; output units such as various types of displays and speakers; storage units such as disks and optical discs; and communication units such as network interface cards (NICs), modems, and wireless transceivers. The communication unit allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0060] The processing unit executes the various methods and processes described above, such as steps S1-S2 of the present invention. For example, in some embodiments, steps S1-S2 of the present invention may be implemented as a computer software program tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via ROM and / or a communication unit. When the computer program is loaded into RAM and executed by the CPU, one or more steps of steps S1-S2 of the present invention described above may be performed. Alternatively, in other embodiments, the CPU may be configured to execute steps S1-S2 of the present invention by any other suitable means (e.g., by means of firmware).

[0061] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0062] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0063] This embodiment also provides a computer-readable storage medium storing a computer program, which is executed by a processor to provide a method for predicting sepsis-related encephalopathy. The prediction method includes the following steps:

[0064] S1: Obtain neuron-specific enolase index, transcranial ultrasound measurement of left middle cerebral artery systolic peak velocity index, and APACHE II score reflecting disease severity.

[0065] S2: Based on the obtained neuron-specific enolase index, the transcranial ultrasound measurement of the peak systolic velocity of the left middle cerebral artery, and the APACHE II score reflecting the severity of the disease, the risk probability of sepsis-associated encephalopathy in sepsis patients is obtained through a pre-built and trained predictive model.

[0066] Preferably, the prediction model is a nodal plot.

[0067] Preferably, the computer-readable storage medium is used within the 0-24 hour period following the onset of sepsis.

[0068] In the context of this invention, a machine-readable storage medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0069] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A system for predicting sepsis-associated encephalopathy, characterized by, The application relates to a sepsis-related encephalopathy prediction system, comprising: a data acquisition module for acquiring the measurement values of a neuron-specific enolase index, a transcranial ultrasound measured left middle cerebral artery systolic peak flow rate index and an APACHE II score reflecting the severity of a disease; a sepsis-related encephalopathy prediction module for acquiring the risk probability of sepsis-related encephalopathy according to the acquired measurement values of the neuron-specific enolase index, the transcranial ultrasound measured left middle cerebral artery systolic peak flow rate index and the APACHE II score reflecting the severity of a disease by using a pre-constructed and trained prediction model; the prediction model is a nomogram; the prediction system is used in the early stage of sepsis.

2. The system for predicting sepsis-associated encephalopathy according to claim 1, wherein The early stage of sepsis is within the range of 0-24 hours after the occurrence of sepsis. 3.An electronic device comprising a memory and a processor, the memory having stored thereon a computer program, characterized in that, The processor implements a prediction method for sepsis-related encephalopathy when executing the program, and the prediction method comprises the following steps: S1: acquiring the measurement values of a neuron-specific enolase index, a transcranial ultrasound measured left middle cerebral artery systolic peak flow rate index and an APACHE II score reflecting the severity of a disease; S2: acquiring the risk probability of sepsis-related encephalopathy according to the acquired measurement values of the neuron-specific enolase index, the transcranial ultrasound measured left middle cerebral artery systolic peak flow rate index and the APACHE II score reflecting the severity of a disease by using a pre-constructed and trained prediction model; the prediction model is a nomogram; the prediction method is used in the early stage of sepsis.

4. The electronic device of claim 3, wherein, The electronic device is used within the range of 0-24 hours after the occurrence of sepsis.

5. A computer readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement a prediction method for sepsis-related encephalopathy, and the prediction method comprises the following steps: S1: acquiring the measurement values of a neuron-specific enolase index, a transcranial ultrasound measured left middle cerebral artery systolic peak flow rate index and an APACHE II score reflecting the severity of a disease; S2: acquiring the risk probability of sepsis-related encephalopathy according to the acquired measurement values of the neuron-specific enolase index, the transcranial ultrasound measured left middle cerebral artery systolic peak flow rate index and the APACHE II score reflecting the severity of a disease by using a pre-constructed and trained prediction model; the prediction model is a nomogram; the prediction method is used in the early stage of sepsis.

6. The computer-readable storage medium of claim 5, wherein, The computer readable storage medium is used within the range of 0-24 hours after the occurrence of sepsis.

Images