CN-121971032-A - Multi-modal pain perception objective quantitative evaluation system and application

CN121971032ACN 121971032 ACN121971032 ACN 121971032ACN-121971032-A

Abstract

The invention discloses a multi-mode pain perception objective quantitative evaluation system and application thereof, relating to the technical field of pain perception, wherein the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring visual data, voice data, text data, photoplethysmogram PPG signals and galvanic skin response EDA signals corresponding to a target user; the data processing module is used for determining the pain index of the target user according to the visual data, the voice data and the text data, performing amplitude differentiation processing on the PPG signal to generate PPG amplitude variation delta PPG, performing slope integration processing on the EDA signal to generate EDA cumulative variation delta EDA, determining the energy competition index according to the ratio of the delta PPG to the delta EDA, determining the type of the pain index according to the size of the energy competition index, and outputting the pain index of the target user and the type of the pain index. The invention distinguishes the true pain with positive pain through the ratio of delta PPG and delta EDA, and improves the accuracy of pain level evaluation of patients.

Inventors

WU SONGBIN
XIAO LIZU
XIONG DONGLIN
HUANG JIABIN
LI RONGZHEN

Assignees

深圳市南山区人民医院

Dates

Publication Date: 20260505
Application Date: 20250930

Claims (10)

1. A multi-modal pain perception objective quantitative assessment system, comprising: the data acquisition module is used for acquiring visual data, voice data, text data, photoplethysmogram PPG signals and galvanic skin response EDA signals corresponding to a target user; A data processing module for: determining a pain index of the target user from the visual data, the speech data, and the text data; performing amplitude differentiation processing on the PPG signal to generate a PPG amplitude variation delta PPG; slope integration processing is carried out on the EDA signal, and EDA accumulated change amount delta EDA is generated; determining an energy competition index from the ratio of the Δppg and the Δeda; determining a type of the pain index according to the magnitude of the energy competition index; and the decision output module is used for outputting the pain index and the type of the pain index of the target user.
2. The system of claim 1, wherein the data acquisition module is further configured to acquire a heart rate variability HRV signal corresponding to the target user; the data processing module is further configured to, prior to said determining an energy competition index from the ratio of the Δppg and the Δeda: Extracting a low frequency power spectrum signal from the HRV signal; The determining an energy competition index according to the ratio of the Δppg and the Δeda includes: Determining an energy competition index from a product between the ratio of the Δppg and the Δeda and the low frequency power spectrum signal; The decision output module is further configured to, prior to said outputting the pain index of the target user and its type: generating treatment recommendation information according to the type of the pain index; The outputting the pain index of the target user and its type includes: and outputting the pain index of the target user and the type thereof, and the treatment advice information.
3. The system of claim 2, wherein the types of pain indices include positive, negative, and review, and wherein the determining the type of pain index based on the size of the energy competition index includes: if the energy competition index is greater than a first threshold and less than a second threshold, determining the type of pain index as positive; If the energy competition index is greater than a third threshold, determining that the type of pain index is negative, wherein the third threshold is greater than the second threshold; If the energy competition index is greater than the second threshold and less than the third threshold, or the energy competition index is less than the first threshold, determining the type of the pain index as rechecking; The generating of the treatment recommendation information according to the type of the pain index includes: If the type of pain index is positive, the treatment recommendation information includes using a quick acting opioid infusion pump for the target user; If the type of pain index is negative, the treatment recommendation information includes activating a transcranial magnetic stimulation anxiolytic device for the target user; if the type of pain index is a review, the treatment recommendation information includes again assessing pain of the target user.
4. The system of claim 3, wherein if the type of pain index is a review, the treatment recommendation information includes again assessing pain of the target user, including: Identifying a plurality of rising edges in the EDA signal; determining a slope of the plurality of rising edges; Determining a rising edge of the plurality of rising edges with a slope greater than a first preset slope threshold as a fast rising phase; determining a starting point of the rapid rise phase as a rapid rise starting point; Determining a mutation period according to the rapid rising starting point and a preset time window; Determining the voice data of the abrupt change period as target voice data; determining fundamental frequency data and spectral entropy data of the target voice data; If the fundamental frequency data of the target voice data is larger than a preset frequency threshold value, determining the type of the pain index as positive, and generating processing suggestion information comprising the use of a quick-acting opioid infusion pump for the target user; If the fundamental frequency data of the target voice data is smaller than or equal to the preset frequency threshold value and the spectral entropy data is smaller than the preset spectral entropy threshold value, the type of the pain index is determined to be negative, and processing suggestion information comprising starting the transcranial magnetic stimulation anxiolytic device for the target user is generated.
5. The system of claim 4, wherein said determining the pain index of the target user from the visual data, the speech data, and the text data comprises: Performing sliding window difference processing on the PPG signals to determine the amplitude change of adjacent windows; if the amplitudes of the sliding windows with continuous preset numbers are all reduced to exceed a preset amplitude threshold value, determining a reduction starting point from the PPG signal; Performing peak detection on the EDA signal to determine a peak value; determining a pain parameter from a time difference between the start of the decrease and the peak value, the pain parameter being inversely related to the time difference; And determining a pain index of the target user according to the pain parameter, the visual data, the voice data and the text data.
6. The system of claim 5, wherein the data processing module is further configured to monitor pain parameters of the target user in response to opioid usage information; If the difference value between the pain parameter after receiving the opioid use information and the pain parameter before receiving the opioid use information is continuously within a preset difference value range, generating drug tolerance information; The decision output module is also used for outputting the drug tolerance information.
7. The system of claim 6, wherein the data processing module is further to: if the difference value between the pain parameter after receiving the opioid use information and the pain parameter before receiving the opioid use information is out of the preset difference value range, generating medicine effective information; The decision output module is also used for outputting the medicament validation information.
8. The system of claim 7, wherein said performing an amplitude differentiation process on said PPG signal to generate a PPG amplitude variation Δppg comprises: Filtering the PPG signal; Determining a peak sequence of the filtered PPG signal; Determining the amplitude differences of adjacent peaks according to the peak sequence to obtain an amplitude difference sequence; And carrying out moving average filtering on the amplitude difference sequence to generate delta PPG.
9. The system of claim 8, wherein the slope integration process of the EDA signal generates an EDA cumulative change amount Δeda, comprising: dividing the EDA signal into a plurality of non-overlapping segments; determining the slope of each segment by least square linear regression; Determining a segment with the slope larger than a second preset slope threshold as an effective sweat gland activation interval; performing trapezoidal numerical integration on the effective sweat gland activation interval to obtain integrated data; and normalizing the integral data according to the total duration of the effective sweat gland activation interval to generate delta EDA.
10. Use of the multi-modal pain perception objective quantitative assessment system as claimed in claims 1-9 in postoperative self-controlled analgesia monitoring.

Description

Multi-modal pain perception objective quantitative evaluation system and application Technical Field The invention relates to the technical field of pain perception, in particular to a multi-mode pain perception objective quantitative evaluation system and application. Background In the context of postoperative self-controlled analgesia (PCA), accurate assessment of patient pain is a key element in the rational implementation of analgesic treatment, aimed at determining whether the necessary opioid needs to be injected for analgesia, and whether the dosage of the analgesic pump needs to be adjusted. However, in practical clinical applications, problems of misdiagnosis of pain, opioid abuse, pain sensitization, and chronic pain are interwoven, creating a very unfavorable vicious circle. For example, when a patient has anxiety, if their anxiety manifestations are evaluated as pain responses by mistake, it may lead to the irrational use of opioids. Statistics from the american centers for disease control and prevention (CDC) show that opioid abuse problems are one of the major public health challenges facing the united states and that death from opioid abuse is numerous annually. Misjudgment of anxiety is pain which largely leads to unreasonable use of opioid drugs, thereby increasing the risk of serious adverse events such as respiratory depression. Also, in our country, the rate of drug addiction is increased by the unnecessary use of opium after surgery. U.S. patent publication No. US20090259113A1 proposes a system and method for determining pain levels using a video imager to continuously monitor the posture of a patient, identify a patient state from the monitored gestures that corresponds to at least one clinical factor, and automatically record the patient state in an Electronic Medical Record (EMR), which describes the use of facial expressions and sounds to determine the pain level of the patient in a clinical environment. However, it is not accurate enough to evaluate pain levels, misjudging anxiety as pain, causing unnecessary opioid infusions, missed detection of real pain, resulting in increased postoperative chronic pain conversion rates, and extrusion of medical resources. Therefore, how to improve the accuracy of pain level assessment for PCA patients is a technical problem that is urgently addressed. Disclosure of Invention The invention solves the technical problem that the evaluation of the pain level of the PCA patient is not accurate enough. In order to solve the technical problems, the invention provides a multi-mode pain perception objective quantitative evaluation system, which comprises: the data acquisition module is used for acquiring visual data, voice data, text data, photoplethysmogram PPG signals and galvanic skin response EDA signals corresponding to a target user; A data processing module for: determining a pain index of the target user from the visual data, the speech data, and the text data; performing amplitude differentiation processing on the PPG signal to generate a PPG amplitude variation delta PPG; slope integration processing is carried out on the EDA signal, and EDA accumulated change amount delta EDA is generated; determining an energy competition index from the ratio of the Δppg and the Δeda; determining a type of the pain index according to the magnitude of the energy competition index; and the decision output module is used for outputting the pain index and the type of the pain index of the target user. Preferably, the data acquisition module is further configured to acquire a heart rate variability HRV signal corresponding to the target user; the data processing module is further configured to, prior to said determining an energy competition index from the ratio of the Δppg and the Δeda: Extracting a low frequency power spectrum signal from the HRV signal; The determining an energy competition index according to the ratio of the Δppg and the Δeda includes: Determining an energy competition index from a product between the ratio of the Δppg and the Δeda and the low frequency power spectrum signal; The decision output module is further configured to, prior to said outputting the pain index of the target user and its type: generating treatment recommendation information according to the type of the pain index; The outputting the pain index of the target user and its type includes: and outputting the pain index of the target user and the type thereof, and the treatment advice information. Preferably, the type of pain index includes positive, negative and recheck, and the determining the type of pain index according to the magnitude of the energy competition index includes: if the energy competition index is greater than a first threshold and less than a second threshold, determining the type of pain index as positive; If the energy competition index is greater than a third threshold, determining that the type of pain index is negative, wherein the third threshold is