Advancing shock prediction: leveraging prior knowledge and self-controlled data for enhanced model accuracy and generalizability
Author(s)
Type
Journal Article
Abstract
Objectives
Timely intervention in shock is vital, as delays over one hour greatly increase mortality. This study aims to develop an enhanced machine learning model that improves predictive performance by utilizing self-controlled data and applying feature engineering informed by medical knowledge to physiological waveforms, enabling the prediction of shock one hour in advance without relying on blood tests.
Methods
Patient data and physiological waveforms were obtained from the Medical Information Mart for Intensive Care III (MIMIC-3) database. Shock was defined as a mean arterial pressure ≤ 65 mmHg for more than one minute, combined with serum lactate levels ≥ 2 mmol/L within 12 h before or after the hypotension event. Waveforms used for prediction were extracted from 30 min time-segment before a 1-hour period prior to the event. Self-controlled waveforms were obtained from the same patient either one day before or up to seven days after the shock event.
Results
The study included 389 ICU patients who met the shock criteria and had complete physiological waveform data available for analysis. A total of 299 features were derived: 90 from arterial blood pressure (ABP), 89 from electrocardiogram (ECG), 112 from respiratory waveforms (RESP), and 8 from blood oxygen saturation (SpO2). The weighted ensemble model showed the best performance with an AUC of 0.93 and accuracy of 84.15%, and sensitivity of 79.64% in the testing set. The most predictive features included ECG_HRV_pNN50 (proportion of successive heartbeat intervals differing by more than 50 ms), RESP_Width_Mean (mean width of respiratory waveform), RESP_Cycle_Rate_Mean (mean respiratory cycle rate), ABP_TimeSBP2DBP_SampEn (sample entropy of systolic-diastolic intervals), and ABP_AmplitudeDBP_Median (median amplitude of diastolic peaks).
Conclusions
This study demonstrated the feasibility of predicting shock one hour before its onset using only four physiological waveforms, combined with feature engineering based on physiological concepts and self-sampling data. The model achieved a strong AUC and a high sensitivity.
Timely intervention in shock is vital, as delays over one hour greatly increase mortality. This study aims to develop an enhanced machine learning model that improves predictive performance by utilizing self-controlled data and applying feature engineering informed by medical knowledge to physiological waveforms, enabling the prediction of shock one hour in advance without relying on blood tests.
Methods
Patient data and physiological waveforms were obtained from the Medical Information Mart for Intensive Care III (MIMIC-3) database. Shock was defined as a mean arterial pressure ≤ 65 mmHg for more than one minute, combined with serum lactate levels ≥ 2 mmol/L within 12 h before or after the hypotension event. Waveforms used for prediction were extracted from 30 min time-segment before a 1-hour period prior to the event. Self-controlled waveforms were obtained from the same patient either one day before or up to seven days after the shock event.
Results
The study included 389 ICU patients who met the shock criteria and had complete physiological waveform data available for analysis. A total of 299 features were derived: 90 from arterial blood pressure (ABP), 89 from electrocardiogram (ECG), 112 from respiratory waveforms (RESP), and 8 from blood oxygen saturation (SpO2). The weighted ensemble model showed the best performance with an AUC of 0.93 and accuracy of 84.15%, and sensitivity of 79.64% in the testing set. The most predictive features included ECG_HRV_pNN50 (proportion of successive heartbeat intervals differing by more than 50 ms), RESP_Width_Mean (mean width of respiratory waveform), RESP_Cycle_Rate_Mean (mean respiratory cycle rate), ABP_TimeSBP2DBP_SampEn (sample entropy of systolic-diastolic intervals), and ABP_AmplitudeDBP_Median (median amplitude of diastolic peaks).
Conclusions
This study demonstrated the feasibility of predicting shock one hour before its onset using only four physiological waveforms, combined with feature engineering based on physiological concepts and self-sampling data. The model achieved a strong AUC and a high sensitivity.
Date Issued
2025-07-14
Date Acceptance
2025-07-08
Citation
BMC Medical Informatics and Decision Making, 2025, 25
ISSN
1472-6947
Publisher
BMC
Start Page
262
Journal / Book Title
BMC Medical Informatics and Decision Making
Volume
25
Issue
1
Copyright Statement
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
License URL
Identifier
https://www.ncbi.nlm.nih.gov/pubmed/40660187
PII: 10.1186/s12911-025-03108-2
Subjects
Early identification models
Feature engineering
Machine learning
Medical information Mart for intensive care III (MIMIC-3)
Shock
Humans
Shock
Female
Male
Machine Learning
Middle Aged
Aged
Intensive Care Units
Publication Status
Published
Coverage Spatial
England
Article Number
262
Date Publish Online
2025-07-14