Personalized Predictions of Therapeutic Hypothermia Outcomes in Cardiac Arrest Patients with Shockable Rhythms Using Explainable Machine Learning

被引：0

作者：

Hong, Chien-Tai ^{[1
,2
,3
]}

Bamodu, Oluwaseun Adebayo ^{[4
,5
,6
]}

Chiu, Hung-Wen ^{[7
,8
]}

Chiu, Wei-Ting ^{[1
,2
,3
]}

Chan, Lung ^{[1
,2
,3
]}

Chung, Chen-Chih ^{[1
,2
,3
]}

机构：

[1] Taipei Med Univ, Shuang Ho Hosp, Dept Neurol, New Taipei City 235, Taiwan

[2] Taipei Med Univ, Coll Med, Sch Med, Dept Neurol, Taipei City 110, Taiwan

[3] Taipei Med Univ, Shuang Ho Hosp, Taipei Neurosci Inst, New Taipei City 235, Taiwan

[4] George Washington Univ, Sch Publ Hlth, Dept Prevent & Community Hlth, Milken Inst, Washington, DC 20052 USA

[5] Muhimbili Univ Hlth & Allied Sci, Sch Clin Med, Directorate Postgrad Studies, POB 65001, Dar Es Salaam, Tanzania

[6] Ocean Rd Canc Inst, POB 3592, Dar Es Salaam, Tanzania

[7] Taipei Med Univ, Coll Med Sci & Technol, Grad Inst Biomed Informat, Taipei 110, Taiwan

[8] Taipei Med Univ Hosp, Clin Big Data Res Ctr, Taipei 110, Taiwan

来源：

DIAGNOSTICS | 2025年 / 15卷 / 03期

关键词：

artificial neural network; cardiac arrest; therapeutic hypothermia; shockable rhythms; machine learning; Shapley Additive exPlanations; clinical outcome; TARGETED TEMPERATURE MANAGEMENT; LOGISTIC-REGRESSION; METAANALYSIS; SURVIVAL; AGE;

D O I：

10.3390/diagnostics15030267

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

Background: Therapeutic hypothermia (TH) represents a critical therapeutic intervention for patients with cardiac arrest, although treatment efficacy and prognostic factors may vary between individuals. Precise, personalized outcome predictions can empower better clinical decisions. Methods: In this multi-center retrospective cohort study involving nine medical centers in Taiwan, we developed machine learning algorithms to predict neurological outcomes in patients who experienced cardiac arrest with shockable rhythms and underwent TH. The study cohort comprised 209 patients treated between January 2014 and September 2019. The models were trained on patients' pre-treatment characteristics collected during this study period. The optimal artificial neural network (ANN) model was interpretable using the SHapley Additive exPlanations (SHAP) method. Results: Among the 209 enrolled patients, 79 (37.80%) demonstrated favorable neurological outcomes at discharge. The ANN model achieved an area under the curve value of 0.9089 (accuracy = 0.8330, precision = 0.7984, recall = 0.7492, specificity = 0.8846) for outcome prediction. SHAP analysis identified vital predictive features, including the dose of epinephrine during resuscitation, diabetes status, body temperature at return of spontaneous circulation (ROSC), whether the cardiac arrest was witnessed, and diastolic blood pressure at ROSC. Using real-life case examples, we demonstrated how the ANN model provides personalized prognostic predictions tailored to individuals' distinct profiles. Conclusion: Our machine learning approach delivers personalized forecasts of TH outcomes in cardiac arrest patients with shockable rhythms. By accounting for each patient's unique health history and cardiac arrest event details, the ANN model empowers more precise risk stratification, tailoring clinical decision-making regarding TH prognostication and optimizing personalized treatment planning.

引用

页数：16

共 42 条

[1] Predicting neurological outcome after out-of-hospital cardiac arrest with cumulative information; development and internal validation of an artificial neural network algorithm [J].