What is the clinical evidence from this study?

Study design: Observational. Population: Military personnel undergoing sanatorium treatment for musculoskeletal diseases of mild or moderate severity with previous combat zone exposure (n=90). Intervention: ECG and HRV analysis using innovative miniature ECG device and machine learning-based Universal Scoring System vs. Psychological self-assessments (Beck Anxiety Scale, PCL-5, PHQ-9, formal psychologist conclusion). Primary outcome: Prediction of psychological assessment outcomes based on ECG/HRV parameters measured by machine learning models (cross-validated R2 training score 0.520 on Beck Anxiety Scale prediction model).

What question did this study set out to answer?

This research seeks to develop a technology for objectively monitoring the psychological state of military personnel using ECG data.

March 2, 2026Open Access

Analysis of heart rate variability and subtle ECG changes based on machine learning for objective assessment of the psychological state of military personnel

Key Result

Machine learning analysis of ECG and HRV data predicted Beck Anxiety Scale scores with a cross-validated R2 of 0.52 on the training set and 0.36 on the test set in military personnel undergoing rehabilitation.

Key Points

This research seeks to develop a technology for objectively monitoring the psychological state of military personnel using ECG data.
Utilized a miniature ECG device on 90 servicemen during rehabilitation.
Conducted ECG and heart rate variability (HRV) analysis via a Universal Scoring System.
Compared ECG results with psychological self-assessment methods like the Beck Anxiety Scale.
Employed correlation analysis and machine learning for feature selection.
Identified 40 ECG/HRV features for effective prediction of psychological outcomes.
Found strongest correlations between ECG/HRV parameters and the Beck Anxiety Scale.
Achieved cross-validated R^2 scores of 0.520 and 0.359 for training and test sets, respectively.

Study Design

Type

Observational (n=90)

Multicenter

Structured PICO

基于机器学习的心电图和心率变异性分析能预测军人的心理状态吗？

Population

90名军人（士兵），平均年龄38岁，接受轻度或中度肌肉骨骼疾病的疗养治疗，之前在战斗区域暴露至少3个月。

Intervention

使用微型心电图设备和机器学习（通用评分系统）对心电图和心率变异性信号进行深入分析。

Outcome

心电图/心率变异性特征与心理评估方法（贝克焦虑量表、PCL-5、PHQ-9及正式心理学家结论）之间的相关性。

机器学习分析微妙的心电图变化和心率变异性可以为军人的心理情绪状态，特别是焦虑，提供客观评估。

Main Result

Effect estimate: cross-validated R2 training score 0.520 on Beck Anxiety Scale prediction model

Limitations

Small sample size (n=90) which may limit generalizability and power
No randomization or control group; observational design only
Limited hyperparameter tuning and no benchmarking of alternative models
Potential confounders such as age, gender, and physical activity were noted but controlled for only partially
Results may not apply outside the studied population of Ukrainian military personnel in rehabilitation setting

Abstract

Introduction The implementation of objective methods for rapid assessment of the psychological and physiological readiness of military personnel is an extremely relevant task. The cardiovascular system acts as a “mirror” of functional and psychological state. The most common and accessible method for the objective study of the cardiovascular system remains electrocardiography (ECG). This study aims to develop a technology for objective monitoring of the psycho-emotional state and overall functional condition of personnel in the Ukrainian Defense Forces using miniature ECG devices and in-depth analysis of ECG signals with artificial intelligence. Methods Using an innovative ECG device, 90 servicemen, average age of 38 years, undergoing sanatorium treatment and rehabilitation at the Central Military Clinical Sanatorium “Khmilnyk” were examined. The examination was conducted on the first or second day after the start of sanatorium treatment. ECG and HRV analysis were performed using our previously developed Universal Scoring System. The results of ECG analysis from limb leads in 6 leads were compared with 4 well-known psychological self-assessment methods: Beck Anxiety Scale, PCL-5, PHQ-9, as well as a formalized psychologist’s conclusion. Correlation analysis and Sequential Feature Selector were used. Results Forty ECG/HRV features were selected for each of the four psychological methods to find the maximum R 2 metric. The highest number of reliable correlations between ECG and HRV parameters and psychological tests was found for the Beck Anxiety Scale. The same can be said when using feature selection via machine learning. The cross-validated R 2 scores for the training and test sets in the case of the Beck Anxiety Scale were 0.520/0.359, respectively. Similar results were obtained for the Preliminary Psychological. Conclusion The study’s results demonstrate the potential for significant prediction of routine psychological assessment outcomes based on in-depth analysis of ECG and HRV, especially regarding the Beck Anxiety Scale and Preliminary Psychological Conclusion.

Bookmark

View Full Paper