Kang Ri-Ra, Kim Yong-Gyom, Hong Minseok, Min Ahn Yong, Lee KangYoon
Department of Computer Engineering, Gachon University, Seoul 13120. Republic of Korea.
Department of Neuropsychiatry, Seoul National University Hospital, 101 Daehak-ro, Jongno-Gu, Seoul 03080, Republic of Korea.
Int J Med Inform. 2025 Jun;198:105870. doi: 10.1016/j.ijmedinf.2025.105870. Epub 2025 Mar 12.
Suicide is a major global health issue, with approximately 700,000 deaths annually (WHO). In psychiatric wards, managing harmful behaviors such as suicide, self-harm, and aggression is essential to ensure patient and staff safety. However, psychiatric wards in South Korea face challenges due to high patient-to-psychiatrist ratios and heavy workloads. Current models relying on demographic data struggle to provide real-time predictions. This study introduces the Temporal Fusion Transformer (TFT) model to address these limitations by integrating sensor, location, and clinical data for predicting harmful behaviors. The TFT model's advanced features, such as Variable Selection Networks and temporal attention mechanisms, make it particularly suitable for capturing complex time-series patterns and providing interpretable results in psychiatric settings.
Data from 145 patients across three hospitals were collected using wearable devices that tracked heart rate, movement, and location. The data were aggregated hourly, preprocessed to handle missing values, and standardized. A binary classification model using TFT was developed and evaluated with accuracy, recall, F1 score, and AUC. Bayesian optimization was employed for hyperparameter tuning, and 5-fold cross-validation was performed to ensure generalizability.
The TFT model outperformed Multi-LSTM and Multi-GRU models, achieving 95.1% accuracy, 74.9% recall, an F1 score of 78.1, and an AUC of 0.863. The Variable Selection Network effectively identified key predictive factors, such as daily entropy and heart rate variability, improving interpretability. Incorporating location and biometric data enhanced prediction accuracy and enabled real-time risk assessments.
This study is the first to use the TFT model for predicting behavioral risks in psychiatric wards. The model's ability to integrate diverse data sources, prioritize cirtical variables, and capture temporal dependencies make it highly suitable for psychiatric environments. While the TFT model performed well, challenges remain with recall due to the limited dataset. Future research will focus on expanding datasets, optimizing variable selection, and standardizing data through a multimodal Common Data Model (CDM) to further improve performance and clinical utility.
自杀是一个重大的全球健康问题，每年约有70万例死亡（世界卫生组织）。在精神科病房，管理诸如自杀、自残和攻击行为等有害行为对于确保患者和工作人员的安全至关重要。然而，由于患者与精神科医生的比例过高以及工作量繁重，韩国的精神科病房面临挑战。当前依赖人口统计学数据的模型难以提供实时预测。本研究引入时间融合Transformer（TFT）模型，通过整合传感器、位置和临床数据来预测有害行为，以解决这些局限性。TFT模型的高级功能，如变量选择网络和时间注意力机制，使其特别适合捕捉复杂的时间序列模式，并在精神科环境中提供可解释的结果。
使用可穿戴设备收集了来自三家医院的145名患者的数据，这些设备可跟踪心率、运动和位置。数据按小时汇总，进行预处理以处理缺失值并标准化。开发了一个使用TFT的二元分类模型，并通过准确率、召回率、F1分数和AUC进行评估。采用贝叶斯优化进行超参数调整，并进行5折交叉验证以确保通用性。
TFT模型优于多层长短期记忆网络（Multi-LSTM）和多层门控循环单元（Multi-GRU）模型，准确率达到95.1%，召回率为74.9%，F1分数为78.1，AUC为0.863。变量选择网络有效地识别了关键预测因素，如每日熵和心率变异性，提高了可解释性。纳入位置和生物特征数据提高了预测准确性，并实现了实时风险评估。
本研究首次使用TFT模型预测精神科病房的行为风险。该模型整合多种数据源、对关键变量进行优先级排序以及捕捉时间依赖性的能力使其非常适合精神科环境。虽然TFT模型表现良好，但由于数据集有限，召回率仍存在挑战。未来的研究将集中在扩大数据集、优化变量选择以及通过多模态通用数据模型（CDM）标准化数据，以进一步提高性能和临床实用性。
