From the Predictive Medicine Group, Boston Children's Hospital Informatics Program, Boston; the Technion, Israeli Institute of Technology, Haifa, Israel; the Partners Research Information Systems and Computing, Boston; the Department of Psychiatry, Massachusetts General Hospital, Boston; the Psychiatric and Neurodevelopmental Genetics Unit, Center for Human Genetic Research, Massachusetts General Hospital, Boston; the Department of Psychology, Harvard University, Boston; and Harvard Medical School, Boston.
Am J Psychiatry. 2017 Feb 1;174(2):154-162. doi: 10.1176/appi.ajp.2016.16010077. Epub 2016 Sep 9.
The purpose of this article was to determine whether longitudinal historical data, commonly available in electronic health record (EHR) systems, can be used to predict patients' future risk of suicidal behavior.
Bayesian models were developed using a retrospective cohort approach. EHR data from a large health care database spanning 15 years (1998-2012) of inpatient and outpatient visits were used to predict future documented suicidal behavior (i.e., suicide attempt or death). Patients with three or more visits (N=1,728,549) were included. ICD-9-based case definition for suicidal behavior was derived by expert clinician consensus review of 2,700 narrative EHR notes (from 520 patients), supplemented by state death certificates. Model performance was evaluated retrospectively using an independent testing set.
Among the study population, 1.2% (N=20,246) met the case definition for suicidal behavior. The model achieved sensitive (33%-45% sensitivity), specific (90%-95% specificity), and early (3-4 years in advance on average) prediction of patients' future suicidal behavior. The strongest predictors identified by the model included both well-known (e.g., substance abuse and psychiatric disorders) and less conventional (e.g., certain injuries and chronic conditions) risk factors, indicating that a data-driven approach can yield more comprehensive risk profiles.
Longitudinal EHR data, commonly available in clinical settings, can be useful for predicting future risk of suicidal behavior. This modeling approach could serve as an early warning system to help clinicians identify high-risk patients for further screening. By analyzing the full phenotypic breadth of the EHR, computerized risk screening approaches may enhance prediction beyond what is feasible for individual clinicians.
本文旨在确定电子健康记录（EHR）系统中常见的纵向历史数据是否可用于预测患者未来发生自杀行为的风险。
采用回顾性队列研究方法开发贝叶斯模型。使用来自一个大型医疗保健数据库的 15 年（1998-2012 年）住院和门诊就诊的 EHR 数据来预测未来有记录的自杀行为（即自杀未遂或死亡）。纳入了有 3 次或更多就诊的患者（N=1,728,549）。通过对 2700 份电子病历记录（来自 520 名患者）进行专家临床医生共识审查，并结合州死亡证明，得出基于 ICD-9 的自杀行为病例定义。使用独立测试集对模型性能进行了回顾性评估。
在研究人群中，有 1.2%（N=20,246）符合自杀行为的病例定义。该模型对患者未来自杀行为具有较高的敏感性（33%-45%）、特异性（90%-95%）和早期预测能力（平均提前 3-4 年）。模型识别出的最强预测因子包括众所周知的（如物质滥用和精神障碍）和不太常见的（如某些损伤和慢性疾病）风险因素，表明数据驱动的方法可以生成更全面的风险概况。
临床实践中常见的纵向 EHR 数据可用于预测未来自杀行为的风险。这种建模方法可以作为早期预警系统，帮助临床医生识别高危患者进行进一步筛查。通过分析 EHR 的完整表型范围，计算机化的风险筛查方法可能会提高预测能力，超出个体临床医生的能力范围。
