Cusick Marika, Velupillai Sumithra, Downs Johnny, Campion Thomas R, Sholle Evan T, Dutta Rina, Pathak Jyotishman
WeiCornell Medicine, 402 E. 67th St., New York, NY 10065, USA.
South London and Maudsley NHS Foundation Trust, London, UK.
J Affect Disord Rep. 2022 Dec;10. doi: 10.1016/j.jadr.2022.100430. Epub 2022 Oct 25.
In the global effort to prevent death by suicide, many academic medical institutions are implementing natural language processing (NLP) approaches to detect suicidality from unstructured clinical text in electronic health records (EHRs), with the hope of targeting timely, preventative interventions to individuals most at risk of suicide. Despite the international need, the development of these NLP approaches in EHRs has been largely local and not shared across healthcare systems.
In this study, we developed a process to share NLP approaches that were individually developed at King's College London (KCL), UK and Weill Cornell Medicine (WCM), US - two academic medical centers based in different countries with vastly different healthcare systems. We tested and compared the algorithms' performance on manually annotated clinical notes (KCL: = 4,911 and WCM = 837).
After a successful technical porting of the NLP approaches, our quantitative evaluation determined that independently developed NLP approaches can detect suicidality at another healthcare organization with a different EHR system, clinical documentation processes, and culture, yet do not achieve the same level of success as at the institution where the NLP algorithm was developed (KCL approach: F1-score 0.85 vs. 0.68, WCM approach: F1-score 0.87 vs. 0.72).
Independent NLP algorithm development and patient cohort selection at the two institutions comprised direct comparability.
Shared use of these NLP approaches is a critical step forward towards improving data-driven algorithms for early suicide risk identification and timely prevention.
在全球预防自杀死亡的努力中，许多学术医疗机构正在采用自然语言处理（NLP）方法，从电子健康记录（EHR）中的非结构化临床文本中检测自杀倾向，以期针对自杀风险最高的个体及时进行预防性干预。尽管存在国际需求，但这些EHR中的NLP方法在很大程度上是本地化开发的，并未在医疗系统之间共享。
在本研究中，我们开发了一个流程，以共享分别由英国伦敦国王学院（KCL）和美国威尔康奈尔医学院（WCM）开发的NLP方法，这两个学术医疗中心位于不同国家，拥有截然不同的医疗系统。我们在人工标注的临床记录上测试并比较了算法的性能（KCL： = 4911，WCM = 837）。
在成功对NLP方法进行技术移植后，我们的定量评估确定，独立开发的NLP方法能够在另一个拥有不同EHR系统、临床文档流程和文化的医疗机构中检测出自杀倾向，但无法达到开发NLP算法的机构所取得的相同成功水平（KCL方法：F1分数0.85对0.68，WCM方法：F1分数0.87对0.72）。
两个机构的独立NLP算法开发和患者队列选择构成了直接可比性。
共享使用这些NLP方法是朝着改进用于早期自杀风险识别和及时预防的数据驱动算法迈出的关键一步。
