Using Natural Language Processing on Electronic Health Records to Enhance Detection and Prediction of Psychosis Risk

Jessica Irving; Rashmi Patel; Dominic Oliver; Craig Colling; Megan Pritchard; Matthew Broadbent; Helen Baldwin; Daniel Stahl; Robert Stewart; Paolo Fusar-Poli

doi:10.1093/schbul/sbaa126

Using Natural Language Processing on Electronic Health Records to Enhance Detection and Prediction of Psychosis Risk

Schizophr Bull. 2021 Mar 16;47(2):405-414. doi: 10.1093/schbul/sbaa126.

Authors

Jessica Irving¹, Rashmi Patel¹, Dominic Oliver¹, Craig Colling², Megan Pritchard^{2

3}, Matthew Broadbent², Helen Baldwin^{1

2}, Daniel Stahl⁴, Robert Stewart^{2

3}, Paolo Fusar-Poli^{1

2

5}

Affiliations

¹ Early Psychosis: Interventions and Clinical-Detection (EPIC) Lab, Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK.
² South London and Maudsley NHS Foundation Trust, London, UK.
³ Department of Psychological Medicine, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK.
⁴ Department of Biostatistics & Health Informatics, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK.
⁵ Department of Brain and Behavioral Sciences, University of Pavia, Pavia, Italy.

Abstract

Background: Using novel data mining methods such as natural language processing (NLP) on electronic health records (EHRs) for screening and detecting individuals at risk for psychosis.

Method: The study included all patients receiving a first index diagnosis of nonorganic and nonpsychotic mental disorder within the South London and Maudsley (SLaM) NHS Foundation Trust between January 1, 2008, and July 28, 2018. Least Absolute Shrinkage and Selection Operator (LASSO)-regularized Cox regression was used to refine and externally validate a refined version of a five-item individualized, transdiagnostic, clinically based risk calculator previously developed (Harrell's C = 0.79) and piloted for implementation. The refined version included 14 additional NLP-predictors: tearfulness, poor appetite, weight loss, insomnia, cannabis, cocaine, guilt, irritability, delusions, hopelessness, disturbed sleep, poor insight, agitation, and paranoia.

Results: A total of 92 151 patients with a first index diagnosis of nonorganic and nonpsychotic mental disorder within the SLaM Trust were included in the derivation (n = 28 297) or external validation (n = 63 854) data sets. Mean age was 33.6 years, 50.7% were women, and 67.0% were of white race/ethnicity. Mean follow-up was 1590 days. The overall 6-year risk of psychosis in secondary mental health care was 3.4 (95% CI, 3.3-3.6). External validation indicated strong performance on unseen data (Harrell's C 0.85, 95% CI 0.84-0.86), an increase of 0.06 from the original model.

Conclusions: Using NLP on EHRs can considerably enhance the prognostic accuracy of psychosis risk calculators. This can help identify patients at risk of psychosis who require assessment and specialized care, facilitating earlier detection and potentially improving patient outcomes.

Keywords: electronic health records; machine learning; natural language processing; prediction; prevention; psychosis.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adolescent
Adult
Electronic Health Records*
Female
Follow-Up Studies
Humans
London
Male
Middle Aged
Models, Statistical*
Natural Language Processing*
Psychotic Disorders / diagnosis*
Psychotic Disorders / physiopathology
Retrospective Studies
Risk Assessment*
Young Adult

Abstract

Publication types

MeSH terms

Grants and funding