Electronic health records reveal transdiagnostic clinical features and diverse trajectories of serious mental illness

Abstract

Investigations using Electronic Health Records (EHR) databases could enable accurate delineation of psychiatric disease trajectories at an unprecedented scale. Using EHR from a single institution (Clinica San Juan de Dios in Manizales, Colombia), we characterize diagnostic trajectories of >22,000 (ages 4-90, 60% female) individuals treated for severe mental illness (SMI), including schizophrenia (SCZ), bipolar disorder (BD), and severe or recurrent major depressive disorder (MDD). We extracted diagnostic codes, clinical notes, and healthcare use data collected since 2005. Using a subsample of 105 SMI patients, we assessed diagnostic reliability, comparing EHR to clinical chart review. EHR diagnostic codes showed very good agreement with chart review diagnoses (Cohens kappa 0.78). Using 3,600 annotated sentences from 2,788 patients, we developed a pipeline for extracting clinical features from the electronic text, which showed high agreement with gold-standard annotations (average F1 0.88). Factors associated with diagnostic instability, defined as changes in diagnosis between successive visits, were identified using mixed-effect logistic regression models. Of SMI patients with >3 visits (n=12,962), 64% had multiple EHR diagnoses; diagnostic switches (19%), comorbidities (30%), and both (15%). While some diagnostic switches are common, such as the switch from MDD to BD (observed in 22% of BD patients), trajectories are highly heterogeneous, with rare trajectories (occurring in <1% of patients) making up the majority (58% of all patients). Predictors of diagnostic instability include time since initial visit (OR 0.56 by visit number, p-value 2e-66), previous diagnostic change (OR= 4.02, p-value 3e-250) and NLP-derived descriptions of delusions (OR 1.50, p-values 2e-18). Our results underline the importance of considering longitudinal rather than cross-sectional diagnoses in psychiatric research and show how high-quality EHR data can contribute to global efforts to understand disease trajectories.

Predicting diagnostic conversion from major depressive disorder to bipolar disorder: an EHR based study from Colombia

“…The unstructured part of the EHR is composed of diverse types of notes, as described in De la Hoz et al, (Hoz et al, 2022). We extracted information on symptoms, behaviors, substance use, and family history of psychiatric disorders from the unstructured part of the EHR using Named Entity Recognition (NER) and Negation Detection (Hoz et al, 2022), In comparison to manual chart review of 105 patients by psychiatrists at CSJDM (our gold standard), our data extraction methods for unstructured data have recall ranging between 0.67 and 0.86 and precision ranging between 0.75 and 0.86 (Hoz et al, 2022).…”

“…We condensed use of prescription medications into five dummy variables: use of any anti-depressant, use of any anti-psychotic, use of any mood stabilizer, use of any hypnotic/anti-anxiety, and use of any hypothyroid medication, up to and including the time of the first MDD diagnosis. We focused on three symptoms/behaviors that were reliably extracted in De la Hoz et al, (Hoz et al, 2022): suicide attempt, suicidal ideation, and presence of delusions. Each was coded as a dummy variable, and recorded presence/absence of these symptoms/behaviors at any point up to and including the time of the first MDD diagnosis.…”

“…EHR data have been available since 2005, and treatment is available to all residents regardless of insurance status (Song et al, 2022). We previously validated information related to diagnoses in the records and established a Natural Language Processing (NLP) pipeline for the reliable and precise extraction of symptoms and behaviors from the clinical notes (Hoz et al, 2022). We further showed how the longitudinal EHR data including diagnoses and clinical features can be used to delineate psychiatric patient trajectories and to study factors associated with diagnostic stability.…”