Longitudinal evolution of the transdiagnostic prodrome to severe mental disorders: a dynamic temporal network analysis informed by natural language processing and electronic health records

Abstract

ABSTRACTImportanceModelling the prodrome to severe mental disorders (SMD), including unipolar mood disorders (UMD), bipolar mood disorders (BMD) and psychotic disorders (PSY), should consider both the evolution and interactions of symptoms and substance use (prodromal features) over time. Temporal network analysis can detect causal dependence between and within prodromal features by representing prodromal features as nodes, with their connections (edges) indicating the likelihood of one feature preceding the other. In SMD, node centrality could reveal insights into important prodromal features and potential intervention targets. Community analysis can identify commonly occurring feature groups to define SMD at-risk states.ObjectiveTo develop a global transdiagnostic SMD network of the temporal relationships between prodromal features, and to examine within-group differences with sub-networks specific to UMD, BMD and PSYDesignRetrospective (2-year), real-world, electronic health records (EHR) cohort study. Validated natural language processing algorithms extracted the occurrence of 61 prodromal features every three months from two years to six months prior to SMD onset. To construct temporal networks of prodromal features, we employed generalized vector autoregression panel analysis, adjusting for covariates.SettingSouth London and Maudsley NHS Foundation Trust EHRs.Participants7,049 individuals with an SMD diagnosis (UMD:2,306; BMD:817; PSY:3,926).Main OutcomesEdge weights (correlation coefficients,z) in autocorrelative, unidirectional and bidirectional relationships. Centrality was calculated as the sum of connections leaving (out-centrality,cout) or entering (in-centrality,cin) a node. The three sub-networks (UMD, BMD, PSY) were compared using permutation analysis. Community analysis was performed using Spinglass.ResultsThe SMD network was characterised by unidirectional positive relationships, with aggression (cout=.082) and tearfulness (cin=.124) as the most central features. The PSY sub-network showed few significant differences compared to UMD (3.9%) and BMD (1.6%), and UMD-BMD showed even fewer (0.4%). Two positive psychotic (delusional thinking-hallucinations-paranoia, and aggression-agitation-hostility) and one depressive community (guilt-poor insight-tearfulness) were the most common.Conclusions and RelevanceThis study represents the most extensive temporal network analysis conducted on the longitudinal interplay of SMD prodromal features. These findings provide further evidence to support transdiagnostic early detection services across SMD, refine assessments to detect individuals at risk and identify central features as potential intervention targets.Key Points CountQuestionHow does the dynamic evolution of the prodrome differ across severe mental disorder (SMD) diagnostic groups (unipolar mood disorders, bipolar mood disorders and psychotic disorders) in secondary mental healthcare?FindingsThis large temporal network analysis study (n=7,049) highlights a transdiagnostic overlap in the pattern of progression of prodromal symptoms of different SMD diagnostic groups in secondary mental healthcare.MeaningTransdiagnostic early detection services for SMD may be beneficial in extending the benefits of preventive psychiatry. We have identified prodromal symptoms that are central to SMD onset, which could be useful targets for preventive interventions to disrupt the progression of SMD.