Recorded poor insight as a predictor of service use outcomes: cohort study of patients with first-episode psychosis in a large mental healthcare database

Abstract

ObjectivesTo investigate recorded poor insight in relation to mental health and service use outcomes in a cohort with first-episode psychosis.DesignWe developed a natural language processing algorithm to ascertain statements of poor or diminished insight and tested this in a cohort of patients with first-episode psychosis.SettingThe clinical record text at the South London and Maudsley National Health Service Trust in the UK was used.ParticipantsWe applied the algorithm to characterise a cohort of 2026 patients with first-episode psychosis attending an early intervention service.Primary and secondary outcome measuresRecorded poor insight within 1 month of registration was investigated in relation to (1) incidence of psychiatric hospitalisation, (2) odds of legally enforced hospitalisation, (3) number of days spent as a mental health inpatient and (4) number of different antipsychotic agents prescribed; outcomes were measured over varying follow-up periods from 12 months to 60 months, adjusting for a range of sociodemographic and clinical covariates.ResultsRecorded poor insight, present in 46% of the sample, was positively associated with ages 16-35, bipolar disorder and history of cannabis use and negatively associated with White ethnicity and depression. It was significantly associated with higher levels of all four outcomes over all five follow-up periods.ConclusionsRecorded poor insight in people with recent onset psychosis predicted subsequent legally enforced hospitalisations and higher number of hospital admissions, number of unique antipsychotics prescribed and days spent hospitalised. Improving insight might benefit patients’ course of illness as well as reduce mental health service use.

Gender differences in clinical presentation and illicit substance use during first episode psychosis: a natural language processing, electronic case register study

“…The final sample comprised 3350 patients of predominantly male gender (n=2077, 62%). Median (IQR) age was 24 (20)(21)(22)(23)(24)(25)(26)(27)(28)(29). White (n=1037), black-other (n=847) and black-Caribbean (n=635) were the most frequently represented ethnic groups.…”

“…24 These techniques use machine learning to learn from human-annotated examples and are able to navigate term negation (eg, 'No thought disorder elicited') and mentions irrelevant to that which is being measured (eg, 'His father has thought disorder'). This approach has previously been used to investigate transdiagnostic risk for psychosis, 25 the association of negative symptoms with antipsychotic treatment failure, 26 poor insight as a predictor of service use outcomes 27 and the association of cannabis use with hospital admissions 28 in people with psychotic disorders. Our sample of 3350 patients represents the largest known sample in this field to date.…”

Introspective accuracy for substance use across a year of treatment for first episode psychosis

“…However, some research suggests an insight paradox, wherein better insight is associated with worse outcomes. For example, better insight is linked to greater depression ( Lysaker et al, 2007 ; Ramu et al, 2019 ; Tariku et al, 2019 ), but this is inconsistently observed ( Arraras et al, 2019 ; Konsztowicz and Lepage, 2019 ). Relatedly, increased suicidality and attempts are sometimes ( Ozturk et al, 2018 ; Villa et al, 2018 ), but not always ( Ayesa-Arriola et al, 2018 ) associated with better insight.…”

Stages of recovery in psychosis: Converging qualitative research and psychoanalysis

“…Awareness of illness as a predictor of a more favorable outcome in first‐episode psychosis has been evaluated in research studies 32,33 . Moreover, the significance of relationships and mental differentiation in the early stages of recovery was recently supported by research findings by Bourdeau et al 16 who followed 49 patients with early psychosis and found a very significant increase in social engagement, narrative development, and occupation between the moratorium and awareness stages of recovery.…”