Comparing early signs and basic symptoms as methods for predicting psychotic relapse in clinical practice

Abstract

Background: Early signs interventions show promise but could be further developed. A recent review suggested that 'basic symptoms' should be added to conventional early signs to improve relapse prediction. This study builds on preliminary evidence that basic symptoms predict relapse and aimed to: 1. examine which phenomena participants report prior to relapse and how they describe them; 2. determine the best way of identifying pre-relapse basic symptoms; 3. assess current practice by comparing self- and casenote-reported pre-relapse experiences.

Methods: Participants with non-affective psychosis were recruited from UK mental health services. In-depth interviews (n=23), verbal checklists of basic symptoms (n=23) and casenote extracts (n=208) were analysed using directed content analysis and non-parametric statistical tests.

Results: Three-quarters of interviewees reported basic symptoms and all reported conventional early signs and 'other' pre-relapse experiences. Interviewees provided rich descriptions of basic symptoms. Verbal checklist interviews asking specifically about basic symptoms identified these experiences more readily than open questions during in-depth interviews. Only 5% of casenotes recorded basic symptoms; interviewees were 16 times more likely to report basic symptoms than their casenotes did.

Conclusions: The majority of interviewees self-reported pre-relapse basic symptoms when asked specifically about these experiences but very few casenotes reported these symptoms. Basic symptoms may be potent predictors of relapse that clinicians miss. A self-report measure would aid monitoring of basic symptoms in routine clinical practice and would facilitate a prospective investigation comparing basic symptoms and conventional early signs as predictors of relapse.

Keywords: Basic symptoms; Early signs; Psychosis; Relapse; Schizophrenia.

Fig. 1

Number of basic symptoms, early signs and ‘other’ experiences reported pre-relapse in the in-depth interview or verbal checklist (n = 23), ranked by basic symptoms.

Fig. 2

A descriptive ROC curve exploring the predictive value of different basic symptom criteria (data labels indicate threshold number of basic symptoms used to estimate sensitivity and specificity figures).