The authors developed a practical and clinically useful model to predict the risk of psychosis that utilizes clinical characteristics empirically demonstrated to be strong predictors of conversion to psychosis in clinical high-risk (CHR) individuals. The model is based upon the Structured Interview for Psychosis Risk Syndromes (SIPS) and accompanying clinical interview, and yields scores indicating one's risk of conversion.

Baseline data, including demographic and clinical characteristics measured by the SIPS, were obtained on 199 CHR individuals seeking evaluation in the early detection and intervention for mental disorders program at the New York State Psychiatric Institute at Columbia University Medical Center. Each patient was followed for up to 2 years or until they developed a syndromal DSM-4 disorder. A LASSO logistic fitting procedure was used to construct a model for conversion specifically to a psychotic disorder.

At 2 years, 64 patients (32.2%) converted to a psychotic disorder. The top five variables with relatively large standardized effect sizes included SIPS subscales of visual perceptual abnormalities, dysphoric mood, unusual thought content, disorganized communication, and violent ideation. The concordance index (c-index) was 0.73, indicating a moderately strong ability to discriminate between converters and non-converters.

The prediction model performed well in classifying converters and non-converters and revealed SIPS measures that are relatively strong predictors of conversion, comparable with the risk calculator published by NAPLS (c-index = 0.71), but requiring only a structured clinical interview. Future work will seek to externally validate the model and enhance its performance with the incorporation of relevant biomarkers.

Current ultra-high-risk (UHR) criteria appear insufficient to predict imminent onset of first-episode psychosis, as a meta-analysis showed that about 20% of patients have a psychotic outcome after 2 years. Therefore, we aimed to develop a stage-dependent predictive model in UHR individuals who were seeking help for co-morbid disorders.

Baseline data on symptomatology, and environmental and psychological factors of 185 UHR patients (aged 14–35 years) participating in the Dutch Early Detection and Intervention Evaluation study were analysed with Cox proportional hazard analyses.

At 18 months, the overall transition rate was 17.3%. The final predictor model included five variables: observed blunted affect [hazard ratio (HR) 3.39, 95% confidence interval (CI) 1.56–7.35, p < 0.001], subjective complaints of impaired motor function (HR 5.88, 95% CI 1.21–6.10, p = 0.02), beliefs about social marginalization (HR 2.76, 95% CI 1.14–6.72, p = 0.03), decline in social functioning (HR 1.10, 95% CI 1.01–1.17, p = 0.03), and distress associated with suspiciousness (HR 1.02, 95% CI 1.00–1.03, p = 0.01). The positive predictive value of the model was 80.0%. The resulting prognostic index stratified the general risk into three risk classes with significantly different survival curves. In the highest risk class, transition to psychosis emerged on average ⩾8 months earlier than in the lowest risk class.

Predicting a first-episode psychosis in help-seeking UHR patients was improved using a stage-dependent prognostic model including negative psychotic symptoms (observed flattened affect, subjective impaired motor functioning), impaired social functioning and distress associated with suspiciousness. Treatment intensity may be stratified and personalized using the risk stratification.