Dataset Information

Using clinical information to make individualized prognostic predictions in people at ultra high risk for psychosis.

ABSTRACT: Recent studies have reported an association between psychopathology and subsequent clinical and functional outcomes in people at ultra-high risk (UHR) for psychosis. This has led to the suggestion that psychopathological information could be used to make prognostic predictions in this population. However, because the current literature is based on inferences at group level, the translational value of the findings for everyday clinical practice is unclear. Here we examined whether psychopathological information could be used to make individualized predictions about clinical and functional outcomes in people at UHR. Participants included 416 people at UHR followed prospectively at the Personal Assessment and Crisis Evaluation (PACE) Clinic in Melbourne, Australia. The data were analysed using Support Vector Machine (SVM), a supervised machine learning technique that allows inferences at the individual level. SVM predicted transition to psychosis with a specificity of 60.6%, a sensitivity of 68.6% and an accuracy of 64.6% (p<0.001). In addition, SVM predicted functioning with a specificity of 62.5%, a sensitivity of 62.5% and an accuracy of 62.5% (p=0.008). Prediction of transition was driven by disorder of thought content, attenuated positive symptoms and functioning, whereas functioning was best predicted by attention disturbances, anhedonia-asociality and disorder of thought content. These results indicate that psychopathological information allows individualized prognostic predictions with statistically significant accuracy. However, this level of accuracy may not be sufficient for clinical translation in real-world clinical practice. Accuracy might be improved by combining psychopathological information with other types of data using a multivariate machine learning framework.

SUBMITTER: Mechelli A

PROVIDER: S-EPMC5477095 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectivePeople at ultra-high risk (UHR) for psychosis have a high prevalence of tobacco smoking, and rates are even higher among the subgroup that later develop a psychotic disorder. However, the longitudinal relationship between the course of tobacco smoking and clinical outcomes in UHR subjects is unknown.MethodsWe investigated associations between tobacco smoking and clinical outcomes in a prospective study of UHR individuals (n = 324). Latent class mixed model analyses were used to identify trajectories of smoking severity. Mixed effects models were applied to investigate associations between smoking trajectory class and the course of attenuated psychotic symptoms (APS) and affective symptoms, as assessed using the CAARMS.ResultsWe identified four different classes of smoking trajectory: (i) Persistently High (n = 110), (ii) Decreasing (n = 29), (iii) Persistently Low (n = 165) and (iv) Increasing (n = 20). At two-year follow-up, there had been a greater increase in APS in the Persistently High class than for both the Persistently Low (ES = 9.77, SE = 4.87, p = 0.046) and Decreasing (ES = 18.18, SE = 7.61, p = 0.018) classes. There were no differences between smoking classes in the incidence of psychosis. There was a greater reduction in the severity of emotional disturbance and general symptoms in the Decreasing class than in the High (ES = -10.40, SE = 3.41, p = 0.003; ES = -22.36, SE = 10.07, p = 0.027), Increasing (ES = -11.35, SE = 4.55, p = 0.014; ES = -25.58, SE = 13.17, p = 0.050) and Low (ES = -11.38, SE = 3.29, p = 0.001; ES = -27.55, SE = 9.78, p = 0.005) classes, respectively.ConclusionsThese findings suggests that in UHR subjects persistent tobacco smoking is associated with an unfavorable course of psychotic symptoms, whereas decrease in the number of cigarettes smoked is associated with improvement in affective symptoms. Future research into smoking cessation interventions in the early stages of psychoses is required to shine light on the potential of modifying smoking behavior and its relation to clinical outcomes.

Dataset Information

Using clinical information to make individualized prognostic predictions in people at ultra high risk for psychosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets