Implementing Precision Psychiatry: A Systematic Review of Individualized Prediction Models for Clinical Practice

Abstract

Background The impact of precision psychiatry for clinical practice has not been systematically appraised. This study aims to provide a comprehensive review of validated prediction models to estimate the individual risk of being affected with a condition (diagnostic), developing outcomes (prognostic), or responding to treatments (predictive) in mental disorders. Methods PRISMA/RIGHT/CHARMS-compliant systematic review of the Web of Science, Cochrane Central Register of Reviews, and Ovid/PsycINFO databases from inception until July 21, 2019 (PROSPERO CRD42019155713) to identify diagnostic/prognostic/predictive prediction studies that reported individualized estimates in psychiatry and that were internally or externally validated or implemented. Random effect meta-regression analyses addressed the impact of several factors on the accuracy of prediction models. Findings Literature search identified 584 prediction modeling studies, of which 89 were included. 10.4% of the total studies included prediction models internally validated (n = 61), 4.6% models externally validated (n = 27), and 0.2% (n = 1) models considered for implementation. Across validated prediction modeling studies (n = 88), 18.2% were diagnostic, 68.2% prognostic, and 13.6% predictive. The most frequently investigated condition was psychosis (36.4%), and the most frequently employed predictors clinical (69.5%). Unimodal compared to multimodal models (β = .29, P = .03) and diagnostic compared to prognostic (β = .84, p < .0001) and predictive (β = .87, P = .002) models were associated with increased accuracy. Interpretation To date, several validated prediction models are available to support the diagnosis and prognosis of psychiatric conditions, in particular, psychosis, or to predict treatment response. Advancements of knowledge are limited by the lack of implementation research in real-world clinical practice. A new generation of implementation research is required to address this translational gap.

Prospective Long-Term Cohort Study of Subjects With First-Episode Psychosis Examining Eight Major Outcome Domains and Their Predictors: Study Protocol

“…Moreover, health care providers and policy makers are increasingly recommending the use of prediction models within clinical practice guidelines to inform decision making at various stages of the clinical pathway. However, advances of knowledge are limited by the lack of implementation research in real-world clinical practice (82). Characterizing the long-term outcomes of psychotic disorders and identifying their baseline and clinical pathways represent crucial steps enabling risk-stratification and personalized, riskadapted treatment.…”

Preventive psychiatry: a blueprint for improving the mental health of young people

“…Despite these progresses, prognostic accuracy for most of these models is not sufficient to prove clinical utility and implementability across different scenarios 239 . In fact, a systematic review has found that only about 5% of the total pool of risk prediction models published in psychiatry is externally validated, and that only 0.2% are being considered for implementation (most models may not cross the implementation threshold, as they would not improve outcomes), highlighting a profound replication and translational gap 240 . For example, across all prognostic models reviewed in Table 5, only the transdiagnostic risk calculator has been piloted for real-world implementation in clinical practice 241 .…”

Machine learning model to predict mental health crisis from electronic health records

“…Yet, the rising demand for mental healthcare is increasingly prompting hospitals to actively work on identifying novel methods for anticipating demand and better deploying their limited resources to improve patient outcomes and decrease long-term costs 7,40 . Evaluating the technical feasibility and the clinical usefulness are inevitable steps to be made before integrating prediction models into care 28 . Along this vision, our study paves the way towards a more optimised allocation of the mental healthcare staff as well as towards an enablement of a long awaited shift in the mental health paradigm -from reactive care (delivered in the Emergency Room) to preventative care (delivered in the community).…”

“…In this regard, little is yet known about the feasibility of querying machine learning models continuously to estimate an imminent risk of mental health crisis, which would be a key enabler for improving triage processes, for optimising healthcare staff allocation and for preventing crisis onsets. Furthermore, even a highly accurate predictive model does not guarantee the improvement of mental health outcomes and saving long-term costs 25,26 -whether predictive technologies would provide a useful tool to the practitioners in the mental healthcare practice remain unanswered to date 27,28 .…”