A Risk Calculator to Predict the Individual Risk of Conversion From Subthreshold Bipolar Symptoms to Bipolar Disorder I or II in Youth

Abstract

Objective: Youth with subthreshold mania are at elevated risk of conversion to bipolar disorder (BP) I/II. Predictors for conversion have been published for the group as a whole. However, risk factors are heterogeneous, indicating the need for personalized risk assessment. Method: 140 BP Not-Otherwise-Specified (BP-NOS) youths (6–17 years old) followed through the Course and Outcome of Bipolar Youth (COBY) study with at least one follow-up assessment prior to conversion to BP-I/II were included. Youths were assessed on average every 7 months for a median of 11.5 years using standard instruments. Risk predictors reported in the literature were utilized to build a 5-year risk calculator. Discrimination was measured using the time-dependent area under the curve (AUC) after 1000 bootstrap resamples. Calibration was evaluated comparing observed vs. predicted probability of conversion. External validation was performed using an independent sample of 58 BP-NOS youths recruited from the Pittsburgh Bipolar Offspring Study. Results: Seventy-five (53.6%) COBY BP-NOS youths converted to BP-I/II, of which 57 (76.0%) converted within 5 years. Earlier-onset BP-NOS, familial hypomania/mania, and high mania, anxiety, and mood lability symptoms were important predictors of conversion. The calculator showed excellent consistency between the predicted/observed risks of conversion, good discrimination between converters/non-converters (AUC: 0.71, CI: 0.67–0.74), and a proportionally increasing rate of converters at each successive risk class. Discrimination in the external validation sample was good (AUC: 0.75). Conclusion: If replicated, the risk calculator provides a useful tool to predict personalized risk of conversion from subsyndromal mania to BP-I/II and inform individualized interventions and research.

Machine learning and big data analytics in bipolar disorder: A position paper from the International Society for Bipolar Disorders Big Data Task Force

“…Authors found an AUC of 0.76 by using Cox proportional hazards regression. Another similar study built a risk calculator to predict the individual risk of transition from subthreshold bipolar symptoms to bipolar I or II in youth and reported an AUC of 0.71 …”

Identifying Adolescents at Risk for Depression: A Prediction Score Performance in Cohorts Based in 3 Different Continents

“…4,6 Up to now, the majority of psychiatric composite prognostic models studies have focused on model development, with very few being adequately validated in independent samples. [13][14][15] In contrast to other areas of medicine, where hard outcomes are more easily defined, imprecise characterization of psychiatric outcomes imposes additional barriers for accurate prognostic model development and validation, as reliability of common mental disorders such as depression has been shown to be low. 16 Substantial heterogeneity in clinical presentation and high rate of comorbidity produce additional obstacles for prediction of psychiatric disorders, as different assessment strategies influence the likelihood of endorsing a diagnosis.…”

Risk Calculators in Bipolar Disorder: A Systematic Review

“…After the full-text review, only three studies met the eligibility criteria for inclusion in this systematic review. One study was from China [27] and the other two were from the United States of America [18,28]. In Figure 1, the PRISMA flow diagram is presented, providing more detailed information regarding the selection process.…”

“…Risk calculators are clinical instruments developed based on the data available for a particular disease, identifying the ideal set of clinical factors that makes it possible to estimate the likelihood that an individual will develop a specific condition in the future. [18] They make it possible to derive the risk forecast for an individual, using a multivariate model based on the disease's progression in a large sample of patients. Through imputation, calculators can accommodate incomplete information about risk indicators, complementing the traditional clinical assessment.…”

“…All studies were evaluated as being of good quality, although all three present a risk of significant selection bias, since the sample is obtained from selected groups. In another study from the same group, Birmaher et al recruited youths with BP N Specified (BP-NOS) from the Course and Outcome of Bipolar Youth (COBY) study an risk calculator of conversion to BP-I or II [18]. This model is based on ten demograp variables (mania, depression, anxiety, emotional lability, functioning, duration of ill gender, and family history), with an AUC of 0.71.…”