Accurately Predicting Bipolar Disorder Mood Outcomes

Abstract

Background Successful use of health information to monitor mental health treatment outcomes will require understanding which patient information is needed in electronic format and is feasible to obtain in routine care. Objective To examine whether bipolar disorder outcomes can be accurately predicted using information of limited clinical detail but feasible to collect electronically. Research Design, Data Sources and Subjects Longitudinal study of bipolar disorder patients treated 2000–2004 in the 19-site Systematic Treatment Enhancement Program for Bipolar Disorder observational study arm (N=3,168). Clinical data were obtained at baseline and quarterly over one year. We fit a “gold-standard” longitudinal random-effects regression model using detailed clinical information and estimated the area under the ROC curve (AUC) to predict accuracy. The model was then modified to include patient characteristics feasible in routinely collected electronic data (such as in administrative data).We compared the AUCs for the “limited-detail” and gold-standard models using the full sample and clinical subgroups. Measure Remission, defined as a Montgomery-Asberg Depression Rating Scale score<5 and a Young Mania Rating Scale score<4. Results The gold-standard models had baseline AUC of 0.91 ([95% CI=0.89–0.93]) and 0.89[0.86–0.92] at one-year follow-up. The limited-detail models had similar predictive accuracies (all AUC ≥ 0.89). Both the gold-standard and limited-detail models performed well and similarly in predicting remission rates at one year. Conclusions Predicting bipolar disorder remission is feasible and accurate, even using data of limited clinical detail that are feasible to gather in routine care.

Systematic literature review on patterns of pharmacological treatment and adherence among patients with bipolar disorder type I in the USA

“…Since nonadherence has been related to worse clinical outcomes and higher costs in patients with BD-I, 25 , 27 , 28 , 40 , 49 , 50 it is evident that there is a need to improve adherence rates in these patients.…”

Control charts for monitoring mood stability as a predictor of severe episodes in patients with bipolar disorder

“…It is likely that taking them into account when applying control chart methodology could have resulted in a larger PPV. Busch et al ( 2012 ) investigated the prediction accuracy for remission of random effect regression models fitted to mood scores obtained through the Montgomery-Asberg Depression Rating Scale and Young Mania Rating Scale at quarterly time points over a year. They found that prediction models that include more complete medical information have a good prediction accuracy, which is higher than those models including limited information with non-significantly different accuracy in the longer term.…”

“…Prediction models for episodes have so far considered covariates correlated with symptom severity, treatment complexity, or remission to predict long-term outcomes (Busch et al 2012 ). However, variability between severe episodes has not been considered as a potential predictor.…”

Predictive modeling in e-mental health: A common language framework

“… 4 Kessing (1999) ICD-10 Depression rating Relapse risk, suicide risk Cox-regression The risk of relapse is significantly related to the severity of baseline and post-treatment depression. 4 Busch et al (2012) Demographics, medication, clinical data Predict one year follow up outcome Hierarchical logistic regression The outcome of bipolar clients at one year follow up is predicted using clinical data. 4 Farren and McElroy (2010) Demographics, previous drinking characteristics, comorbidity Alcoholic relapse risk Logistic regression Relapse after 3 or 6 months of clients with alcohol-dependence and depression or bipolar disorder.…”