Development and validation of prediction algorithms for major depressive episode in the general population

Abstract

More studies are needed to further validate and refine these algorithms. However, the ability of a small number of easily assessed variables to predict MDE risk indicates that algorithms are a promising strategy for identifying individuals in need of enhanced monitoring and preventive interventions. Ultimately, application of algorithms may lead to increased personalization of treatment, and better clinical outcomes.

A prediction algorithm for first onset of major depression in the general population: development and validation

“…However, the questions can be easily incorporated into clinical practice, population health surveys and mental health surveillance systems. Once the computerised version becomes available, it will not take a significant amount of time to answer the questions and calculate the risk in office setting and by self-assessment 26. Finally, the algorithm was developed with the US general population data.…”

“…Well-known examples include the Framingham risk prediction algorithms for cardiovascular disease22 and prediction algorithms for cancer risk 23 24. Risk prediction models can also be used for population uses, including the prediction of the number of new cases of disease in populations and the estimation of the potential benefit of preventive interventions implemented community-wide 25 26. Finally, risk prediction models can be used for self-assessments so that individuals can monitor their own risk over time.…”

Multiple risk factors predict recurrence of major depressive disorder in women

“…Several recent studies have investigated multivariate prediction algorithms for MD onset (King, et al, 2008; Wang, et al, 2013), MD treatment resistance (Perils, 2013), suicide (Kessler, et al, 2015; Tran, et al, 2014), and persistence and severity of course of MD (van Loo, et al, 2014; Wardenaar, et al, 2014). One study developed a multivariate prediction model for recurrence of MD, which resulted in an algorithm with 19 unique factors and a C-statistics of 0.72 in independent test data (Wang, et al, 2014).…”

The Effects of an E-Mental Health Program and Job Coaching on the Risk of Major Depression and Productivity in Canadian Male Workers: Protocol for a Randomized Controlled Trial

“…The proposed trial will target Canadian male workers who are aged 18 years or older, are working for pay at the time of recruitment, and at the time of recruitment and baseline assessment, are not experiencing a MDE, but have a high risk of having MDE based on our prediction algorithm. Since it was found that 20% of Canadian adult men had a probability of 6.51% or higher in terms of the predicted MDE risk [13], for the proposed study, a personalized risk (or probability) of 6.51% or higher will be defined as high risk for men. In addition, the trial will target workers who may have had MDE in the past 12 months, but are in remission for at least 2 months prior to the study, have no language barriers to English or French, have access to the Internet for personal use, and can provide email and mailing addresses.…”

“…The program was designed to be used by working men who don’t have MDE, but are at high risk determined by a multivariable risk prediction algorithm [13]. The development of BroHealth was informed by the results of a national survey in the target population, about high risk men’s preferences for the design features of e-mental health programs [12].…”