This article is more than 5 years old. Information may no longer be current.

Depression model quickly, accurately predicts treatment outcomes

A recently developed depression questionnaire predicted symptomatic remission after citalopram with significant accuracy, according to recent findings.

“As few as 11% to 30% of patients with depression reach remission with initial treatment, even after 8 to 12 months. One factor reducing effectiveness of treatment is the inability to personalize pharmacotherapy,” Adam Mourad Chekroud, MSc, a PhD candidate at Yale University, and colleagues wrote. “Clinicians match patients with specific antidepressants via a prolonged period of trial and error, delaying clinical improvement and increasing risks and costs of treatment. The absence of clinical prediction tools in psychiatry starkly contrasts with other areas of medicine, such as oncology, cardiology and critical care, where algorithmic models often have important roles in medical decision making, and routinely outperform judgment of individual clinicians.”

To develop an algorithm that assesses symptomatic remission from a 12-week course of citalopram, researchers used patient-reported data from individuals with depression from level 1 of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) to identify predicative variables of treatment outcomes. They used these variables to train a machine-learning model to predict clinical depression remission and externally validated the model in the escitalopram treatment group (n = 151) of an independent clinical trial.

Researchers identified 25 variables that were most predicative of treatment outcomes.

Using these variables, the model predicted outcomes in the STAR*D cohort with accuracy significantly above chance (64.6%; P < .0001).

Among the escitalopram treatment group, the model had 59.6% accuracy (P < .043).

The model also had accuracy significantly above chance in a combined escitalopram-buproprion treatment group (59.7%; P = .023), but not in a combined venlafaxine-mirtazapine group (51.4%; P = .53).

“We developed a model to predict symptomatic remission after taking citalopram, a common antidepressant, with clinical rating data. Our model performance is similar to that of calculators of disease risk, recurrence, or treatment response in various areas of medicine, including oncology and cardiovascular disease. In the context of depression, the model performs comparably to the best available biomarker — an [electroencephalogram]-based index — but is less expensive, easier to implement, and validated in large internal and external clinical trial samples (a direct comparison is not possible owing to the different patient samples),” the researchers wrote.

“These are questions any patient can fill out in 5 or 10 minutes, on any laptop or smartphone, and get a prediction immediately,” Chekroud added in a press release.

Disclosure: Chekroud reports no relevant financial disclosures. Please see the full study for a list of all authors’ relevant financial disclosures.