Brain response to emotional faces in anxiety and depression: neural predictors of cognitive behavioral therapy outcome and predictor-based subgroups following therapy

Cross-trial prediction of depression remission using problem-solving therapy: A machine learning approach

BACKGROUND

Psychotherapy is a standard depression treatment; however, determining a patient's prognosis with therapy relies on clinical judgment that is subject to trial-and-error and provider variability.

PURPOSE

To develop machine learning (ML) algorithms to predict depression remission for patients undergoing 6 months of problem-solving therapy (PST).

METHOD

Using data from the treatment arm of 2 randomized trials, ML models were trained and validated on ENGAGE-2 (ClinicalTrials.gov, #NCT03841682) and tested on RAINBOW (ClinicalTrials.gov, #NCT02246413) for predictions at baseline and at 2-months. Primary outcome was depression remission using the Depression Symptom Checklist (SCL-20) score < 0.5 at 6 months. Predictor variables included baseline characteristics (sociodemographic, behavioral, clinical, psychosocial) and intervention engagement through 2-months.

RESULTS

Of the 26 candidate variables, 8 for baseline and 11 for 2-months were predictive of depression remission, and used to train the models. The best-performing model predicted remission with an accuracy significantly greater than chance in internal validation using the ENGAGE-2 cohort, at baseline [72.6% (SD = 3.6%), p < 0.0001] and at 2-months [72.3% (5.1%), p < 0.0001], and in external validation with the RAINBOW cohort at baseline [58.3% (0%), p < 0.0001] and at 2-months [62.3% (0%), p < 0.0001]. Model-agnostic explanations highlighted key predictors of depression remission at the cohort and patient levels, including female sex, lower self-reported sleep disturbance, lower sleep-related impairment, and lower negative problem orientation.

CONCLUSIONS

ML models using clinical and patient-reported data can predict depression remission for patients undergoing PST, affording opportunities for prospective identification of likely responders, and for developing personalized early treatment optimization along the patient care trajectory.

Network Diffusion Embedding Reveals Transdiagnostic Subnetwork Disruption and Potential Treatment Targets in Internalizing Psychopathologies

Network diffusion models are a common and powerful way to study the propagation of information through a complex system and they offer straightforward approaches for studying multimodal brain network data. We developed an analytic framework to identify brain subnetworks with perturbed information diffusion capacity using the structural basis that best maps to resting state functional connectivity and applied it towards a heterogeneous dataset of internalizing psychopathologies (IPs), a set of psychiatric conditions in which similar brain network deficits are found across the swath of the disorders, but a unifying neuropathological substrate for transdiagnostic symptom expression is currently unknown. This research provides preliminary evidence of a transdiagnostic brain subnetwork deficit characterized by information diffusion impairment of the right area 8BM, a key brain region involved in organizing a broad spectrum of cognitive tasks, which may underlie previously reported dysfunction of multiple brain circuits in the IPs. We also demonstrate that models of neuromodulation involving targeting this brain region normalize IP diffusion dynamics towards those of healthy controls. These analyses provide a framework for multimodal methods that identify both brain subnetworks with disrupted information diffusion and potential targets of these subnetworks for therapeutic neuromodulatory intervention based on previously well-characterized methodology.