Sensing Technologies for Maternal Depression Treatment in Low-Resource Settings

Overview

In certain low- and middle- income country settings, there is a disproportionate level of untreated postpartum depression that presents both acute and long-term risks to a mother's well-being. Although there is increasing willingness among health systems to involve non-specialists, such as community health workers, in the delivery of psychosocial interventions for postpartum depression, the effectiveness of these interventions has been mixed. The incorporation of digital technology, though, has the potential to improve the effectiveness of non-specialist-delivered interventions. The goal of this clinical trial is to evaluate the acceptability and clinical efficacy of the StandStrong intervention- a non-specialist, passive sensing technology-informed (i.e., digital) mental health intervention- as compared to a standard non-specialist mental health intervention among postpartum-depressed mothers in Nepal. Successful completion of the trial will contribute to the optimization of psychosocial intervention delivery for the postpartum context in low- and middle-income country settings.

Among certain low- and middle- income countries, there is a disproportionate level of untreated postpartum depression that presents both acute and long-term risks to a mother's well-being and her child's survival, health, and development. Although there is increasing willingness among health systems to involve non-specialists, such as community health workers, in the delivery of psychosocial interventions for postpartum depression, the outcomes of these interventions have been mixed. Digital technology, specifically the use of passive sensing data collection to quantitatively asses a mother's health and monitor behavior change, has the potential to improve the effectiveness of non-specialist-delivered interventions. Per this clinical trial, our research team will expand upon previous pilot work and evaluate the StandStrong intervention, a passive sensing technology-informed intervention adapted for postpartum depression. StandStrong- a passive sensing technology platform that consists of passive sensors (i.e., smartphone and GPS beacon), a passive sensing data visualization application, and a passive data analysis engine based in a modern machine-learning approach- transmits passive sensing data from a given mother and her infant to a trained, albeit non-specialist provider who interprets such data and then personalizes the intervention for her. Throughout the trial, the intervention within which this data will be integrated is Problem Management Plus (PM+). Validated across multiple low- and middle-income country settings, PM+ is World Health Organization-developed, five-session task-sharing intervention for mild to moderate distress. Per the (manualized) intervention, trained non-specialist providers coach eligible clients to address practical problems and/or distress in their daily lives via the use of fundamental cognitive behavioral strategies (e.g., deep breathing and stress management, behavioral activation, strengthening of social support, etc.). In particular, our team will conduct a double-arm, single-blind, individual-randomized controlled trial (RCT) that evaluates the clinical efficacy of platform-informed delivery of the intervention as compared to standard delivery of the intervention. We hypothesize that platform-informed delivery will more significantly reduce severity of symptoms- such as depression, anxiety, and quality of life- associated with postpartum depression relative to standard delivery; moreover, we imagine that platform-informed delivery will prove both cost-effective and scalable. Moreover, we will pose recommendations for platform and intervention implementation within the Nepal health system relative to the RE-AIM framework (i.e., Reach; Effectiveness; Adoption; Implementation; Maintenance). Successful completion of the trial will contribute to the optimization of psychosocial intervention delivery for the postpartum context in low- and middle-income country settings.