Electroconvulsive therapy (ECT) is an effective treatment for severe and refractory mood disorders such as major depressive disorder and bipolar disorder. Although success rates of this form of treatment are high there are many unknowns related to patient selection, dosing, and the duration of therapy. Current treatment approaches select patients based on subjective clinical characteristics rather than objective biological data or biomarkers. Currently, the dosing of ECT in terms of stimulus strength, number of initial treatments, and ongoing maintenance treatment is based more on historical dogma and individual physician opinion rather than scientific studies or individualized patient characteristics. Patient centered treatment informed by emerging technologies has the prospect of improving outcomes with ECT treatments and establishing precision medicine approaches for the delivery of ECT. This is possible by jointly analyzing large volumes of data relating to behavior, biology and physiology of disease and treatment outcomes.
In collaboration with a computer scientist who is an expert in Artificial Intelligence (AI), our team now has the ability to collect and analyze large amounts of physiological data (continuous measures of sleep, movement, heart rate variability, and stress levels) from patient smart watches. With probabilistic graphs, a type of AI, physiological data from smart watches can be used to 1) model the heterogeneity in treatment outcomes, 2) identify unique patient signatures to guide the initiation of ECT and, 3) to finally inform the dosing as patients progress in treatment. This pilot study will collect preliminary clinical, ecological momentary assessment and smart watch physiological information from patients undergoing acute and maintenance ECT and a comparison group. The long-term goal of this project is to identify patients that are most likely to respond to ECT based on physiological measures and to develop dosing protocols for ECT based on patient level physiological data. The smart watch used in this study is a Garmin Vivoactive 4 (https://buy.garmin.com/en-US/US/p/643382).
Aim 1: To identify correlates of remission of depressive symptoms based on a clinical measure of depression called the Quick Inventory of Depressive Symptoms with physiological measures collected from smart watches in patients undergoing ECT.
Aim 2: To monitor the trajectory of depressive symptoms and physiological data across the course of ECT treatment to develop dosing paradigms.
Aim 3: To establish a physiological signature based on smart watch data that predicts responsiveness to ECT.
Study statuses change often. Please contact us for help.