SBIR-STTR Award

Sober Grid has built a smartphone based recovery focused social network already in use by recovering addicts and addiction treatment facilities to help users achieve better health outcomes and reduce rates of relapse The goal of this phase I SBIR study is to determine the feasibility of leveraging predictive analytics within the context of an addiction recovery focused social network to enable the system to identify users who are in need of support before they relapse The specific aim is to assess the feasibility of using predictive modeling to identify those most vulnerable to relapse in order to advance phase II efforts Sober Grid will work with a team of addiction researchers including co investigator Dr Brenda Curtis Assistant Professor at the Perlman School of Medicine at the University of Pennsylvania U Penn and consultant Dr Warren Bickel Director of Addiction Recovery Research Center and Professor of Psychiatry and Behavioral Medicine at the Virginia Tech Carilion School of Medicine and Sober Grid advisor to compile a database of known triggers e g life stressors environment life changes etc words and phrases topics and lexica associated with relapse The team will mine the data in order to identify the factors that correspond with relapse measures e g change in sobriety status content indicative of relapse etc and employ supervised learning through support vector networks with labeled data as well as unsupervised learning through support vector clustering to identify patterns indicative of relapse within our unlabeled data The team will build models on a training data set and assess them for prediction accuracy Understanding the feasibility of mobile based predictive capabilities and integrating the real time adaptive interventions proposed shows significant potential for reducing relapse rates in populations regardless of whether they have attended treatment programs These capabilities will not only increase treatment efficacy they will also help to reduce overall costs within the healthcare system including the Veteran s Administration and relieve pressure on already overburdened clinicians a significant commercial opportunity for Sober Grid Through the proposed project Sober Grid will work to improve the efficacy and efficiency of its software and smartphone application for supporting peer groups and providers delivering drug and alcohol treatment to more than million Americans who exhibit relapse rates as high as Applying predictive analytics within the context of Sober Grid s addiction recovery focused social network will enable it to modify its system to predict relapse before it occurs which will enable users and providers to realize greater treatment efficacy and health outcomes while significantly reducing costs to the system

Sober Grid™ has developed a smartphone-based mobile application currently in use by over 120,000 individuals worldwide who are in, or seeking, recovery from drug and alcohol addiction. The “Grid”, as it is known, is a mobile-based, social recovery community providing rapid context- specific peer support, efficient help seeking, motivational enhancement exercises, and member ratings of support content – all aimed to prevent relapse. The overarching goal of this phase II project is to extend the current capabilities of the Sober Grid app to achieve a comprehensive social recovery support app featuring intelligent, context appropriate resource matching and 24/7 rapid response peer-coaching that is effective in reducing disordered substance use and is cost effective. We hypothesize that providing this functionality to high-risk members will be acceptable, feasible, increase access to and engagement with resources, and have a positive effect in increasing time to relapse and days of consecutive abstinence. The company’s priority commercial goal is to leverage the insights gained from its large database of information and behaviors recorded in its existing addiction recovery-focused social network, combined with its recently completed SBIR phase I work, to identify users at risk for relapse and deliver tailored lay and professional peer support, telehealth, and provider interventions prompted by near real-time automated risk indicators built into an Enhanced Sober Grid (ESG) solution. The specific goals of this proposed phase II project include: (1) implementing the relapse risk scoring algorithm successfully developed in phase I in a production environment, (2) developing a ML resource relevancy matching algorithm, and (3) using this system to pilot test the feasibility and acceptability as well as to estimate the effect on abstinence of providing peer-coaching and resource information to a national sample of Sober Grid members in recovery from non- alcohol/nicotine substances who are predicted to be at high risk for relapse. We will accomplish our objectives by: (Aim 1) Implementing an accurate, near real-time production risk prediction system; (Aim 2) Developing an enhanced, in-app substance-addiction recovery resource locator; and, (Aim 3) Determining the feasibility, acceptability and estimating the effect size of the proposed ESG among high relapse-risk participants in recovery from opioid, stimulant, or cannabis use. The expected impact of this project is to substantially enhance Sober Grid's ability to deliver effective and timely interventions to the right individuals, at the right time – including those high-need and underserved populations that would otherwise lack access to care and draw considerable resources from the healthcare system. This capability holds the promise to reduce drug and alcohol relapse and the associated negative health impacts at both an individual and societal level while reducing the total cost of providing treatment services.

Public Health Relevance Statement:
PROJECT NARRATIVE Sober Grid is combining near real-time risk prediction with automated phone-app messaging, peer-coaching, and resource visibility and transparency in order to dramatically improve support for recovery from substance abuse. The strategy is to provide continuously available responsive connection and support with simple and familiar ways to search, filter, sort, identify, and review/rate resource options in order to lower overall relapse rates within the population, enabling Sober Grid users to achieve improved health outcomes and institutional payers to reduce the total cost of achieving those outcomes. Over time, the innovations resulting from this project will significantly reduce costs for individuals, public and private payers, the healthcare system, and society at large.

Project Terms:
Abstinence; addiction; Aftercare; Alcohol consumption; Alcohol dependence; Alcohol or Other Drugs use; alcohol relapse; Algorithms; Android; Back; base; Behavior; Behavioral; Cannabis; Caring; Cellular Phone; Characteristics; Client; Clinical; cloud based; Communities; cost; Cost Control; cost effective; Data; Databases; design; Diagnostic; disorder later incidence prevention; Drug Addiction; drug relapse; Drug usage; effective therapy; Enhancement Technology; Environment; Exercise; Foundations; Goals; Group Meetings; Health; Health Personnel; Health Services Accessibility; Healthcare Systems; help-seeking behavior; high risk; high risk population; improved; Individual; innovation; insight; Insurance; Intelligence; Intervention; Location; Machine Learning; machine learning algorithm; marijuana use; medication-assisted treatment; member; mobile application; mobile computing; Modeling; Monitor; Motivation; Natural Language Processing; new technology; Nicotine; Opiate Addiction; Opioid; opioid use; Outcome; Participant; Patients; peer; peer coaching; peer support; Personality Traits; Pharmaceutical Preparations; Phase; phase 2 study; Population; prediction algorithm; Predictive Analytics; preference; prevent; Privatization; Process; Production; Provider; provider intervention; Published Comment; Randomized; Recovery; Relapse; relapse risk; Reporting; Resources; response; Risk; Sampling; satisfaction; Services; Small Business Innovation Research Grant; sobriety; social; social media; Social Network; Social support; Societies; stimulant use; Stream; Substance abuse problem; Substance Addiction; Substance Use Disorder; success; Support Groups; Surveys; System; Technology; telehealth; Telephone; Testing; Time; tool; treatment center; Treatment Efficacy; treatment program; treatment services; Underserved Population; Work; Writing