# A Wearable, Biomarker-Tracking Device Platform Using Machine Learning and Predictive Technology for Positive Behavior Change.

> **NIH NIH R43** · BEHAIVIOR INC. · 2020 · $55,000

## Abstract

Project Summary/Abstract
Behaivior is developing a patent-pending platform to predict and prevent addiction relapses and
overdoses by treating those in recovery with timely interventions using wearables (like an
advanced FitBit) and artificial intelligence. Knowing in real time when someone with opioid use
disorder is at a high risk of relapsing revolutionizes the ability to intervene at the right moment to
help people stay sober. Our research will contribute to fundamental knowledge about the
specific information needed to be gathered in order to accurately detect when someone
struggling with opioid use disorder is in a high risk opioid craving/obsession state and enabled
the creation of a predictive model for just in time intervention. The number of deaths from opioid
overdose is increasing every day, so reducing opioid addiction relapses will save lives and
families and it will reduce rearrests, reincarcerations, and rehospitalizations. Over 23 million
Americans are addicted to drugs and alcohol, and these addictions cost the U.S. $442 billion
per year, according to the US Surgeon General’s office. The majority of treatment tools used to
keep those in recovery sober have low or mixed success rates. Many people in recovery end up
relapsing multiple times, with the heroin relapse rate around 90%. With the technology that we
are developing, Behaivior will detect if someone in recovery is in a red alert craving or
“obsession” state and then, using artificial intelligence, we will provide support in real time by
connecting someone to a support network member and/or provide a customized digital
intervention.
The broader impact/commercial potential of this I-Corps project revolves around the human
brain’s proclivity towards substances detrimental to human health and wellbeing, such as
dangerous amounts of sugar, salt, and drugs, which is causing global health and safety risks.
Inability to avoid these temptations shortens lifespans, increases healthcare costs, and strains
resources. This team uses machine learning and pattern recognition AI to identify and react to
factors that result in destructive human behaviors. While the initial focus is opioids, this
unsupervised learning AI could, in subsequent iterations, be used to identify and react to any
behavior -- such as unsafe driving, binge eating, or anger management. Helping people identify
the precursors to their behaviors could serve as a type of biofeedback that gives them and their
support networks timely and individualized insights, preventions, and interventions, resulting in
cost and health benefits across many populations.

## Key facts

- **NIH application ID:** 10085849
- **Project number:** 3R43DA046149-01S1
- **Recipient organization:** BEHAIVIOR INC.
- **Principal Investigator:** Ellie Gordon
- **Activity code:** R43 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2020
- **Award amount:** $55,000
- **Award type:** 3
- **Project period:** 2018-07-15 → 2020-06-23

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10085849

## Citation

> US National Institutes of Health, RePORTER application 10085849, A Wearable, Biomarker-Tracking Device Platform Using Machine Learning and Predictive Technology for Positive Behavior Change. (3R43DA046149-01S1). Retrieved via AI Analytics 2026-05-26 from https://api.ai-analytics.org/grant/nih/10085849. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*