Presenter Information

Theodore WeberFollow

Presentation Title

Designing Personalized Models to Identify the Optimal Timing for Intervention Delivery to Facilitate Smoking Cessation

Presentation Type

Oral Presentation

Abstract

Mobile health (mHealth) technology refers to the use of mobile and wearable devices for addressing health-related challenges. Such technology shows tremendous potential to support various health care needs including addiction prevention. Tobacco addiction is one of the most challenging behavioral health problems today, with a successful cessation rates remaining in the single digits. Designing effective cessation strategy has received attention from the research community where the focus has been on understanding challenges pertaining to cessation and identifying factors contributing to lapse. Advances in wearable technology enable researchers to collect a wealth of sensor data from smokers in their natural environment. This presents an unique opportunity to design models capable of identifying when users are susceptible to lapse in near real-time, allowing us to deliver intervention just-in-time. Some of the key challenges faced when designing such models include high data volumes, data diversity, and the need for personalization. In this presentation we will discuss strategies to address these challenges in practice, and approaches to investigate the efficacy of these models in the field. We will also discuss the impact of using mHealth technology for addiction prevention, and how our models could be generalized to provide support for other behavioral health problems such as eating disorders and drug addiction.

Start Date

10-5-2018 2:30 PM

This document is currently not available here.

Share

COinS
 
May 10th, 2:30 PM

Designing Personalized Models to Identify the Optimal Timing for Intervention Delivery to Facilitate Smoking Cessation

Mobile health (mHealth) technology refers to the use of mobile and wearable devices for addressing health-related challenges. Such technology shows tremendous potential to support various health care needs including addiction prevention. Tobacco addiction is one of the most challenging behavioral health problems today, with a successful cessation rates remaining in the single digits. Designing effective cessation strategy has received attention from the research community where the focus has been on understanding challenges pertaining to cessation and identifying factors contributing to lapse. Advances in wearable technology enable researchers to collect a wealth of sensor data from smokers in their natural environment. This presents an unique opportunity to design models capable of identifying when users are susceptible to lapse in near real-time, allowing us to deliver intervention just-in-time. Some of the key challenges faced when designing such models include high data volumes, data diversity, and the need for personalization. In this presentation we will discuss strategies to address these challenges in practice, and approaches to investigate the efficacy of these models in the field. We will also discuss the impact of using mHealth technology for addiction prevention, and how our models could be generalized to provide support for other behavioral health problems such as eating disorders and drug addiction.