Project Overview

A major challenge in using Biometric monitoring technologies (BioMeTs) data is the lack of time- and cost-efficient strategies to analyze a large amount of data to understand the state of patients. Machine learning, artificial intelligence, and data mining are rapidly expanding and evolving and could hold promise to bridge this gap. As evidenced by a growing list of DiMe’s Crowdsourced Library of Digital Endpoints in Industry-Sponsored Studies, there is a growing need for a standardized methodology for analyzing digital measures to predict individualized patient outcomes in clinical trials.

Project Goal

The goal of this project is to develop standardized statistical approaches to analyze and interpret large amounts of data generated by BioMeTs. By bringing together expertise from data science, biostatistics, bioengineering, regulatory, clinical development, and patient advocacy, we aim to develop a framework for analyzing and interpreting digital measures using current trends in machine learning and data mining technologies.

This workgroup is already in progress. Please check back for updates, and if you have your own idea for a project you can submit it here.

Already a member? Login 

Not yet a member? Become a Member

Project Overview

Previous work by DiMe included the establishment of the V3 (verification, analytical validation, and clinical validation) framework. While this work has been the leading guideline for the evaluation of BioMeTs, it was not originally scoped to include the evaluation of usability and utility of biometric monitoring technologies (BioMeTs). A BioMeT may perform well under V3, but is useless if it cannot be used appropriately by the target population in the anticipated setting [1]. There is currently no standardized framework for usability and user testing/reporting of BioMeTs. This project will involve extending the V3 framework to include usability, utility, and user experience testing of BioMeTs.

Project Goal

The purpose of this study is to incorporate guidelines on usability and user experience testing in order to extend the original V3 framework. Building upon previous work by DiMe, this group will define best practices for usability, utility, and user experience testing of BioMeTs. Analysis of guidelines in adjacent fields and discussion will be a large component of this project, which will conclude with a published manuscript. Team members with experience in usability, utility, and user testing of BioMeTs are especially encouraged to join! 

This workgroup is already in progress. Please check back for updates, and if you have your own idea for a project you can submit it here.

Already a member? Login 

Not yet a member? Become a Member

Project Overview

Some evidence quality considerations are unique to, or more relevant for, digital health (DH) interventions. For example, poor user experiences in DH interventions can cause attrition of all but the most motivated patients, and paradoxically skew poor DH interventions toward favorable per-protocol results. This and similar issues may receive inadequate attention. Moreover, best practices for DH evidence assessment should be dynamic, to keep pace with rapid changes in digital health. The 2011 CONSORT-eHealth checklist does not address many common issues in DH evidence assessment. More than 45 DH assessment frameworks are available; however, to our knowledge, none thoroughly address critical issues in DH evidence quality. We will therefore develop an evidence assessment checklist to supplement–not replace–existing frameworks for evidence assessment in digital health.

Project Goals

The goal of this initiative is to develop a checklist of key evidence assessment considerations that may receive inadequate attention in DH. The scope will be limited to evidence quality criteria that are unique to, or may arise more commonly, in evidence pertaining to digital health interventions (relative to evidence pertaining to drugs or other modalities). The checklist will be designed to supplement–not replace–existing frameworks for assessment in digital health. Living systematic review methodologies will be adapted to create an agile process for updating this checklist as the DH landscape evolves.

This workgroup is already in progress. Please check back for updates, and if you have your own idea for a project you can submit it here.

Already a member? Login 

Not yet a member? Become a Member

Project Overview

Despite a growing body of evidence that light exposure is an important predictor of health and could be a promising target for interventions, there are few standards for light exposure studies conducted in free-living individuals. Applying the V3 framework to light monitoring technologies will support rigorous science into healthy light, and enable light-sensing technologies to be embedded in the clinical trials.

Project Goal

The goal of this project is to apply the V3 framework to light sensing technologies and evaluate whether and to what extent they are currently fit for being included into clinical trials. We will develop a road map to lay out steps needed to achieve verification, analytical and clinical validation of light as a meaningful biometric monitoring technologies (BioMets). We will also showcase studies to illustrate the need and usefulness of V3 for light exposure monitoring. Together, this manuscript will outline a clear path forward towards fit for purpose light sensing to improve patient and population health.

This workgroup is already in progress. Please check back for updates, and if you have your own idea for a project you can submit it here.

Already a member? Login 

Not yet a member? Become a Member

Project Overview

There is a growing availability and penetration of smartphones and other digital health technologies, such as wearables, available to consumers. We can leverage this technology to capture patient-generated health data (PGHD) and harness real-life, real-time data about study participants, whilst allowing them to use technologies they are already familiar with and can be more compliant to. Bring Your Own Device (BYOD) models have the potential to improve efficiency and diversity in clinical trials, enhance patient centricity, and facilitate hybrid and decentralized clinical trials. This project aims to bring together expertise from various stakeholders to develop a framework that facilitates the deployment of BYOD models in clinical studies.

Project Goal

The goal of this project is to discuss methodological considerations, including regulatory, technological, operational, and ethical aspects, to the deployment of BYOD models. The framework will address study design, informed consent, endpoint selection, data management strategies, and statistical approaches to BYOD data, to ensure compliance with regulatory requirements.

This workgroup is already in progress. Please check back for updates, and if you have your own idea for a project you can submit it here.

Project Overview

While digital medicine has gained traction in many healthcare settings globally, little is known about assessing the right digital medicine technology for low-resource settings, strategies to implement them and finally providing tools to evaluate their impact in real-life scenarios. Through this project, we would like to draw on real-life examples of designing, implementing, and evaluating digital medicine products for low-resource settings.

Project Goal

“The overarching objective is to provide strategies and tools for effective implementation of digital medicine in low-resource settings. Goals to reach this objective will include-
a. Complete a systematic review of digital medicine interventions in low-resource settings
b. Seek inputs from digital medicine entrepreneurs and researchers working in the field
c. Gather real-world insights and build the strategy-tool base”

This workgroup is already in progress. Please check back for updates, and if you have your own idea for a project you can submit it here.

Already a member? Login 

Not yet a member? Become a Member

PROJECT OVERVIEW

The use of digital medicine tools in clinical research has become increasingly common in recent years, a trend that has continued during the COVID-19 pandemic as investigators look for efficient ways to conduct research in remote settings.  Alongside the many advantages of this new research paradigm, there are important challenges associated with selecting and utilizing digital medicine tools appropriately while maintaining scientific rigor.  The digital medicine field today is reminiscent of the field of laboratory assay based biomarkers twenty years ago.  Many elements of the “fit-for-purpose” concept developed for laboratory assay based biomarkers can be extended and applied to digitally-measured biomarkers. 

The goal of this research project was to summarize historical perspectives and lessons learned from the early days of the laboratory-lab biomarker field, highlighting the commonalities to digitally-measured biomarkers as well as areas in which the two modalities differ.  The resulting manuscript contains several recommendations for future considerations, which we consider to be critical to the appropriate adoption of scalable digital medicine solutions. The manuscript “Fit‐for‐Purpose Biometric Monitoring Technologies (BioMeT): Leveraging the Laboratory Biomarker Experience” was peer-reviewed and published in the Clinical and Translational Science journal in August 2020.

PROJECT CONTRIBUTORS

Project Lead: Elena S. Izmailova;  First Authors: Alan Godfrey, Benjamin Vandendriessche Contributors: Jessie P. Bakker, Cheryl Fitzer-Attas, Ninad Gujar, Matthew Hobbs, Qi Liu, Carrie A Northcott, Virginia Parks, William A Wood, Vadim Zipunnikov, John A. Wagner

INTERESTED IN PARTICIPATING?

Already a member? Login 

Not yet a member? Become a Member

Project Overview:

Suboptimal adherence to data collection procedures or a study intervention is often the cause of a failed clinical trial. Data from connected sensors, including wearables, referred to here as biometric monitoring technologies (BioMeTs), are capable of capturing adherence to both digital therapeutics and digital data collection procedures, thereby providing the opportunity to identify the determinants of adherence and thereafter, methods to maximize adherence.

The goal of this project was to describe the methods and definitions by which adherence has been captured and reported using BioMeTs in recent years, identify key gaps, and make recommendations regarding minimum reporting requirements and consistency of definitions for BioMeT-based adherence data. The manuscript “Recommendations for Defining and Reporting Adherence Measured by Biometric Monitoring Technologies: Systematic Review” was peer-reviewed and published in the Journal of Medical Internet Research in April 2022.

Project Contributors:

Project Lead: Jessie P Bakker; Contributors: Iredia M Olaye, Mia P Belovsky, Lauren Bataille, Royce Cheng, Ali Ciger, Karen L Fortuna, Elena S Izmailova, Debbe McCall, Christopher J Miller, Willie Muehlhausen, Carrie A Northcott, Isaac R Rodriguez-Chavez, Abhishek Pratap, Benjamin Vandendriessche, Yaara Zisman-Ilani