Technology and Machine-Learning Enabled Systematic Reviews: How Can They Be Leveraged to Support Global Health Technology Assessments?

Author(s)

Moderator: Chris G. Cameron, MSc, PhD, Data Analytics and Evidence Synthesis, EVERSANA, Sydney, NS, Canada
Panelists: Candyce Hamel, MPH, Canadian Association of Radiologists, Ottawa, ON, Canada; Brian Hutton, Ph.D., School of Epidemiology, Public Health and Preventive Medicine, University of Ottawa, Ottawa, ON, Canada; Ian Stefanison, BS, Evidence Partners, Ottawa, ON, Canada

ISSUE: There have been significant advances in technology and machine learning methods to support systematic reviews. Indeed, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) for reporting systematic reviews has recognized the application of automation tools within their recently updated 2020 updated guideline. However, many health technology assessment (HTA) agencies have not yet issued formal guidance around the application and use of technology and machine-learning applications to support systematic reviews in submissions and technology appraisals. In the absence of such guidance, it is unclear whether use of emerging technologies and machine learning applications to support systematic reviews will be accepted by global HTA bodies. There is an urgent need to explore this issue from a multi-stakeholder perspective.

OVERVIEW: This panel will debate whether technology and machine-learning enabled systematic reviews can meet the evidence requirements of global HTA bodies. Dr. Chris Cameron will moderate the panel and provide an overview of the current landscape of technology and machine-learning applications, as well as HTA requirements on systematic reviews to support global HTA submissions. He will also pose key questions for the panelists to debate, including:

  • What are the opportunities with leveraging technology and machine-learning enabled systematic reviews for HTA submissions?
  • What are the challenges with leveraging technology and machine-learning enabled systematic reviews for HTA submissions?
  • Why might technology and machine-learning enabled systematic reviews be acceptable for publications, but not be considered well suited for HTA submissions?
  • Which technology and machine-learning methods are most acceptable from an HTA perspective?
International experts will each describe their unique perspective from technology/ML developer, HTA and academic perspective on technology and machine-learning enabled systematic reviews in support of HTA submissions. Target stakeholders include HTA agencies, academics, patient advocacy organizations, and pharma/biotech manufacturers.

Conference/Value in Health Info

2022-05, ISPOR 2022, Washington, DC, USA

Code

224

Topic

Health Technology Assessment

Explore Related HEOR by Topic


Your browser is out-of-date

ISPOR recommends that you update your browser for more security, speed and the best experience on ispor.org. Update my browser now

×