Program

In-person AND virtual! – We are pioneering a new conference format that will connect in-person and virtual audiences to create a unique experience. Matching the innovation that comes through our members’ work, ISPOR is pushing the boundaries of innovation to design an event that works in today’s quickly changing environment. 

In-person registration included the full virtual experience, and virtual-only attendees will be able to tune into live in-person sessions and/or watch captured in-person sessions on-demand in addition to having a variety of virtual-only sessions to attend.

Using Artificial Intelligence Methods for Systematic Review in Health Sciences: A Systematic Review

Speaker(s)

Blaizot A1, Veettil SK1, Saidoung P2, Moreno-Garcia CF3, Wiratunga N4, Aceves-Martins M4, Lai NM5, Chaiyakunapruk N1
1University of Utah, Salt Lake City, UT, USA, 2Chiang Mai University, Chiang Mai, Thailand, 3Robert Gordon University, Aberdeen, UK, 4University of Aberdeen, Aberdeen, UK, 5Taylor’s University Malaysia, Subang Jaya, Malaysia

OBJECTIVES: The exponential increase in published articles makes a thorough and expedient review of literature increasingly challenging. Artificial Intelligent (AI) platforms have been developed to attempt to address this problem, with them progressively being incorporated into practice. This review delineated the common automated tools and platforms that employ AI approaches and evaluated the reported benefits and challenges in using such methods.

METHODS: A search was conducted in 4 databases (Medline, Embase, Cochrane database of systematic reviews, and Epistemonikos) up to April 2021 for systematic reviews and other related reviews implementing AI methods. To be included, an AI-assisted review must use any form of AI method, including machine learning, deep learning, neural network, or any other applications that are used to enable the full or semi-autonomous performance of one or more stages in the development of evidence synthesis.

RESULTS: From a total of 4911 records identified, 87 articles underwent full-text screening, and 12 reviews were included. These reviews used nine different tools to implement 15 different AI methods. Eleven methods were used in the screening stages of the review (73%). The rest were divided: two in data extraction (13%) and two in risk of bias assessment (13%). The ambiguous benefits of the data extractions, combined with the reported advantages from 10 reviews, indicate that AI platforms have taken hold with varying success in evidence synthesis. The results are qualified by the reliance on the self-reporting of the review authors.

CONCLUSIONS: Extensive human validation still appears required at this stage in the implementation of AI/ML methods, though further evaluation is required to define the overall contribution of such platforms in enhancing efficiency and quality in evidence synthesis.

Code

MSR1

Topic

Methodological & Statistical Research, Study Approaches

Topic Subcategory

Artificial Intelligence, Machine Learning, Predictive Analytics, Literature Review & Synthesis

Disease

No Additional Disease & Conditions/Specialized Treatment Areas