Deep Neural Network for Reducing the Screening Workload in Systematic Reviews for Clinical Guidelines: Algorithm Validation Study

Abstract

Background: Performing systematic reviews is a time-consuming and resource-intensive process.

Objective: We investigated whether a machine learning system could perform systematic reviews more efficiently.

Methods: All systematic reviews and meta-analyses of interventional randomized controlled trials cited in recent clinical guidelines from the American Diabetes Association, American College of Cardiology, American Heart Association (2 guidelines), and American Stroke Association were assessed. After reproducing the primary screening data set according to the published search strategy of each, we extracted correct articles (those actually reviewed) and incorrect articles (those not reviewed) from the data set. These 2 sets of articles were used to train a neural network-based artificial intelligence engine (Concept Encoder, Fronteo Inc). The primary endpoint was work saved over sampling at 95% recall (WSS@95%).

Results: Among 145 candidate reviews of randomized controlled trials, 8 reviews fulfilled the inclusion criteria. For these 8 reviews, the machine learning system significantly reduced the literature screening workload by at least 6-fold versus that of manual screening based on WSS@95%. When machine learning was initiated using 2 correct articles that were randomly selected by a researcher, a 10-fold reduction in workload was achieved versus that of manual screening based on the WSS@95% value, with high sensitivity for eligible studies. The area under the receiver operating characteristic curve increased dramatically every time the algorithm learned a correct article.

Conclusions: Concept Encoder achieved a 10-fold reduction of the screening workload for systematic review after learning from 2 randomly selected studies on the target topic. However, few meta-analyses of randomized controlled trials were included. Concept Encoder could facilitate the acquisition of evidence for clinical guidelines.

Keywords: clinical guideline; deep learning; evidence-based medicine; machine learning; meta-analysis; neural network; systematic review.

Figure 1

Flow diagram of information processing and user interaction with Concept Encoder.

Figure 2

Literature search and study selection strategy.

Figure 3

Average cumulative recall curves for all data sets: (a) Chatterjee et al [27], (b) Balsells et al [28], (c) Muduliar et al [29], (d) Yanovski and Yanovski [30], (e) Eng et al [31], (f) McBrien et al [32], (g) Andrade Castetllanos et al [33], and (h) Arguedas et al [34]. WSS: work saved over sampling.

Figure 4

Performance for an increasing number of prioritization steps: (a) Chatterjee et al [27], (b) Balsells et al [28], (c) Muduliar et al [29], (d) Yanovski and Yanovski [30], (e) Eng et al [31], (f) McBrien et al [32], (g) Andrade Castetllanos et al [33], and (h) Arguedas et al [34]. AUROC: area under the receiver operating characteristic curve.