Active learning-based systematic reviewing using switching classification models: the case of the onset, maintenance, and relapse of depressive disorders

Jelle Jasper Teijema, Laura Hofstee, Marlies Brouwer, Jonathan de Bruin, Gerbrich Ferdinands, Jan de Boer, Pablo Vizan, Sofie van den Brand, Claudi Bockting, Rens van de Schoot, Ayoub Bagheri

Abstract: sec><title>Introduction</title><p>This study examines the performance of active learning-aided systematic reviews using a deep learning-based model compared to traditional machine learning approaches, and explores the potential benefits of model-switching strategies.</p></sec><sec><title>Methods</title><p>Comprising four parts, the study: 1) analyzes the performance and stability of active learning-aided systematic review; 2) implements a convolutional neural network classifier; 3) compares classifier and feature extractor performance; and 4) investigates the impact of model-switching strategies on review performance.</p></sec><sec><title>Results</title><p>Lighter models perform well in early simulation stages, while other models show increased performance in later stages. Model-switching strategies generally improve performance compared to using the default classification model alone.</p></sec><sec><title>Discussion</title><p>The study's findings support the use of model-switching strategies in active learning-based systematic review workflows. It is advised to begin the review with a light model, such as Naïve Bayes or logistic regression, and switch to a heavier classification model based on a heuristic rule when needed.</p></sec>