Boosting efficiency in a clinical literature surveillance system with LightGBM

Given the suboptimal performance of Boolean searching to identify methodologically sound and clinically relevant studies in large bibliographic databases, exploring machine learning (ML) to efficiently classify studies is warranted. To boost the efficiency of a literature surveillance program, we used a large internationally recognized dataset of articles tagged for methodological rigor and applied an automated ML approach to train and test binary classification models to predict the probability of clinical research articles being of high methodologic quality. We trained over 12,000 models on a dataset of titles and abstracts of 97,805 articles indexed in PubMed from 2012–2018 which were manually appraised for rigor by highly trained research associates and rated for clinical relevancy by practicing clinicians. As the dataset is unbalanced, with more articles that do not meet the criteria for rigor, we used the unbalanced dataset and over- and under-sampled datasets. Models that maintained sensitivity for high rigor at 99% and maximized specificity were selected and tested in a retrospective set of 30,424 articles from 2020 and validated prospectively in a blinded study of 5253 articles. The final selected algorithm, combining a LightGBM (gradient boosting machine) model trained in each dataset, maintained high sensitivity and achieved 57% specificity in the retrospective validation test and 53% in the prospective study. The number of articles needed to read to find one that met appraisal criteria was 3.68 (95% CI 3.52 to 3.85) in the prospective study, compared with 4.63 (95% CI 4.50 to 4.77) when relying only on Boolean searching. Gradient-boosting ML models reduced the work required to classify high quality clinical research studies by 45%, improving the efficiency of literature surveillance and subsequent dissemination to clinicians and other evidence users.Author summary: With so many health-related research studies being published, it can be overwhelming to find the best ones for making healthcare decisions. For nearly 25 years, our research group has been helping by creating tools to search through these studies. Our expert team uses these tools to find and assess the most reliable and important studies for healthcare providers and patients. In this study, we used an automated machine learning technique to speed up this process and reduce the effort needed. We trained models to identify studies with strong methods using data from almost 98,000 articles. We tested over 12,000 models and chose the best one, that used a technique called LightGBM, which missed the fewest good studies. Adding this model to our process reduced our workload by 45%. This means we can now find high-quality research more quickly and efficiently, helping healthcare providers and other users get the best evidence faster.