Replicating prediction algorithms for hospitalization and corticosteroid use in patients with inflammatory bowel disease

Machine Learning-based Characterization of Longitudinal Health Care Utilization Among Patients With Inflammatory Bowel Diseases

BACKGROUND

Inflammatory bowel disease (IBD) is associated with increased health care utilization. Forecasting of high resource utilizers could improve resource allocation. In this study, we aimed to develop machine learning models (1) to cluster patients according to clinical utilization patterns and (2) to predict longitudinal utilization patterns based on readily available baseline clinical characteristics.

METHODS

We conducted a retrospective study of adults with IBD at 2 academic centers between 2015 and 2021. Outcomes included different clinical encounters, new prescriptions of corticosteroids, and initiation of biologic therapy. Machine learning models were developed to characterize health care utilization. Poisson regression compared frequencies of clinical encounters.

RESULTS

A total of 1174 IBD patients were followed for more than 5673 12-month observational windows. The clustering method separated patients according to low, medium, and high resource utilizers. In Poisson regression models, compared with low resource utilizers, moderate and high resource utilizers had significantly higher rates of each encounter type. Comparing moderate and high resource utilizers, the latter had greater utilization of each encounter type, except for telephone encounters and biologic therapy initiation. Machine learning models predicted longitudinal health care utilization with 81% to 85% accuracy (area under the receiver operating characteristic curve 0.84-0.90); these were superior to ordinal regression and random choice methods.

CONCLUSION

Machine learning models were able to cluster individuals according to relative health care resource utilization and to accurately predict longitudinal resource utilization using baseline clinical factors. Integration of such models into the electronic medical records could provide a powerful semiautomated tool to guide patient risk assessment, targeted care coordination, and more efficient resource allocation.

Machine learning-based feature selection to search stable microbial biomarkers: application to inflammatory bowel disease

BACKGROUND

Biomarker discovery exploiting feature importance of machine learning has risen recently in the microbiome landscape with its high predictive performance in several disease states. To have a concrete selection among a high number of features, recursive feature elimination (RFE) has been widely used in the bioinformatics field. However, machine learning-based RFE has factors that decrease the stability of feature selection. In this article, we suggested methods to improve stability while sustaining performance.

RESULTS

We exploited the abundance matrices of the gut microbiome (283 taxa at species level and 220 at genus level) to classify between patients with inflammatory bowel disease (IBD) and healthy control (1,569 samples). We found that applying an already published data transformation before RFE improves feature stability significantly. Moreover, we performed an in-depth evaluation of different variants of the data transformation and identify those that demonstrate better improvement in stability while not sacrificing classification performance. To ensure a robust comparison, we evaluated stability using various similarity metrics, distances, the common number of features, and the ability to filter out noise features. We were able to confirm that the mapping by the Bray-Curtis similarity matrix before RFE consistently improves the stability while maintaining good performance. Multilayer perceptron algorithm exhibited the highest performance among 8 different machine learning algorithms when a large number of features (a few hundred) were considered based on the best performance across 100 bootstrapped internal test sets. Conversely, when utilizing only a limited number of biomarkers as a trade-off between optimal performance and method generalizability, the random forest algorithm demonstrated the best performance. Using the optimal pipeline we developed, we identified 14 biomarkers for IBD at the species level and analyzed their roles using Shapley additive explanations.

CONCLUSION

Taken together, our work not only showed how to improve biomarker discovery in the metataxonomic field without sacrificing classification performance but also provided useful insights for future comparative studies.

Artificial intelligence in gastroenterology and hepatology: how to advance clinical practice while ensuring health equity

Artificial intelligence (AI) and machine learning (ML) systems are increasingly used in medicine to improve clinical decision-making and healthcare delivery. In gastroenterology and hepatology, studies have explored a myriad of opportunities for AI/ML applications which are already making the transition to bedside. Despite these advances, there is a risk that biases and health inequities can be introduced or exacerbated by these technologies. If unrecognised, these technologies could generate or worsen systematic racial, ethnic and sex disparities when deployed on a large scale. There are several mechanisms through which AI/ML could contribute to health inequities in gastroenterology and hepatology, including diagnosis of oesophageal cancer, management of inflammatory bowel disease (IBD), liver transplantation, colorectal cancer screening and many others. This review adapts a framework for ethical AI/ML development and application to gastroenterology and hepatology such that clinical practice is advanced while minimising bias and optimising health equity.