Machine Learning and Large Language Models (LLMs) for Healthcare Analytics

Dear Colleagues,

Machine learning and large language models (LLMs) are rapidly transforming healthcare analytics, enabling new approaches to clinical decision support, risk prediction, and multimodal data integration. From structured electronic health records to clinical text, imaging, and physiological signals, these methods offer new opportunities to extract actionable insights and improve patient outcomes.

Despite these advances, growing evidence suggests that current models often fail in critical aspects of clinical reasoning, particularly in complex, multi-step decision processes and real-world clinical scenarios. Traditional evaluation metrics such as accuracy may obscure important limitations related to robustness, generalization, and interpretability. In addition, the increasing use of LLM-based agents introduces new challenges in evaluating system-level behavior, coordination, and reliability.

This Special Issue aims to advance both the development and rigorous evaluation of machine learning- and LLM-based systems in healthcare analytics. We place particular emphasis on understanding model behavior, identifying limitations, and developing methods that are reliable, interpretable, and clinically meaningful.

We explicitly welcome rigorous studies reporting negative results, including well-designed analyses of model failures, limitations, and boundary conditions in realistic healthcare settings. Such contributions are essential for advancing the field in a transparent and scientifically grounded manner.

Topics of interest:

• Reasoning and evaluation of LLMs in healthcare.
• Failure analysis and limitations (including negative results).
• Data representation and multimodal challenges (e.g., tabular-to-text, missing data, clinical text structuring, 2D/3D medical imaging, and physiological signals).
• Automated evaluation and real-world deployment considerations (e.g., reliability, efficiency, drift, and system integration).

Dr. Roni Ramon-Gonen
Dr. Haya Engelstein
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the Special Issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Computation is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.