Explainable AI in Healthcare and Medicine

When AI is used in healthcare, a prediction is only part of the story: clinicians, patients, and caregivers also need to understand how a system reached its conclusion. Explainable AI in Healthcare and Medicine brings that challenge into focus through research on transparency, interpretability, and real-world applications across health and medicine.

Making healthcare AI easier to examine

Edited by Arash Shaban-Nejad, Martin Michalowski, and David L. Buckeridge, this collection gathers revised papers from the 2020 International Workshop on Health Intelligence. Its central concern is how computational models can contribute to health decisions while making their reasoning more understandable and accountable.

From clinical records to patient-facing applications

The research ranges across patient similarity and clinical time-series analysis, medical imaging, electronic health records, and physician–patient conversations. Individual studies address subjects such as Parkinson’s disease staging, personalized control for type 1 diabetes, mental-stress identification, and the extraction of medication information from conversations. Together, these examples show the variety of data and tasks involved in digital and clinical health intelligence.

Interpretability is part of the healthcare problem

Alongside methods and applications, the volume considers the issues and challenges that arise when AI systems are used in medicine and public health. Its emphasis on explainable and interpretable models connects technical research with broader questions of transparency and accountability—important considerations in settings where model outputs may inform diagnosis, treatment, or intervention.

Who will find it relevant?

This research-focused collection is suited to scientists, students, health and data professionals, and readers working in public health, clinical informatics, or digital and precision medicine. The range of contributions offers multiple points of entry for readers exploring how AI methods are being investigated across healthcare—not a single step-by-step guide or one unified technical approach.

For readers interested in both the promise of healthcare AI and the need to make its decisions more legible, this volume offers a wide-ranging view of the field’s research questions and applications.