AI in Healthcare: Navigating the Path to Responsible Innovation

Amira Soliman

Content

How can AI-driven decisions, such as diagnoses or treatment plans, be easily interpreted and trusted, helping clinicians make informed decisions and fostering greater confidence in AI technologies? Responsible AI in healthcare requires the ethical and transparent use of AI to ensure patient safety, privacy, fairness, and accountability. The poster explores the journey of integrating AI into clinical practice, covering every stage from data collection and modeling to deployment. It emphasizes the importance of recognizing and addressing potential challenges, such as data bias, model accuracy limitations, and the need for explainable AI (XAI) to foster trust in AI-driven decisions. The overarching goal is to harness AI to improve healthcare outcomes while protecting patient safety and maintaining trust throughout the process. We also explain the co-production development framework used in two ongoing projects under the CAISR Health profile.

Researchers

Farzaneh Etminani(1,4), Amira Soliman(1), Jens Nygren(2), Petra Svedberg(2), Lina Lundgren(3), Monika Nair(2), Jonas Sjöström(1), Omar Hamed(1), Björn Agvall(4), and Markus Lingman(1,4)

(1) School of Information Technology Halmstad University, Halmstad, Sweden,

(2) School of Health and Welfare, Halmstad University, Halmstad, Sweden

(3) School of Business, innovation and Sustainability, Halmstad University, Halmstad, Sweden

(4) Department of Research and Development, Region Halland, Halmstad, Sweden

Partners

Region Halland, Cambio, and Capio Ramsay Santé

Funding

The knowledge Foundation

Sjöström, Jonas, et al. "Design Principles for Machine Learning Based Clinical Decision Support Systems: A Design Science Study." International Conference on Design Science Research in Information Systems and Technology. Cham: Springer Nature Switzerland, 2024.

Nair, Monika, et al. "Machine Learning Model for Readmission Prediction of Patients With Heart Failure Based on Electronic Health Records: Protocol for a Quasi-Experimental Study for Impact Assessment." JMIR Research Protocols1 (2024): e52744.

Soliman, Amira, et al. "The price of explainability in machine learning models for 100-day readmission prediction in heart failure: retrospective, comparative, machine learning study." Journal of Medical Internet Research 25 (2023): e46934.

Hamed, Omar, Amira Soliman, and Kobra Etminani. "Temporal Context Matters: An Explainable Model for Medical Resource Utilization in Chronic Kidney Disease." MIE. 2023.

Soliman, Amira, et al. "Interdisciplinary human-centered AI for hospital readmission prediction of heart failure patients." Caring is Sharing–Exploiting the Value in Data for Health and Innovation. IOS Press, 2023. 556-560.

Contact

Amira Soliman

Senast ändrad: