The adoption of machine learning (ML) and, more specifically, deep learning (DL) applications into all major areas of our lives is underway. The development of trustworthy AI is especially important in healthcare due to the large implications for patients’ lives. In comparison, trustworthiness concerns various aspects, including ethics, transparency, and safety requirements. One of the most critical parts of an AI is the quality of its input data since it has a fundamental impact on the resulting system. It lays the foundation and inherently provides limitations for the AI application. However, both AI researchers and practitioners overwhelmingly concentrate on models/algorithms while undervaluing data quality. This workshop aims to unite leaders, practitioners, and researchers to explore and discuss novel solutions, the latest techniques, best practices, and future directions for developing high-performance and trustworthy AI systems for healthcare from a data quality perspective.

Submission Guidelines

We invite submissions that contribute to foundational theory, novel methodologies, and practical applications within the field of Data Quality Aware, High-Performance, and Trustworthy AI Systems for Healthcare. Submissions can take the form of:

• Research papers should be between four and eight pages, including references, figures, and all other content. Submissions must contain original work not previously published or under consideration elsewhere. Papers that introduce novel technological solutions (including early and in-progress work) and vision or position papers outlining emerging challenges and gaps in the field are encouraged. Accepted research papers will be presented orally and included in the workshop proceedings, archived in the ACM Digital Library.
• Posters limited to two pages, plus references, and may describe early-stage work or work in progress. Posters will be presented as posters and published on the workshop website.
• Demo proposals should describe a technology or system and outline how it will be demonstrated at the workshop. They are limited to one page, plus references.

List of Topics

• Data quality frameworks in healthcare.
• Data quality assessment and improvement.
• Data-centric AI approaches for healthcare.
• Task-driven data quality assurance for healthcare AI.
• Multi-modal and multi-source data fusion in healthcare.
• Hallucination and bias mitigation in LLMs for healthcare applications.
• Demographic bias in training datasets for healthcare datasets.
• Seamless (“zero-click”) integration of healthcare imaging AI in physicians’ workflow.
• The role of standards for input and output of healthcare AI.
• Methodologies to investigate the effect data quality has on medical AI system characteristics.
• Techniques to validate the trustworthiness of AI in healthcare.
• Privacy-preserving AI techniques for healthcare.
• Methods to improve transparency and explainability of LLMs in healthcare applications.
• Large language models for high-quality synthetic health data generation.
• Human-in-the-loop systems for data quality control.
• Case studies of data-quality-aware AI in healthcare.
• Evaluating the capacity of large language models for different healthcare applications.
• Retrieval-augmented generation for high-performance and trustworthy healthcare AI.
• Ethical and social implications of AI in healthcare.
• Addressing bias mitigation and fairness of AI in healthcare.
• Use of AI (XAI) techniques to promote trust of AI in healthcare.

Committees

Program Committee

• TBD

Organizing committee

• Dr. Haihua Chen, Department of Information Science, University of North Texas, USA
• Dr. Ana D. Cleveland, Department of Information Science, University of North Texas, USA
• Dr. Daniel Schwabe, Department of Medical Physics and Metrological Information Technology, Physikalisch-Technische Bundesanstalt (PTB), Germany
• Dr. Sagnik Ray Choudhury, Department of Computer Science and Engineering, University of North Texas, USA
• Herman Oosterwijk, President and Principal Consultant, OTConsulting Inc., USA

Invited Speakers

• TBD

Publication

Submissions should follow the ACM conference proceedings format. All submissions will undergo a peer-review process, and accepted papers will be included in the workshop proceedings.

Venue

The workshop Data Quality Aware, High-Performance, and Trustworthy AI Systems for Healthcare will be held in conjunction with IEEE/ACM CHASE 2025, Manhattan, New York City, USA.

Contact

All questions about submissions should be emailed to Dr. Haihua Chen (haihua.chen@unt.edu)