Informatics can provide insight into how how to use information technology to improve health and is a critical foundation of any learning health system or network by enabling all phases of the learning cycle (P-D, D-K, K-P).
Artificial intelligence and data can be transformed into knowledge using digital technology, advanced data science, and analytic techniques, which stakeholders across the healthcare delivery ecosystem can apply to improve outcomes, lower costs, increase safety, and promote access to high-quality services.
The U-M Medical School Department of Learning Health Sciences boasts strong faculty expertise across a wide range of informatics and AI methods and applications, whose work is supported by competitive research funding from NIH, PCORI and NSF. The department's informatics and AI faculty collaborate with Michigan Medicine and clinical departments across the medical school to develop infrastructure and support for research, learning, and health improvement activities across the health system and the state.
Additionally, our faculty offer courses in informatics and data science related topics as part of the Health Infrastructures and Learning Systems (HILS) Programs, and provide training and mentorship to graduate and post-doctoral trainees.
Areas of specific expertise include:
- Natural Language Processing
- Clinical data analysis
- Real-World Evidence generation
- Clinical decision support
- Computational phenotyping
- Precision feedback
- Informatics tools to support clinical and translational research
- Network-based research
- Patient Registries
- Knowledge representation and ontologies
- Data exchange and transmissions standards
- Mobilizing Computable Biomedical Knowledge
The AI for Global Health Research Group led by Akbar K. Waljee, MD, MSc focuses on leveraging data science innovations to improve health outcomes in resource-constrained settings.
Faculty, staff, and research fellows in this group employ novel machine leaning techniques to develop AI-enabled decision support systems and tools to facilitate more personalized care for disease management and healthcare utilization. The ultimate goal is to deliver more efficient, effective, and equitable care both domestically and globally.
Led by Rachel Richesson, RN, MS, PhD, FACMI the Clinical and research Data Quality and Standardization Research Group focuses on development of infrastructure and methods that standardize approaches for accessing and using clinical data. This methods includes looking at data from Electronic Health Record (EHR) Systems, for observational and regulated research and clinical interventions, including Clinical Decision Support (CDS).
Dr. Richesson is an expert in Clinical Research Informatics and editor of Springer Clinical Research Informatics. Staff and students in her lab develop and apply methods for: computational phenotyping, network-based research and patient registries, Real-World Evidence generation, knowledge representation and ontologies, and data harmonization and standardization.
The DISPLAY Lab is led by Professor Zach Landis-Lewis, whose research focuses on software-based tools for coaching and appreciation feedback in health systems.
DISPLAY Lab’s projects are organized around the development and evaluation of a precision feedback system called SCAFFOLD (Scalable Coaching and Appreciation Feedback For Optimal Learning and Decision-making). The lab’s projects span clinical settings and levels of the health system (individual, team, and organizational), and incorporate methods from biomedical informatics, implementation science, and human-centered design.
The NLP4Health Research Group led by Professor V.G.Vinod Vydiswaran focuses on health care research involving natural language processing (NLP) and AI over clinical documentation, EHRs, and social media.
Dr. Vydiswaran's current research encompasses developing and evaluating novel NLP and AI approaches including large language models, neural and federated networks, information extraction pipelines, and ethical and trustworthy AI to address various health informatics challenges. Dr. Vydiswaran mentors graduate students from the Medical School and the School of Information, as well as postdoctoral researchers and undergraduate students.
TIERRA, led by Jodyn Platt, MPH, PhD, aims to lead research and best practices on issues at the intersection of public trust and health information technologies.
With the growing influence of clinical AI and machine learning in healthcare operations, as well as the increasing complexity of public health and bioethical issues, TIERRA conducts research and investigates policy and practice options to promote responsible AI.
TIERRA was established in 2024 in partnership with the Department of Learning Health Sciences and the Institute of Healthcare Policy and Innovation (IHPI).
