Parkinson’s disease & movement disorders
We use clinical data and AI methods to study natural history, develop prediction methods, and understand access to specialty care.
Longitudinal phenotyping · Clinical trajectories
We study how Parkinson’s disease presents and changes over time through longitudinal phenotyping of clinical records and natural history cohorts. Generative AI and agentic workflows are methods we investigate to extract clinical features and reconstruct disease trajectories.
Longitudinal cohorts · Clinical outcomes
We investigate how longitudinal clinical information can help anticipate important outcomes and identify meaningful risk groups in Parkinson’s disease. Our focus is on clinically grounded questions, careful validation, and understanding uncertainty.
Health services research · Care pathways
We study who reaches Parkinson’s disease specialists, how pathways to specialty care differ, and where gaps in access arise. Our aim is to understand how the care people can reach shapes the care they receive.
Selected work related to our research, including work completed before the lab was established.
Automated extraction of longitudinal fall information from clinical narratives, connecting routine clinical records with the study of disease course.
Development and external validation of models for first and recurrent falls, examining clinical predictors, risk groups, and the added value of imaging and fluid biomarkers.
A viewpoint on how Parkinson’s care is distributed across settings, and how data and AI could help extend specialist expertise beyond specialist centers.
An analysis of fall frequency, clinical characteristics, injuries, and healthcare use by sex across Parkinson’s disease duration and stage.
A study comparing dopamine-transporter imaging and brain atrophy across α-synuclein biomarker groups to characterize biological variation in Parkinson’s disease.
A systematic review of AI methods for diagnosis and quantitative phenotyping in hyperkinetic movement disorders, examining validation, reporting, and clinical interpretability.
Clinical questions guide the methods
The Clinical Intelligence Lab is based in the Department of Biostatistics, Health Informatics and Data Sciences at the University of Cincinnati College of Medicine.
We bring clinical expertise, longitudinal health data, and AI methods together to study Parkinson’s disease and movement disorders. Our work connects electronic health records with questions studied in natural history cohorts: how disease progresses, how risk differs between people, and how care is delivered. We develop methods intended to support research across other clinical conditions.
MD, MSTR · Principal Investigator
Assistant Professor
Department of Biostatistics, Health Informatics and Data Sciences
University of Cincinnati College of Medicine
Secondary appointment: Neurology, Division of Movement Disorders
For questions about the lab, collaborations, or research opportunities, email us.
Email the labcontact@clinicalintelligencelab.com
