The AIR·MS Data Platform for Artificial Intelligence in Healthcare
The reference architecture paper on AIR·MS has been accepted for publication by JAMIA OPEN. The platform provides unified access to clinical data from over 12 million patients treated at Mount Sinai in New York – including structured records, clinical notes, imaging metadata, and genomic information. Researchers from the U.S. and Germany use AIR·MS to build cohorts and develop AI models in a secure, high-performance environment.
ABSTRACT
Objective
To present the Artificial Intelligence-Ready Mount Sinai (AIR·MS) platform -unified access to diverse clinical datasets from the Mount Sinai Health System (MSHS), along with computational infrastructure for AI-driven research- and demonstrate its utility with three research projects.
Materials and Methods
AIR·MS integrates structured and unstructured data from multiple MSHS sources via the OMOP Common Data Model on an in-memory columnar database. Unstructured pathology and radiology data is integrated through metadata extracted from and linking the raw source data. Data access and analytics are supported from the HIPAA-compliant Azure cloud and the on-premises Minerva High-Performance Computing (HPC) environment.
Results
AIR·MS provides access to structured electronic health records, clinical notes, and metadata for pathology and radiology images, covering over 12M patients. The platform enables interactive cohort building and AI model training. Experimentation with complex cohort queries confirm a high system performance. Three use cases demonstrate, risk-factor discovery, and federated cardiovascular risk modeling.
Discussion
AIR·MS demonstrates how clinical data and infrastructure can be integrated to support large-scale AI-based research. The platform’s performance, scale, and cross-institutional design position it as a model for similar initiatives.
Conclusion
AIR·MS provides a scalable, secure, and collaborative platform for AI-enabled healthcare research on multimodal clinical data.
LAY SUMMARY
Modern hospitals collect vast amounts of patient data, including test results, doctor notes, and medical images. These are valuable for research and improving care, especially when applying artificial intelligence (AI) to uncover complex patterns. However, combining and accessing data from different hospital systems and across data types is challenging. In this paper, we present the AI-Ready Mount Sinai (AIR·MS) platform. It brings together multiple types of clinical data from the Mount Sinai Health System and makes them available securely for research. The platform includes electronic health records, clinical notes, and metadata from pathology slides and radiology images, from over 12M patients. Through the project, researchers from the US and Germany can use computing tools to explore data, build patient groups, and train AI models in a secure, privacy-protecting environment. We show how AIR·MS supports research by highlighting three projects: one that uses AI to better understand Crohn’s disease, another that identifies a possible link between menstrual pain and heart disease in women, and one that uses federated learning to improve the performance of cardiovascular risk assessment tools. By providing both the data and tools for advanced analysis, AIR·MS helps researchers uncover insights that could improve diagnosis, treatment, and care.
Complete list of authors:
- Guerrero, Pablo; Hasso-Plattner-Institut fur Digital Engineering gGmbH, Digital Global Public Health; D4L data4life gGmbH
- Ernebjerg Morten; Doctolib GmbH; D4L data4life gGmbH
- Holst, Thomas; D4L data4life gGmbH
- Weese, David; D4L data4life gGmbH
- DiBello, Herve; Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai; Icahn School of Medicine at Mount Sinai, Windreich Dept. of Artificial Intelligence and Human Health
- Ibing, Susanne; Hasso-Plattner-Institut fur Digital Engineering gGmbH, Digital Engineering Faculty, University of Potsdam; Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai; Icahn School of Medicine at Mount Sinai, Windreich Dept. of Artificial Intelligence and Human Health
- Schmidt, Linea; Hasso-Plattner-Institut fur Digital Engineering gGmbH, Digital Engineering Faculty, University of Potsdam
- Ungaro, Ryan; Icahn School of Medicine at Mount Sinai Division of Gastroenterology
- Renard, Bernhard; Hasso-Plattner-Institut fur Digital Engineering gGmbH, Digital Engineering Faculty, University of Potsdam; Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai; Icahn School of Medicine at Mount Sinai, Windreich Dept. of Artificial Intelligence and Human Health
- Lippert, Christoph; Hasso-Plattner-Institut fur Digital Engineering gGmbH, Digital Engineering Faculty, University of Potsdam; Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai; Icahn School of Medicine at Mount Sinai, Windreich Dept. of Artificial Intelligence & Human Health
- Alleva Bonomi, Eugenia Alessandra Enrica; Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai; Icahn School of Medicine at Mount Sinai, Windreich Dept. of Artificial Intelligence and Human Health
- Quinn, Timothy; Icahn School of Medicine at Mount Sinai
- Kovatch, Patricia; Icahn School of Medicine at Mount Sinai, Windreich Dept. of Artificial Intelligence and Human Health; Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai; Mount Sinai Health System, The Center of Excellence in AI and Digital Health
- Antao, Esther-Maria; Hasso-Plattner-Institut for Digital Engineering gGmbH, Digital Global Public Health
- Heyneke, Elmien; Hasso-Plattner-Institut for Digital Engineering gGmbH, Digital Global Public Health
- Rasheed, Aadil; Hasso-Plattner-Institut for Digital Engineering gGmbH, Digital Global Public Health
- Kalabakov, Stefan; Hasso-Plattner-Institut for Digital Engineering gGmbH, Digital Engineering Faculty, University of Potsdam; Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai; Icahn School of Medicine at Mount Sinai, Windreich Dept. of Artificial Intelligence and Human Health
- Arnrich, Bert; Hasso-Plattner-Institut fur Digital Engineering gGmbH, Digital Engineering Faculty, University of Potsdam
- Charney, Alexander; Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai; Icahn School of Medicine at Mount Sinai, Windreich Dept. of Artificial Intelligence and Human Health; Icahn School of Medicine at Mount Sinai, Charles Bronfman Institute for Personalized Medicine
- Wieler, Lothar; Hasso-Plattner-Institut fur Digital Engineering gGmbH, Digital Engineering Faculty, University of Potsdam; Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai; Icahn School of Medicine at Mount Sinai, Windreich Dept. of Artificial Intelligence and Human Health
- Nadkarni, Girish; Icahn School of Medicine at Mount Sinai, Hasso Plattner Institute for Digital Health at Mount Sinai; Icahn School of Medicine at Mount Sinai, Windreich Dept. of Artificial Intelligence and Human Health; Icahn School of Medicine at Mount Sinai, Charles Bronfman Institute for Personalized Medicine
