Two new studies from the Department of Computational Biomedicine at Cedars-Sinai are advancing what we know about using machine learning and big data to improve healthcare and medical research. Both studies were published in the peer-reviewed journal Patterns.
In the first study, Cedars-Sinai investigators applied advanced statistical techniques to analyze electronic health records from nearly 100,000 hospital stays. This approach identified drugs that were unexpectedly associated with raising or lowering blood sugar levels of hospitalized patients.
Our findings offer practical insights to help clinicians anticipate and manage medication-related blood sugar changes, ultimately improving glycemic safety for patients in hospitals."
Jesse G. Meyer, PhD, assistant professor of Computational Biomedicine at Cedars-Sinai and corresponding author of the study
In the second study, co-led by Cedars-Sinai, investigators developed a secure method to pool patient data from multiple hospitals for research studies. This method allows hospitals to send statistical summaries of their patients' characteristics, rather than the healthcare data of individuals, to a central location for analysis by investigators, reducing the risk of inadvertent disclosure of sensitive patient information.
"Our innovative approach opens the door for larger, more diverse studies that better protect patient privacy, improve research quality and support the development of more effective treatments," said Ruowang Li, PhD, assistant professor of Computational Biomedicine at Cedars-Sinai and co-corresponding author of the study.
"Both studies emphasize our unique approach to using machine learning and big data in academic medicine," said Jason Moore, PhD, professor and chair of the Department of Computational Biomedicine at Cedars-Sinai and co-corresponding author of the study. "These studies foster collaboration, ultimately leading to patient care and research that are driven by data, overcoming gaps in outcomes and creating healthier lives.".
Source:
Journal references:
- Momenzadeh, A., et al. (2025). Data-driven discovery of medication effects on blood glucose from electronic health records. Patterns. doi.org/10.1016/j.patter.2025.101312.
- Li, R., et al. (2025). A one-shot, lossless algorithm for cross-cohort learning in mixed-outcomes analysis. Patterns. doi.org/10.1016/j.patter.2025.101321.