CompHealth Corner September 2026
Computational and digital health ideas evolve quickly. Our monthly research roundup highlights the latest publications — from our Center faculty and other leaders in the field. Here’s what you should be reading this month!
Can Math Help Scientists Design Smarter Cancer-fighting Cells?
Mathematical modeling and sensitivity analysis of synNotch-CAR T-cells identify engineering targets for dynamic tunability
Alexander J. Diefes, Bashir Sbaiti, Maria-Veronica Ciocanel, Cameron M. Kim. “Mathematical modeling and sensitivity analysis of synNotch-CAR T-cells identify engineering targets for dynamic tunability.” bioRxiv (2026): 2026-03.
A new Duke-led preprint, co-authored by CCDHI Associate Director of Education Cameron Kim, uses mathematical modeling to investigate synNotch-CAR T cells—engineered immune cells that can recognize specific cancer-related signals and control how they respond.
The researchers developed models of how synthetic receptors activate and regulate gene expression, then used sensitivity analysis to identify which components have the greatest influence on the cells’ behavior.
The models highlighted several promising targets for future engineering, including receptor binding and unintended activation, promoter strength, and the rates at which mRNA and CAR proteins break down.
Importantly, this work shows how mathematical modeling can help researchers decide which parts of a complex cellular system to fine-tune before moving into the laboratory. By narrowing the experimental search space, the approach could support the development of more precise, predictable, and controllable cell-based cancer therapies.
Congratulations to Cameron and the entire team on this exciting work!
Can Machine Learning Make Noninvasive Coronary Artery Assessment Faster and More Accurate
Optimizing Non-invasive Fractional Flow Reserve Estimation with Machine Learning-Enhanced 1D Hemodynamic Modeling
Cyrus Tanade, Japneet Kaur Mavi, Guinevere Ferreira, Sam Schwaller & Amanda Randles. “Optimizing Non-invasive Fractional Flow Reserve Estimation with Machine Learning-Enhanced 1D Hemodynamic Modeling: C. Tanade et al.” Cardiovascular Engineering and Technology (2026): 1-14.
A recent study published in Cardiovascular Engineering and Technology from the Randles Lab explores how machine learning and physics-based modeling can work together to improve the assessment of coronary artery disease.
Fractional flow reserve, or FFR, helps clinicians determine whether a narrowing in a coronary artery is significantly restricting blood flow. Although FFR is the clinical gold standard, measuring it typically requires an invasive pressure wire procedure. Computational models offer a noninvasive alternative, but detailed simulations can require substantial time and computing resources.
Using data from 132 patients across two medical centers, the researchers developed an efficient approach that combines one-dimensional blood flow simulations with a machine learning feedback loop. The simplified steady-state simulations closely matched more computationally demanding pulsatile models while reducing computational overhead by approximately half.
In the held out test set, machine learning refinement improved diagnostic accuracy from 77.8% to 92.6% and increased specificity from 73.3% to 100%. The greatest improvements appeared in the diagnostically challenging FFR “gray zone,” where clinical treatment decisions can be especially difficult.
Importantly, this work demonstrates how machine learning can strengthen efficient, physics-based models without sacrificing interpretability. By combining patient-specific simulations with targeted data-driven refinement, this approach could help make noninvasive cardiovascular assessment faster, more scalable, and better suited for clinical use.
Authors include Center members and alum: Cyrus Tanade, Japneet Kaur Mavi, Guinevere Ferreira, Sam Schwaller, and Amanda Randles.
What Can Online Conversations Reveal About Menopause That Clinical Records May Miss?
Divergence in Menopause Symptom Narratives Between Online and Clinical Settings
Tanya Mehta, BS; Monica Agrawal, PhD; Irene Y. Chen, PhD, Yulin Hswen, ScD, MPH. “Divergence in Menopause Symptom Narratives Between Online and Clinical Settings.” JAMA Network Open 9.7 (2026): e2623217.
A study published in JAMA Network Open, co-authored by CCDHI Co-Associate Director for AI Monica Agrawal, compares menopause experiences discussed in an online forum with those documented in electronic health records.
The researchers found that emotional well-being, cognitive concerns, and weight changes appeared more frequently in forum posts. Clinical notes more often documented hot flashes, night sweats, and treatments.
These differences matter because each source captures a different view of the menopause experience. Online patient narratives can complement clinical records, helping researchers see concerns that may receive less attention during medical visits and build a fuller picture of women’s health and aging.
