Bakr, A., Garcia-Agundez, A., Atkison, T., Rudrapatna, V. A., & Gupta, T. (2026). MEDAL: Sequential adapter learning for privacy-preserving multicenter clinical language models. Journal of Biomedical Informatics, Article 105101. https://doi.org/10.1016/j.jbi.2026.105101
Machine learning-driven spleen imaging and genomics uncover a splenic connection to coronary artery disease
Kamineni, M., Raghu, V., Hua, Z., Tian, H., Truong, B., Alaa, A., Schuermans, A., Friedman, S., Reeder, C., Bhattacharya, R., Libby, P., Ellinor, P. T., Maddah, M., Philippakis, A., Hornsby, W., Yu, Z., & Natarajan, P. (2026). Machine learning-driven spleen imaging and genomics uncover a splenic connection to coronary artery disease. Science Translational Medicine, 18(866), eaeh2517. https://doi.org/10.1126/scitranslmed.aeh2517
Investigating social bias changes in quantized large language models
Hua, S. B. Z., Lotfi, S., & Chen, I. Y. (2026). Investigating social bias changes in quantized large language models. In Proceedings of the Third Conference on Language Modeling. https://openreview.net/forum?id=sr6xTPBZ5b
Adaptive auditing of AI systems with anytime-valid guarantees
Zhou, S., Vossler, P., Sivaraman, V., Mai, Y., & Feng, J. (2026). Adaptive auditing of AI systems with anytime-valid guarantees. Advances in Neural Information Processing Systems. https://doi.org/10.48550/arXiv.2605.07002
Artificial intelligence-based speech error detection to differentiate primary progressive aphasia variants
Vonk, J. M. J., Lian, J., Kurteff, G. L., Cho, C. J., Antonicelli, G., Ezzes, Z., Wauters, L. D., Keegan-Rodewald, W., Rodriguez, D. A., Dronkers, N., Henry, M. L., Miller, Z. A., Mandelli, M. L., Anumanchipalli, G. K., & Gorno-Tempini, M. L. (2026). Artificial intelligence-based speech error detection to differentiate primary progressive aphasia variants. Brain Communications, 8(5), fcag353. https://doi.org/10.1093/braincomms/fcag353
Opportunistic Chest CT Paraspinal Muscle Biomarkers to Predict Longitudinal Thoracic Vertebral Bone Mineral Density Loss: Results from MESA
Hathaway, Q. A., Ghotbi, E., Pan, T., Momtazmanesh, S., Klein, J. G., Allison, M., Mortani Barbosa, E. J., Jr., Barr, R. G., Bluemke, D. A., Lima, J. A. C., Post, W., Tison, G. H., Ambale-Venkatesh, B., Budoff, M., & Demehri, S. (2026). Opportunistic chest CT paraspinal muscle biomarkers to predict longitudinal thoracic vertebral bone mineral density loss: Results from MESA. Radiology, 320(3). https://doi.org/10.1148/radiol.260238
Why exercise does not work equally well for everyone: Life-course conditions and the limits of precision medicine.
Horwitz, R. I., Hayes Conroy, A., Cullen, M. R., Matory, A., & Sim, I. (2026). Why exercise does not work equally well for everyone: Life-course conditions and the limits of precision medicine. The American Journal of Medicine. Advance online publication. https://doi.org/10.1016/j.amjmed.2026.08.023
Transporting a pediatric surgical site infection prediction model to the electronic health record: external validation, harmonization, and recalibration
Chan, C. T., Pletcher, M. J., Balakrishnan, K., Hswen, Y., Scheffler, A. (2026). Transporting a pediatric surgical site infection prediction model to the electronic health record: External validation, harmonization, and recalibration. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocag162
Andreas Rauschecker, MD, PhD, and Jinchi Wei Develop a Fully Automated Framework for Tumor Segmentation on Clinical Brain MRIs
CPH AGG member, Andreas Rauschecker, MD, PhD, CPH PhD student, Jinchi Wei, and collaborators, featured in UCSF News for their npj Digital Medicine study paving the way for uncertainty-aware quantitative monitoring of tumor dynamics in routine clinical care.
Mark van der Laan, PhD, and Toru Shirakawa, MD, receive $1 million to Improve Comparative Clinical Effectiveness Research
Congratulations to CPH AGG member, Mark van der Laan, PhD, CPH PhD student, Toru Shirakawa, MD, and co-investigators from the Kaiser Permanente Division of Research (DOR) for receiving funding from the Patient-Centered Outcomes Research Institute (PCORI) to improve how researchers compare the clinical effectiveness of sequential treatment decisions.
