This research investigates how the choice of time interval affects reinforcement learning models for sepsis treatment in intensive care. By comparing one-, two-, four-, and eight-hour patient timelines, it demonstrates that shorter intervals better capture patient dynamics, improve estimated survival outcomes, and may enable more effective AI-assisted clinical decision-making.

This research examines how continuity of care at Federally Qualified Health Centers affects low-income adults as they age into Medicare eligibility. Using national Medicare and Medicaid data, it investigates whether maintaining long-term primary care relationships improves health outcomes, informing policies that strengthen community healthcare services and support healthy ageing.

This research challenges the long-standing assumption that brain regions causing no errors during awake brain surgery are functionally unimportant. By measuring subtle delays in speech rather than errors alone, it introduces causal parametric mapping, offering surgeons a more sensitive way to preserve language function and improve patient outcomes.

Dental implants restore missing teeth but face high infection rates. This research investigates zirconia crown design, bacterial leakage, and material strength. Using microscopy and mechanical testing, it identifies a three-step sealing method for implant screw access holes, reducing infection risk and improving long-term implant success and patient confidence.