Aquaporin-4 Genetics, Sleep, and Brain Atrophy: Untangling a New Web in Alzheimer’s Disease
Do AQP4 genetic variants and sleep disturbances interact to influence Alzheimer’s-related brain changes and cognitive decline?
Insights
Evidence-Based Clinical AI
AI, biomarkers, and older-adult care. My notes on medical AI, dementia biomarkers, frailty, and older-adult care. This section is supported by my custom AI-assisted literature surveillance workflow that helps me identify recent papers that I then review. Each item is manually curated, edited, and approved before publication. The aim is not to summarize everything. The aim is to notice what may matter clinically, what is fragile, and what still needs to prove itself in real older-adult care.
Latest insights
Machine Learning and the Problem of Nonhome Discharge After Lower Extremity Bypass
Do contemporary machine learning models improve prediction of nonhome discharge after lower extremity bypass above standard regression, and how actionable is this for perioperative care?
Emulated Trials, Latent Classes, and Causal Inference in High-Risk Coronary Revascularization
Can trial emulation using linked health data, latent class analysis, and instrumental variable methods shape better adaptive RCTs in high-risk patients poorly represented by prior trials?
Impact of LLM-Derived Linguistic Features
Does extracting structured linguistic features with large language models (LLMs) actually lead to earlier or more accurate identification of Alzheimer’s disease, and is the approach interpretable enough for clinical trust and use?
Amyloid PET in the Age of Therapy
With anti-amyloid therapies on the menu, does amyloid PET scanning deliver enough diagnostic and therapeutic precision to justify its complexity, cost, and infrastructural demands?
Who Does It Best?
When curating real-world imaging cohorts or automating radiology workflows, do large language models, rule-based systems, or radiologists produce the most accurate labels—and what hybrid mixes make sense?
When the AI Speaks
What happens—ethically and practically—when large language models start explaining clinical findings directly to patients and families, particularly in nursing-led communication?
Mechanistic Interpretability for Clinical LLMs
Can sparse autoencoders offer the kind of actionable interpretability for large language models that would make clinicians more comfortable relying on these models?
Multimodal GPT Models in Emergency Stroke Prognosis
Can the latest multimodal GPT models, used at the bedside in real time, accurately predict functional outcomes for intracerebral hemorrhage—and do their calibration and reproducibility pass muster for routine clinical decisions?