Cover image

HyFedRAG: Caching Privacy into Federated RAG

Hospital search is rarely a search problem in the clean, consumer-internet sense. The useful information is not sitting in one tidy index, wearing a name badge, waiting to be embedded. It is scattered across clinical notes, relational databases, knowledge graphs, departmental systems, hospital networks, and legal boundaries. Naturally, this is where people decide to add a large language model and call it “modernisation.” Brave. ...

September 12, 2025 · 15 min · Zelina
Cover image

Paging Dr. Model: When AI Runs the Workup

TL;DR for operators DxDirector-7B is interesting because it does not behave like a normal medical chatbot. It does not wait for a doctor to gather a neat case history and then offer a polished answer. It starts with a vague chief complaint, decides what information is missing, asks for clinical operations when necessary, and stops when it believes enough evidence exists to make a diagnosis.1 ...

August 18, 2025 · 18 min · Zelina

From Patient Messages to Clinician-Ready Intake: An AI Triage Agent for a Private Clinic

A private outpatient clinic redesigned its patient intake workflow from manual multi-channel coordination into a human-reviewed AI-agent workflow that improves intake completeness, routing discipline, and doctor preparation.

August 15, 2025 · 10 min · Vox
Cover image

Confounder Hunters: How LLM Agents are Rewriting the Rules of Causal Inference

TL;DR for operators Clinical analytics teams already know the unpleasant truth: observational data is cheap, rich, and biased in ways that do not politely announce themselves. The paper behind this article proposes a way to make that bias-hunting process less artisanal. Instead of asking experts to manually inspect every causal-tree rule, the framework lets causal trees segment patients, asks medical LLM agents to suggest plausible confounders using decomposed prompting plus retrieval, sends those suggestions through expert validation, then recursively focuses on samples whose treatment-effect estimates still have wide confidence intervals.1 ...

August 12, 2025 · 14 min · Zelina
Cover image

Twin It to Win It: How BedreFlyt Reimagines Hospital Resource Planning

TL;DR for operators Hospital bed allocation is not just “find an empty bed.” It is a rolling constraint problem: patients arrive, diagnoses imply treatment trajectories, treatment phases require different levels of care, rooms have different capacities and monitoring categories, some patients cannot share rooms, hospital policy may forbid mixed-gender rooms, and moving patients unnecessarily is bad practice. Yes, the spreadsheet is sweating. ...

May 13, 2025 · 14 min · Zelina