Health AI
Ambient Documentation Tools in the Exam Room: Promise, Limits and Consent
Ambient tools that draft clinical notes from a recorded conversation can reduce typing, but they add questions about accuracy, consent and review.
Latest
Medical Devices
AI-Enabled Imaging Devices: What Regulatory Clearance Does and Does Not Tell You
A regulatory listing for an AI imaging tool shows it was reviewed for a defined use, which is not the same as proof it works in every hospital.
Digital Health
See all →
Securing Hospital Data: A Practical Review of the Basics That Still Fail
Hospital cyberattacks often exploit ordinary weaknesses such as weak access control, unpatched systems and untested backups.
FHIR Explained for Hospital Teams: What the Standard Does and Does Not Solve
HL7 FHIR gives health systems a common way to exchange data, but agreeing on a format does not by itself make records meaningful across systems.
Choosing a Telehealth Platform: Six Questions Beyond the Video Call
A telehealth platform is more than video, and the questions that decide success are about integration, access and operations.
Medical Devices
See all →AI-Enabled Imaging Devices: What Regulatory Clearance Does and Does Not Tell You
A regulatory listing for an AI imaging tool shows it was reviewed for a defined use, which is not the same as proof it works in every hospital.
How Regulators Treat Software in Medical Devices: Intended Use Comes First
Whether software counts as a regulated medical device depends mainly on what the manufacturer says it is for, not on how the product is built.
Continuous Glucose Monitors Beyond Diabetes: Reading the Evidence Carefully
Continuous glucose monitors are established tools for diabetes care, while their use by people without diabetes rests on far thinner evidence.
Health AI
See all →Ambient Documentation Tools in the Exam Room: Promise, Limits and Consent
Ambient tools that draft clinical notes from a recorded conversation can reduce typing, but they add questions about accuracy, consent and review.
Hospital Risk Scores and the Alert Problem: Why Good Predictions Still Get Ignored
Early-warning models for hospital patients only help if the alerts they raise fit into how nurses and physicians actually work.
Bias Audits for Clinical Algorithms: What a Useful Review Includes
A useful bias audit compares model performance across patient groups and checks what the model was trained to predict.