Medical AI in plain language, with the error bars left in.
Each post takes one decision from inside a chest X-ray model and turns it into the question a hospital, a regulator, or a patient should be asking.
The instrument · what "99% accurate" means on your patients
Read the postEvery alarm a screening tool raises is either a real case or a false one. The split depends less on the model than on how rare the disease is among the people screened. Move the sliders.
Screen 100,000 people at this rate. About 3 have the disease. The tool flags 1,003: 3 real, 1,000 false alarms.
At this sensitivity it misses almost no one who is sick.
Real cases caught = rate × sensitivity. False alarms = everyone else × (1 − specificity). The share of alarms that are real is the positive predictive value. Rates from CDC (US, 2025) and WHO (global, 2024).
Uncertain Terms takes the decisions inside medical AI and translates them into questions a hospital administrator, a regulator, a legislator or a patient can ask. It argues that the rules should require a model to say how sure it is and to admit the limits of what it has seen.
Writing
Sources at the bottom of every post; what I'm unsure about in the margin.
Podcast
Ten to twelve minutes, one voice, one question per episode.
Why this exists
When I first applied one of my models to chest X-rays from a hospital that had never been used in training, the accuracy dropped from above 99% to somewhere in the sixties. There were two columns of data in a spreadsheet. The first column was like something a vendor might put on a brochure. The second column was like a coin that has been slightly tilted.
After this there was a long discussion about which column to use for the paper. Both were true. The 99% was the model on data similar to the data that it had been trained on. The sixties number was the performance of the model on strangers. The conclusion I came to was that a hospital only ever meets strangers.
Contact
Questions from a hospital, a newsroom, a classroom, or a legislator's office are welcome. If a post gets something wrong, say so; corrections are noted in place with a date.
Guests and press
Guest requests for the podcast (clinicians, regulators, and people who buy these tools for a living) are especially welcome. Episodes are one question long.
Based in Coral Springs, Florida. Research at Florida Atlantic University, Boca Raton.