I had a blood clot. An AI diagnosis may have saved my life | Gleb Tsipursky
TL;DR
Gleb Tsipursky describes how five days of calf pain and swelling, first treated as a muscle issue, were flagged by his personal AI health tool as possible deep vein thrombosis. The tool pointed him to the key diagnostic step: an ultrasound. Instead of waiting through slower primary care or urgent care routes, he went to the emergency room. Doctors found four blood clots in his left leg. Tsipursky stresses that AI did not treat him, but helped him ask the right question before the risk became fatal.
Nauti's Take
This is the kind of AI story worth taking seriously: not machine beats doctor, but software helps a patient avoid explaining away a dangerous signal. Still, the piece sits close to personal product logic, because Tsipursky used his own tool and professionally works in AI adoption.
The strong point remains: better medicine does not need fewer doctors, it needs fewer blind spots between symptoms, scheduling pathways and diagnostics.
Briefingshow
The case exposes a real gap in healthcare: dangerous patterns can look like ordinary symptoms, and patients often have to navigate fragmented systems on their own. AI can help as a second layer of scrutiny, but only if it is framed as a tool for better questions, better records and faster escalation, not as an oracle.
Sources