But for every textbook case, there were a hundred ambiguous ones. Patients who were tall, but not that tall. Patients with long fingers, but no family history. Patients who walked out of her clinic with a diagnosis of "maybe" and a return ticket for an echocardiogram six months later.
She called it the Marfan Calculator.
"One day," she typed, "someone will build a tool that learns from every misdiagnosis, every dissection, every mother's phone call. It will not be perfect. But it will be humble." marfan calculator
One evening, frustrated by a borderline case—a fifteen-year-old boy named Eli who had the arm span of a pro athlete but none of the aortic dilation—Lena started scribbling on the back of a prescription pad. She wasn't designing a test. She was designing a filter . But for every textbook case, there were a
The "maybe" was what kept her up at night. Patients who walked out of her clinic with
It wasn't AI. It wasn't even particularly sophisticated. It was a weighted algorithm that took twenty-three physical markers—from wrist sign (the thumb and pinky overlapping around the wrist) to the ratio of upper to lower body segment, from lens dislocation to a family history of pneumothorax. Each marker had a value. Each value fed into a probability curve.
Below it, a sentence: "Elevated probability of systemic features. Recommend genetic sequencing for FBN1."