AI models fail when x-ray settings change
Medical AI models are passing clinical tests by reading machine settings instead of actual patient disease.
AI Spots Brain Tumor Risks From Routine Slides
High-tech cancer diagnostics are currently a luxury of the wealthiest health systems, but a shift in how we analyze basic tissue slides could soon level the playing field.
Disentangling Confounders from Pathology in Long-COVID Trajectory Prediction for Women: An Interpretable Large-Language-Model Approach
A new language model attempts to solve a major diagnostic bias by separating normal hormonal transitions from actual viral damage in women.
AI Identifies Hidden Signs of Sudden Cardiac Death
A new wave of AI models is finding invisible patterns in routine heart tests to predict sudden cardiac arrest before it strikes.
AI maps organ damage to predict hypertension risks
A new machine learning model proves that tracking silent organ damage is far more predictive of survival than standard blood pressure readings.
Danaher Acquires Masimo to Control Patient Monitoring
A life-sciences giant just bought its way from the laboratory bench directly to the hospital bedside.
AI detects early stroke on basic CT scans
A new algorithm can spot hyperacute stroke tissue changes on cheap, standard CT scans, but it struggles to map the exact boundaries of smaller lesions.
The Return of Simple Math
Clinical AI models are increasingly being outperformed by, or failing to improve upon, traditional statistical methods and established clinical formulas in critical predictive tasks.
Why pharma wants smart rings on GLP-1 patients
A new partnership between a smart ring maker and a pharmaceutical giant reveals how drugmakers are using consumer hardware to keep patients compliant.
Three flagship AI models fail breast cancer diagnosis
Hiring a commercial AI to read breast cancer biopsies does not just introduce errors; it forces clinicians to choose which specific flavor of diagnostic failure they can tolerate.