Electrodes coated with DNA could enable inexpensive tests with a long shelf-life, which could detect many diseases and be deployed in the doctor’s office or at home.

Researchers find nonclinical information in patient messages — like typos, extra white space, and colorful language — reduces the accuracy of an AI model.

Trained with a joint understanding of protein and cell behavior, the model could help with diagnosing disease and developing new drugs.

Words like “no” and “not” can cause this popular class of AI models to fail unexpectedly in high-stakes settings, such as medical diagnosis.

The model could help clinicians assess breast cancer stage and ultimately help in reducing overtreatment.

The low-cost hardware outperforms state-of-the-art versions and could someday enable an affordable, in-home device for health monitoring.

A new microscopy technique that enables high-resolution imaging could one day help doctors diagnose and treat brain tumors.

MIT CSAIL researchers develop advanced machine-learning models that outperform current methods in detecting pancreatic ductal adenocarcinoma.

The advance makes it easier to detect circulating tumor DNA in blood samples, which could enable earlier cancer diagnosis and help guide treatment.

The diagnostic, which requires only a simple urine test to read the results, could make lung cancer screening more accessible worldwide.