Ovarian cancer kills more than 184,000 women worldwide every year. A better way to detect early-stage cases could greatly lower that number. Mijin Kim, 32, combined machine learning with a special sensor to detect a blood-based “fingerprint” of ovarian cancer. Kim hopes the benefits of her liquid biopsy don’t end with one illness. “This method could be rapidly adapted to the detection of many conditions,” she says. “The array could be used to train an algorithm to recognize nearly any disease when given enough data from the sensor.”