נדב רפופורט

The standard of care for a physician to review laboratory tests results is to weigh each individual laboratory test result and compare it to against a standard reference range. Such a method of scanning can lead to missing high-level information. Different methods have tried to overcome a part of the problem by creating new types of reference values. This research proposes looking at test scores in a higher dimension space. And using machine learning approach, determine whether a subject has abnormal tests result that, according to current practice, would be defined as valid-and thus indicating a possible disease or illness. To determine health status, we look both at a disease-specific level and disease-independent level, while looking at several different outcomes.