Stanford Center for Biomedical Informatics Research
Dr. Morteza Noshad received his Ph.D. in computer science from the University of Michigan in 2019 where he investigated information theoretic methods to machine learning and deep learning. He then joined Stanford as a postdoctoral research fellow at Jonathan Chen’s lab and is currently a research scientist. His research interests include applying machine learning and deep learning methods to improve medical decision-making and health-care processes.
SAGE Project: Prediction of Specialty Diagnostic Procedures for the Patients with Cognitive Impairment Diseases Using Deep Representation Learning of Electronic Health Record
Dementia is one of the major causes of mortality and morbidity in older people worldwide. However, dementia and mild cognitive impairment (MCI) are under-diagnosed. Early detection of cognitive decline may be critical to the efforts to stop dementia progression, including Alzheimer’s disease (AD) and AD-related dementias (ADRD). Early and accurate diagnosis of such diseases can be addressed by proposing new tools and models based on the patients’ medical records. In this project we use deep representation learning of the electronic health records (EHR) to predict patients who are likely to have early symptoms of cognitive impairment related diseases and need referral to specialists for further assessment as well as recommending the necessary specialty diagnostic procedures for these patients.