Disease prediction has recently received a lot of attention as a result of the increasing availability of electronic medical records (EMRs), which require an accurate classifier to map the input prediction signals (e.g., symptoms, patient demographics, etc.) to the estimated diseases for each patient. Existing machine learningbased algorithms, on the other hand, rely heavily on huge amounts of manually tagged EMR training data to produce sufficient prediction results, which limits their applicability in the case of rare illnesses with little data. The bare minimum of EMR data for each unusual disease is insufficient to allow a model to distinguish it from other diseases with similar clinical symptoms. By aggregating information, the proposed neural network encoder may successfully build embeddings that encapsulate knowledge from both data sources.
₹10000 (INR)
NON IEEE -2022