Differential diagnosis feature engineering for machine learning applications
Abstract:
Methods and systems for improved preparing of received data using differential diagnosis for analysis by machine learning models. In one embodiment, a method is provided that includes receiving an identifier of an event. A plurality of inquiries may be sequentially processed, and subsequent inquiries for processing may be selected based on the responses to earlier inquiries. A tensor may be used to store indications of which inquiries were processed and the responses received to the inquiries. A machine learning model may use the tensor to determine a diagnosis and whether the event is an emergency event requiring intervention. If the event is an emergency event, an intervention may be generated for the emergency event, which may include a computer system taking automatic action to respond to the emergency event.
Information query
Patent Agency Ranking
0/0