Symptom-Diagnosis-Care: A Framework for a Collaborative Medical Chat Bot.

Medical chat bots could have the ability to deliver fast, high- quality information directly to people all over the world. A step preventing this from becoming a reality is training medical chat bots with reliable medical data. Medical books though, such as The American Medical Association Family Medical Guide, are well structured with a series of flowcharts to help users diagnose their symptoms by answering yes and no questions. In this paper we present and evaluate a tool for crowd workers to train medical chat bots using the information in books. To enable the collaboration of crowd workers, we present the symptom- diagnosis- care framework. The medical chat bot on the phone allows the information accessible to people that primarily use a mobile phone and are not medical professionals. By having the data on the phone, we are able to make the data actionable by integrating it with the computational capabilities and sensors of the phone.