Overview / Usage

The automated doctor voice prescription application has a conversation with the doctor, and the doctor provides information on a particular patient’s name, age, gender, symptoms, diagnosis, medication, and general advice. The processing of the text is done through NLP. After generating the data, a form is populated in the web client, and the input boxes are up for review and editing by the doctor (to correct any transcription errors, if they arise). After correction, the form is converted into PDF format and a link to this PDF is securely sent to the patient via WhatsApp or SMS.

Finally, the prescription PDF is stored in a database so that it can be stored, and retrieved in the future with ease.

​

Methodology / Approach

Please watch the demo video.

Technologies Used

For the front end of the web and the mobile app, React JS is used in addition to Google’s Cloud Speech (Speech to Text) API for transcriptions. As far as the backend is concerned, Node JS and Express is used and for database storing purposes Mongo DB is used.

Collaborators