System and Method Using Speech-to-Text Artificial Intelligence to Transcribe a Doctor-Patient Interaction Into a Text Form

20240404526

18/733702

June 04, 2024

A system and method using speech-to-text artificial intelligence to transcribe a doctor-patient interaction into a text format. A website or application on a computer, phone, or device records an interaction. A speech-to-text artificial intelligence that will transcribe the doctor-patient interaction into a text format. After the system of the present invention has received the transcription, it will ask the doctor what sections he would like in his medical note. After a selection of the pieces of the note desired, the transcription of the recording between the doctor and patient is sent to the application server. The application server will use a large-language model AI to determine the content of any of the medical note sections. This input length is almost universally significantly shorter than the length of a standard medical interaction. The application uses three techniques to create a single note from the input.

1. A computer implemented method for using speech-to-text artificial intelligence to transcribe a doctor-patient interaction into a text format, the method comprising: running and executing an application using speech-to-text artificial intelligence to record an audible doctor-patient interaction; and running and executing an application using speech-to-text artificial intelligence to transcribe a doctor-patient interaction into a text format on an electronic device.

2. The method of claim 1, further comprising the recording steps of providing a website or application on a computer, phone, or device for recording a doctor-patient interaction; after logging in, the doctor will press “record” as he begins to interact with a patient; and the doctor's device will record the interaction.

3. The method of claim 1, further comprising the speech-to-text steps of using a speech-to-text artificial intelligence to transcribe the doctor-patient interaction into a text format; switching on and off which speech-to-text AI that it uses; and after the system of the present invention has received the transcription, it will ask the doctor what sections he would like in his medical note.

4. The method of claim 3, wherein the sections include: Chief Complaint, History of Present Illness, Past Medical History, Review of Systems, Family History, Social History, Medication List, Physical Examination/Objective section, Assessment or Diagnosis, Plan, and Notes.

5. The method of claim 3, further comprising the speech-to-text steps of after the doctor has made a selection of the pieces of the note he would like, the transcription of the recording between the doctor and patient is sent to the application server; and the application server uses one or more a large-language model AI (LLM) to determine the content of any of the medical note sections.

6. The method of claim 5, further comprising the large language model (LLM) steps of splitting the transcription into chunks that are shorter than the token limit of the large language model (LLM).

7. The method of claim 6, further comprising the large language model (LLM) steps of using the AI to write a note for each section as if the chunk were the entirety of the visit; concatenate these notes into a single string, and pass this string back into the LLM with the instruction to create a single note out of the many.

8. The method of claim 6, further comprising the large language model (LLM) steps of using the AI to summarize the medically relevant portions of the chunks, and using the summarized medical portions as the input for the original AI to write the sections on the whole note.

9. The method of claim 6, further comprising the large language model (LLM) steps of using the AI to extract the medically relevant information with regards to each section of the medical note from the encounter, and using the original AI to write sections based on the chunked summaries.

10. The method of claim 1, further comprising a templating system enabling selecting which sections of the note for the AI to write.

11. The method of claim 1, further comprising a templating system enabling creating a new template from one or more existing user sections by going through a template generator wizard to generate sections for the note to contain, and give instructions to the AI for each section of the template.

12. The method of claim 11, wherein in the templating system uploading a previously written note from another patient, the AI will generate a template from the previously written note in the same format as if a user had gone through the template generator wizard.

13. The method of claim 11, wherein in the templating system accomplishes generating a template from the previously written note by giving a large language model (LLM) instructions and/or training data around a specific template format, and then placing the desired template in the prompt along with the transcription and instructions to follow the template.

14. The method of claim 10, further comprising a template sharing system wherein there is an online-hosted page in the website where users can try out other users' templates; and an online library that organizes templates by the user's medical specialty and use-case.

15. The method of claim 10, further comprising a lexicon system providing a place where the user can input words and definitions that the AI tends to misinterpret or spell incorrectly.

16. The method of claim 15, wherein words and definitions are inputted using the lexicon system; and the AI adds these into the LLM prompts to make sure that it is not mistaking any words that should be otherwise interpreted.

17. The method of claim 1, further comprising the speech-to-text steps of speaking to the AI and asking it to make edits to the note in its entirety; and speaking to the AI to have the AI make changes to the note.

10; 16

edspap.20240404526