Granted Patent B1

US 12,347,573 · App. 18/902,532 · Granted Jul 1, 2025

Inventors: Chaitanya Gharpure (Santa Clara, CA); Ahmed Omar (Santa Clara, CA); Ahmed Nasser (Santa Clara, CA)

Assignee: SULLY.AI

G16H80/00G16H15/00G16H10/60G16H20/00

Abstract

Claims (121)

1. A method, comprising:

receiving, by one or more processors, a conversation between a doctor and a patient;

performing, by the one or more processors, an analysis of the conversation using an artificial intelligence comprising a large language model, the artificial intelligence trained, using training data that includes multiple audio conversations between doctors and patients, to create a trained artificial intelligence;

determining, by the one or more processors and based at least in part on the analysis, a first trigger phrase in the conversation;

selecting, by the one or more processors, a template of a patient visit note from a plurality of templates, the template associated with the first trigger phrase, the template comprising multiple sections;

determining, by the one or more processors and based at least in part on the analysis, a second trigger phrase in the conversation;

selecting, by the one or more processors, a particular treatment plan from a plurality of treatment plans, the particular treatment plan associated with the second trigger phrase;

adding, by the one or more processors, the particular treatment plan to the template;

splitting, by the one or more processors, the conversation into multiple portions based on the template;

adding, by the one or more processors, a first portion of the multiple portions to a first section of the template using a first instance of the trained artificial intelligence;

adding, by the one or more processors, a second portion of the multiple portions to a second section of the template using a second instance of the trained artificial intelligence, the second portion added to the second portion in parallel with adding the first portion of to the first section;

verifying the first section of the template, using a first verification artificial intelligence, wherein the first verification artificial intelligence is trained to verify the first section of the template;

verifying the second section of the template, using a second verification artificial intelligence, in parallel with the first verification artificial intelligence verifying the first section, wherein the second verification artificial intelligence is trained to verify the second section of the template;

providing, by the one or more processors, the template of the patient visit note to a device associated with the doctor; and

re-training, by the one or more processors, the trained artificial intelligence using additional data that includes the conversation between the doctor and the patient.

2. The method of claim 1 , wherein the first portion of the conversation comprises one or more of:

a complaint associated with the patient;

at least a portion of a history of a present illness associated with the patient;

at least a portion of a medical history associated with the patient: or

any combination thereof.

3. The method of claim 1 , further comprising:

adding one or more biometric measurements associated with the patient to the template, the one or more biometric measurements comprising at least one of: a body temperature, a diastolic blood pressure measurement, a systolic blood pressure measurement, a pulse rate, a blood oxygen level, an electro-cardiogram, or any combination thereof.

4. The method of claim 1 , wherein the patient visit note comprises at least:

a subjective section;

an objective section;

an assessment section; and

a plan section.

5. The method of claim 4 , wherein the plan section comprises at least one of:

a physical therapy session;

a surgery;

dietary restrictions;

an exercise regimen;

one or more over-the-counter supplements;

one or more prescription drugs;

a referral to another doctor; or

any combination thereof.

6. The method of claim 1 , further comprising:

generating, by the trained artificial intelligence, one or more billing codes based on the analysis of the conversation; and

adding the one or more billing codes to the patient visit note.

7. The method of claim 1 , wherein the conversation between the doctor and the patient comprises a text-based transcription created using a speech-to-text converter.

8. A server comprising:

one or more processors; and

one or more non-transitory computer-readable storage media to store instructions that are executable by the one or more processors to perform operations comprising:

receiving a conversation between a doctor and a patient;

performing, by an artificial intelligence comprising a large language model, an analysis of the conversation between the doctor and the patient, the artificial intelligence trained using training data that includes multiple audio conversations between doctors and patients to create a trained artificial intelligence;

determining, based at least in part on the analysis, a first trigger phrase in the conversation;

selecting a template of a patient visit note from a plurality of templates, the template associated with the first trigger phrase, the template comprising multiple sections;

determining, based at least in part on the analysis, a second trigger phrase in the conversation;

selecting a particular treatment plan from a plurality of treatment plans, the particular treatment plan associated with the second trigger phrase;

adding the particular treatment plan to the template;

splitting the conversation into multiple portions based on the template;

adding a first portion of the multiple portions to a first section of the template using a first instance of the trained artificial intelligence;

adding a second portion of the multiple portions to a second section of the template using a second instance of the artificial intelligence, the second portion added to the second section in parallel with the first portion being added to the first section;

verifying the first section of the template, using a first verification artificial intelligence, wherein the first verification artificial intelligence is trained to verify the first section of the template;

verifying the second section of the template, using a second verification artificial intelligence, in parallel with the first verification artificial intelligence verifying the first section, wherein the second verification artificial intelligence is trained to verify the second section of the template;

providing the template of the patient visit note to a device associated with the doctor; and

re-training the trained artificial intelligence using additional data that includes the conversation between the doctor and the patient.

9. The server of claim 8 , further comprising:

generating, by the trained artificial intelligence, one or more billing codes based on the analysis of the conversation; and

adding the one or more billing codes to the patient visit note.

10. The server of claim 8 , wherein the patient visit note comprises at least:

a subjective section;

an objective section;

an assessment section; and

a plan section.

11. The server of claim 10 , the plan section comprising:

a physical therapy session;

a surgery;

dietary restrictions;

an exercise regimen;

one or more over-the-counter supplements;

one or more prescription drugs;

a referral to another doctor; or

any combination thereof.

12. The server of claim 8 , wherein the first portion of the conversation comprises one or more of:

a complaint associated with the patient;

at least a portion of a history of a present illness associated with the patient;

at least a portion of a medical history associated with the patient or

any combination thereof.

13. The server of claim 8 , wherein the second portion of the conversation comprises a diagnosis expressed by the doctor during the conversation.

14. The server of claim 13 , further comprising:

adding one or more biometric measurements associated with the patient to the template, the one or more biometric measurements comprising at least one of: a body temperature, a diastolic blood pressure measurement, a systolic blood pressure measurement, a pulse rate, a blood oxygen level, an electro-cardiogram, or any combination thereof.

15. A non-transitory computer-readable storage medium to store instructions that are executable by one or more processors to perform operations comprising:

receiving a conversation between a doctor and a patient;

performing, by an artificial intelligence comprising a large language model, an analysis of the conversation between the doctor and the patient, the artificial intelligence trained using training data that includes multiple audio conversations between doctors and patients to create a trained artificial intelligence;

determining, based at least in part on the analysis, a first trigger phrase in the conversation;

selecting a template of a patient visit note from a plurality of templates, the template associated with the first trigger phrase, the template comprising multiple sections;

determining, based at least in part on the analysis, a second trigger phrase in the conversation;

selecting a particular treatment plan from a plurality of treatment plans, the particular treatment plan associated with the second trigger phrase;

adding the particular treatment plan to the template;

splitting the conversation into multiple portions based on the template;

adding a first portion of the multiple portions to a first section of the template using a first instance of the trained artificial intelligence;

adding a second portion of the multiple portions to a second section of the template using a second instance of the artificial intelligence, the second portion added to the second section in parallel with the first portion of the conversation being added to the first section;

verifying the first section of the template, using a first verification artificial intelligence, wherein the first verification artificial intelligence is trained to verify the first section of the template;

verifying the second section of the template, using a second verification artificial intelligence, in parallel with the first verification artificial intelligence verifying the first section, wherein the second verification artificial intelligence is trained to verify the second section of the template;

providing the template of the patient visit note to a device associated with the doctor; and

re-training the trained artificial intelligence using additional data that includes the conversation between the doctor and the patient.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the first portion of the conversation comprises one or more of:

a complaint associated with the patient;

at least a portion of a history of a present illness associated with the patient;

at least a portion of a medical history associated with the patient; or

any combination thereof.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the patient visit note comprises at least:

a subjective section;

an objective section;

an assessment section; and

a plan section.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the plan section comprises at least one of:

a physical therapy session;

a surgery;

dietary restrictions;

an exercise regimen;

one or more over-the-counter supplements;

one or more prescription drugs;

a referral to another doctor; or

any combination thereof.

19. The non-transitory computer-readable storage medium of claim 15 , the operations further comprising:

generating, by the artificial intelligence, one or more billing codes based on the analysis of the conversation; and

adding the one or more billing codes to the patient visit note.

20. The non-transitory computer-readable storage medium of claim 15 , further comprising:

adding one or more biometric measurements associated with the patient to the template, the one or more biometric measurements comprising at least one of: a body temperature, a diastolic blood pressure measurement, a systolic blood pressure measurement, a pulse rate, a blood oxygen level, an electro-cardiogram, or any combination thereof.

Assignments (3)

Continuity (1)

References Cited (21)