System for transcribing and performing analysis on patient data
Methods, apparatuses, and systems for transcribing and performing analysis on patient data are disclosed. Data is collected from one or more medical professionals as well as sensors and imaging devices positioned on or oriented towards a patient. An analysis is performed on the patient data and the data is presented to a medical professional via a verbal interface in a conversational manner, allowing the medical professional to provide additional data such as observations or instructions which may be used for further analysis or to perform actions related to the patient's care.
1. A computer-implemented method comprising:
transcribing physician input received from a physician using a voice-interactive transcription system that is configured to be voice-controlled by the physician, wherein the voice-interactive transcription system has a plurality of transcription modules that are selectable by the physician for a surgical procedure;
during the surgical procedure being performed on a patient's body,
analyzing the patient's body using a machine learning model associated with a selected one of the transcription modules to identify one or more surgical events based on sensor data generated from intraoperative patient vital measurements of the patient's body and the transcribed physician input, wherein the machine learning model is trained based on input from the physician, historical patient data, and historical treatment data; and
outputting verbally the analysis of the patient's body to the physician using computer-generated natural language.
2. The computer-implemented method of claim 1 , comprising:
generating the sensor data from the measurements of the patient's body using one or more sensors.
3. The computer-implemented method of claim 1 , comprising:
retrieving patient data of the patient from a patient database, the patient data comprising at least a medical history of the patient; and
determining a diagnosis based on the sensor data and the patient data.
4. The computer-implemented method of claim 3 , wherein the patient data comprises sequenced DNA of the patient, and the diagnosis comprises a hereditary medical condition.
5. The computer-implemented method of claim 1 , comprising:
monitoring live surgical procedures; and
training the machine learning model based on the live surgical procedures while the live surgical procedures are being performed.
6. The computer-implemented method of claim 1 , wherein the transcribed physician input comprises medical notes, the method comprising:
determining a diagnosis based on the medical notes.
7. The computer-implemented method of claim 1 , wherein the sensor data comprises medical images of the patient's body received from an imaging device, the method comprising:
extracting an anomalous feature from the medical images; and
determining a diagnosis using machine learning performed on the anomalous feature.
8. The computer-implemented method of claim 1 , comprising:
for each of one or more medical conditions:
assigning a statistical probability that the patient has each medical condition using the machine learning model; and
selecting a medical condition having a greatest statistical probability.
9. The computer-implemented method of claim 8 , comprising:
selecting each of the one or more medical conditions having a statistical probability greater than a threshold statistical probability.
10. The computer-implemented method of claim 1 , wherein training the machine learning model comprises:
generating a predicted diagnosis and a predicted treatment for a previous patient based on the historical patient data; and
comparing the predicted diagnosis and the predicted treatment to an actual diagnosis and an actual treatment provided by a previous surgeon in the historical patient data, the comparing for training a regression model of the system.
11. A system comprising:
one or more computer processors; and
a non-transitory computer-readable storage medium storing computer instructions, which when executed by the one or more computer processors cause the system to:
transcribe physician input received from a physician using a voice-interactive transcription system that is configured to be voice-controlled by the physician, wherein the voice-interactive transcription system has a plurality of transcription modules that are selectable by the physician for a surgical procedure;
during the surgical procedure being performed on a patient's body,
analyze the patient's body using a machine learning model associated with a selected one of the transcription modules to identify one or more surgical events based on sensor data generated from intraoperative patient vital measurements of the patient's body and the transcribed physician input, the machine learning model trained based on input from the physician, historical patient data, and historical treatment data; and
output verbally an analysis of the patient's body to the physician using computer-generated natural language.
12. The system of claim 11 , wherein the computer instructions cause the system to:
generate the sensor data from the measurements of the patient's body using one or more sensors.
13. The system of claim 11 , wherein the computer instructions cause the system to:
retrieve patient data of the patient from a patient database, the patient data comprising at least a medical history of the patient; and
determine a diagnosis based on the sensor data and the patient data.
14. The system of claim 13 , wherein the patient data comprises sequenced DNA of the patient, and the diagnosis comprises a hereditary medical condition.
15. The system of claim 11 , wherein the computer instructions cause the system to:
monitor live surgical procedures; and
train the machine learning model based on the live surgical procedures while the live surgical procedures are being performed.
16. The system of claim 11 , wherein the transcribed physician input comprises medical notes, and the computer instructions cause the system to:
determine a diagnosis based on the medical notes.
17. The system of claim 11 , wherein the sensor data comprises medical images of the patient's body received from an imaging device, and the computer instructions cause the system to:
extract an anomalous feature from the medical images; and
determine a diagnosis using machine learning performed on the anomalous feature.
18. The system of claim 11 , wherein the computer instructions cause the system to:
for each of one or more medical conditions:
assign a statistical probability that the patient has each medical condition using the machine learning model; and
select a medical condition having a greatest statistical probability.
19. The system of claim 18 , wherein the computer instructions cause the system to:
select each of the one or more medical conditions having a statistical probability greater than a threshold statistical probability.
20. A non-transitory computer-readable storage medium storing computer instructions, which when executed by one or more computer processors cause the one or more computer processors to:
transcribe physician input received from a physician using a voice-interactive transcription system that is configured to be voice-controlled by the physician, wherein the voice-interactive transcription system has a plurality of transcription modules that are selectable by the physician for a surgical procedure;
during the surgical procedure being performed on a patient's body,
analyze the patient's body using a machine learning model associated with a selected one of the transcription modules to identify one or more surgical events based on sensor data generated from intraoperative patient vital measurements of the patient's body and the transcribed physician input, the machine learning model trained based on input from the physician, historical patient data, and historical treatment data; and
output verbally an analysis of the patient's body to the physician using computer-generated natural language.