Generating clinical summaries using machine learning
View Patent ↗A computer system generates a clinical summary for a patient based on machine learning. One or more templates are generated, each indicating medical information for a corresponding clinical summary with respect to a medical condition of a patient. Preferences for medical information for each corresponding clinical summary are learned based on a history of desired medical information for clinical summaries for the medical condition. The learned preferences are applied to the one or more templates. A clinical summary is generated with respect to the medical condition of the patient based on the one or more templates with the learned preferences. Embodiments of the present invention further include a method and program product for generating a clinical summary for a patient based on machine learning in substantially the same manner described above.
1. A computer-implemented method of generating a clinical summary for a patient based on machine learning comprising:
generating, via a processor, one or more templates each indicating medical information for a corresponding clinical summary with respect to a medical scenario of a patient, wherein the one or more templates are generated based on crowdsourced indications for the medical information, the crowdsourced indications received from a plurality of users associated with a plurality of medical specialties;
learning, via the processor, preferences for medical information for each corresponding clinical summary based on a history of desired medical information for clinical summaries for the medical scenario;
applying, via the processor, the learned preferences to the one or more templates; and
generating, via the processor, a clinical summary with respect to the medical scenario of the patient based on the one or more templates with the learned preferences, wherein the clinical summary is generated by applying machine learning to analyze the medical scenario and to determine a corresponding template for producing the clinical summary with respect to the medical scenario of the patient, and wherein the medical scenario is analyzed based on user feedback from multiple users and a set of parameters for the medical scenario, the set of parameters including one or more of: a reason for a medical examination, a complaint for the patient, a modality, automatic image findings based on image processing, information within a DICOM medical image header, information within a HL7 message, and anatomical measurements.
2. The computer-implemented method of claim 1 , wherein generating the one or more templates comprises:
generating a personalized template based on user indications of relevant medical information for the personalized template.
3. The computer-implemented method of claim 1 , wherein the one or more templates are associated with a medical specialty and a corresponding medical scenario.
4. The computer-implemented method of claim 1 , wherein the user feedback from multiple users includes an indication of a medical specialty for each user.
5. A computer system for generating a clinical summary for a patient based on machine learning, the computer system comprising:
one or more computer processors;
one or more computer readable storage media;
program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising instructions to:
generate one or more templates each indicating medical information for a corresponding clinical summary with respect to a medical scenario of a patient, wherein the one or more templates are generated based on crowdsourced indications for the medical information, the crowdsourced indications received from a plurality of users associated with a plurality of medical specialties;
learn preferences for medical information for each corresponding clinical summary based on a history of desired medical information for clinical summaries for the medical scenario;
apply the learned preferences to the one or more templates; and
generate a clinical summary with respect to the medical scenario of the patient based on the one or more templates with the learned preferences, wherein the clinical summary is generated by applying machine learning to analyze the medical scenario and to determine a corresponding template for producing the clinical summary with respect to the medical scenario of the patient, and wherein the medical scenario is analyzed based on user feedback from multiple users and a set of parameters for the medical scenario, the set of parameters including one or more of: a reason for a medical examination, a complaint for the patient, a modality, automatic image findings based on image processing, information within a DICOM medical image header, information within a HL7 message, and anatomical measurements.
6. The computer system of claim 5 , wherein the instructions to generate the one or more templates comprise instructions to:
generate a personalized template based on user indications of relevant medical information for the personalized template.
7. The computer system of claim 5 , wherein the one or more templates are associated with a medical specialty and a corresponding medical scenario.
8. The computer system of claim 5 , wherein the user feedback from multiple users includes an indication of a medical specialty for each user.
9. A computer program product for generating a clinical summary for a patient based on machine learning, the computer program product comprising one or more computer readable storage media collectively having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:
generate one or more templates each indicating medical information for a corresponding clinical summary with respect to a medical scenario of a patient, wherein the one or more templates are generated based on crowdsourced indications for the medical information, the crowdsourced indications received from a plurality of users associated with a plurality of medical specialties;
learn preferences for medical information for each corresponding clinical summary based on a history of desired medical information for clinical summaries for the medical scenario;
apply the learned preferences to the one or more templates; and
generate a clinical summary with respect to the medical scenario of the patient based on the one or more templates with the learned preferences, wherein the clinical summary is generated by applying machine learning to analyze the medical scenario and to determine a corresponding template for producing the clinical summary with respect to the medical scenario of the patient, and wherein the medical scenario is analyzed based on user feedback from multiple users and a set of parameters for the medical scenario, the set of parameters including one or more of: a reason for a medical examination, a complaint for the patient, a modality, automatic image findings based on image processing, information within a DICOM medical image header, information within a HL7 message, and anatomical measurements.
10. The computer program product of claim 9 , wherein the instructions to generate the one or more templates comprise instructions to:
generate a personalized template based on user indications of relevant medical information for the personalized template.
11. The computer program product of claim 9 , wherein the one or more templates are associated with a medical specialty and a corresponding medical scenario.
12. The computer program product of claim 9 , wherein the user feedback from multiple users includes an indication of a medical specialty for each user.