Automated report generation using artificial intelligence algorithms

A computer system for medical report generation, comprising:

• one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories to specifically configure the computer system to implement a medical report generation computer system, wherein the medical report generation computer system operates to perform a method comprising:
• receiving, by the medical report generation computer system, a plurality of patient images of a patient;
• executing, in the medical report generation computer system, an imaging machine learning model on the plurality of patient images to output, based on a processing of the plurality of patient images through the imaging machine learning model, a medical image positive finding, wherein the imaging machine learning model is a convolutional neural network (CNN) pretrained based on a database of existing patient medical images;
• executing, in the medical report generation computer system, a segmentation CNN model on the plurality of patient images to identify characteristics of the medical image positive finding;
• executing, in the medical report generation computer system, a text monitoring machine learning model based on the medical image positive finding and the characteristics of the medical image positive finding, to retrieve relevant data comprising relevant patient data, from a patient medical record of the patient, and a relevant medical guideline corresponding to the medical image positive finding and the characteristics of the medical image positive finding, wherein different relevant medical guidelines and patient data are retrieved for different medical image positive findings and different characteristics of the medical image positive finding;
• providing the relevant data to a user, wherein the relevant data provided to the user is in accordance with the relevant medical guideline;
• and
• monitoring data input to generate a tailored medical report, wherein the text monitoring machine learning model searches for a previous mention in the patient medical record of a previous finding corresponding to the medical image positive finding, wherein providing the relevant data to the user comprises providing an output that specifies whether the previous finding was acted upon and raises an alert for previously detected conditions that require a follow up, and wherein monitoring data input to generate the tailored medical report comprises:
• monitoring a user click action on at least one patient image in the plurality of patient images;
• and
• modifying an output of the relevant data to the user based on the user click action to provide relevant information corresponding to a portion of the at least one patient image clicked on by the user click action.

A non-transitory computer program product for medical report generation, comprising:

• one or more non-transitory computer-readable storage media and program instructions stored on at least one of the one or more non-transitory computer-readable storage media, the program instructions executable by a processor to cause the processor to specifically configure the processor to implement a medical report generation computer system, wherein the medical report generation computer system operates to perform a method comprising:
• receiving, by the medical report generation computer system, a plurality of patient images of a patient;
• executing, in the medical report generation computer system, an imaging machine learning model on the plurality of patient images to output, based on a processing of the plurality of patient images through the imaging machine learning model, a medical image positive finding, wherein the imaging machine learning model is a convolutional neural network (CNN) pretrained based on a database of existing patient medical images;
• executing, in the medical report generation computer system, a segmentation CNN model on the plurality of patient images to identify characteristics of the medical image positive finding;
• executing, in the medical report generation computer system, a text monitoring machine learning model based on the medical image positive finding and the characteristics of the medical image positive finding, to retrieve relevant data comprising relevant patient data, from a patient medical record of the patient, and a relevant medical guideline corresponding to the medical image positive finding and the characteristics of the medical image positive finding, wherein different relevant medical guidelines and patient data are retrieved for different medical image positive findings and different characteristics of the medical image positive finding;
• providing the relevant data to a user, wherein the relevant data provided to the user is in accordance with the relevant medical guideline;
• and
• monitoring data input to generate a tailored medical report, wherein the text monitoring machine learning model searches for a previous mention in the patient medical record of a previous finding corresponding to the medical image positive finding, wherein providing the relevant data to the user comprises providing an output that specifies whether the previous finding was acted upon and raises an alert for previously detected conditions that require a follow up, and wherein monitoring data input to generate the tailored medical report comprises:
• monitoring a user click action on at least one patient image in the plurality of patient images;
• and
• modifying an output of the relevant data to the user based on the user click action to provide relevant information corresponding to a portion of the at least one patient image clicked on by the user click action.