| CPC G16H 15/00 (2018.01) [G16H 40/60 (2018.01); G16H 50/20 (2018.01)] | 15 Claims |
|
1. A method, executed within a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to specifically configure the data processing system to implement a medical report generation computer system that performs the method, the 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.
|