Artificial intelligence based alert system
View Patent ↗A mechanism is provided to implement an artificial intelligence (AI) based alert mechanism system for alerting a medical professional of potential inaccuracies in medical image analysis. Responsive to receiving a medical image of a patient and a radiology report associated with the medical image, the AI based alert mechanism analyzes the radiology report to identify medical findings detected by the medical professional and analyzes the medical image to detect one or more medical findings associated with the medical image. Responsive to the AI based alert mechanism identifying one or more medical findings, the AI based alert mechanism compares the identified medical findings to those medical findings identified in the radiology report. Responsive to the AI based alert mechanism identifying a discrepancy between the identified medical findings to those in the radiology report, the AI based alert mechanism generates an alert to the medical professional who generated the radiology report.
1. A method, in 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 cause the at least one processor to implement an artificial intelligence (AI) based alert mechanism system for alerting a medical professional of potential inaccuracies in medical image analysis, wherein the AI based alert mechanism system operates to:
receiving, by the AI based alert mechanism, a medical image of a patient and a radiology report associated with the medical image;
analyzing, by the AI based alert mechanism, the radiology report to identify medical findings detected by the medical professional;
analyzing, by the AI based alert mechanism, the medical image to detect one or more medical findings associated with the medical image;
responsive to the AI based alert mechanism detecting one or more medical findings associated with the medical image, comparing, by the AI based alert mechanism, the one or more medical findings associated with the medical image to those medical findings detected by the medical professional and identified in the radiology report; and
responsive to the AI based alert mechanism identifying a discrepancy between the detected medical findings associated with the medical image to those medical findings detected by the medical professional and identified in the radiology report, generating, by the AI based alert mechanism, an alert to the medical professional who generated the radiology report, wherein the alert identifies missing medical findings in the radiology report, errors in interpretation of the medical image, and errors in a criticality level of the medical findings detected by the medical professional and identified in the radiology report.
2. The method of claim 1 , wherein the medical image is selected from the group consisting of a computerized axial tomography (CT) scan, magnetic resonance imaging (MRI) scan, ultrasound (U/S) scan, positron emission tomography (PET) scan, or X-ray scan.
3. The method of claim 1 , wherein analyzing the radiology report comprises the use of natural language processing (NLP).
4. The method of claim 1 , wherein analyzing the medical image to detect one or more medical findings associated with the medical image comprises the use of an image analytics algorithm trained to detect diseases or conditions associated with the medical image.
5. The method of claim 1 , wherein analyzing the medical image to detect one or more medical findings associated with the medical image further comprises:
analyzing, by the AI based alert mechanism, one or more of the patient's electronic health record (EHR), non-image based information, demographics, family history, medical history, lab results, or other radiology reports.
6. The method of claim 1 , wherein the alert comprises one or more of the radiology report, the one or more medical findings associated with the medical image detected by the AI based alert mechanism, the comparison making note of any discrepancies between the detected medical findings associated with the medical image to those medical findings detected by the medical professional and identified in the radiology report.
7. The method of claim 1 , wherein the receiving, analyzing, analyzing, comprising, and generating occur upon the medical professional signing off on the radiology report so as to directly impact the clinical care of the patient.
8. The method of claim 1 , wherein the receiving, analyzing, analyzing, comprising, and generating occur as part of a peer review workflow.
9. A computer program product comprising a non-transitory computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a data processing system, causes the data processing system to implement an artificial intelligence (AI) based alert mechanism system for alerting a medical professional of potential inaccuracies in medical image analysis, and further causes the data processing system to:
receive, by the AI based alert mechanism, a medical image of a patient and a radiology report associated with the medical image;
analyze, by the AI based alert mechanism, the radiology report to identify medical findings detected by the medical professional;
analyze, by the AI based alert mechanism, the medical image to detect one or more medical findings associated with the medical image;
responsive to the AI based alert mechanism detecting one or more medical findings associated with the medical image, compare, by the AI based alert mechanism, the one or more medical findings associated with the medical image to those medical findings detected by the medical professional and identified in the radiology report; and
responsive to the AI based alert mechanism identifying a discrepancy between the detected medical findings associated with the medical image to those medical findings detected by the medical professional and identified in the radiology report, generate, by the AI based alert mechanism, an alert to the medical professional who generated the radiology report, wherein the alert identifies missing medical findings in the radiology report, errors in interpretation of the medical image, and errors in a criticality level of the medical findings detected by the medical professional and identified in the radiology report.
10. The computer program product of claim 9 , wherein the medical image is selected from the group consisting of a computerized axial tomography (CT) scan, magnetic resonance imaging (MRI) scan, ultrasound (U/S) scan, positron emission tomography (PET) scan, or X-ray scan.
11. The computer program product of claim 9 , wherein analyzing the radiology report comprises the use of natural language processing (NLP).
12. The computer program product of claim 9 , wherein analyzing the medical image to detect one or more medical findings associated with the medical image comprises the use of an image analytics algorithm trained to detect diseases or conditions associated with the medical image.
13. The computer program product of claim 9 , wherein the computer readable program to analyze the medical image to detect one or more medical findings associated with the medical image further causes the data processing system to:
analyze, by the AI based alert mechanism, one or more of the patient's electronic health record (EHR), non-image based information, demographics, family history, medical history, lab results, or other radiology reports.
14. The computer program product of claim 9 , wherein the alert comprises one or more of the radiology report, the one or more medical findings associated with the medical image detected by the AI based alert mechanism, the comparison making note of any discrepancies, between the detected medical findings associated with the medical image to those medical findings detected by the medical professional and identified in the radiology report.
15. A data processing system comprising:
at least one processor; and
at least one memory coupled to the at least one processor, wherein the at least one memory comprises instructions which, when executed by the at least one processor, cause the at least one processor to implement an artificial intelligence (AI) based alert mechanism system for alerting a medical professional of potential inaccuracies in medical image analysis, and further cause the at least one processor to:
receive, by the AI based alert mechanism, a medical image of a patient and a radiology report associated with the medical image;
analyze, by the AI based alert mechanism, the radiology report to identify medical findings detected by the medical professional;
analyze, by the AI based alert mechanism, the medical image to detect one or more medical findings associated with the medical image;
responsive to the AI based alert mechanism detecting one or more medical findings associated with the medical image, compare, by the AI based alert mechanism, the one or more medical findings associated with the medical image to those medical findings detected by the medical professional and identified in the radiology report; and
responsive to the AI based alert mechanism identifying a discrepancy between the detected medical findings associated with the medical image to those medical findings detected by the medical professional and identified in the radiology report, generate, by the AI based alert mechanism, an alert to the medical professional who generated the radiology report, wherein the alert identifies missing medical findings in the radiology report, errors in interpretation of the medical image, and errors in a criticality level of the medical findings detected by the medical professional and identified in the radiology report.
16. The data processing system of claim 15 , wherein the medical image is selected from the group consisting of a computerized axial tomography (CT) scan, magnetic resonance imaging (MRI) scan, ultrasound (U/S) scan, positron emission tomography (PET) scan, or X-ray scan.
17. The data processing system of claim 15 , wherein analyzing the radiology report comprises the use of natural language processing (NLP).
18. The data processing system of claim 15 , wherein analyzing the medical image to detect one or more medical findings associated with the medical image comprises the use of an image analytics algorithm trained to detect diseases or conditions associated with the medical image.
19. The data processing system of claim 15 , wherein the instructions to analyze the medical image to detect one or more medical findings associated with the medical image further cause the at least one processor to:
analyze, by the AI based alert mechanism, one or more of the patient's electronic health record (EHR), non-image based information, demographics, family history, medical history, lab results, or other radiology reports.
20. The data processing system of claim 15 , wherein the alert comprises one or more of the radiology report, the one or more medical findings associated with the medical image detected by the AI based alert mechanism, the comparison making note of any discrepancies between the detected medical findings associated with the medical image to those medical findings detected by the medical professional and identified in the radiology report.