Methods and systems for automatically scoring diagnoses associated with clinical images
Methods and systems for automatically scoring diagnoses associated with clinical images. One system includes a server including an electronic processor and an interface for communicating with at least one data source. The electronic processor is configured to receive a diagnosis associated with an image of a patient from the at least one data source over the interface. The diagnosis is for an anatomical structure represented in the image. The electronic processor is also configured to receive a pathology result for the patient for the anatomical structure generated after the diagnosis from the at least one pathology result source over the interface. The electronic processor is also configured to automatically generate a score based on a comparison of the diagnosis and the pathology result. The electronic processor is also configured to display the score within a graphical user interface.
1. A system for automatically scoring diagnoses associated with clinical images, the system comprising:
a server including
an electronic processor and an interface for communicating with at least one data source,
the electronic processor configured to
receive a plurality of diagnoses a plurality of image studies from the at least one data source over the interface, wherein each of the plurality of diagnoses is for an anatomical structure represented in the image,
receive a plurality of pathology results for the patient for the anatomical structure generated after the plurality of diagnoses from at least one pathology result source over the interface,
automatically generate a score based on a comparison of the plurality of diagnoses and the plurality of pathology results,
assign a weight to training information used to generate a model using machine learning based on the score,
generate the model using machine learning using the training information as weighted; and
use the model to automatically diagnose a new image study.
2. The system of claim 1 , wherein the score is for an individual diagnosing physician.
3. The system of claim 1 , wherein the electronic processor is further configured to automatically generate a plurality of scores and rank the plurality of scores.
4. The system of claim 1 , wherein the score is for a plurality of diagnosing physicians.
5. The system of claim 1 , wherein the score is for an individual facility.
6. The system of claim 1 , wherein the score is for a network of a plurality of facilities.
7. The system of claim 1 , wherein the score includes a percentage of the plurality of diagnoses not matching a corresponding pathology result from the plurality of pathology results.
8. The system of claim 1 , wherein the score includes a percentage of the plurality of diagnoses matching a corresponding pathology result from the plurality of pathology results.
9. The system of claim 1 , wherein the electronic processor is further configured to obtain an imaging parameter for the diagnosis and automatically determine a potential imaging parameter impacting the score.
10. The system of claim 1 , wherein the electronic processor is further configured to determine and display a trend based on the score.
11. The system of claim 10 , wherein the trend includes identification of a population of patients associated with a particular diagnosis from the plurality of diagnoses.
12. The system of claim 10 , wherein the trend includes identification of a population of patients associated with a particular pathology result from the plurality of pathology results.
13. The system of claim 10 , wherein the trend includes an epidemic.
14. The system of claim 1 , wherein the electronic processor is further configured to determine training based on the score.
15. The system of claim 1 , wherein at least one diagnosis from the plurality of diagnoses includes a computer-generated diagnosis.
16. The system of claim 15 , wherein the electronic processor is further configured to update a model used to generate the computer-generated diagnosis based on the score.
17. The system of claim 1 , wherein the score is a first score associated with a first diagnosing physician and the electronic processor is further configured to compare the first score to a second score.
18. The system of claim 17 , wherein the second score is associated with a second physician or a model configured to automatically diagnose images.
19. The system of claim 1 , wherein the score is associated with a type of imaging modality.
20. The system of claim 1 , wherein the score is associated with a type of the image or a type of imaging exam associated with the image.
21. The system of claim 1 , wherein the score is associated with a geographic location.
22. The system of claim 1 , wherein the score is associated with a time of day.
23. The system of claim 1 , wherein the score is associated with a type or population of patients.
24. The system of claim 1 , wherein the score is configurable based on one or more preferences.