Methods and systems for automatically analyzing clinical images using models developed using machine learning based on graphical reporting

1. A system for automatically analyzing clinical images using image analytics developed using graphical reporting associated with previously-analyzed 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 training information from the at least one data source over the interface, the training information including a plurality of images and graphical reporting associated with each of the plurality of images, each graphical reporting including a graphical marker designating a portion of one of the plurality of images and diagnostic information associated with the portion of the one of the plurality of images,

perform machine learning to develop a model using the training information,

receive an image for analysis, and

automatically process the image using the model to generate a diagnosis for the image, wherein the generating the diagnosis includes

determining additional information to generate the diagnosis,

receiving the additional information, and

generating the diagnosis using the model and the additional information, wherein the electronic processor is configured to determine the additional information by

generating a set of diagnoses for the image based on the model, and

determining the additional information based on the set of diagnoses, wherein the diagnosis includes the set of diagnoses updated based on the additional information.

2. The system of claim 1 , wherein the diagnosis includes a category of the image, the category including a normal category, an abnormal category, and an indeterminate category.

3. The system of claim 1 , wherein the diagnosis includes a flag designating the image as needing manual review.

4. The system of claim 1 , wherein the diagnosis includes an identification of an abnormality included in the image.

5. The system of claim 1 , wherein the diagnosis includes a probability of an abnormality.

6. The system of claim 5 , wherein the diagnosis includes a basis for the probability.

7. The system of claim 1 , wherein the image includes a plurality of images and the diagnosis includes a flagging at least one of the plurality of images to be manually reviewed.

8. The system of claim 1 , wherein the diagnosis includes an identification of an anatomical structure.

9. The system of claim 1 , wherein the diagnosis includes an amount of change between the image and at least one additional image.

10. The system of claim 1 , wherein the diagnosis includes a recommendation for a follow-up, the follow-up including at least one selected from a group consisting of an imaging procedure, a laboratory procedure, a treatment procedure, or a surgical procedure.

11. The system of claim 1 , wherein the diagnosis includes an order for a procedure, the procedure including at least one selected from a group consisting of an imaging procedure, a laboratory procedure, a treatment procedure, or a surgical procedure.

12. The system of claim 1 , wherein the diagnosis includes a structured report.

13. The system of claim 1 , wherein the diagnosis includes a Digital Imaging and Communications in Medicine (DICOM) structured report.

14. The system of claim 1 , wherein the diagnosis includes a value for a data field of a structured report.

15. The system of claim 14 , wherein the electronic processor is further configured to map the diagnosis to the data field.

16. The system of claim 1 , wherein the electronic processor is further configured to receive medical history information for a patient associated with the image and wherein the diagnosis includes a notification of a prior procedure or treatment potentially impacting anatomy represented in the image based on the medical history information.

17. The system of claim 16 , wherein the notification includes a graphical indication or a textual indication.

18. The system of claim 17 , wherein a characteristic of the graphical indication specifies a type of the prior procedure or treatment potentially impacting the anatomy represented in the image.

19. The system of claim 17 , wherein the electronic processor is further configured to display at least a portion of the medical history information in response to a user selection of the graphical indication.

20. The system of claim 1 , wherein the electronic processor is configured to process the image using the model to generate the diagnosis by

receiving medical history information for a patient associated with the image, the medical history information including clinical notes associated with the patient, and

determining a portion of the image of clinical concern based on the medical history information.

21. The system of claim 20 , where the electronic processor is further configured to generate and display an indication of the portion of the image of clinical concern.

22. The system of claim 21 , wherein the indication includes a textual indication or a graphical indication displayed with or on the image.

23. The system of claim 20 , wherein the clinical notes includes a compliant of the patient.

24. The system of claim 20 , wherein the clinical notes includes an anatomical structure of the patient.

25. The system of claim 1 , wherein the image includes an image of a skin lesion and the diagnosis includes a diagnosis of the skin lesion.

26. The system of claim 1 , wherein the image includes an image of an internal structure of a patient and the diagnosis includes an indication of whether the internal structure includes a fracture.

27. The system of claim 1 , wherein the image includes an image of an internal structure of a patient and the diagnosis includes an indication of whether the patient is experiencing internal bleeding.

28. The system of claim 1 , wherein the image includes electrocardiogram (ECG) data and the diagnosis includes a diagnosis.

29. The system of claim 1 , wherein the image represents a lung of a patient and the diagnosis includes an identification of whether the lung includes a cancerous nodule.

30. The system of claim 1 , wherein the electronic processor is configured to receive the additional information by at least one selected from a group consisting of prompting a user for the additional information and automatically accessing the additional information from at least one electronic data repository.

31. The system of claim 30 , wherein the electronic processor is configured to prompt the user for the additional information by transmitting an electronic message to the user, wherein the electronic message includes at least one selected from a group consisting of a page, an e-mail message, a Direct protocol message, a text message, a voicemail message, and an electronic notification within an information system.

32. The system of claim 30 , wherein the electronic processor is further configured to receive a preference for the user specifying when or how to prompt the user for the additional information.

33. The system of claim 1 , wherein the configuration setting includes a threshold associated with an initial diagnosis, wherein the electronic processor is configured to prompt the user for the additional information when a first probability associated with the initial diagnosis is less than the threshold or when a change in a second probability associated with the initial diagnosis when the additional information is available exceeds the threshold.

34. The system of claim 1 , wherein the electronic processor is configured receive the additional information by prompting a user whether the additional information should be obtained.

35. The system of claim 1 , wherein the electronic processor is configured to display at least one of the set of diagnoses and the set of diagnoses updated based on the additional information, wherein each displayed diagnosis is associated with at least one of a probability and a basis.

36. The system of claim 1 , wherein the diagnosis includes a data structure indicating a change in an anomaly detected in the image based on a comparison to prior images.

37. The system of claim 36 , wherein the data structure is cross-referenced with at least one medical procedure or treatment performed on a patient associated with the image.

38. The system of claim 1 , wherein the electronic processor is configured to process the image using the model to generate the diagnosis by prompting a user for additional information regarding the image and generating the diagnosis using the model and the additional information.

39. The system of claim 38 , wherein the additional information includes at least one selected from a group consisting of an additional image, patient demographic information, medical history, and a laboratory result.

40. The system of claim 38 , wherein the electronic processor is configured to prompt the user for the additional information by contacting one or more individuals associated with a patient associated with the image.

41. The system of claim 38 , wherein the electronic processor is configured to prompt the user for the additional information by transmitting an electronic message to the user, wherein the electronic message includes at least one selected from a group consisting of a page, an e-mail message, a Direct protocol message, a text message, a voicemail message, and an electronic notification within an information system.

42. The system of claim 1 , wherein the diagnosis includes a value within a range of values, and wherein the electronic processor is further configured to compare the value to at least one threshold and take at least one automatic action when the value satisfies the at least one threshold.

43. The system of claim 1 , wherein the diagnosis includes an identification of the image as a reference image and wherein the electronic processor is further configured to store the reference image to at least one electronic data repository.

44. The system of claim 43 , wherein the reference image includes an image used for research, teaching, marketing, patient education, or public health.