Differential diagnosis mechanisms based on cognitive evaluation of medical images and patient data
Methods and systems for automatically triaging an image study of a patient generated as part of a medical imaging procedure. One system comprises a computing device including an electronic processor. The electronic processor is configured to receive, from a cognitive system applying a model developed using computer vision and machine learning techniques based on deep learning methodology to classify image studies, a classification assigned to the image study using the model, automatically generate a differential diagnosis for the patient based on the classification assigned by the model, and automatically adjust triaging of the image study based on the differential diagnosis.
1. A system for automatically triaging an image study of a patient generated as part of a medical imaging procedure, the system comprising:
a computing device including an electronic processor configured to
receive, from a cognitive system applying a model developed using computer vision and machine learning techniques based on deep learning methodology to classify image studies, a classification assigned to the image study using the model,
automatically generate a differential diagnosis for the patient based on the classification assigned by the model by comparing at least one image included in the image study with patient data, wherein the differential diagnosis provides a set of possible diagnoses and a probability associated with each possible diagnosis of the set of possible diagnoses, and
automatically adjust triaging of the image study based on the differential diagnosis.
2. The system of claim 1 , wherein the classification includes a BI-RADS classification.
3. The system of claim 1 , wherein the electronic processor is further configured to assign a severity classification to the image study based on the classification assigned by the model and wherein the electronic processor is configured to automatically generate the structured report based on the severity classification.
4. The system of claim 3 , wherein the electronic processor is configured to assign the severity classification by comparing an image included in the image study with an image included in a prior image study for the patient.
5. The system of claim 3 , wherein image study is a first image study and the electronic processor is configured to assign the severity classification based on the classification for the first image study assigned by the model and a classification for a second image study for the patient.
6. The system of claim 5 , wherein the second image study for the patient was generated using a different modality than the first image study.
7. The system of claim 1 , wherein the electronic processor is further configured to access the patient data through an electronic medical record of the patient.
8. The system of claim 1 , wherein the differential diagnosis eliminates at least one diagnosis of the patient.
9. The system of claim 1 , wherein the differential diagnosis provides a probability of at least one diagnosis of the patient.
10. The system of claim 1 , wherein the electronic processor is configured to automatically adjust triaging of the image study based on the differential diagnosis by automatically changing a worklist priority for the image study.
11. The system of claim 1 , wherein the electronic processor is configured to automatically adjust triaging of the image study based on the differential diagnosis by automatically generating a structured report for the image study based on the classification assigned by the model.
12. The system of claim 1 , wherein the electronic processor is configured to automatically adjust triaging of the image study based on the differential diagnosis by automatically communicating with a resource allocation system to reserve at least one medical resource for treating the patient.
13. The system of claim 1 , wherein the electronic processor is further configured to automatically generate a worklist based on the classification assigned to the image study using the model, the worklist prioritizing a plurality of tasks for treating the patient.
14. The system of claim 1 , wherein the electronic processor is configured to automatically generate the differential diagnosis based on the classification by applying at least one rule to the classification, the at least one rule associated with at least one selected from a group consisting of the patient, a facility, a radiologist, a network, a geographical area, and a type of imaging modality.
15. Non-transitory computer-readable medium including instructions that, when executed by an electronic processor, perform a set of functions, the set of functions comprising:
receiving, from a cognitive system applying a model developed using computer vision and machine learning techniques based on deep learning methodology to classify image studies, a classification assigned to the image study using the model;
automatically generating a differential diagnosis for the patient based on the classification assigned by the model, wherein the differential diagnosis provides a set of possible diagnoses and a probability associated with each possible diagnosis of the set of possible diagnoses;
automatically generating a worklist based on the classification assigned to the image study using the model, the worklist prioritizing a plurality of tasks for treating the patient; and
automatically adjusting triaging of the image study based on the differential diagnosis by automatically changing a priority of a task of the worklist.
16. A method of automatically analyzing an image study of a patient generated as part of a medical imaging procedure, the method comprising:
receiving, with an electronic processor, a classification from a cognitive system for the image study, the cognitive system applying a model developed using computer vision and machine learning techniques based on deep learning methodology to classify image studies based on a classification schema;
automatically, with the electronic processor, generating a differential diagnosis for the patient based on the classification assigned by the model and data accessible via an electronic medical record of the patient, wherein the differential diagnosis provides a set of possible diagnoses and a probability associated with each possible diagnosis of the set of possible diagnoses; and
automatically adjusting triaging of the image study based on the differential diagnosis;
wherein automatically adjusting triaging of the image study based on the differential diagnosis includes automatically communicating with a resource allocation system to reserve at least one medical resource for treating the patient.
17. The method of claim 16 , wherein generating the differential diagnosis based on the classification includes applying at least one rule to the classification, the at least one rule associated with at least one selected from a group consisting of the patient, a facility, a radiologist, a network, a geographical area, and a type of imaging modality.
18. The method of claim 16 , wherein automatically adjusting triaging of the image study based on the differential diagnosis includes automatically changing a worklist priority for the image study.