Coronary computed tomography clinical decision support system
A CT-based clinical decision support system provides coronary decision support. With or without CT-FFR, a machine learnt predictor predicts the clinical decision for the patient based on input from various sources. Using the machine learnt predictor provides more consistent and comprehensive consideration of the available information. The clinical decision support may be provided prior to review of coronary CT data by a radiologist and/or treating physician, providing a starting point or recommendation that may be used by the radiologist and/or treating physician.
1. A method for coronary decision support using a computed tomography (CT)-based clinical decision support system, the method comprising:
scanning a patient with a computed tomography system, the scanning providing coronary CT data representing a heart of the patient;
acquiring, from a computerized medical record database, patient data different than the coronary CT data;
extracting values for features of an input vector of a machine-learnt predictor of the CT-based clinical decision support system from the coronary CT data and the patient data;
generating, by the machine-learnt predictor of the CT-based clinical decision support system, a clinical decision for treatment of the patient based on the input vector; and
transmitting the clinical decision.
2. The method of claim 1 wherein acquiring, extracting, generating, and transmitting are performed upon scanning and before a review by a physician.
3. The method of claim 1 wherein acquiring comprises acquiring as the patient data (1) a CT-based fractional flow reserve (FFR) value and (2) clinical data for the patient, and not acquiring an invasive FFR prior to performing the generating, and wherein extracting comprises extracting the values from the CT-FFR value and the clinical data.
4. The method of claim 1 wherein generating comprises determining whether to perform CT-based fractional flow reserve (FFR) as the clinical decision.
5. The method of claim 1 wherein acquiring comprises acquiring non-invasive data, biochemical information, and model information fit to the coronary CT data, and wherein extracting comprises extracting the values from the CT-FFR value, the clinical data, the model information, and the coronary CT data.
6. The method of claim 1 wherein acquiring comprises acquiring model information fit to the coronary CT data, the model information being from a physiological or functional model, from an anatomical model, or from both the physiological or functional model and the anatomical model, and wherein extracting comprises extracting the values from the model information, and the coronary CT data.
7. The method of claim 1 wherein generating comprises generating the clinical decision from options including sending the patient for invasive stenting, sending the patient for invasive measurement, sending the patient for a non-invasive test, prescribing medication to the patient, and discharging the patient.
8. The method of claim 1 wherein generating comprises generating the clinical decision as a recommendation for the treatment.
9. The method of claim 1 wherein generating comprises generating with the machine-learnt predictor comprising a cascade or parallel set of machine-learnt classifiers.
10. The method of claim 1 wherein transmitting comprises transmitting the clinical decision as information for physician decision.
11. The method of claim 1 wherein transmitting comprises displaying a decision tree showing the clinical decision, other possible decisions, and further treatment options resulting from the clinical decision.
12. A system for coronary decision support, the system comprising:
a computed tomography (CT) scanner for scanning a patient, the CT scanner is configured to output coronary CT data for the patient;
a memory stores a computerized patient record; and
a decision support processor configured to extract an input feature vector from the coronary CT data and the computerized patient record, to apply the input feature vector to a machine-learnt classifier, and to output a clinical decision for the patient from the machine-learnt classifier in response to the application of the input feature vector.
13. The system of claim 12 wherein the decision support processor is configured to output the clinical decision prior to entry of a treatment into the computerized patient record by a physician.
14. The system of claim 12 wherein the decision support processor is configured to output the clinical decision prior to review of the coronary CT data by a radiologist.
15. The system of claim 12 wherein the clinical decision comprises a recommendation to perform non-invasive CT-based fractional flow reserve.
16. The system of claim 12 wherein the input feature vector comprises non-invasive patient data and biochemical measurements from the computerized patient record and comprises features from the coronary CT data, anatomical information derived from the coronary CT data, and functional evaluation value derived from the coronary CT data.
17. The system of claim 12 further comprising a display configured to display the clinical decision in a decision tree of possible clinical decisions.