Candidate screening for a target therapy
View Patent ↗Techniques are provided for candidate screening for a target therapy. A plurality of medical codes corresponding to patient billing data are identified. A candidate classification model for a target therapy is generated by selecting a set of medical codes from the plurality of medical codes and assigning a weight to each medical code selected. The candidate classification model is applied to patient billing data for a plurality of patients to generate a set of target therapy scores. The patient billing data includes associations between one or more patients of the plurality of patients and one or more medical codes of the plurality of medical codes. Each target therapy score corresponds to a patient of the plurality of patients, and is calculated based on weights for one or more medical codes associated with the patient.
1. A method comprising:
performing, by one or more processors, the steps of:
identifying a plurality of medical codes corresponding to patient billing data, the plurality of medical codes including a first medical code corresponding to a risk for bleeding and a second medical code corresponding to existence of atrial fibrillation;
generating a candidate classification model for a target therapy by selecting a set of medical codes from the plurality of medical codes and assigning a weight to each medical code selected, the target therapy being a left atrial appendage (“LAA”) occlusion therapy;
receiving patient billing data for a plurality of patients, the patient billing data including associations between one or more patients of the plurality of patients and one or more medical codes of the plurality of medical codes;
applying the candidate classification model to the patient billing data to generate a set of target therapy scores, each target therapy score of the set of target therapy scores corresponding to a patient of the plurality of patients and calculated based on weights for one or more medical codes associated with the patient, wherein the set of target therapy scores includes (i) a first score indicating that the corresponding patient has previously received the LAA occlusion therapy, (ii) a second score indicating that the corresponding patient is at a high risk of stroke, and (iii) a third score indicating that the corresponding patient is not at a high risk of stroke; and
providing target therapy candidate data generated based on the set of target therapy scores;
based on the provided target therapy candidate data, identifying a selected patient from the plurality of patients, the target therapy score corresponding to the selected patient being the second score indicating that the selected patient is at the high risk of stroke; and
after identifying the selected patient, implanting a LAA occluder into the LAA of the selected patient to occlude the LAA of the selected patient.
2. The method of claim 1 , wherein the target therapy candidate data identifies one or more candidate patients having a target therapy score that meets a target therapy score threshold.
3. The method of claim 1 , wherein the target therapy candidate data includes an individual report for at least one patient of the plurality of patients.
4. The method of claim 1 , wherein the target therapy candidate data includes aggregate data for one or more target therapy classifications over one or more groupings of the plurality of patients.
5. The method of claim 1 , wherein generating the candidate classification model for the target therapy includes:
assigning one or more negative weights to one or more medical codes corresponding to one or more exclusion criteria for the target therapy; and
assigning one or more positive weights to one or more medical codes corresponding to one or more inclusion criteria for the target therapy.
6. The method of claim 1 , wherein generating the candidate classification model includes:
grouping two or more medical codes in the set of medical codes into a code group; and
assigning a single weight to the code group to indirectly assign weights to the two or more medical codes of the code group.
7. The method of claim 1 ,
wherein receiving the patient billing data includes receiving the patient billing data from a medical organization;
wherein providing the target therapy candidate data set comprises providing the set of target therapy scores to the medical organization;
wherein the patient billing data is received from the medical organization in a deidentified form; and
wherein the target therapy candidate data references individual patients in the plurality of patients by pseudonym.
8. The method of claim 1 , wherein generating the candidate classification model includes use of machine learning techniques to assign one or more weights of the candidate classification model based on a training data set comprising:
input data comprising associations between medical codes and a plurality of sample patients; and
output data comprising a sample target therapy score for each sample patient of the plurality of sample patients.
9. The method of claim 1 , further comprising:
receiving care provider review data corresponding to one or more target therapy scores of the set of target therapy scores; and
updating the candidate classification model by adjusting one or more weights assigned to the one or more medical codes of the set of medical codes based on the care provider review data.