Modifying a patient adherence score
Systems and techniques are disclosed for determining an intervention for a patient based at least in part on a likelihood of the patient to adhere to a prescription. In some implementations, a patient profile for a patient is obtained from one or more computer-readable storage devices in a patient population, the patient profile including multiple patient attributes; an adherence score is obtained for the patient profile, the adherence score for predicting patient adherence based on one or more of the multiple patient attributes wherein the adherence score indicates a likelihood of adherence of the patient to a prescribed treatment; and the adherence score obtained for the patient profile is modified into a modified score for intervention based on a set of weights for weighting the patient attributes.
1. A computer-implemented method for modifying a patient adherence score, the method comprising:
obtaining, by a computer system from one or more computer-readable storage devices, patient profiles in a patient population, each of the patient profiles including multiple patient attributes;
for each patient profile from among the patient profiles in the patient population,
obtaining, by the computer system, an adherence score based on one or more of the multiple patient attributes, wherein the adherence score indicates a likelihood of adherence of a patient associated with the patient profile to a prescribed treatment;
modifying, by the computer system, the adherence score obtained for the patient profile, based on a first set of weights for a type of intervention, into a first modified adherence score for the type of intervention;
stratifying, by the computer system, the patient profiles in the patient population based on the first modified adherence scores for the type of intervention;
grouping, by the computer system, the stratified patient profiles into two or more groups based on said stratifying;
for each patient profile from among patient profiles in at least one of the groups, modifying, by the computer system, the first modified adherence score for the type of intervention for the patient profile, with a second set of weights for intervention timing, into a second modified adherence score for the intervention timing with respect to the type of intervention;
sub-grouping, by the computer system, the patient profiles from the at least one of the groups into sub-groups based on the second modified adherence scores for the intervention timing with respect to the type of intervention; and
implementing an intervention campaign, corresponding to the intervention timing and the type of intervention, for the patient profiles from the at least one of the groups based on in which sub-group the patient profiles belong.
2. The method of claim 1 , wherein the type of the intervention comprises a cost of the intervention campaign.
3. The method of claim 1 , wherein the intervention timing comprises a frequency for performing the intervention campaign.
4. The method of claim 1 , wherein the intervention timing is a function of a dosing schedule or a refill schedule for a prescription for a patient.
5. The method of claim 1 , wherein the at least one of the groups comprises patient profiles from among the stratified patient profiles which correspond to patients in the population whose behavior is most likely to change as a result of the type of intervention.
6. The method of claim 1 , wherein the grouping comprises combining the stratified patient profiles into the group to receive the intervention campaign based at least in part on a cost of implementing the intervention campaign.
7. A non-transitory computer-readable storage medium storing instructions, which, when executed by a processor, causes the processor to perform operations comprising
obtaining patient profiles in a patient population, each of the patient profiles including multiple patient attributes;
for each patient profile from among the patient profiles in the patient population,
obtaining an adherence score based on one or more of the multiple patient attributes, wherein the adherence score indicates a likelihood of adherence of a patient associated with the patient profile to a prescribed treatment;
modifying the adherence score obtained for the patient profile, based on a first set of weights for a type of intervention, into a first modified adherence score for the type of intervention;
stratifying the patient profiles in the patient population based on the first modified adherence scores for the type of intervention;
grouping the stratified patient profiles into two or more groups based on the operation of stratifying;
for each patient profile from among patient profiles in at least one of the groups, modifying the first modified adherence score for the type of intervention for the patient profile, with a second set of weights for intervention timing, into a second modified adherence score for the intervention timing with respect to the type of intervention;
sub-grouping the patient profiles from the at least one of the groups into sub-groups based on the second modified adherence scores for the intervention timing with respect to the type of intervention; and
implementing an intervention campaign, corresponding to the intervention timing and the type of intervention, for the patient profiles from the at least one of the groups based on in which sub-group the patient profiles belong.
8. The non-transitory computer-readable storage medium of claim 7 , wherein the type of the intervention a cost of the intervention campaign.
9. The non-transitory computer-readable storage medium of claim 7 , wherein the operation of grouping comprises combining the stratified patient profiles into the group to receive the intervention campaign based at least in part on a cost of implementing the intervention campaign.
10. The non-transitory computer-readable storage medium of claim 7 , wherein the intervention timing comprises a frequency for performing the intervention campaign.
11. The non-transitory computer-readable storage medium of claim 7 , wherein the intervention timing is a function of a dosing schedule or a refill schedule for a prescription for a patient.
12. The non-transitory computer-readable storage medium of claim 7 , wherein the at least one of the groups comprises patient profiles from among the stratified patient profiles which correspond to patients in the population whose behavior is most likely to change as a result of the type of intervention.
13. A system comprising
one or more processors; and
non-transitory computer-readable medium encoding instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
obtaining patient profiles in a patient population, each of the patient profiles including multiple patient attributes;
for each patient profile from among the patient profiles in the patient population,
obtaining an adherence score based on one or more of the multiple patient attributes, wherein the adherence score indicates a likelihood of adherence of a patient associated with the patient profile to a prescribed treatment;
modifying the adherence score obtained for the patient profile, based on a first set of weights for a type of intervention, into a first modified adherence score for the type of intervention;
stratifying the patient profiles in the patient population based on the first modified adherence scores for the type of intervention;
grouping the stratified patient profiles into two or more groups based on the operation of stratifying;
for each patient profile from among patient profiles in at least one of the groups, modifying the first modified adherence score for the type of intervention for the patient profile, with a second set of weights for intervention timing, into a second modified adherence score for the intervention timing with respect to the type of intervention;
sub-grouping the patient profiles from the at least one of the groups into sub-groups based on the second modified adherence scores for the intervention timing with respect to the type of intervention; and
implementing an intervention campaign, corresponding to the intervention timing and the type of intervention, for the patient profiles from the at least one of the groups based on in which sub-group the patient profiles belong.
14. The system of claim 13 , wherein the type of the intervention a cost of the intervention campaign.
15. The system of claim 13 , wherein the operation of grouping comprises combining the stratified patient profiles into the group to receive the intervention campaign based at least in part on a cost of implementing the intervention campaign.
16. The system of claim 13 , wherein the intervention timing comprises a frequency for performing the intervention campaign.
17. The system of claim 13 , wherein the intervention timing is a function of a dosing schedule or a refill schedule for a prescription for a patient.
18. The system of claim 13 , wherein the at least one of the groups comprises patient profiles from among the stratified patient profiles which correspond to patients in the population whose behavior is most likely to change as a result of the type of intervention.