Can purchasing information be used to predict adherence to cardiovascular medications? An analysis of linked retail pharmacy and insurance claims data

Abstract

ObjectiveThe use of retail purchasing data may improve adherence prediction over approaches using healthcare insurance claims alone.DesignRetrospective.Setting and participantsA cohort of patients who received prescription medication benefits through CVS Caremark, used a CVS Pharmacy ExtraCare Health Care (ECHC) loyalty card, and initiated a statin medication in 2011.OutcomeWe evaluated associations between retail purchasing patterns and optimal adherence to statins in the 12 subsequent months.ResultsAmong 11 010 statin initiators, 43% were optimally adherent at 12 months of follow-up. Greater numbers of store visits per month and dollar amount per visit were positively associated with optimal adherence, as was making a purchase on the same day as filling a prescription (p<0.0001 for all). Models to predict adherence using retail purchase variables had low discriminative ability (C-statistic: 0.563), while models with both clinical and retail purchase variables achieved a C-statistic of 0.617.ConclusionsWhile the use of retail purchases may improve the discriminative ability of claims-based approaches, these data alone appear inadequate for adherence prediction, even with the addition of more complex analytical approaches. Nevertheless, associations between retail purchasing behaviours and adherence could inform the development of quality improvement interventions.

Adherence predictor variables in AIDS patients: an empirical study using the data mining-based RFM model

“…The data of AIDS outpatients from August 1, 2009, to December 31, 2019 were exported from the HIS of the research unit using the methods from literature [ 25 , 26 , 29 , 30 ]. The fields included the consultation time, patient’s identification card number, gender, age, place of residence (local/no-local) and medical costs, for a total of 257,305 data elements (16,440 patients).…”

Adherence predictor variables in AIDS patients: An empirical study using the data mining-based RFM model

“…The data were cleaned, and the following elds were expanded by the methods used in literature [25][26]30]: (1) The consultation time eld was expanded to "recent consultation month", with December 2019 as the rst month, November 2019 as the second month and so on until August 2009 as the 125th month;…”

“…In this experiment, we tested the RFM and RFm models with several clustering analysis and decision algorithms to determine the best components to construct and evaluate the adherence prediction model. We employed methods from literature [25][26]29] and used the RFM model theory as follows: (1) The three elds of recent consultation month, consultation frequency and total medical costs were used for the RFM model [26]; (2) The three elds of recent consultation month, consultation frequency and average medical costs per visit were used for the RFm model [25,29]. Three clustering methods (K-means, Kohonen and two-step clustering) were used to construct the clustering models, in which four decision algorithms (C5.0, classi cation and regression tree (CART), Chi-square Automatic Interaction Detector (CHAID) and Quick, Unbiased, E cient, Statistical Tree (QUEST)) were used in each model to construct several preliminary prediction models.…”

“…Thus, there were some attempts to build adherence prediction models. Krumme AA [25] used the classical recency, frequency and monetary value (RFM) model [26] in the customer relationship management (CRM) theory [26][27][28] to predict that the adherence of the patients buying cardiovascular drugs from retail pharmacies was positively correlated with the number of store visits per month and the dollar amount per visit. Zare Hosseini Z [26] employed clustering analysis and decision algorithms in an RFM model-based data mining for the prediction using the data of patients in Iran and found that the adherence in hospital patients is associated with the recent consultation time, hospital treatment cycle, consultation frequency and total amount paid.…”

“…that is used in the CRM theory in various industries. Zare Hosseini Z[26] used the total medical costs (RFM model), whereas Krumme AA[25] used the average cost per visit (RFm) model for the analysis. Aiming to have an overall assessment of the RFM/m models and different clustering analysis and decision algorithms, we constructed RFM and RFm models, and evaluated the predictor variable stability and clustering model robustness to nd the best elements.…”