Integrating E-Prescribing and Pharmacy Claims Data for Predictive Modeling: Comparing Costs and Utilization of Health Plan Members Who Fill Their Initial Medications with Those Who Do Not

Challenges and advantages of electronic prescribing system: a survey study and thematic analysis

INTRODUCTION

Electronic prescribing (e-prescribing) systems can bring many advantages and challenges. This system has been launched in Iran for more than two years. This study aimed to investigate the challenges and advantages of the e-prescribing system from the point of view of physicians.

METHODS

In this survey study and thematic analysis, which was conducted in 2023, a researcher-made questionnaire was created based on the literature review and opinions of the research team members and provided to the physician. Quantitative data were analyzed using SPSS software, and qualitative data were analyzed using ATLAS.ti software. Rank and point biserial, Kendall's tau b, and Phi were used to investigate the correlation between variables.

RESULTS

Eighty-four physicians participated in this study, and 71.4% preferred to use paper-based prescribing. According to the results, 53.6%, 38.1%, and 8.3% of physicians had low, medium, and high overall satisfaction with this system, respectively. There was a statistically significant correlation between the sex and overall satisfaction with the e-prescribing system (p-value = 0.009) and the computer skill level and the prescribing methods (P-value = 0.042). Physicians face many challenges with this system, which can be divided into five main categories: technical, patient-related, healthcare providers-related, human resources, and architectural and design issues. Also, the main advantages of the e-prescribing system were process improvement, economic efficiency, and enhanced prescribing accuracy.

CONCLUSION

The custodian and service provider organizations should upgrade the necessary information technology infrastructures, including hardware, software, and network infrastructures. Furthermore, it would be beneficial to incorporate the perspectives of end users in the system design process.

Real-world primary nonadherence to antiobesity medications

BACKGROUND: Primary nonadherence (PNA), when a medication is newly prescribed but not filled, has been identified as a major research gap potentially impacting the optimal treatment of patients with overweight and obesity who are newly prescribed antiobesity medications (AOMs). OBJECTIVES: To assess PNA among patients with newly prescribed AOMs and to examine factors associated with PNA to AOMs. METHODS: This was a retrospective study that used the Optum Integrated Clinical plus Claims database to identify individuals who had at least 1 prescription order for an AOM the US Food and Drug Administration approved for long-term use. Individuals with prescription orders between January 1, 2012, and February 28, 2019, were identified, and patient demographics, clinical characteristics, medication prescribed, baseline health care utilization, and obesity-related complications were described by PNA status. PNA was defined as no pharmacy claim for the AOM within 60 days of the date of the new prescription order as identified in electronic health record data. A multivariable logistic regression model was used to examine factors associated with PNA. RESULTS: The study sample included a total of 1,563 patients. The mean body mass index was 38.4 kg/m2; 10.7% were prescribed liraglutide 3.0 mg, 26.0% were prescribed lorcaserin, 36.3% of patients were prescribed naltrexone-bupropion, 5.4% were prescribed orlistat, and 21.6% were prescribed phentermine-topiramate. Most patients (91.1%) exhibited PNA, with only 8.9% filling their newly prescribed AOM within 60 days. Both the adherent and nonadherent groups were predominately female sex, White, and covered by commercial insurance. The mean age was similar between the 2 groups. Most obesity-related complications were less prevalent in the adherent group, although the Charlson comorbidity index score was similar between the 2 groups. After adjustment for patient demographics and clinical characteristics, there was not a statistically significant association between the specific AOM and PNA (P = 0.299). Patients with depression or living in the Midwest or South regions were at significantly increased risk of PNA. CONCLUSIONS: The rate of PNA to AOMs was very high, suggesting barriers in effective medical management of patients with overweight and obesity. Future research is warranted to understand reasons for PNA to AOMs and how to address these barriers. DISCLOSURES: Dr Kan, Dr Bae, Dr Dunn, and Dr Ahmad are employees of Eli Lilly and Company. Ms Buysman and Dr Gronroos are employees of Optum. Dr Swindle was an employee of Optum at the time the study was conducted and is currently employed at Evidera. Dr Bengtson is employed at Boehringer Ingelheim Pharmaceuticals, Inc. (Boehringer Ingelheim has no connection to this study), and during the conduct of this study was employed at Optum.

Assessing the Added Value of Vital Signs Extracted from Electronic Health Records in Healthcare Risk Adjustment Models

Purpose

Patient vital signs are related to specific health risks and outcomes but are underutilized in the prediction of health-care utilization and cost. To measure the added value of electronic health record (EHR) extracted Body Mass Index (BMI) and blood pressure (BP) values in improving healthcare risk and utilization predictions.

Patients and Methods

A sample of 12,820 adult outpatients from the Johns Hopkins Health System (JHHS) were identified between 2016 and 2017, having high data quality and recorded values for BMI and BP. We evaluated the added value of BMI and BP in predicting health-care utilization and cost through a retrospective cohort design. BMI, mean arterial pressure (MAP), systolic and diastolic BPs were summarized as annual aggregated values. Concurrent annual BMI and MAP changes were quantified as the difference between maximum and minimum recorded values. Model performance estimates consisted of repeated 10-fold cross validation, compared to base model point estimates for demographic and diagnostic, coded events: (1) patient age and sex, (2) age, sex, and the Charlson weighted index, (3) age, sex and the Johns Hopkins ACG system’s DxPM risk score.

Results

Both categorical BMI and BP were progressively indicative of disease comorbidity, but not uniformly related to health-care utilization or cost. Annual change in BMI and MAP improved predictions for most concurrent year outcomes when compared to base models.

Conclusion

When a healthcare system lacks relevant diagnostic or risk assessment information for a patient, vital signs may be useful for a simple estimation of disease risk, cost and utilization.

Improving the Prediction of Persistent High Healthcare Utilizers: Using an Ensemble Methodology

Background

A small proportion of high-need patients persistently use the bulk of health care services and incur disproportionate costs. Population health management (PHM) programs often refer to these patients as persistent high utilizers (PHUs). Accurate PHU prediction enables PHM programs to better align scarce health care resources with high-need PHUs while generally improving outcomes. While prior research in PHU prediction has shown promise, traditional regression methods used in these studies have yielded limited accuracy.

Objective

We are seeking to improve PHU predictions with an ensemble approach in a retrospective observational study design using insurance claim records.

Methods

We defined a PHU as a patient with health care costs in the top 20% of all patients for 4 consecutive 6-month periods. We used 2013 claims data to predict PHU status in next 24 months. Our study population included 165,595 patients in the Johns Hopkins Health Care plan, with 8359 (5.1%) patients identified as PHUs in 2014 and 2015. We assessed the performance of several standalone machine learning methods and then an ensemble approach combining multiple models.

Results

The candidate ensemble with complement naïve Bayes and random forest layers produced increased sensitivity and positive predictive value (PPV; 49.0% and 50.3%, respectively) compared to logistic regression (46.8% and 46.1%, respectively).

Conclusions

Our results suggest that ensemble machine learning can improve prediction of care management needs. Improved PPV implies reduced incorrect referral of low-risk patients. With the improved sensitivity/PPV balance of this approach, resources may be directed more efficiently to patients needing them most.

Assessing the Value of Unsupervised Clustering in Predicting Persistent High Health Care Utilizers: Retrospective Analysis of Insurance Claims Data

BACKGROUND

A high proportion of health care services are persistently utilized by a small subpopulation of patients. To improve clinical outcomes while reducing costs and utilization, population health management programs often provide targeted interventions to patients who may become persistent high users/utilizers (PHUs). Enhanced prediction and management of PHUs can improve health care system efficiencies and improve the overall quality of patient care.

OBJECTIVE

The aim of this study was to detect key classes of diseases and medications among the study population and to assess the predictive value of these classes in identifying PHUs.

METHODS

This study was a retrospective analysis of insurance claims data of patients from the Johns Hopkins Health Care system. We defined a PHU as a patient incurring health care costs in the top 20% of all patients' costs for 4 consecutive 6-month periods. We used 2013 claims data to predict PHU status in 2014-2015. We applied latent class analysis (LCA), an unsupervised clustering approach, to identify patient subgroups with similar diagnostic and medication patterns to differentiate variations in health care utilization across PHUs. Logistic regression models were then built to predict PHUs in the full population and in select subpopulations. Predictors included LCA membership probabilities, demographic covariates, and health utilization covariates. Predictive powers of the regression models were assessed and compared using standard metrics.

RESULTS

We identified 164,221 patients with continuous enrollment between 2013 and 2015. The mean study population age was 19.7 years, 55.9% were women, 3.3% had ≥1 hospitalization, and 19.1% had 10+ outpatient visits in 2013. A total of 8359 (5.09%) patients were identified as PHUs in both 2014 and 2015. The LCA performed optimally when assigning patients to four probability disease/medication classes. Given the feedback provided by clinical experts, we further divided the population into four diagnostic groups for sensitivity analysis: acute upper respiratory infection (URI) (n=53,232; 4.6% PHUs), mental health (n=34,456; 12.8% PHUs), otitis media (n=24,992; 4.5% PHUs), and musculoskeletal (n=24,799; 15.5% PHUs). For the regression models predicting PHUs in the full population, the F1-score classification metric was lower using a parsimonious model that included LCA categories (F1=38.62%) compared to that of a complex risk stratification model with a full set of predictors (F1=48.20%). However, the LCA-enabled simple models were comparable to the complex model when predicting PHUs in the mental health and musculoskeletal subpopulations (F1-scores of 48.69% and 48.15%, respectively). F1-scores were lower than that of the complex model when the LCA-enabled models were limited to the otitis media and acute URI subpopulations (45.77% and 43.05%, respectively).

CONCLUSIONS

Our study illustrates the value of LCA in identifying subgroups of patients with similar patterns of diagnoses and medications. Our results show that LCA-derived classes can simplify predictive models of PHUs without compromising predictive accuracy. Future studies should investigate the value of LCA-derived classes for predicting PHUs in other health care settings.

Persistence as a Robust Indicator of Medication Adherence-Related Quality and Performance

Medication adherence is a priority for health systems worldwide and is widely recognised as a key component of quality of care for disease management. Adherence-related indicators were rarely explicitly included in national health policy agendas. One barrier is the lack of standardised adherence terminology and of routine measures of adherence in clinical practice. This paper discusses the possibility of developing adherence-related performance indicators highlighting the value of measuring persistence as a robust indicator of quality of care. To standardise adherence and persistence-related terminology allowing for benchmarking of adherence strategies, the European Ascertaining Barriers for Compliance (ABC) project proposed a Taxonomy of Adherence in 2012 consisting of three components: initiation, implementation, discontinuation. Persistence, which immediately precedes discontinuation, is a key element of taxonomy, which could capture adherence chronology allowing the examination of patterns of medication-taking behaviour. Advances in eHealth and Information Communication Technology (ICT) could play a major role in providing necessary structures to develop persistence indicators. We propose measuring persistence as an informative and pragmatic measure of medication-taking behaviour. Our view is to develop quality and performance indicators of persistence, which requires investing in ICT solutions enabling healthcare providers to review complete information on patients' medication-taking patterns, as well as clinical and health outcomes.