Impact of a centralized population health pharmacy program on value-based Medicare patients.

BACKGROUND: Memorial Healthcare System (MHS) participated in the Centers for Medicare and Medicaid Services Bundled Payments for Care Improvement Advanced value-based program aimed to improve patient care and reduce health care costs. Challenges with medication therapy problems (MTPs) led to the development of a centralized tele-health population health pharmacy program. This innovative approach aimed to provide comprehensive postdischarge medication support and resolve MTPs during the 90-day risk period. OBJECTIVES: The program aimed to provide longitudinal medication support, resolve MTPs, and affect 90-day readmission rates. PRACTICE DESCRIPTION: MHS established uniform workflows, a pharmacy task force, and a dual pharmacy team approach with population health registered nurses (PHRNs). The population health pharmacists (PHPs) conducted postdischarge telephonic encounters to resolve MTPs longitudinally throughout the risk period. PRACTICE INNOVATION: The program used a centralized tele-health model with electronic health record-integrated tools. It targeted readmission rates up to 90 days, beyond the conventional 30-day period. PHPs collaborated with onsite transitions of care pharmacists, PHRNs, and health care professionals for coordinated patient care and MTP resolution. EVALUATION METHODS: A retrospective analysis using descriptive statistics, a Kruskal-Wallis test, and multivariate regression models after stratifying patients into 4 groups were used to assess MTP resolution rates and differences in readmission rates. RESULTS: Over 7 months, PHPs completed 801 telephonic visits, identifying 433 MTPs with a 94% resolution rate. The program led to a statistically significant reduction in 90-day readmission rates from 35% to a range of 10%-17% (P < 0.01). CONCLUSION: The centralized tele-health population health pharmacy program improved patient outcomes, resolved MTPs, and reduced readmission rates. The program serves as a model for integrating pharmacists into value-based care initiatives.

Statins utilization trends and expenditures in the U.S. before and after the implementation of the 2013 ACC/AHA guidelines.

Importance: Statins are drugs of choice in treating hyperlipidemia and preventing or reducing cardiovascular diseases. Purpose: Explore statins utilization and expenditure trends in the United States before and after the publication of the 2013 ACC/AHA guidelines. Method: A retrospective, cross-sectional study of US noninstitutionalized civilians was conducted using MEPS data from 2008 to 2019. Adults who were ≥ 40 years old and who reported taking statins were included in the study. Primary outcomes: Statins use patterns, total cost, and out-of-pocket spending in the general adults who reported taking statins medications. Expenditures were expressed in 2019 US dollars. Results: In this study, 409,804 individuals were eligible to be included (mean age [SE], 59 [0.1] years; 54% female). Of those participants, 22% reported taking statin therapy, and 11% of them filled only one statin prescription. The number of individuals in the general population who reported taking any statin climbed from 31 million (12%) in 2008-2009 to 92 million (35%) in 2018-2019, representing a 197% increase. After 2013, the number of individuals who used statins increased by 149%, from 37 million in 2012-2013 to 92 million users in 2018-2019. The annual number of statins prescriptions increased from 461 million to 818 million (77%; p = 0.000) between 2008 and 2019. Atorvastatin was the most prescribed medication in the statins class (36%), followed by simvastatin (34%). The moderate-intensity statins were the most used by the participants (60%). The total statins cost in 2013 was $8 billion and increased to $10 billion in 2019 (25%; p = 0.000). The total OOP expenditure trend sloped from $4.0 billion in the 2008-2009 cycle to $3.1 billion in 2018-2019. The average OOP paid by Asians was higher than that of other races at $141. Conclusion: The proportion of individuals who used statins significantly increased following the adoption of the 2013 ACC/AHA guidelines. The findings, however, demonstrated suboptimal prescribing trends of high-intensity statins, which need to be addressed by the stakeholders to maximize medication outcomes. Statins expenditures, especially the co-payments, significantly decreased. The results have shown that revised or new regulations have a substantial impact on the healthcare industry.

Deep Learning-Based Survival Analysis for Receiving a Steatotic Donor Liver Versus Waiting for a Standard Liver.

BACKGROUND: An emerging strategy to expand the donor pool is the use of a steatotic donor liver (SDLs; ≥ 30% macrosteatosis on biopsy). With the obesity epidemic and prevalence of nonalcoholic fatty liver disease, SDLs have been reported in 59% of all deceased donors. Many potential candidates need to decide whether to accept an SDL offer or remain on the waitlist for a nonsteatotic donor liver (non-SDL). The objective of this study was to compare the survival of accepting an SDL vs using a non-SDL after waiting various times. METHODS: Using data from the United States' organ procurement and transplantation network, deep survival learning predictive models were built to compare post-decision survival after accepting an SDL vs waiting for a non-SDL. The comparison subjects contain simulated 20,000 different scenarios of a candidate either accepting an SDL immediately or receiving a non-SDL after waiting various times. The research variables were selected using the LASSO-Cox and Random Survival Forest (RSF) models. The Cox proportional hazards and RSF models were also comparatively included for survival prediction. In addition, personalized survival curves for randomly selected candidates were generated. RESULT: Deep survival learning outperformed Cox proportional hazards and RSF in predicting the survival of liver transplants. Among the simulations, 25% to 30% of scenarios demonstrated a higher 3-year survival post-decision for candidates accepting an SDL than waiting and receiving a non-SDL. The difference was only 1.43% in 3-year survival post-decision between accepting an SDL and waiting 260 days (mean waitlist time) for a non-SDL. As the number of days on the waitlist increases, the difference in survival between accepting SDLs and waiting for non-SDLs decreases. CONCLUSIONS: Appropriately used SDLs could expand the donor pool and relieve the candidates' unmet need for donor livers, which presents long-term survival benefits for recipients.

Machine learning algorithms to predict major adverse cardiovascular events in patients with diabetes.

BACKGROUND: Major Adverse Cardiovascular Events (MACE) are common complications of type 2 diabetes mellitus (T2DM) that include myocardial infarction (MI), stroke, and heart failure (HF). The objective of the current study was to predict MACE among T2DM patients. METHODS: Type 2 diabetes mellitus patients above 18 years old were recruited for the study from the All of Us Research Program. Eligible participants were those who took sodium-glucose cotransporter 2 inhibitors. Different Machine learning algorithms: including RandomForest (RF), XGBoost, logistic regression (LR), and weighted ensemble model (WEM) were employed. Clinical attributes, electrolytes and biomarkers were explored in predicting MACE. The feature importance was determined using mean decrease accuracy. RESULTS: Overall, 9, 059 subjects were included in the analyses, of which 5197 (57.4%) were females. The XGBoost Model demonstrated a prediction accuracy of 0.80 [0.78-0.82], which is higher as compared to the RF 0.78[0.76-0.80], the LR model 0.65 [0.62-0.67], and the WEM 0.75 [0.73-0.76], respectively. The classification accuracy of the models for stroke was more than 95%, which was higher than prediction accuracy for MI (∼85%), and HF (∼80%). Phosphate, blood urea nitrogen and troponin levels were the major predictors of MACE. CONCLUSION: The ML models had shown acceptable performance in predicting MACE in T2DM patients, except the LR model. Phosphate, blood urea nitrogen, and other electrolytes were important predictors of MACE, which is consistent between the individual components of MACE, such as stroke, MI, and HF. These parameters can be calibrated as prognostic parameters of MACE events in T2DM patients.

Application of Machine Learning Algorithms to Predict Uncontrolled Diabetes Using the All of Us Research Program Data.

There is a paucity of predictive models for uncontrolled diabetes mellitus. The present study applied different machine learning algorithms on multiple patient characteristics to predict uncontrolled diabetes. Patients with diabetes above the age of 18 from the All of Us Research Program were included. Random forest, extreme gradient boost, logistic regression, and weighted ensemble model algorithms were employed. Patients who had a record of uncontrolled diabetes based on the international classification of diseases code were identified as cases. A set of features including basic demographic, biomarkers and hematological indices were included in the model. The random forest model demonstrated high performance in predicting uncontrolled diabetes, yielding an accuracy of 0.80 (95% CI: 0.79-0.81) as compared to the extreme gradient boost 0.74 (95% CI: 0.73-0.75), the logistic regression 0.64 (95% CI: 0.63-0.65) and the weighted ensemble model 0.77 (95% CI: 0.76-0.79). The maximum area under the receiver characteristics curve value was 0.77 (random forest model), while the minimum value was 0.7 (logistic regression model). Potassium levels, body weight, aspartate aminotransferase, height, and heart rate were important predictors of uncontrolled diabetes. The random forest model demonstrated a high performance in predicting uncontrolled diabetes. Serum electrolytes and physical measurements were important features in predicting uncontrolled diabetes. Machine learning techniques may be used to predict uncontrolled diabetes by incorporating these clinical characteristics.

Exploratory Analysis of Survival and Mortality Rates among Older Lung Cancer Patients Utilizing Different Treatment Modalities.

Objective: To explore the impact of different lung cancer treatment modalities on survival time and mortality rates in older patients. Methods: The Surveillance Epidemiology and End Results (SEER) database was used to identify lung cancer patients aged ≥50 years old in the United States. Descriptive statistics and trend charts from 2000 to 2016 were generated. Regression analysis was performed among lung cancer patients to explore the association between survival time and treatment utilization (chemotherapy, radiation, and surgery). A regression model was also applied to explore the association between treatment modalities and odds of dying. Results: A total of 826,217 patients were diagnosed with lung cancer between 2000-2016. The number of lung cancer cases increased by 7%, and the average annual frequency was 48,529 cases per year. Survival, mortality, and treatment utilization varied over the years based on demographic, clinical characteristics, and social status. Five-year survival rate was less than 10% among the study population, and 84% of included lung cancer patients died. Chemotherapy was more commonly used (62%), followed by radiation (35%) and surgical interventions (22%). Chemotherapy and surgery showed a survival advantage. The odds of dying were two times higher among patients treated with surgery than those who were not (OR: 2.62, 95%Cl: 2.58-2.67). Conclusion: This study highlighted the importance of considering treatment modalities and individual patient characteristics, which may impact survival times and mortality rates among older lung cancer patients.

Cost Effectiveness of Dapagliflozin Added to Standard of Care for the Management of Diabetic Nephropathy in the USA.

BACKGROUND: Angiotensin-converting enzyme inhibitors have been used as the standard of care for the treatment of diabetic nephropathy. Recently, dapagliflozin has been shown to reduce diabetic nephropathy when added to the standard of care. OBJECTIVE: The objective of this study was to determine the cost effectiveness of dapagliflozin added to the standard of care in diabetic nephropathy in the United States of America (USA). METHODS: A Markov model was developed to determine the cost-effectiveness outcomes from the Medicare/Medicaid health coverage perspective. Model inputs were derived from the literature. The primary outcomes were total costs, quality-adjusted life-years (QALYs), and the incremental cost-effectiveness ratio. Deterministic and probabilistic sensitivity analyses were performed to determine the robustness of our results. A willingness-to-pay threshold of $100,000 per QALY was applied, which is based on previous studies. RESULTS: Dapagliflozin yielded a lifetime QALY of 2.8. The discounted QALY associated with the standard of care was 2.6. The standard of care was the less costly treatment with a lifetime cost of $106,150.25 as compared with dapagliflozin, which costs $110,689.25. Dapagliflozin demonstrated an incremental cost-effectiveness ratio of $21,141.51 per additional QALY. The most influential parameters of the incremental cost-effectiveness ratio were the adverse drug reaction-related cost of the standard of care and dapagliflozin, the acquisition cost, and the adverse drug reaction-related cost of dapagliflozin. The effects and costs of the interventions were consistent between base-case analyses and the probabilistic model (incremental cost-effectiveness ratio: $19,023.35 [$13,637.8-$27,483.1]). CONCLUSIONS: Dapagliflozin added to the standard of care was cost effective relative to the standard of care alone in the USA for patients with diabetic nephropathy.

Exploring job satisfaction among pharmacy professionals in the Arab world: a multi-country study.

OBJECTIVES: The study objectives were to (1) describe the characteristics of the pharmacy professionals and (2) explore the association between job satisfaction and factors, such as work control, work stress, workload and organization and professional commitments. METHODS: This study was a cross-sectional design. The survey items were mainly adapted from the US National Pharmacist Workforce Survey. An electronic (Qualtrics) questionnaire was posted on pharmacist social media in several Arab countries. The survey link was posted from 22 March 2021 to 1 May 2021. The multiple linear regression measured the association between 12 independent variables and pharmacist job satisfaction. KEY FINDINGS: A total of 2137 usable surveys were received from pharmacists (54.7% female) working in 18 Arabic countries. The job satisfaction rate varied among countries in the Arab world. The fields with the highest satisfaction average included pharmaceutical marketing, academia and the pharmaceutical industry. At the same time, pharmacists working in community pharmacy and Ministry of Health/administrative positions had the lowest satisfaction rates. Overall, pharmacist satisfaction was average (3.1 out of 5). The pharmacists had the lowest satisfaction averages with income and job expectations. The pharmacists with bachelor's degrees had significantly lower satisfaction than pharmacists with postgraduate degrees. Male pharmacists had significantly higher job satisfaction compared with female pharmacists. Workload and the feelings of organization and professional commitments had significant positive associations with job satisfaction. CONCLUSIONS: The pharmacy profession in Arabic countries faced several challenges that negatively impacted job satisfaction. Improving work environment, professional management, income and organization loyalty is necessary to enhance pharmacist job satisfaction.

Smartphones: dermatologic impact of the digital age.

As smartphones continue to gain popularity, skin changes to the fifth digit caused by extended use of these devices will become more prevalent. A 20-item survey was designed to assess smartphone use and skin changes that may be associated with smartphone use. This study is an initial step in uncovering a possible phenomenon of smartphone use affecting the digits, namely the fifth digit.