A 4-Year Retrospective Claims Analysis of Oral Corticosteroid Use and Health Conditions in Newly Diagnosed Medicare FFS Patients with COPD.

Purpose: We analyzed population-level administrative claims data for Medicare fee-for-service (FFS) beneficiaries to provide insights on systemic oral corticosteroid (OCS) use patterns and associated health conditions and acute events among patients newly diagnosed with chronic obstructive pulmonary disease (COPD). Background: COPD is a progressive inflammatory disease of the lungs, characterized by acute exacerbations that may lead to increased mortality. Short courses of systemic corticosteroids (SCS) are recommended to reduce recovery time from exacerbations, although SCS use has been associated with increased risk of adverse events. Methods: This study used 2013-2019 Medicare 100% FFS research identifiable files, which contain all Medicare Parts A, B, and D paid claims incurred by 100% of Medicare FFS beneficiaries. Descriptive statistics for patients newly diagnosed with COPD were analyzed, including OCS use, select health conditions and acute events, and COPD exacerbations. Statistical models were used to analyze the relationship between the incidence of select health conditions and events and cumulative OCS dosage. Results: Of Medicare FFS patients newly diagnosed with COPD, 36% received OCS in the 48 months following diagnosis, and 38% of OCS episodes lasted longer than the recommended 5-7 days. Patients had a variety of health conditions or acute events in the 24-month period prior to new COPD diagnosis, such as hypertension, depression/anxiety, type 2 diabetes, or osteoporosis, that could heighten the risks of OCS use. Patients treated with >1000 mg of prednisolone equivalent OCS in the 48 months following COPD diagnosis had a higher incidence of new conditions or events, including cardiovascular disease, heart failure, hypertension, obesity, dyspepsia, infections, and depression/anxiety, than patients with no OCS use. Conclusion: These results highlight the potential risks of OCS in COPD treatment, including prolonged use among complex Medicare patients, and reinforce the importance of preventive treatment strategies and therapy optimization early in the disease course.

Applying Machine Learning Techniques to Identify Undiagnosed Patients with Exocrine Pancreatic Insufficiency.

BACKGROUND: Exocrine pancreatic insufficiency (EPI) is a serious condition characterized by a lack of functional exocrine pancreatic enzymes and the resultant inability to properly digest nutrients. EPI can be caused by a variety of disorders, including chronic pancreatitis, pancreatic cancer, and celiac disease. EPI remains underdiagnosed because of the nonspecific nature of clinical symptoms, lack of an ideal diagnostic test, and the inability to easily identify affected patients using administrative claims data. OBJECTIVES: To develop a machine learning model that identifies patients in a commercial medical claims database who likely have EPI but are undiagnosed. METHODS: A machine learning algorithm was developed in Scikit-learn, a Python module. The study population, selected from the 2014 Truven MarketScan® Commercial Claims Database, consisted of patients with EPI-prone conditions. Patients were labeled with 290 condition category flags and split into actual positive EPI cases, actual negative EPI cases, and unlabeled cases. The study population was then randomly divided into a training subset and a testing subset. The training subset was used to determine the performance metrics of 27 models and to select the highest performing model, and the testing subset was used to evaluate performance of the best machine learning model. RESULTS: The study population consisted of 2088 actual positive EPI cases, 1077 actual negative EPI cases, and 437 530 unlabeled cases. In the best performing model, the precision, recall, and accuracy were 0.91, 0.80, and 0.86, respectively. The best-performing model estimated that the number of patients likely to have EPI was about 12 times the number of patients directly identified as EPI-positive through a claims analysis in the study population. The most important features in assigning EPI probability were the presence or absence of diagnosis codes related to pancreatic and digestive conditions. CONCLUSIONS: Machine learning techniques demonstrated high predictive power in identifying patients with EPI and could facilitate an enhanced understanding of its etiology and help to identify patients for possible diagnosis and treatment.

Pharma APMs: A Learning Curve Awaits You, Pharma.

There are some valuable lessons for pharmaceutical manufacturers in provider alternative payment models (APMs), but whether pharmaceutical APMs succeed or fail will depend on finding solutions to operational and logistical challenges-some of which are unique to the pharmaceutical industry. Pharmaceutical APMs may require the collection of information beyond the claims data that many provider APMs depend on.

Pharma APMs: Can the Industry Learn To Play Well With Others?

The alternative payment model (APM) is a nontraditional financial arrangement that rewards health care providers who deliver cost-effective, high-quality care. Now we are facing the possibility that pharmaceutical manufacturers and insurers will embrace APMs as a payment mechanism in some situations.