Research Presented at ASCO 2023 Shows Implementing Value-Based Care Strategies Such as Dose Rounding Reduces Drug Waste and Total Cost of Care

June 05, 2023

The US Oncology Network shares additional research on how certain aspects of the Enhancing Oncology Model could offer community practices financial protection and how machine learning can increase access to care

THE WOODLANDS, Texas, June 5, 2023 — Principal investigators from The US Oncology Network (The Network), the largest organization of its kind dedicated to advancing local cancer care and better patient outcomes, presented findings at the 2023 American Society of Clinical Oncology (ASCO) Annual Meeting showing that dose rounding resulted in less drug waste and increased cost savings.

Waste from partially used single dose vials of expensive drugs is a leading contributor to avoidable total cost of care (TCOC) expenditures. In response, a dose-rounding program was adopted by many practices in The Network participating in the Centers for Medicare & Medicaid Innovation (CMMI) Oncology Care Model (OCM), a program aimed at providing higher quality and more coordinated care at the same or lower cost to Medicare. Investigators looked at data accumulated prior to and after the dose rounding program began in 2018 and researched the impact of the program targeting bevacizumab and its biosimilars (B+B) on TCOC and drug waste. They found:

  • Drug waste led to $156 of additional TCOC per member episode per month prior to implementation of dose rounding.
  • Dose rounding resulted in a TCOC reduction of approximately $100 per member episode per month for episodes with B+B administrations in the OCM.
  • The highest waste reduction was seen with B+B administered for treatment of gastrointestinal cancers (colon, rectal, anal, gastroesophageal, or pancreatic cancers) compared to other cancer types (lung, brain, ovarian, etc.), and in administrations where drug waste was greater than 10% of the total dose.

“These findings provide tangible evidence and insights for community oncologists, so they can reduce avoidable waste and spending and deliver value-based care for their patients and their practices,” said lead author and presenter Puneeth Indurlal, MD, MS, MBBS, senior director of Care Transformation for The US Oncology Network. “It’s encouraging to see proof that feasible measures can be taken by practices that make a huge difference on the quality and cost of care.”

Beyond this research, The Network presented two additional studies at the meeting examining how the Enhancing Oncology Model could offer financial protection against increasing drug costs and how a machine learning model could improve a patient’s access to care.

Impacting Medicare Programs with a Cancer-Specific Novel Therapy Adjustment

The Network researchers presented a poster reviewing claims and performance data from 14 practices in The Network participating in the OCM. This review looked at data from ten performance periods in the OCM, and investigators found that applying a novel therapy adjustment (NTA) at a cancer type level, rather than a population-based level, would have resulted in more instances where practices would have qualified for an adjustment of their benchmark to appropriately align the use of novel therapies with cost. Novel therapies generally come with increased expense, leading to concerns that the EOM could discourage use of novel therapies. CMMI implemented a NTA to provide financial protection to help support appropriate use of these costly therapies.

“The Network undertook this research to support practices that were considering participation in the Enhancing Oncology Model,” said lead author and presenter Erica Feinberg, PharmD, BCPS, senior clinical data analyst for The US Oncology Network. “More than 900 physicians in The Network participated in the Oncology Care Model — one fourth of the entire population of physicians nationwide. Based on our analysis, we believe that the EOM approach to NTAs applied at a cancer type level is more favorable for practices and provides valuable financial protections when incorporating clinically appropriate novel therapies for cancer treatment. We commend CMMI for making improvements to the NTA risk adjustment methodology and think this information is very helpful for those practices as they assess joining the EOM.”

Predicting Treatment Initiation with a Machine Learning Model

This study found that a machine learning model, developed by The Network to predict intravenous IV treatment initiation among new patients, would allow for targeted interventions for key populations with the goal to improve access to care. Researchers built and applied a machine learning model on data from a cohort of new cancer patients from 27 practices in The Network to evaluate various patient characteristics and their impact on patients initiating IV treatment. Researchers found that clinical characteristics, including diagnosis and stage, are the most important features to predict the patient decision to initiate IV treatment, while noting patient age and gender features as areas for focused intervention. This study confirmed that a machine learning model could guide patient service and direct personalized care navigation to enhance patient access to treatment.

“Every day, The Network, a leader in value-based cancer care, helps more than 2,300 independent providers deliver high-quality, integrated care to patients—close to home,” said Lalan Wilfong, MD, senior vice president of Payer and Care Transformation for The Network who participated in an ASCO case-based panel on payment reform. “Value-based care is here to stay, and the smooth transition from a fee-for-service to a value-based model has become critical to the survival of the community oncology practice. The Network provides independent practices with access to coordinated resources, best business practices, and actionable research, like that presented at this year’s ASCO, to help make that transition.”

About the studies

Dose rounding bevacizumab and its biosimilars to reduce drug waste in the oncology care model in a community oncology network (ASCO poster)

Claims data for 14 practices in The Network participating in the OCM were assessed. Drug administration data for B+B was used to evaluate drug waste, total dose, TCOC, dose rounding, and the financial impact of drug waste reduction on TCOC from 2017 to 2021.

The impact of a cancer-specific novel therapy adjustment (NTA) in Medicare value-based care programs: A simulation exercise (ASCO poster)

Claims and performance data from ten performance periods (PP) in the OCM (PP1 to PP10) for 14 practices in The US Oncology Network were reviewed. Descriptive statistics for the simulation were evaluated to determine changes from population-based NTA to cancer-based NTA. The OCM NTA methodology was deconstructed to apply the NTA at a cancer type level. Researchers performed a simulation exercise by applying cancer specific NTA methodology systematically to the claims and performance data. They then evaluated the impact of NTA on the EOM cancer types.

A machine learning model to predict treatment initiation among new patients in a community oncology network (ASCO publication)

A retrospective cohort was formed by identifying new patients with cancer from 27 practices in The Network between July 1, 2021, and June 30, 2022. Structured data were extracted and processed from the electronic health records, claims, physician referrals, and the American Community Survey. Patient characteristics included demographics, clinical information, payor types, and socioeconomic status. The referral pattern and the geographic region of practices, and the provider workload were considered as well. Gradient-boosted decision trees, random forest, neural network, and logistic regression models were developed to predict the probability of starting IV treatment within 90 days of the first visit. Model performance was evaluated based on the area under the receiver operating characteristic (AUROC) curve using cross-valuation and 4:1 training/validation random split. Shapley Additive Explanations (SHAP) values were applied to the model to explain feature importance.

About The US Oncology Network

Every day, The US Oncology Network (The Network) helps approximately 2,300 independent providers deliver value-based, integrated care to patients — close to home. Through The Network, these independent doctors come together to form a community of shared expertise and resources dedicated to advancing local cancer care and to delivering better patient outcomes. The Network provides practices with access to coordinated resources, best business practices, and the experience, infrastructure, and support of McKesson Corporation. This collaboration allows the providers in The Network to focus on the health of their patients, while McKesson focuses on the health of their practices. The Network is committed to the success of independent practices, everywhere.

About McKesson Oncology and Specialty Solutions

It’s an unprecedented time for patients living with cancer as life sciences companies race to create new, cutting-edge therapies. With cancer care becoming more targeted, providers, life sciences companies, and payers face a multitude of challenges and complexity in the development of new treatments and making them accessible to patients in need. At McKesson, our unmatched portfolio of oncology businesses and partners provide research, insights, technologies, and services that are helping to address these hurdles and improve cancer and specialty care.

  • McKesson is fueling discovery by helping patients participate in cutting-edge clinical trials closer to home through the joint venture between US Oncology Research and Sarah Cannon Research Institute.
  • The US Oncology Network and McKesson Provider Solutions are advancing specialty care and high-quality cancer care in the communities where patients live by supporting the practices of thousands of independent, community-based providers.
  • Ontada®, a McKesson business dedicated to oncology, generates real-world data (RWD) and real-world evidence (RWE) and provides clinical education and provider technology to inform and improve cancer care.
  • As one of the largest distributors of oncology and specialty medicines, we are ensuring medicines make their way to the those who are counting on them.
  • And through CoverMyMeds, Biologics by McKesson, and GPO services, our work continues to help patients access, afford, and adhere to their medicines.

Public Relations Contact