Utilization of Clinical Pathways Can Reduce Drug Spend Within the Oncology Care Model.

PURPOSE: Reducing drug spend is one of the greatest challenges for practices participating in the Oncology Care Model (OCM). Evidence-based clinical pathways have the potential to decrease drug spend while maintaining clinical outcomes consistent with published evidence. The goal of this study was to determine whether voluntary use of clinical pathways by a practice can maximize OCM episodic cost savings. METHODS AND MATERIALS: A community oncology practice used evidence-based clinical pathways for OCM-attributed patients. All treatment plans were submitted to the pathway vendor in real time for clinical pathway adherence measurement. Analysis was conducted before implementation and on an ongoing daily and weekly basis to identify cases in which higher cost drugs or regimens were ordered. A clinical data governance committee met biweekly to review clinical pathway performance metrics and drug utilization. RESULTS: From quarter 1 of 2017 to quarter 1 of 2019, the median drug spend increased less rapidly for Cancer Care Specialists of Illinois (CCSI; 18.6%) compared with OCM (34.4%). Furthermore, the percent difference in drug spend for CCSI relative to OCM decreased from 13.5% to 0.1% (P < .001). Each quarter, there was approximately a 1.7% decrease (95% CI, 1.0% to 2.4%) in drug spend for CCSI relative to OCM. Additional analyses found that, over a 15-month period (October 2017 through December 2019), CCSI achieved an increase in pathway adherence from 69% to 81%. CONCLUSION: Reduction in drug spend is possible within a value-based care model, using evidence-based clinical pathways.

Using Big Data and Predictive Analytics to Determine Patient Risk in Oncology.

Big data and predictive analytics have immense potential to improve risk stratification, particularly in data-rich fields like oncology. This article reviews the literature published on use cases and challenges in applying predictive analytics to improve risk stratification in oncology. We characterized evidence-based use cases of predictive analytics in oncology into three distinct fields: (1) population health management, (2) radiomics, and (3) pathology. We then highlight promising future use cases of predictive analytics in clinical decision support and genomic risk stratification. We conclude by describing challenges in the future applications of big data in oncology, namely (1) difficulties in acquisition of comprehensive data and endpoints, (2) the lack of prospective validation of predictive tools, and (3) the risk of automating bias in observational datasets. If such challenges can be overcome, computational techniques for clinical risk stratification will in short order improve clinical risk stratification for patients with cancer.