303 Background: Aggressive medical interventions and associated high costs of care for cancer pts near the EOL are common. Addressing this issue at the local level requires an accurate, automated process to merge real-time clinical EHR data with cost data for performance reporting. Methods: This was a single-center, observational cohort study of decedents treated with anticancer therapy (antiCT) in the last 6 months of life from January 2016 to October 2017. Pts were stratified by antiCT use in the last 30 days of life. The primary outcome measure was total cost of care. Secondary outcome measures (hospitalizations, ER and ICU utilization, antiCT use, and hospice referral) were obtained through Flatiron Health EHR-based automated data processing. Cost data were merged from the Value-Driven Outcomes analytics framework. Results: 650 pts were included. 228 (35.1%) received antiCT in the 30 days before death. Non-drug costs for pts who received antiCT in the last 30 days of life were higher than those who did not (p < 0.01, median 38X higher). A higher proportion of pts who received antiCT in the last 30 days of life had ≥1 ER visit (29.4% vs 9.5%, p < 0.01) and hospital admission (58.8% vs 27.3%, p < 0.01) during the last 30 days. In addition, more of these pts received ICU care (35.5% vs 11.4%, p < 0.01). AntiCT in the last 30 days was associated with shorter median time from first hospice referral to death (1.4 vs 4.7 weeks; IQR 0.7-2.0 vs 3.14-7.7 weeks, p < 0.01). Distribution of antiCT types administered to pts in the last 30 days versus those given antiCT > 30 days from the EOL was significantly different, with the most substantial difference seen in the proportion of pts receiving immunotherapy (20.2% vs 12.6%, p = 0.04). Conclusions: Real-time assessment of EOL outcomes shows antiCT in the last 30 days of life is associated with aggressive medical interventions and increased total cost of care. Future research should identify pts who are unlikely to benefit from aggressive care, and whether performance reporting to oncologists will reduce futile interventions near the EOL.

BACKGROUND Evidence supports streamlined approaches for inpatients with community-acquired pneumonia (CAP) including early transition to oral antibiotics and shorter therapy. Uptake of these approaches is variable and best approaches to local implementation of infection-specific guidelines are unknown. Our objective was to evaluate the impact of a clinical decision support (CDS) tool linked with a clinical pathway on CAP care. METHODS This is a retrospective, observational pre-post intervention study of inpatients with pneumonia admitted to a single academic medical center. Interventions were introduced in three sequential six-month phases; Phase 1: Education alone; Phase 2: education and a CDS driven CAP pathway coupled with active antimicrobial stewardship and provider feedback, and Phase 3: education and CDS driven CAP pathway without active stewardship. The twelve months preceding the intervention were used as a baseline. Primary outcomes were length of intravenous antibiotic therapy and total length of antibiotic therapy. Clinical, process and cost outcomes were also measured. RESULTS The study included 1021 visits. Phase 2 was associated with significantly lower length of intravenous and total antibiotic therapy, higher procalcitonin lab utilization and a 20% cost reduction compared to baseline. Phase 3 was associated with significantly lower length of intravenous antibiotic therapy and higher procalcitonin lab utilization compared to baseline. CONCLUSIONS A CDS-driven CAP pathway supplemented by active antimicrobial stewardship review led to the most robust improvements in antibiotic use and decreased costs with similar clinical outcomes.