FROM DATA TO CLINICAL TRANSFORMATION: SELF-SERVICE ANALYTICS AS A CATALYST FOR NURSING-LED REDUCTION IN CHEMOTHERAPY TREATMENT WAIT TIMES
Author(s)
Ori Lechno, RN1, Vardit Shwartz, MD1, Damien Urban, MD1, Eden Davidor, RN1, Sigal Torati, RN1, Leenor Alfahel, Phd2, Dana Yafe, PhD2, Vicki Snavely, RN2.
1Sheba Medical Center, Tel Hashomer, Israel, 2MDClone, San Jose, CA, USA.
1Sheba Medical Center, Tel Hashomer, Israel, 2MDClone, San Jose, CA, USA.
OBJECTIVES: Oncology departments face significant operational inefficiencies in chemotherapy delivery, where treatment delays aggregate into thousands of lost inpatient hours annually. Despite abundant clinical data, healthcare teams frequently lack the tools to independently identify bottlenecks and drive real-time process improvement. This study examined whether self-service data analytics could empower front-line nursing staff to identify, act on, and monitor a systemic workflow inefficiency without IT or analyst intermediation.
METHODS: Researchers used a self-service data analytics platform to independently analyze chemotherapy treatment initiation wait times across morning and evening shifts at a tertiary oncology center performing more than 2,000 treatments annually. The departmental benchmark was treatment initiation within 3 hours of admission. Baseline performance was assessed across 2025, and a root-cause analysis was conducted using the platform without external data support. The identified bottleneck, mandatory physician sign-off for treatment initiation, informed a targeted intervention in February 2026: expanding certified oncology nurse scope of practice to independently authorize defined chemotherapy protocols for eligible patients. Post-intervention wait times were monitored continuously through May 2026.
RESULTS: At baseline, 78% of morning-shift patients and 46% of evening-shift patients waited more than 3 hours to begin treatment, with average wait times of 4.07 and 3.0 hours respectively. Following nursing scope expansion, morning-shift wait times decreased to 2.80 hours by May 2026, a 31% reduction, with evening shifts reaching equivalent improvement. Both shifts now consistently meet the 3-hour benchmark. Across more than 2,000 annual treatments, this represents thousands of recovered inpatient hours and expanded patient throughput capacity without additional infrastructure.
CONCLUSIONS: Self-service data analytics enabled a front-line nurse researcher to independently identify a high-impact operational bottleneck, design an evidence-based intervention, and demonstrate sustained improvement. The speed from insight to measurable clinical transformation illustrates the organizational value of democratizing data access in complex care settings.
METHODS: Researchers used a self-service data analytics platform to independently analyze chemotherapy treatment initiation wait times across morning and evening shifts at a tertiary oncology center performing more than 2,000 treatments annually. The departmental benchmark was treatment initiation within 3 hours of admission. Baseline performance was assessed across 2025, and a root-cause analysis was conducted using the platform without external data support. The identified bottleneck, mandatory physician sign-off for treatment initiation, informed a targeted intervention in February 2026: expanding certified oncology nurse scope of practice to independently authorize defined chemotherapy protocols for eligible patients. Post-intervention wait times were monitored continuously through May 2026.
RESULTS: At baseline, 78% of morning-shift patients and 46% of evening-shift patients waited more than 3 hours to begin treatment, with average wait times of 4.07 and 3.0 hours respectively. Following nursing scope expansion, morning-shift wait times decreased to 2.80 hours by May 2026, a 31% reduction, with evening shifts reaching equivalent improvement. Both shifts now consistently meet the 3-hour benchmark. Across more than 2,000 annual treatments, this represents thousands of recovered inpatient hours and expanded patient throughput capacity without additional infrastructure.
CONCLUSIONS: Self-service data analytics enabled a front-line nurse researcher to independently identify a high-impact operational bottleneck, design an evidence-based intervention, and demonstrate sustained improvement. The speed from insight to measurable clinical transformation illustrates the organizational value of democratizing data access in complex care settings.
Conference/Value in Health Info
2026-11, ISPOR Europe 2026, Vienna, Austria
Value in Health, Volume 29, Issue 12S
Code
HSD88
Topic
Health Service Delivery & Process of Care, Organizational Practices, Study Approaches
Disease
Oncology