PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 29, 2026Journal of Clinical Oncology0 citations

Impact of the Navya Earthshot–enabled clinical decision support system on treatment turnaround time in oncology care: A real-world study from a tertiary cancer center in India.

View Full Paper
UMUmesh MahantshettyRMRaviteja MiriyalaSSShveta Sharma

Key Points

  • This study aims to evaluate the impact of the Navya Earthshot clinical decision support system on treatment turnaround time in oncology care.
  • Prospective, pre–post observational study conducted in two phases
  • Baseline data collected prior to Navya Earthshot integration and compared with post-implementation data
  • Statistical comparisons performed using the Mann–Whitney U test
  • Median turnaround time decreased from 21.4 days pre-implementation to 16.73 days post-implementation, a reduction of 21.8% (p < 0.05)
  • Statistically significant reduction in overall treatment turnaround time observed post-implementation
  • Faster progression from patient registration to treatment decision noted in the post-implementation cohort

Abstract

1588 Background: Delays in Oncology care often result from systemic inefficiencies and patient-related barriers, leading to delayed treatment decision. Navya Earthshot is a validated Artificial Intelligence (AI) enabled clinical decision support system that matches patient records to standard-of-care oncology guidelines to generate evidence-based treatment recommendations. This study evaluated the real-world impact of Navya Earthshot implementation at a Tertiary Cancer Centre in India on turnaround time (TAT) for cancer directed treatment decision. Methods: This was a prospective, pre–post observational study conducted in two phases at a tertiary cancer centre in India. Baseline data collected prior to Navya Earthshot integration (December 2023–February 2024; n = 148) were compared with data from the post-implementation phase (February 2025–May 2025; n = 488). Navya Earthshot was embedded into routine clinical workflows, matching patient-specific clinical information to National Cancer Grid (NCG) guidelines to generate treatment options. These recommendations were reviewed by treating oncologists and discussed in daily multidisciplinary tumour boards. Patients were tracked from registration through diagnostic completion to treatment decision. The primary outcome was the turnaround time (TAT) for treatment decision, defined as the number of days from patient registration to treatment decision. Statistical comparisons were performed using the Mann–Whitney U test, with significance set at p < 0.05. Results: A total of 636 patients were included in the analysis, with 148 (pre-implementation phase) and 488 (post-implementation phase). Median TAT decreased from 21.4 Interquartile Range (IQR) days pre-implementation to 16.73 days (IQR) post-implementation, representing a 21.8% reduction ( p < 0.05). The use of the Navya Earthshot decision support system was associated with a statistically significant reduction in overall TAT. This reduction reflects faster progression from patient registration through diagnostic completion to treatment decision in the post-implementation cohort. Conclusions: Integration of Navya Earthshot-enabled decision support system significantly improved treatment decision timelines in a high-volume public oncology setting. These findings demonstrate that scalable, guideline-aligned, patient-centric AI solutions can enhance workflow efficiency and strengthen end-to-end cancer care delivery in resource-constrained environments. Impact of Navya Earthshot implementation on turnaround time for treatment decision. Metric Pre-ImplementationPhase Post- ImplementationPhase % Change p-value Turnaround Time (TAT) 21.4 days 16.73 days ↓ 21.8% <0.05

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Mahantshetty et al. (2026) studied this question.

synapsesocial.com/papers/6a192e68fab5b468c44176fehttps://doi.org/10.1200/jco.2026.44.16_suppl.1588
Ask AI
Helpful
Bookmark
Share
View Full Paper