Researchpredictive analyticsoncologyhealth economicselectronic health records
Predictive Model Reduces Oncology Acute Care Costs
8.0
Stanford researchers analyzed 20,556 oncology patients treated 2010–2022 to estimate cost savings from deploying a predictive model for acute care use (ACU) after systemic therapy. They found 3,820 (18.6%) experienced ACU, with average total ACU patient costs $17,031.92 versus $9,591.06 for non-ACU, and modeled savings of $910,000 in year 1 rising to $9.46 million by year 6, totaling $31.11 million avoided over six years assuming 35% prevention.
Key Points
- 1Report demonstrates 18.6% (3,820/20,556) patients experienced ACU, increasing mean costs substantially
- 2Quantify model-driven savings: projected $910,000 year 1 and $9.46M by year 6
- 3Enable hospitals to justify ML deployment investments through measurable six‑year cumulative avoided costs ($31.11M)
Scoring Rationale
Provides actionable, peer-reviewed cost projections for ML deployment in oncology but limited to a single-center retrospective cohort.
Sources
Public references used for this report.
Practice with real Health & Insurance data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
250 free problems · No credit card
See all Health & Insurance problems
