81% ROC-AUC out-of-sample on the unseen 2025 NFL injury set — validated, reproducible, and live. Every claim on this page can be reproduced from the public repo.
Every platform below helps you rank healthy players. None of them tell you which players are most likely to stop being healthy. INJSUR.AI is the only tool that prices pre-season durability into your board — and validates it against real injury data.
| Capability | Consensus Rankings & DFS Tools | INJSUR.AI | Why It Matters |
|---|---|---|---|
| Pre-Season Durability Scoring | Not offered | 20-feature frailty model scored per player | Workload, contact rate, age, experience and injury history quantified before Week 1 |
| Injury-Risk Ranking Accuracy | No pre-season signal (effectively 50% — coin flip) | 81% ROC-AUC out-of-sample on the unseen 2025 injury set | Trained on 2024 labels, evaluated against 2025 with time-correct features — no leakage, fully reproducible from the repo |
| Position-Calibrated Risk Bands | Generic "questionable / doubtful / out" labels | Per-position sigmoid calibration (QB, RB, WR, TE, OL, DL, LB, DB) | A high-risk RB and a high-risk QB mean the same thing on INJSUR’s scale |
| Historical Injury Integration | Current-week status only | 5 recency-weighted injury features (count, severity, games missed, structural, soft-tissue) | A player with two ACL tears scores differently than a player with zero — before they even take the field |
All INJSUR.AI metrics are computed from public NFL statistics. The model is trained on the 2024 notable-injury labels and evaluated out-of-sample against the unseen 2025 set. Run the backtest yourself in the app.
Every player was scored by INJSUR’s frailty model using only pre-2025 history in the features. Across every (2025-injured · healthy) pair, the model ranked the injured player higher 81% of the time, and a High-Risk flag landed on injured players at 7.1× the league base rate. The fit never saw 2025 labels — this is the honest pre-season ranking accuracy, recomputed live on the Results tab.
The frailty model that posted those 2025 numbers is now scoring every player on every 2026 active roster — sourced from the official nflverse data feed and refreshed continuously. You see the exact same High-Risk / Medium / Low bands the backtest produced, applied to the season about to start.
| Platform Tier | Brands | Monthly Cost | Annual / Seasonal | What You Get |
|---|---|---|---|---|
| Low-End Aggregators | FantasyPros, Draft Sharks, RotoWire | $3.99 – $11.99/mo (annual lock-in required) |
$72 – $130+/yr | Generic rankings, consensus expert lists, basic draft advice |
| Betting-Focused Data | Action Network PRO, BettingPros | $14.99/wk or $24.99/mo | $100 – $150/yr | Line movements, public vs. sharp money %, sportsbook liabilities |
| Elite DFS / High-Stakes | Establish The Run, RotoGrinders, The Solver | $49.99/mo | $300 – $500+/season | Linear projections, optimizer tools, high-stakes content grids |
| INJSUR.AI | INJSUR.AI | $39/season | $99 Lifetime One-time. Forever. |
Patent-pending AI scoring 20 workload, contact and injury-history features per player — what no one else tracks |
FantasyPros locks you into $72–$130/year for consensus rankings anyone can find. INJSUR.AI gives you patent-pending injury intelligence for $39/season — no annual commitment, no hidden upsells.
High-stakes players pay $300–$500 every season for projection optimizers. INJSUR.AI's $99 Lifetime Pass gives you the one variable they can't see — forever.
No platform at any price publishes pre-season durability scores. You can pay $500/year for projections that assume every player stays healthy — or pay $39 for the algorithm that knows they won't.
We took every notable 2025 NFL injury, scored the player pre-season with the trained frailty model, and asked the only question a bettor cares about: was a same-position alternative available that INJSUR ranked as both safer and more productive? No double-dipping — each alternative usable only once across the entire backtest.
| Player who got hurt | Pos | Frailty | PPR | INJSUR’s alternative | Frailty | PPR | +PPR |
|---|---|---|---|---|---|---|---|
| Chris Godwin | WR | 83.6 | 81.0 | Jaxon Smith-Njigba | 80.0 | 361.9 | +280.9 |
| Brock Purdy | QB | 59.3 | 179.4 | Josh Allen | 55.6 | 364.6 | +185.2 |
| Daniel Jones | QB | 84.3 | 230.4 | Matthew Stafford | 78.3 | 354.4 | +124.0 |
| Christian Watson | WR | 77.3 | 132.4 | Zay Flowers | 75.3 | 249.3 | +116.9 |
| Sam Darnold | QB | 77.0 | 241.4 | Drake Maye | 51.3 | 354.0 | +112.6 |
| CeeDee Lamb | WR | 81.2 | 200.9 | George Pickens | 78.7 | 289.9 | +89.0 |
| Patrick Mahomes | QB | 71.6 | 281.7 | Trevor Lawrence | 53.7 | 340.2 | +58.5 |
| Kyler Murray | QB | 47.4 | 77.8 | Justin Fields | 44.4 | 134.7 | +56.9 |
| George Kittle | TE | 80.5 | 161.5 | Jake Ferguson | 73.3 | 190.1 | +28.6 |
| Calvin Ridley | WR | 75.1 | 201.1 | Nico Collins | 71.0 | 226.2 | +25.1 |
| Tucker Kraft | TE | 70.4 | 117.2 | Theo Johnson | 57.3 | 127.8 | +10.6 |
| Malik Nabers | WR | 47.6 | 57.1 | Devaughn Vele | 45.3 | 66.3 | +9.2 |
| Terry McLaurin | WR | 73.7 | 213.5 | Michael Wilson | 64.3 | 220.6 | +7.1 |
| Bo Nix | QB | 58.9 | 298.8 | Jalen Hurts | 53.3 | 303.1 | +4.3 |
| Jayden Daniels | QB | 46.8 | 114.3 | Will Levis | 41.0 | 117.9 | +3.6 |
Full honesty: 4 bettor-relevant players (Ricky Pearsall, Marvin Harrison Jr., Justin Herbert, Dallas Goedert) didn’t get a unique safer-and-better alternative — in each case INJSUR didn’t identify a same-position alternative that was both safer and more productive. Those players sit in the “unavoidable” column. 9 lower-production injuries were excluded from the bettor-relevant denominator (below the 50-PPR meaningful-starter floor). 25 of the 53 notable 2025 injuries didn’t map to a current fantasy roster (retired, free agents, defensive players). Every number above is reproducible by running node js/avoidable-injuries.mjs in the repo.