Hypothesis: Decentralized ledger technology enables rapid, cost-effective aggregation of global surgical expert consensus at scale
The Claim
A blockchain-secured crowdsourcing platform can aggregate high-quality surgical decision-making data from a global panel of spine specialists at < $1 per review, with completion rates exceeding 95% and measurable expert consensus — enabling AI model training that reflects worldwide clinical practice rather than single-institution bias.
Background
Current AI models for spine treatment pathway prediction are constrained by small, geographically homogeneous datasets. Traditional expert data collection is expensive, slow, and rarely captures the clinical variability present across different health systems and surgical cultures.
What We Did
We developed Spine Reviews, a platform using Solana blockchain technology to collect surgical judgments from vetted international experts. Surgeons were credentialed via non-transferable solbound tokens (SBTs) — on-chain identifiers that verify identity and track expertise without storing personal data.
500 synthetic vignettes for low back pain patients (degenerative/deformity, with and without radiculopathy) were generated using:
- Curated corner cases (n=162)
- Constrained-random sampling (n=338)
Variables included demographics, frailty scores, ODI, VAS, neurologic red flags, and treatment history — with automated consistency validation.
52 spine specialists from 8 countries reviewed vignettes via a web dashboard. Each vignette received ≥4 independent reviews providing:
- Surgery likelihood score (0–10)
- Confidence score (1–5)
- Constrained multiple-choice treatment recommendation
Blockchain-automated compensation was provided in $SPINE tokens.
Results
- 2,115 reviews submitted → 2,066 completed (97.7% completion rate)
- Cost: $0.97 per review
- Mean surgery likelihood: 3.46/10 (SD=2.70)
- Red flag / emergency case consensus: 97.2% (≥75% agreement threshold)
- Surgical/interventional recommendation agreement: 72.5–74.5% (reflecting genuine clinical variability)
- Dataset used to train an AI treatment prediction model
Why This Matters
This is — to our knowledge — the first published demonstration that DLT can bridge data, human intelligence, and AI for a clinical decision-making task at scale. The solbound token system produced an immutable record of reviewer credentials and engagement, creating a transparent credibility layer that traditional survey platforms cannot offer.
The dataset captures real clinical variability across 8 countries — exactly the diversity needed to build AI models that generalize beyond single-center datasets.
Presented at
IMASTi 2026 — International Meeting on Advanced Spine Techniques AI & Machine Learning · Novel Technique
Authors: Bassel, Guillaume, Nassim, Joseph, Vincent Challier MD, Virginie Lafage MD — On Behalf of SpineDAO
Next Steps
- Expand Spine Reviews to TLIF outcomes comparison (target: post-Bastia May 2026)
- Integrate findings with TLIF-BAYES multicenter Bayesian study
- Open the dataset for researcher access via SpineBase query API