The DTI score as a contract: what Platinum-grade data actually guarantees
The DTI score assigns every health data record a grade from Bronze to Platinum across 8 weighted dimensions. Platinum-grade data is not a marketing label. It is a contractual guarantee that a record meets verifiable thresholds for provenance, consent, recency, quality, concordance, validation, breadth, and stability before any AI model or regulatory submission touches it.
A FICO score does not tell you whether someone will pay their mortgage. It tells you the probability, measured against standardized criteria, that a lender can verify before extending credit. The Data Trust Index works the same way for health data. A DTI Platinum grade is not an opinion about data quality. It is a contract.
What is the DTI score?
The DTI score is a 0-to-100 composite rating that SuperTruth assigns to every individual health data record. It evaluates eight dimensions, each weighted by its impact on downstream reliability: Provenance (25%), Consent (20%), Recency (15%), Quality (10%), Concordance (10%), Validation (10%), Breadth (5%), and Stability (5%). Each dimension receives its own sub-score. The composite determines the record's trust tier.
Four tiers exist: Bronze (0-49), Silver (50-69), Gold (70-84), and Platinum (85-100). The tier is not decorative. It defines what you can do with the record. Bronze data might support population-level trend analysis. Platinum data supports FDA regulatory submission, clinical AI model training, and payer negotiation.
If you have searched "DTI score" and landed on pages about debt-to-income ratios for mortgages, you are not alone. The financial DTI measures how much of your monthly income goes to debt payments. Lenders use it to decide credit risk. The health data DTI measures how much of a record's content can be independently verified. AI developers, health systems, and regulators use it to decide whether data is safe to act on. Same acronym. Completely different domain.
How does DTI scoring work?
The DTI Engine ingests a health data record and runs it through eight discrete evaluation pipelines. Provenance scoring traces the record's chain of custody: where it originated, what systems touched it, and whether each handoff is documented. Consent scoring checks whether the data subject granted permission for the specific use case being evaluated, not just whether a HIPAA authorization exists on file.
Recency scoring penalizes stale data. A lab result from 2019 does not carry the same weight as one from last month. Quality scoring checks for completeness, structural validity, and coding accuracy. Concordance compares the record against other records for the same patient to flag contradictions. Validation confirms that independent sources corroborate the record's claims.
Breadth measures how many data types are represented: labs, imaging, genomics, social determinants. Stability tracks whether the record's score has changed over time, because a record that swings between Gold and Bronze on successive evaluations is less trustworthy than one that holds steady.
Each dimension produces a sub-score. The weighted composite becomes the final DTI score. Every calculation is explainable and auditable, not a black-box output.
Is a 20% DTI good? Is 43 DTI too high?
These questions come from the mortgage world. A 20% debt-to-income ratio is excellent for a home loan. A 43% DTI is the Dodd-Frank qualified mortgage ceiling. Neither number applies to health data.
In the SuperTruth framework, the numbers mean something different entirely. A DTI score of 20 means the record fails on most trust dimensions. It likely has no verifiable provenance, no documented consent chain, and significant quality gaps. A score of 43 falls in the Bronze tier. You could use it for aggregate analytics with heavy caveats, but no responsible team would train a clinical AI model on it.
The threshold that matters for health data is 85. That is where Platinum begins. That is where the contract kicks in.
What Platinum-grade data actually guarantees
A Platinum DTI score is a verifiable assertion that a health data record meets specific, auditable criteria across all eight dimensions. It guarantees that provenance is fully documented from originating system to current storage. It guarantees that consent covers the intended use case, whether that is model training, regulatory submission, or research. It guarantees that the record is current enough for its stated purpose.
This matters because FDA guidance is moving toward requiring data provenance documentation for AI-enabled medical devices. Health plans face CMS and NCQA audits that demand proof of data accuracy. Pharma companies need audit-ready real-world evidence for submissions.
Without a scored, tiered system, "high-quality data" is a subjective claim. With DTI Platinum, it is a contract backed by eight measurable dimensions.
Key statistics
SuperTruth scored 105,000 diagnostic records for imaware, reducing standardization time from 3 weeks to 2 hours, a 95% time reduction. The process saved over 200 hours per month of manual data work. That scoring also identified a patient segment driving 20% of imaware's revenue that had been invisible in unscored data.
Provenance carries the highest weight in the DTI framework at 25%, reflecting the reality that chain of custody is the hardest dimension to verify and the most consequential when it fails. Consent follows at 20%, because a record with perfect provenance but no valid consent authorization is unusable for AI training under current regulatory expectations.
Why a trust tier is a contract, not a label
Most data platforms describe their data as "clean" or "validated" without specifying what those words mean. The DTI tier system binds each label to a numeric range, and each numeric range to specific, reproducible evaluation criteria.
When SuperTruth certifies a dataset as Platinum-grade, a downstream user can audit the claim. They can inspect the provenance sub-score. They can check whether consent was evaluated for their specific use case. They can see the recency calculation. This is what makes it a contract rather than a marketing promise.
As Brodie Flanders, CEO of imaware, put it: "The lab industry has never had a trust standard. DTI created one."
Health systems evaluating AI deployment, pharma teams preparing regulatory submissions, and payers negotiating value-based contracts all need the same thing: data they can defend under scrutiny. A DTI Platinum score is designed to survive that scrutiny.
The DTI Engine scores every health data record 0-100 across 8 trust dimensions before your AI model sees it. If your team is evaluating data for training, compliance, or clinical use, contact Louis Simeonidis at louis@supertruth.ai or (215) 918-4140.
Further reading:
Jason Alan Snyder
Co-founder of SuperTruth and Artists & Robots, and an inventor on the Data Trust Index patents. Twenty-plus years building technology inside Interpublic Group. He writes here nearly every day on data trust, provenance, and what AI should be allowed to act on, and publishes essays on his Substack.
About SuperTruth · LinkedIn · Substack · jasonalansnyder.com
See it in practice
DTI scores the record, not the patient.
8 dimensions. 0 to 100. Travels with every record permanently.