Information Extraction from Lumbar Spine MRI Radiology Reports Using GPT4: Accuracy and Benchmarking Against Research-Grade Comprehensive Scoring is a dataset published in Diagnostics (2025). On theSindex it has a DataRank of 0.345, placing it in the top 50.9% of the data-sharing corpus. It has been cited 8 times, with 7 citing works in its 1-hop citation network. Its calibrated FAIR score is 8/100.
Ranks in the top 51% for downstream scientific impact
DataRank reads this dataset's downstream impact straight off the citation graph — no black box, no proprietary weighting. How is this computed?
FAIR checklist signals are shown for context only and do not affect DataRank scoring.
Full FAIR picture · advisory
The headline score is computed from the scored criteria — the fact-shaped checks (a repository, an accession, a licence) that two independent models agree on. The advisory criteria below are real FAIR guidance but rest on judgment calls that models read differently, so they inform without moving the number.
No persistent identifier string (DOI, Handle, ARK, URN, repository accession) is given for the study's own data.
RDA-F1-01D — FAIR Data Maturity Model: 'Data is identified by a persistent identifier' (priorit · RDA-F1-02D — FAIR Data Maturity Model: 'Data is identified by a globally unique identifier' · FsF-F1-02D — F-UJI/FAIRsFAIR: 'Data is assigned a persistent identifier'
No repository is named as the holder of the data; the data are held by the authors and available on request.
RDA-F4-01M — FAIR Data Maturity Model: metadata is offered so it can be harvested and indexed ( · NIH DMS Policy Element 4 (NOT-OD-21-014) — name the repository where data will be archived · NSTC Desirable Characteristics of Data Repositories (2022) — 'Long-Term Sustainability', 'Reten
No identifier for the dataset appears anywhere in the paper, so it cannot be cited in any location.
FORCE11 Joint Declaration of Data Citation Principles (2014) — data should be cited as a first- · RDA-F3-01M — metadata clearly and explicitly includes the identifier of the data it describes · FsF-F3-01M — F-UJI: 'Metadata includes the identifier of the data it describes'
Advisory · not in the published score
“The data underlying this article cannot be shared publicly due to the privacy concerns of individuals participating in the study. The data will be shared upon reasonable request to the corresponding author.”
The statement points to a person (corresponding author) for request, which is Colavizza category 1.
Colavizza, Hrynaszkiewicz, Staden, Whitaker & McGillivray (2020), 'The citation advantage of li · Springer Nature research data policy — Data Availability Statements: standard statement templat · RDA-F3-01M — metadata clearly and explicitly includes the identifier of the data it describes
“Table 1. Extracted data points.”
An itemised inventory of the dataset's variables is provided in Table 1, so class yes. [majority verdict 'yes' (4/5 passes agreed)]
RDA-F2-01M — 'Rich metadata is provided to allow discovery' (priority Essential) · FsF-F2-01M — F-UJI: 'Metadata includes descriptive core elements to support data findability' · FsF-R1-01MD — F-UJI: 'Metadata specifies the content of the data'
“The data will be shared upon reasonable request to the corresponding author.”
The only offered route is a discretionary request to a person with no defined, followable process, which is class 3 (no).
RDA-A1.1-01D — 'Data is accessible through a free access protocol' · FsF-A1-01M — F-UJI: 'Metadata contains access level and access conditions of the data' · NSTC Desirable Characteristics of Data Repositories (2022) — 'Free and Easy Access'
Advisory · not in the published score
“The data underlying this article cannot be shared publicly due to the privacy concerns of individuals participating in the study. The data will be shared upon reasonable request to the corresponding author.”
The paper describes an access action (request to author) but does not apply an explicit access-level label from the standard vocabulary.
FsF-A1-01M — F-UJI: 'Metadata contains access level and access conditions of the data' · RDA-A1-01M — metadata contains information to enable the user to get access to the data · COAR Controlled Vocabularies — Access Rights v1.0 (open / embargoed / restricted / metadata-onl
“The data will be shared upon reasonable request to the corresponding author.”
The gatekeeper is a natural person (the corresponding author), not an institutional committee or repository.
NIH Genomic Data Sharing Policy (NOT-OD-14-124) — controlled-access via a Data Access Committee · RDA-A1.2-01D — 'Data is accessible through an access protocol that supports authentication and · NIH DMS Policy Element 5 (NOT-OD-21-014) — Access, Distribution, or Reuse Considerations (conse
No sentence in the paper states when the data become available or how long they persist.
NIH DMS Plan Element 4 (NOT-OD-21-014) — Data Preservation, Access, and Associated Timelines · NSTC Desirable Characteristics (2022), Organizational Infrastructure: 'Retention Policy' · RDA-A2-01M — 'Metadata is guaranteed to remain available after data is no longer available'
No file format of any kind is named for the released data (the data are not released).
FsF-R1.3-02D — F-UJI: 'Data is available in a file format recommended by the target research co · RDA-R1.3-02D — data is expressed in a machine-understandable community standard · RDA-I1-01D — data uses a knowledge representation expressed in a standardised format
Advisory · not in the published score
No data or metadata community standard (e.g., MIAME, BIDS, an ontology) is named and applied to the data.
RDA-R1.3-01M — 'Metadata complies with a community standard' (priority Essential) · RDA-R1.3-01D — 'Data complies with a community standard' · RDA-I2-01M — '(Meta)data use vocabularies that follow FAIR principles'
“https://github.com/michelle-tong18/VERSA-spine”
The paper gives a URL for the code, which is a resource other than its own dataset. [majority verdict 'yes' (3/5 passes agreed)]
RDA-I3-01M — '(meta)data include references to other (meta)data' · RDA-I3-03M — 'metadata includes qualified references to other metadata' · FsF-I3-01M — F-UJI: 'Metadata includes links between the data and its related entities'
No licence is attached to the data; the CC BY licence on the paper does not apply to the data.
RDA-R1.1-01M — 'Metadata includes information about the licence under which the data can be reu · RDA-R1.1-02M — 'Metadata refers to a standard reuse licence' · RDA-R1.1-03M — 'Metadata refers to a machine-understandable reuse licence'
Neither a version token nor a date pins the snapshot of the data.
DataCite Metadata Schema 4.6 — the 'Version' property · RDA-R1.2-01M — provenance information (which version was used is provenance) · NSTC Desirable Characteristics of Data Repositories (2022) — 'Provenance', 'Retention Policy'
“https://github.com/michelle-tong18/VERSA-spine, version 1.0”— not found in the paper; verdict downgraded
A machine-resolvable locator with version is given for the study's own code, so class yes. [downgraded to 'partial' — no verifiable quote from the paper] [majority verdict 'partial' (3/5 passes agreed)]
NIH DMS Policy Element 2 (NOT-OD-21-014) — 'Related Tools, Software and/or Code' · FAIR4RS Principles v1.0 (Chue Hong et al., 2022; RDA/FORCE11/ReSA) — FAIR Principles for Resear · FORCE11 Software Citation Principles (Smith, Katz & Niemeyer, 2016, PeerJ CS 2:e86)
“grant numbers U19AR076737, UH2AR076724, and UH2AR076719”
Alphanumeric award numbers are given attached to the named funder (NIH).
DataCite Metadata Schema 4.6 — 'FundingReference' property (funderName, funderIdentifier, award · Crossref Funder Registry — canonical funder identifiers for funding metadata · RDA-F2-01M — rich metadata provided to allow discovery (funding is part of the descriptive reco
Advisory · not in the published score
“GPT-4 (8-k model, OpenAI, San Francisco, CA, USA; Microsoft Azure, Microsoft, Redmond, WA, USA)”
The paper names specific tools and instruments (GPT-4 model, VERSA-API, text-embedding-ada-002) used to produce the data. [majority verdict 'yes' (4/5 passes agreed)]
RDA-R1.2-01M — 'Metadata includes provenance information according to community- specific standa · FsF-R1.2-01M — F-UJI: 'Metadata includes provenance information about data creation or generati · W3C PROV-O (W3C Recommendation, 2013) — the entity/activity/agent model of provenance
“Table 1 shows the included scoring items.”
Variable-level definitions are provided inside the article (Table 1), but no documentation object is said to accompany the data. [majority verdict 'partial' (4/5 passes agreed)]
RDA-R1-01M — '(Meta)data are richly described with a plurality of accurate and relevant attribu · FsF-R1-01MD — F-UJI: 'Metadata specifies the content of the data' · NIH DMS Policy Element 3 (NOT-OD-21-014) — Standards (documentation and metadata to accompany t
Calibrated FAIR score — a parallel quality metric, independent of the DataRank citation score. See the full evaluation →
Base Score Contribution
0.330
From this paper's citation signal
Citation Network Contribution
0.0151
From 1 citing papers with measurable signal
Ranked by each citer's contribution to N(p) — log1p(Cq) divided by its reference count — out of 7 citers.
National Institute Of Arthritis and Musculoskeletal and Skin Diseases (NIAMS) of the National Institutes of Health (NIH)
Grant: U19AR076737
National Institute Of Arthritis and Musculoskeletal and Skin Diseases (NIAMS) of the National Institutes of Health (NIH)
Grant: UH2AR076724
National Institute Of Arthritis and Musculoskeletal and Skin Diseases (NIAMS) of the National Institutes of Health (NIH)
Grant: UH2AR076719
NIAMS NIH HHS
Grant: U19AR076737 and UH2AR076724
National Institutes of Health
Grant: 3U19AR076737-01S2
REACH Participant Diversity Program
National Institutes of Health
Grant: 1UH2AR076719-01
Novel imaging of endplate biomarkers in chronic low back pain
National Institutes of Health
Grant: 1UH2AR076724-01
Technology Research Site for Advanced, Faster Quantitative Imaging for BACPAC
FWCI
2.73
Citation Percentile
0.9%
Citation Trend
Fields of Study
Keywords