nabu.science
MethodologyAboutContact

 

  • Snapshot
  • Key Claims
  • Strengths & Limitations
  • Commentary
  • From the Authors
  • Author Note / Field Feedback
  • Dimension breakdown
  • Impact Profile
Free · About 5 minutes
Report #NBU-DA222808·Framework v5.9·Pipeline v0.4·Evaluated 08 Oct 2026·OECD: 3.2 Clinical medicine·Subfield: Neurology·Basis: Full text·Type: Observational cohort study

Clinically reported covert cerebrovascular disease and risk of neurological disease: a whole-population cohort of 367 988 people using natural language processing.

Iveson et al.Iveson, Mukherjee, Davidson et al.·2026·Journal of neurology, neurosurgery, and psychiatry·10.1136/jnnp-2025-337689 ↗

Primary claim

CCD and atrophy were associated with a higher risk of both dementia and stroke up to 12 years later, with important differences between CCD exposures.

Supported · Large linked cohort with lag and exclusion analyses, but unmeasured lifestyle confounding and unclassifiable imaging indication limit identification.
In brief

Whole-population NLP of routine brain imaging turns incidental covert cerebrovascular findings into credible stroke and dementia risk markers, undercut by causal framing the observational design cannot carry.

ReliabilityCaveats4 of 4 checks completeRead the entry ↓
Possible — the claim's weakest requirement is that the effect exists at all. Based on how the study was designed and conducted, not on statistics extracted from the paper. Experimental. Every point below is traceable to a quoted passage, but this forecast has not yet been validated against known replication outcomes.
Abstract

BACKGROUND: The relevance of covert cerebrovascular disease (CCD) in practice is uncertain, partly because estimation of risk in whole clinical populations is difficult. Studies have had success extracting CCD from clinical text using natural language processing (NLP), though they have been limited to specific CCD phenotypes. Here, we used NLP to measure multiple clinically-reported CCD phenotypes in a large clinical cohort and estimated subsequent disease risk in health record data.

METHODS: From all people with brain imaging in Scotland (2010-2018), we selected people with no prior hospitalisation for neurological disease (n=367 988). NLP of imaging reports identified: white matter hypoattenuation or hyperintensities (WMH), lacunes, cortical infarcts and cerebral atrophy. Adjusted HRs (aHRs) were estimated between each phenotype and stroke, dementia and Parkinson's disease (conditions previously associated with CCD), epilepsy and colorectal cancer (control conditions).

RESULTS: For each phenotype, the aHR of stroke was WMH 1.4 (95% CI 1.3-1.4), lacunes 1.6 (1.5-1.6), cortical infarct 1.8 (1.7-1.9) and cerebral atrophy 1.1 (1.0-1.1). The aHR of dementia was WMH 1.3 (1.3-1.3), lacunes 1.0 (0.9-1.0), cortical infarct 1.1 (1.1-1.2) and cerebral atrophy 1.7 (1.7-1.8). The aHR of Parkinson's disease was WMH 1.1 (1.0-1.2), lacunes 1.1 (0.9-1.2), cortical infarct 0.7 (0.6-0.9) and cerebral atrophy 1.4 (1.3-1.5). The aHRs between CCD phenotypes and epilepsy and colorectal cancer were around the null.

CONCLUSION: CCD and atrophy have implications for future disease risk and can be identified at scale using NLP of clinical reports. Prevention of neurological disease in people with CCD should be a priority for healthcare policy makers.

Key Claims

Primary finding · Supported

CCD and atrophy were associated with a higher risk of both dementia and stroke up to 12 years later, with important differences between CCD exposures.

Possible — the claim's weakest requirement is that the effect exists at all. Based on how the study was designed and conducted, not on statistics extracted from the paper. Experimental. Every point below is traceable to a quoted passage, but this forecast has not yet been validated against known replication outcomes.

Large linked cohort with lag and exclusion analyses, but unmeasured lifestyle confounding and unclassifiable imaging indication limit identification.

Discussion, final paragraph (Conclusion)
Quote verified
Secondary · Tentative

We demonstrate a higher risk of dementia (particularly Alzheimer's disease) in people with cerebral atrophy and a higher risk of stroke in people with cortical infarcts, but no significant associations with an age-associated control outcome (colorectal cancer), supporting a causal relationship.

One non-brain negative control sharing confounders cannot support causation in a design conceding residual confounding.

Box 'What this study adds'
Quote verified
Secondary · Supported

CCD and atrophy have implications for future disease risk and can be identified at scale using NLP of clinical reports.

Pipeline was run across an entire national population; phenotype accuracy rests on validation reported outside this paper.

Abstract, Conclusion
Quote verified
Secondary · Supported

Compared with those with no CCD or atrophy phenotype, those with each phenotype (accounting for the presence of other phenotypes) had a higher risk of any stroke over the 12-year follow-up period.

Mutually adjusted hazard ratios with tight intervals across all four phenotypes, though atrophy's estimate is marginal and detection bias is unquantified.

Results §Risk of stroke; Figure 3
Quote verified

Derived from the full evaluation — not a separate score.

Strengths · Limitations

Strengths

#contribution

Whole-population cohort with multi-phenotype NLP

All 367,988 people in Scotland with brain imaging and no prior neurological disease were included, with four phenotypes extracted from both CT and MRI reports generated in routine care. This covers district hospitals as well as academic centres, a population that research imaging cohorts systematically miss.

↳ Methods §Study design and participants; Figure 1; Discussion, strengths paragraph

#methodological rigour

Reverse-causation safeguards built into the design

Follow-up begins six months after the index scan, people diagnosed within that window are excluded, and sensitivity analyses repeat the models excluding the first 1 and 5 years. Where estimates shift, the paper reports it openly, noting that the atrophy-stroke association moves to the null at 5 years.

↳ Methods, follow-up paragraph; Results §Sensitivity analyses

#methodological rigour

Negative controls and competing-risk accounting

Epilepsy and colorectal cancer are prespecified as brain-based and non-brain control outcomes, and the cumulative incidence estimates account for the competing risk of death in an elderly, high-mortality cohort. Proportional hazards were tested and violating variables handled by stratification.

↳ Methods §Study definitions and analysis; Table 2; Results §Risk of Parkinson's disease, epilepsy and colorectal cancer

#positioning

Candid, specific and traceable limitations

The Discussion names the rules-based rather than LLM approach, clinical selection, unclassifiable imaging indication, missing primary-care and lifestyle data, dementia-subtype diagnosis bias, epilepsy's imperfection as a control and the crudeness of the phenotypes, each linked to its effect on interpretation.

↳ Discussion, limitations paragraph

Limitations

#reporting

Causal framing exceeds the observational design

The summary box concludes that the absence of a colorectal-cancer association supports 'a causal relationship'. A single non-brain negative control, which shares confounders such as smoking with the exposures, cannot establish causation in a design whose own limitations concede that residual confounding 'could explain some of our findings'.

↳ Box 'What this study adds'; Discussion, limitations paragraph

#methodological rigour

Unmeasured confounding left unquantified

Smoking, obesity, blood pressure and primary-care records are unavailable and the exposed group differs sharply from the unexposed on age and comorbidity (mean 73.4 vs 48.2 years). No quantitative bias analysis, E-value or causal diagram is offered to bound how much of the association this could explain.

↳ Results, Table 1; Discussion, limitations paragraph

#methodological rigour

Population-comparison relative risks are not like-for-like

The analytic cohort excludes prior disease and requires six-month survival while the wider Scottish comparator does not, producing figures such as a 5-year stroke RR of 30.3. The same comparison yields a 5-year colorectal cancer RR of 5.1 (4.9-5.3) while the text describes the group as not more likely to experience colorectal cancer, which clouds the negative control's interpretation.

↳ Results, paragraph on comparison with the wider Scottish population

#positioning

Inverse Parkinson's finding reported but unexplained

Cortical infarct is associated with a lower risk of Parkinson's disease (aHR 0.7, 95% CI 0.6 to 0.9), a direction opposite to the paper's framing. Competing mortality risk and selection are plausible mechanisms, but the Discussion does not engage the result.

↳ Results §Risk of Parkinson's disease; Abstract

#methodological rigour

Multiplicity uncorrected across many tests

Dozens of phenotype-outcome and subgroup interaction tests are reported with p values explicitly uncorrected for multiple comparisons. In a cohort of this size, statistically significant interactions of limited substantive importance are expected.

↳ Methods, final analysis paragraph; Results §Subgroup analyses

Does this match your read? Add your assessment ↓

Nabu Commentary

The evaluation converged on a competently executed national cohort whose principal defect is framing rather than analysis. Scoring turned on where the causal language in the 'What this study adds' box should be priced: that wording is confined to the summary box and the abstract's policy directive, while the Methods, Results, Discussion and Conclusion consistently describe associations and 'a risk marker for stroke and dementia', so the defect was treated as a language-evidence problem rather than as a design-level causal overreach that would clamp the methodology score. Methodological credit rests on the six-month lag, the 1- and 5-year exclusion analyses, mutual adjustment across phenotypes, proportional-hazards testing with stratification, competing-risk cumulative incidence and two prespecified negative controls. Working against that are confounders the data cannot capture with no quantitative bias assessment, an imaging indication that could not be classified, and a wider-population comparison whose relative risks (5-year stroke RR 30.3; colorectal cancer RR 5.1) are computed between groups selected on different criteria and sit uneasily with the text's description of the colorectal result. The inverse cortical-infarct-Parkinson's association (aHR 0.7, 0.6 to 0.9) is reported in both abstract and Results but never discussed, which weighed against an otherwise thorough engagement with prior literature.

Evaluate another paper

Free · About 5 minutes · Research preview

Author Note / Field Feedback

Nabu’s assessment, alongside the field’s view.

Are you an author of this paper?

Dimension breakdown

Evidence Score

Out of 5
012345
3.5±0.1

Contribution
3.6

The study extends prior single-phenotype, older-adult NLP work by measuring four imaging phenotypes across both CT and MRI in an entire national clinical population of 367,988, with subtype-resolved outcomes and two negative controls. The advance is real but incremental: directions largely confirm research-cohort findings, with the added value lying in clinical-population generalisability and phenotype-by-subtype resolution.

Introduction, final two paragraphs; Methods §Study design and participants; Discussion, strengths paragraph

Previous studies have not measured multiple phenotypes, have used smaller cohorts... and have only examined older people.

Methodological Rigour
3.5

Execution is competent for the design: validated rules-based phenotyping, a 6-month lag with 1- and 5-year exclusion sensitivity analyses, extensive covariate adjustment with proportional-hazards testing and stratification, competing-risk cumulative incidence, and two negative-control outcomes. Offsetting this are unmeasured lifestyle confounders with no quantitative bias analysis, unclassifiable imaging indication, outcome detection bias from greater healthcare contact, non-comparable population RRs, and uncorrected multiplicity.

Methods, analysis paragraphs; Results §Sensitivity analyses; Discussion, limitations

important confounders, such as obesity or smoking, were not available, and residual confounding could explain some of our findings

Reporting
3.3

The argument runs cleanly from question to cohort to subtype-resolved results, and the Results and Discussion consistently use calibrated associational and risk-marker language. The score reflects priced-in movement for the summary box's assertion that the null control supports 'a causal relationship' and the abstract's policy-priority directive, either of which could lead a reader to a materially stronger conclusion than the design delivers.

Box 'What this study adds'; Abstract, Conclusion

no significant associations with an age-associated control outcome (colorectal cancer), supporting a causal relationship

Positioning
3.5

Prior research-cohort and clinical-cohort estimates, prevalence figures and ESO guidance are engaged directly, with an explicit account of why the estimates here are lower than research-cohort values. Movement within the band reflects the residual-confounding limitation not being traced into the summary box's causal assertion and the inverse cortical-infarct-Parkinson's result being reported but not interpreted.

Discussion, comparison and limitations paragraphs; Results §Risk of Parkinson's disease

the aHR of Parkinson's disease was lower in people with cortical infarct (aHR 0.7, 95% CI 0.6 to 0.9)

Lower confidence on Methodological Rigour, Positioning — domain match limited.

Reliability

Caveats4 of 4 checks


Results checkNoted
  • CCD and atrophy were associated with a higher risk of both dementia and stroke up to 12 years later, with important differences between CCD exposures: "The aHR of dementia was WMH 1.3 (1.3-1.3), lacunes 1.0 (0.9-1.0)" (Abstract, Results) vs "although not lacunes (1.0, 95% CI 1.0 to 1.0)" (Results, Risk of dementia). The same lacunes–dementia estimate has a lower confidence limit of 0.9 in the abstract and 1.0 in Results, and the supplied text does not establish which is correct. → Effect on result unclear
Reporting and transparencyClean

No reporting or transparency concern can be retained with the required textual grounding; the stated restricted data availability is consistent with the described safe-haven analysis.

Ethics approval: declared · Data availability: declared

Reference IntegrityClean

35 references in manuscript 29 of 29 checkable references found in an index 6 are books, websites or datasets — counted, but not index-checkable

References not verified automatically are resolved manually within 24 hours.

Post-Publication RecordClean

No retraction or expression of concern found in Crossref (includes Retraction Watch).

Last checked: 17 Oct 2026

Sources: Crossref (incl. Retraction Watch) ✓

Impact Profile

Impact areaHealth · Stroke · Stroke
Type of advanceEmpirical
Route to useNamed
AdvanceExtends
BeneficiariesLarge
CitationsToo early
Policy · patentNot yet traced
ReachedNot reachedNot assessable or unverified
ReadinessValidated
Foundational
Controlled
Piloted
Validated
Implementable
FoundationalImplementable

The associations were measured in a whole-population clinical cohort of 367988 people with up to 12 years of real-world health record follow-up, confirming findings from research cohorts.

From the paper
“Prevention of neurological disease in people with CCD should be a priority for healthcare policy makers.”

The paper names healthcare policy makers as actors who should prioritise prevention based on these findings, and discusses clinicians applying primary vascular prevention.

Pathway

Clinicians and healthcare policy makers would act on routinely reported CCD and atrophy findings to target primary vascular prevention and prioritise prevention programmes.

Barrier

The observational design cannot exclude residual confounding, and no specific intervention has proven effective for people with CCD.

Evaluated 13 Nov 2026 · GBD 2023 · glm_v1_3_3 · impact_profile_v1_3_3

Report an issue →

AI-generated, human-governed. Something look off? Contact us to request a review.

Keep reading

Related evaluations

Other papers Nabu has evaluated blind, starting with the same field.

  1. Global burden of cerebral small vessel disease determined from large MRI studies: A systematic review and meta-analysis

    2026 · Clinical medicine

    Primary claim

    This systematic review and meta-analysis based on large MRI studies demonstrated that SVD is a common health problem affecting about one-fifth of the adult population.

    Tentative
    Evidence Score
    3.1±0.1
    Reliability
    Caveats
  2. Experimental models of cerebral small vessel disease: Physiological constraints, translational challenges and future directions

    Beaumont, Singh, Soares, et al. · 2026 · Basic medicine

    Evidence Score
    3.1±0.1
    Reliability
    Caveats
  3. Radiotherapy versus observation following surgical resection of WHO grade 2 atypical meningioma (ROAM/EORTC-1308): an international, multicentre, open-label, phase 3, randomised controlled trial

    Michael D Jenkinson, Anna Rosala-Hallas, Felix Sahm, et al. · 2026 · Clinical medicine

    Primary claim

    Disease-free survival was improved in the radiotherapy group compared with the observation group (hazard ratio 0·51 [95% CI 0·27–0·97]; p=0·0396).

    Supported
    Evidence Score
    3.7±0.1
    Reliability
    Caveats

How the rubric works →