MétaCan
Menu
← Back to cohort
Record W2898005809 · doi:10.1016/j.jalz.2018.06.2208

IC‐P‐142: SURFACE‐BASED MULTIMODAL CLUSTER ANALYSIS REVEALS TOPOGRAPHICAL HETEROGENEITY OF ALZHEIMER'S DISEASE

2018· article· en· W2898005809 on OpenAlexaff
Seun Jeon, Duk L. Na, Young Noh, Alan C. Evans

Bibliographic record

VenueAlzheimer s & Dementia · 2018
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsMcGill UniversityMontreal Neurological Institute and Hospital
Fundersnot available
KeywordsDementiaClinical Dementia RatingAtrophyPathologyMedicineInternal medicineNuclear medicinePsychologyDisease

Abstract

fetched live from OpenAlex

The clinical presentation and atrophy pattern of Alzheimer's disease (AD) dementia is known to be heterogeneous. To address the topographical heterogeneity of the AD, we developed a cortical surface-based cluster analysis framework by combining multimodal imaging such as PET and MRI. We collected THK-5351-PET (tau), 1⁸F-flutemetamol-PET (amyloid-β), and T1-weighted-MRI (T1w) from 60 normal controls and 83 patients (Clinical Dementia Rating≤1). We co-registered each of the two PET modalities into the T1w. We reconstructed cortical surfaces using the CIVET pipeline. Partial-volume effects of PET were corrected. We precisely mapped cortical thickness, tau-SUVR and amyloid-β-SUVR of each subject at each vertex coordinates on mid-cortical surfaces (Figure1). The features were 20mm smoothed and normalized by z-score. We performed agglomerative hierarchical clustering analysis (Figure2). The identified subtypes were compared with the normal controls using a general linear model adjusting for age, sex, years of education. Intracranial volume was included in the cortical thickness analysis. We mapped effect size within significant cortical regions reaching random field theory corrected p-vertex<0.05. Surface-based multimodal feature extraction. Agglomerative hierarchical cluster analysis. The AD dementia patients were subcategorized into three subtypes (Figure3): medial temporal-dominant subtype (MT, n=44), parietal-dominant subtype (P, n=19), and diffuse atrophy subtype (D, n=20). The demographics (Table1) and neuropsychological test results (Table2) showed distinct features among each subtype. In the MT subtype, the patients were older than other subtypes and the female percentage was outnumbered, and this might result from an age-related reduction of estrogen. The patients in the P subtype had the earliest onset-age and were the youngest among subtypes, and the worst scored on most neuropsychological tests, and this might result from the dysfunction of parietal and dorsolateral prefrontal cortex region. The patients in the D subtype had the most education years, and neuropsychological profiles were in between MT and P subtypes. Topographical atrophy of AD subtypes. Our surface-based multimodal cluster analysis framework has revealed three distinct subtypes among AD patients in terms of distribution of cortical atrophy, amyloid plaques, and neurofibrillary tangles, and demographical/neuropsychological profile. Consideration of the heterogeneous atrophy patterns may be important when planning future preventative and treatment strategies because the AD subtypes may have different responses to treatment and different courses of disease progression.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.005
Threshold uncertainty score0.016

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0010.000
Scholarly communication0.0010.000
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0050.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.023
GPT teacher head0.320
Teacher spread0.297 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2018
Admission routes1
Has abstractyes

Explore more

Same venueAlzheimer s & Dementia→Same topicRadiomics and Machine Learning in Medical Imaging→French-language works237,207→