MétaCan
Menu
← Back to cohort

Prognostic Risk Profiles for Dementia: A Machine Learning Approach (P1.091)

2016· article· en· W2557782813 on OpenAlexaff
J. Morgenstern, Mark Daley, Vladimir Hachinski

Bibliographic record

VenueNeurology · 2016
Typearticle
Languageen
FieldMedicine
TopicDementia and Cognitive Impairment Research
Canadian institutionsLondon Health Sciences CentreWestern University
Fundersnot available
KeywordsDementiaMedicineComputer scienceArtificial intelligenceMachine learningInternal medicineDisease

Abstract

fetched live from OpenAlex

Objective: To use a data-driven, machine learning approach to develop better predictive algorithms for outcomes in dementia before and after diagnosis, while also highlighting potentially under-appreciated variables in pathogenesis. Background: Dementia encompasses a broad set of neurological diseases producing progressive declines in memory and/or thinking faculties, sometimes alongside personality and emotional disturbances. Worldwide, approximately 35.6 million people have dementia, and this number is only expected to grow due to an aging population. Unfortunately, it is exceedingly difficult to predict who will develop dementia, let alone what type. This makes it difficult to mobilize various preventative strategies supported by mounting evidence. Methods: We analyzed the National Alzheimer's Coordinating Center Database (NACCD), containing 7, 298 patients. This dataset included demographic, genetic, and intermediate clinical information. We used executive function, memory function, the Mini-Mental State Examination (MMSE), and Braak staging, all at death, as our primary outcome measures. First, feature selection techniques including principal component analysis, recursive feature selection, and extra trees classification were applied to the dataset. Next, 16 distinct machine learning classifiers were applied to the data in these four different forms (including one unmodified). Results: Age at diagnosis of cognitive decline, transient ischemic attack status, years of education, and stroke status were consistently identified as the most important independent variables. Best predictions were achieved for executive function, using unmodified data and a k nearest neighbors classifier, producing accurate predictions of executive function 71.57[percnt] of the time. At best, memory function could be accurately predicted 63.73[percnt] of the time, MMSE results 62.7[percnt] of the time, and Braak stage 32.58[percnt] of the time. Conclusions: These results suggest that vascular factors may play a greater role in dementia pathogenesis than currently thought. Furthermore, using this method we were able to achieve prediction accuracies that compare favorably with the existing literature.

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)0.003
metaresearch head score (Gemma)0.011
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.007
Threshold uncertainty score0.022

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.011
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0040.002
Science and technology studies0.0000.000
Scholarly communication0.0020.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0070.002

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 head0.019
GPT teacher head0.285
Teacher spread0.266 · 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 designSimulation or modeling
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
Published2016
Admission routes1
Has abstractyes

Explore more

Same venueNeurology→Same topicDementia and Cognitive Impairment Research→French-language works237,207→