MétaCan
Menu
Back to cohort
Record W4406994446 · doi:10.1161/str.56.suppl_1.tp28

Abstract TP28: Digital Clock Drawing and Recall Enables Rapid Cognitive Screening in Acute Ischemic Stroke Care

2025· article· en· W4406994446 on OpenAlexaboutno aff
Alex Fedorov, Jessica Saurman, Jennifer Ro, Jewel Ahmed, David W. Loring, Xiao Hu, Fadi Nahab

Bibliographic record

VenueStroke · 2025
Typearticle
Languageen
FieldMedicine
TopicStroke Rehabilitation and Recovery
Canadian institutionsnot available
Fundersnot available
KeywordsMedicineIschemic strokeRecallStroke (engine)CognitionAcute strokeCognitive impairmentInternal medicineCardiologyPhysical medicine and rehabilitationIschemiaPsychiatryCognitive psychology

Abstract

fetched live from OpenAlex

Cognitive impairment following acute stroke significantly impacts patient outcomes and rehabilitation. Early detection is crucial, yet comprehensive assessments are often impractical in acute settings. Digital clock drawing and recall (DCR) offers a rapid 5-minute cognitive screening by assessing clock drawing and three-word recall. While previously shown effective in early Alzheimer's detection, its utility in stroke patients has been underexplored. This study investigates the feasibility and validity of DCR compared to the Montreal Cognitive Assessment (MoCA) in stroke patients. The study involved 80 acute ischemic stroke patients who completed both DCR and MoCA during hospitalization. DCR was implemented on the Linus Health platform. DCR data included DCR scores, battery duration, demographic variables, and recorded NIH Stroke Scale scores. Cognitive impairment was defined using a MoCA threshold of ≤24. Leave-One-Out Cross-Validation and XGBoost were used for analysis. Optuna-optimized hyperparameters and model performance were evaluated via AUC, accuracy, F1-score, sensitivity, and specificity. SHAP analysis provided insights into feature importance. The median time from stroke to cognitive screening was 3 days [1.0, 2.0]. The impaired group (MoCA ≤ 24) was older (mean 63.2 vs. 53.2 years, p = 0.271), had lower education levels (mean 13.4 vs. 15.8 years, p = 0.005), longer battery durations (median 288.0 vs. 232.0 seconds, p = 0.017), and lower DCR scores (median 1.0 vs. 3.0, p < 0.001). NIHSS scores were higher but not statistically significant (median 4.0 vs. 2.0, p = 1.). Gender, race, and ethnicity were insignificant predictors excluded from the final model. The XGBoost model demonstrated strong predictive performance, with an AUC of 0.8114, an F1-score of 0.8916, and an accuracy of 0.9. At the threshold of 0.5656 (Youden’s J statistic), the model achieved high sensitivity 0.9841 and moderate specificity 0.5882. SHAP analysis identified DCR score, education level, and battery duration as the most important features. DCR screening proves to be an effective, rapid cognitive screening tool in acute ischemic stroke care. It demonstrates high sensitivity in detecting subtle cognitive impairments and correlates well with MoCA scores. While further validation is needed, this tool offers a rapid and reliable method for cognitive assessment in acute settings, potentially enhancing personalized treatment approaches and improving patient outcomes in stroke care.

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)0.002
metaresearch head score (Gemma)0.006
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 score0.009
Threshold uncertainty score0.030

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.006
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0090.003

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 head0.010
GPT teacher head0.275
Teacher spread0.265 · 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

Citations3
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueStrokeSame topicStroke Rehabilitation and RecoveryFrench-language works237,207