Back

Algorithmic Multi-Domain Syndromic Profiling in Cerebrovascular Disease: A Deterministic Approach to Post-Stroke Neurocognitive Deficit Mapping

Erzin, A. I.

2026-09-09 psychiatry and clinical psychology
10.64898/2026.09.08.26362502 medRxiv
Show abstract

Background. Post-assessment data processing, quantitative syndromic profiling, and clinical report generation in acute stroke settings typically require up to 50 minutes of manual documentation per patient, straining clinical workflows and driving clinician burnout. Conversely, standard automated screening tools (NIHSS, MoCA) lack sensitivity to the qualitative specificity of focal deficits and fail to generate structured, auditable clinical narratives. Methods. We performed a retrospective observational study of a prospective acute registry (n = 169; 84 males, 85 females; mean age 66.87 years, SD = 13.9, range 18-97). Cognitive mapping was executed via the NeuroDraft platform, which pairs a deterministic Python core implementing a 10-domain "Luria Raw" matrix (scaled 0-5) with a constrained generative linguistic layer for structured reporting. Results. The deterministic scoring pipeline demonstrated high internal consistency (Cronbach's alpha = 0.85). Kruskal-Wallis testing (df = 7, ties-corrected) revealed marked discriminant validity across baseline mental status tiers (p < 0.001), led by visual object perception (H = 44.86) and complex attention (H = 42.55). Principal component analysis of the covariance matrix identified a primary general deficit factor (lambda_1 = 4.13, explaining 41.26% of total variance) dominated by visuoconstructive functions (loading = 0.46), with basic numerical calculation showing relative independence (loading = 0.21). Depressive symptom loading demonstrated negative orthogonality to organic impairment severity (r = -0.20). Conclusion. The NeuroDraft software standardizes and quantifies qualitative Luria's syndromic analysis, mitigating human-error bias and reducing the medical reporting cycle to 5-10 minutes. This deterministic method provides reproducible cognitive profiling suitable for routine clinical workflows. Keywords: Ischemic stroke, cerebrovascular disease, post-stroke cognitive impairment, neuropsychological assessment, Luria's aphasiology, quantified process approach, automated clinical reporting, deterministic algorithms.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.