Factors Associated With Post-Stroke Cognitive Impairment: A Narrative Review DOI Creative Commons
Seyoung Shin, Seung Mi Yeo, Byung Chan Lee

et al.

Brain & Neurorehabilitation, Journal Year: 2024, Volume and Issue: 17(3)

Published: Jan. 1, 2024

Post-stroke cognitive impairment (PSCI) is a common and significant disorder affecting considerable proportion of stroke patients. PSCI known factor that increases the risk mortality, dependency, institutionalization in The early prediction implementation rehabilitation could enhance quality life patients reduce burden on their families. It therefore imperative to identify factors for PSCIs stages implement with an appropriate prognosis. A number can be identified patient characteristics, clinical findings, imaging findings. unfortunate majority associated are non-modifiable. However, only modifiable controlled management secondary prevention. Further research needed elucidate potential benefits various programs prevention improvement PSCI.

Language: Английский

Hypertension linked to Alzheimer’s disease via stroke: Mendelian randomization DOI Creative Commons
Chao Tang, Yayu Ma,

Xiaoyang Lei

et al.

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: Dec. 7, 2023

This study aimed to investigate the relationship between hypertension and Alzheimer's disease (AD) demonstrate key role of stroke in this using mediating Mendelian randomization. AD, a neurodegenerative characterized by memory loss, cognitive impairment, behavioral abnormalities, severely affects quality life patients. Hypertension is an important risk factor for AD. However, precise mechanism underlying unclear. To we used mediated randomization method screened variables AD setting instrumental variables. The results analysis showed that stroke, as variable, plays causal Specifically, indirect effect value obtained multivariate MR was 54.9%. implies approximately 55% owing can be attributed stroke. suggest increased through finding not only sheds light on but also indicates novel methods prevention treatment By identifying critical link provides insights into potential interventions could mitigate impact help develop personalized treatments improve patients with who suffer from hypertension.

Language: Английский

Citations

11
Following intravenous thrombolysis, the outcome of diabetes mellitus associated with acute ischemic stroke was predicted via machine learning DOI Creative Commons
Xiaoqing Liu, Miaoran Wang, Wen Rui

et al.

Frontiers in Pharmacology, Journal Year: 2025, Volume and Issue: 16

Published: Jan. 27, 2025

This cohort study aimed to evaluate the prognostic outcomes of patients with acute ischemic stroke (AIS) and diabetes mellitus following intravenous thrombolysis, utilizing machine learning techniques. The analysis was conducted using data from Shenyang First People’s Hospital, involving 3,478 AIS who received thrombolytic therapy January 2018 December 2023, ultimately focusing on 1,314 after screening. primary outcome measured 90-day Modified Rankin Scale (MRS). An 80/20 train-test split implemented for model development validation, employing various classifiers, including artificial neural networks (ANN), random forest (RF), XGBoost (XGB), LASSO regression. Results indicated that average accuracy XGB 0.7355 (±0.0307), outperforming other models. Key predictors prognosis post-thrombolysis included National Institutes Health Stroke (NIHSS) blood platelet count. findings underscore effectiveness algorithms, particularly XGB, in predicting functional diabetic patients, providing clinicians a valuable tool treatment planning improving patient predictions based receiver operating characteristic (ROC) assessments.

Language: Английский

Citations

0
Development and internal validation of a nomogram for predicting cognitive impairment after mild ischemic stroke and transient ischemic attack based on cognitive trajectories: a prospective cohort study DOI Creative Commons
Panpan Zhao, Lin Shi, Guimei Zhang

et al.

Frontiers in Aging Neuroscience, Journal Year: 2025, Volume and Issue: 17

Published: Jan. 29, 2025

Introduction Many predictive models for cognitive impairment after mild stroke and transient ischemic attack are based on scales at a certain timepoint. We aimed to develop two easy-to-use longitudinal trajectories facilitate early identification treatment. Methods This was prospective cohort study of 556 patients, followed up every 3 months. Patients with least within 2.5 years were included in the latent class growth analysis (LCGA). The patients categorized into groups LCGA. First, difference performed, further univariate stepwise backward multifactorial logistic regression performed. results presented as nomograms, receiver operating characteristic curve analysis, calibration, decision cross-validation performed assess model performance. Results LCGA eventually 255 “22” group selected subgroup analysis. Among them, 29.8% trajectory. Model 1, which incorporated baseline Montreal Cognitive Assessment, ferritin, age, previous stroke, achieved an area under (AUC) 0.973, 2, education, AUC 0.771. Decision showed excellent clinical applicability. Discussion Here, we developed simple post-stroke LCGA, form nomograms suitable application. These provide basis detection prompt

Language: Английский

Citations

0
Artificial intelligence in stroke risk assessment and management via retinal imaging DOI Creative Commons

Parsa Khalafi,

Soroush Morsali, Sana Hamidi

et al.

Frontiers in Computational Neuroscience, Journal Year: 2025, Volume and Issue: 19

Published: Feb. 17, 2025

Retinal imaging, used for assessing stroke-related retinal changes, is a non-invasive and cost-effective method that can be enhanced by machine learning deep algorithms, showing promise in early disease detection, severity grading, prognostic evaluation stroke patients. This review explores the role of artificial intelligence (AI) patient care, focusing on imaging integration into clinical workflows. has revealed several microvascular including decrease central artery diameter an increase vein diameter, both which are associated with lacunar intracranial hemorrhage. Additionally, such as arteriovenous nicking, increased vessel tortuosity, arteriolar light reflex, decreased fractals, thinning nerve fiber layer also reported to higher risk. AI models, Xception EfficientNet, have demonstrated accuracy comparable traditional risk scoring systems predicting For diagnosis, models like Inception, ResNet, VGG, alongside classifiers, shown high efficacy distinguishing patients from healthy individuals using imaging. Moreover, random forest model effectively distinguished between ischemic hemorrhagic subtypes based features, superior predictive performance compared characteristics. support vector achieved classification pial collateral status. Despite this advancements, challenges lack standardized protocols modalities, hesitance trusting AI-generated predictions, insufficient data electronic health records, need validation across diverse populations, ethical regulatory concerns persist. Future efforts must focus validating ensuring algorithm transparency, addressing issues enable broader implementation. Overcoming these barriers will essential translating technology personalized care improving outcomes.

Language: Английский

Citations

0
Nuclear factor erythroid 2-related factor improves depression and cognitive dysfunction in rats with ischemic stroke by mediating wolfram syndrome 1 DOI

Guangxu Hu,

Hongjun Cao

Brain Research, Journal Year: 2025, Volume and Issue: unknown, P. 149572 - 149572

Published: March 1, 2025

Language: Английский

Citations

0
Glymphatic Dysfunction as a Biomarker for Post-stroke Cognitive Impairment DOI
Sheng Zhang,

Weitao Yu,

Xiaofan Zhang

et al.

Published: April 17, 2025

Abstract Ischemic stroke impacts glymphatic function, but its role in prognosis remains unclear. This study evaluated function 146 participants, including non-stroke (healthy controls, n = 48; nonvascular cognitive impairment patients, 47) and ischemic cohorts (n 51). The bilateral diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index, choroid plexus (CP), (PVS) volume ratio, which represent system, were compared across two between pre-rehabilitation (Time 1) 30 days post-rehabilitation 2). Post-stroke (PSCI) was characterized as enduring deficits persisting six months after a stroke. Stroke patients exhibited significantly lower DTI-ALPS index to population (P < 0.05), with improvement observed on infarct side following rehabilitation 0.05). of at Time 1 did not predict poor outcome correlated 6-month PSCI These results indicate that diminishes partially recovering post-rehabilitation, suggest could serve predictor for

Language: Английский

Citations

0
Development and validation of a machine learning-based risk prediction model for post-stroke cognitive impairment DOI Creative Commons
Xia Zhong, Jing Li,

Shunxin Lv

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 30, 2024

Abstract Background Machine learning (ML) risk prediction models for post-stroke cognitive impairment (PSCI) are still far from optimal. This study aims to generate a reliable predictive model predicting PSCI in Chinese individuals using ML algorithms. Methods We collected data on 494 who were diagnosed with acute ischemic stroke (AIS) and hospitalized this condition January 2022 November 2023 at medical institution. All of the observed samples divided into training set (70%) validation (30%) random. Logistic regression combined least absolute shrinkage selection operator (LASSO) was utilized efficiently screen optimal features PSCI. seven different (LR, XGBoost, LightGBM, AdaBoost, GNB, MLP, SVM) compared their performance resulting variables. used five-fold cross-validation measure model's area under curve (AUC), sensitivity, specificity, accuracy, F1 score PR values. SHAP analysis provides comprehensive detailed explanation our optimized performance. Results identified 58.50% eligible AIS patients. The most HAMD-24, FBG, age, PSQI, paraventricular lesion. XGBoost model, among 7 developed based best features, demonstrates superior performance, as indicated by its AUC (0.961), sensitivity (0.931), specificity (0.889), accuracy (0.911), (0.926), AP value (0.967). Conclusion lesion is exceptional It provide clinicians tool early screening patients effective treatment decisions

Language: Английский

Citations

1
Predictive models for secondary epilepsy within 1 year in patients with acute ischemic stroke: a multicenter retrospective study DOI Creative Commons
Jinxin Liu,

Haoyue He,

Yanglingxi Wang

et al.

eLife, Journal Year: 2024, Volume and Issue: 13

Published: July 8, 2024

Background: Post-stroke epilepsy (PSE) is a critical complication that worsens both prognosis and quality of life in patients with ischemic stroke. An interpretable machine learning model was developed to predict PSE using medical records from four hospitals Chongqing. Methods: Medical records, imaging reports, laboratory test results 21,459 stroke were collected analyzed. Univariable multivariable statistical analyses identified key predictive factors. The dataset split into 70% training set 30% testing set. To address the class imbalance, Synthetic Minority Oversampling Technique combined Edited Nearest Neighbors employed. Nine widely used algorithms evaluated relevant prediction metrics, SHAP (SHapley Additive exPlanations) interpret assess contributions different features. Results: Regression revealed complications such as hydrocephalus, cerebral hernia, deep vein thrombosis, well specific brain regions (frontal, parietal, temporal lobes), significantly contributed PSE. Factors age, gender, NIH Stroke Scale (NIHSS) scores, like WBC count D-dimer levels associated increased risk. Tree-based methods Random Forest, XGBoost, LightGBM showed strong performance, achieving an AUC 0.99. Conclusions: accurately predicts risk, tree-based models demonstrating superior performance. NIHSS score, count, most crucial predictors. Funding: research funded by Central University basic young teachers students ability promotion sub-projec t(2023CDJYGRH-ZD06), Emergency Medicine Chongqing Key Laboratory Talent Innovation development joint fund project (2024RCCX10).

Language: Английский

Citations

1
Machine learning–based predictive model for post-stroke dementia DOI Creative Commons
Zemin Wei, Mengqi Li, Chenghui Zhang

et al.

BMC Medical Informatics and Decision Making, Journal Year: 2024, Volume and Issue: 24(1)

Published: Nov. 11, 2024

Post-stroke dementia (PSD), a common complication, diminishes rehabilitation efficacy and affects disease prognosis in stroke patients. Many factors may be related to PSD, including demographic, comorbidities, examination characteristics. However, most existing methods are qualitative evaluations of independent factors, which ignore the interaction amongst various factors. Therefore, purpose this study is explore applicability machine learning (ML) for predicting PSD.

Language: Английский

Citations

1
The use of machine and deep learning to model the relationship between discomfort temperature and labor productivity loss among petrochemical workers DOI Creative Commons
Yilin Zhang, Yifeng Chen,

Qingling Su

et al.

BMC Public Health, Journal Year: 2024, Volume and Issue: 24(1)

Published: Nov. 25, 2024

Workplace may not only increase the risk of heat-related illnesses and injuries but also compromise work efficiency, particularly in a warming climate. This study aimed to utilize machine learning (ML) deep (DL) algorithms quantify impact temperature discomfort on productivity loss among petrochemical workers identify key influencing factors.

Language: Английский

Citations

1