Comprehensive predictive model for cerebral microbleeds: integrating clinical and biochemical markers DOI Creative Commons
Lijing Wang, Yao Li, Yadong Hu

et al.

Frontiers in Neuroscience, Journal Year: 2024, Volume and Issue: 18

Published: Dec. 13, 2024

Background Cerebral Microbleeds (CMBs) serve as critical indicators of cerebral small vessel disease and are strongly associated with severe neurological disorders, including cognitive impairments, stroke, dementia. Despite the importance diagnosing preventing CMBs, there is a significant lack effective predictive tools in clinical settings, hindering comprehensive assessment timely intervention. Objective This study aims to develop robust model for CMBs by integrating broad range laboratory parameters, enhancing early diagnosis risk stratification. Methods We analyzed extensive data from 587 neurology inpatients using advanced statistical techniques, Least Absolute Shrinkage Selection Operator (LASSO) logistic regression. Key factors such Albumin/Globulin ratio, gender, hypertension, homocysteine levels, Neutrophil HDL Ratio (NHR), history stroke were evaluated. Model validation was performed through Receiver Operating Characteristic (ROC) curves Decision Curve Analysis (DCA). Results The demonstrated strong performance applicability. predictors identified include NHR, among others. Validation metrics area under ROC curve (AUC) decision analysis confirmed model’s utility predicting highlighting its potential implementation. Conclusion developed this offers advancement personalized management patients at CMBs. By addressing gap tools, facilitates targeted intervention, potentially reducing incidence impairments microbleeds. Our findings advocate more nuanced approach cerebrovascular management, emphasizing multi-factorial profiling.

Language: Английский

Comprehensive predictive model for cerebral microbleeds: integrating clinical and biochemical markers DOI Creative Commons
Lijing Wang, Yao Li, Yadong Hu

et al.

Frontiers in Neuroscience, Journal Year: 2024, Volume and Issue: 18

Published: Dec. 13, 2024

Background Cerebral Microbleeds (CMBs) serve as critical indicators of cerebral small vessel disease and are strongly associated with severe neurological disorders, including cognitive impairments, stroke, dementia. Despite the importance diagnosing preventing CMBs, there is a significant lack effective predictive tools in clinical settings, hindering comprehensive assessment timely intervention. Objective This study aims to develop robust model for CMBs by integrating broad range laboratory parameters, enhancing early diagnosis risk stratification. Methods We analyzed extensive data from 587 neurology inpatients using advanced statistical techniques, Least Absolute Shrinkage Selection Operator (LASSO) logistic regression. Key factors such Albumin/Globulin ratio, gender, hypertension, homocysteine levels, Neutrophil HDL Ratio (NHR), history stroke were evaluated. Model validation was performed through Receiver Operating Characteristic (ROC) curves Decision Curve Analysis (DCA). Results The demonstrated strong performance applicability. predictors identified include NHR, among others. Validation metrics area under ROC curve (AUC) decision analysis confirmed model’s utility predicting highlighting its potential implementation. Conclusion developed this offers advancement personalized management patients at CMBs. By addressing gap tools, facilitates targeted intervention, potentially reducing incidence impairments microbleeds. Our findings advocate more nuanced approach cerebrovascular management, emphasizing multi-factorial profiling.

Language: Английский

Citations

0