Sex-Specific Imaging Biomarkers for Parkinson’s Disease Diagnosis: A Machine Learning Analysis DOI
Yifeng Yang,

Liangyun Hu,

Yang Chen

и другие.

Deleted Journal, Год журнала: 2024, Номер unknown

Опубликована: Сен. 10, 2024

This study aimed to identify sex-specific imaging biomarkers for Parkinson's disease (PD) based on multiple MRI morphological features by using machine learning methods. Participants were categorized into female and male subgroups, various structural extracted. An ensemble Lasso (EnLasso) method was employed a stable optimal feature subset each sex-based subgroup. Eight typical classifiers adopted construct classification models PD HC, respectively, validate whether specific sex subgroups could bolster the precision of identification. Finally, statistical analysis correlation tests carried out significant brain region potential biomarkers. The best model (MLP) subgroup achieved average accuracy 92.83% 92.11%, which better than that overall samples (86.88%) incorporating gender factor (87.52%). In addition, most discriminative among males lh 6r (FD), but females, it PreS (GI). findings indicate diagnosis yields significantly higher performance compared previous included all participants. Additionally, exhibited greater number changes subgroup, suggesting differences in risk markers. underscore importance stratifying data offer insights variations phenotypes, aid development precise personalized diagnostic approaches early stages disease.

Язык: Английский

Impact of gene-gene interactions in Progressive Supranuclear Palsy: new genetic perspectives in the Asian-Indian population DOI

Saikat Dey,

Monojit Debnath,

Ramchandra Yelamanchi

и другие.

Journal of Neurogenetics, Год журнала: 2025, Номер unknown, С. 1 - 7

Опубликована: Май 14, 2025

Genes play an important role in the risk of Progressive Supranuclear Palsy (PSP). Some major genes identified for PSP include MAPT, STX6, MOBP, and EIF2AK3 several ethnic groups. However, interactions among these have not been explored PSP. Therefore, this prospective case-control study aimed to explore impact gene-gene patients with (n = 106) healthy subjects 109) Indian ethnicity. Eight single nucleotide polymorphisms (SNPs) MAPT gene (rs1467967, rs242557, rs3785883, rs2471738, rs8070723, rs7521, rs12185268, rs62063857, two SNPs STX6 (rs3747957 rs1411478), one SNP each from MOBP (rs1768208) (rs7571971) were genotyped by TaqMan Alleleic Discrimination Assay all participants. Gene-gene 12 performed using multi-dimensionality reduction (MDR) test. The combination rs3785883), along (rs1411478) (rs1768208), appeared be best five-locus model (p < 0.001), suggesting strong modulating Strong synergistic observed within rs244557, rs2471738), between (rs7521) (rs1768208). Additionally, moderately found (i) (rs1411478), (ii) (rs3785883) genes. findings suggest significant amongst This implies that epistatic might constitute mechanism delineating genetic basis

Язык: Английский

Процитировано

0

Explainable machine learning on clinical features to predict and differentiate Alzheimer's progression by sex: Toward a clinician-tailored web interface DOI Creative Commons
Fabrizio d’Amore, Marco Moscatelli, Antonio Malvaso

и другие.

Journal of the Neurological Sciences, Год журнала: 2024, Номер 468, С. 123361 - 123361

Опубликована: Дек. 19, 2024

Alzheimer's disease (AD), the most common neurodegenerative disorder world-wide, presents sex-specific differences in its manifestation and progression, necessitating personalized diagnostic approaches. Current procedures are often costly invasive, lacking consideration of sex-based differences. This study introduces an explainable machine learning (ML) system to predict differentiate progression AD based on sex, using non-invasive, easily collectible predictors such as neuropsychological test scores sociodemographic data, enabling application every day clinical settings. The ML model uses SHapley Additive explanations (SHAP) Local Interpretable Model-Agnostic Explanations (LIME) provide clear insights into decision-making, making complex outcomes easier interpret. includes a user-friendly graphical interface designed collaboration with clinicians, supporting integration medical practice. extends cohort include healthy Mild Cognitive Impairment subjects, aiming support early diagnosis pre-clinical stages. was trained large dataset 2407 subjects from ADNI open dataset, enhancing robustness applicability. By focusing features utilizing longitudinal aims improve prediction accuracy detection AD, ultimately advancing therapeutic Key findings highlight significance Mini-Mental State Examination, Rey Auditory Verbal Learning Test, Logical Memory - Delayed Recall, educational attainment disparities. Despite performance metrics precision, recall, weighted F1-score demonstrating efficacy, future research should address limitations relying single dataset.

Язык: Английский

Процитировано

1

Sex-Specific Imaging Biomarkers for Parkinson’s Disease Diagnosis: A Machine Learning Analysis DOI
Yifeng Yang,

Liangyun Hu,

Yang Chen

и другие.

Deleted Journal, Год журнала: 2024, Номер unknown

Опубликована: Сен. 10, 2024

This study aimed to identify sex-specific imaging biomarkers for Parkinson's disease (PD) based on multiple MRI morphological features by using machine learning methods. Participants were categorized into female and male subgroups, various structural extracted. An ensemble Lasso (EnLasso) method was employed a stable optimal feature subset each sex-based subgroup. Eight typical classifiers adopted construct classification models PD HC, respectively, validate whether specific sex subgroups could bolster the precision of identification. Finally, statistical analysis correlation tests carried out significant brain region potential biomarkers. The best model (MLP) subgroup achieved average accuracy 92.83% 92.11%, which better than that overall samples (86.88%) incorporating gender factor (87.52%). In addition, most discriminative among males lh 6r (FD), but females, it PreS (GI). findings indicate diagnosis yields significantly higher performance compared previous included all participants. Additionally, exhibited greater number changes subgroup, suggesting differences in risk markers. underscore importance stratifying data offer insights variations phenotypes, aid development precise personalized diagnostic approaches early stages disease.

Язык: Английский

Процитировано

0