دانشگاه مازندران

 آمار

تعداد نشریات32
تعداد شماره‌ها554
تعداد مقالات5,380
تعداد مشاهده مقاله8,161,104
تعداد دریافت فایل اصل مقاله6,064,156
shahraki, Golnoush, Mazrooei rad, Elias, Rezvani Kakhki, Behrang, Heidari, Mohammad, Goli, Peyman. (1404). Comparative Evaluation of Brain Biological Age Estimation Methods: Data Sources and Performance Benchmarks in Diverse Deep Learning Architectures. پژوهشنامه مدیریت اجرایی, 2(1), 46-54. doi: 10.22080/frai.2026.30547.1031
Golnoush shahraki; Elias Mazrooei rad; Behrang Rezvani Kakhki; Mohammad Heidari; Peyman Goli. "Comparative Evaluation of Brain Biological Age Estimation Methods: Data Sources and Performance Benchmarks in Diverse Deep Learning Architectures". پژوهشنامه مدیریت اجرایی, 2, 1, 1404, 46-54. doi: 10.22080/frai.2026.30547.1031
shahraki, Golnoush, Mazrooei rad, Elias, Rezvani Kakhki, Behrang, Heidari, Mohammad, Goli, Peyman. (1404). 'Comparative Evaluation of Brain Biological Age Estimation Methods: Data Sources and Performance Benchmarks in Diverse Deep Learning Architectures', پژوهشنامه مدیریت اجرایی, 2(1), pp. 46-54. doi: 10.22080/frai.2026.30547.1031
shahraki, Golnoush, Mazrooei rad, Elias, Rezvani Kakhki, Behrang, Heidari, Mohammad, Goli, Peyman. Comparative Evaluation of Brain Biological Age Estimation Methods: Data Sources and Performance Benchmarks in Diverse Deep Learning Architectures. پژوهشنامه مدیریت اجرایی, 1404; 2(1): 46-54. doi: 10.22080/frai.2026.30547.1031

Comparative Evaluation of Brain Biological Age Estimation Methods: Data Sources and Performance Benchmarks in Diverse Deep Learning Architectures

Future Research on AI and IoT
مقاله 4، دوره 2، شماره 1، فروردین 2026، صفحه 46-54    اصل مقاله (481.62 K)
نوع مقاله: Research Article
شناسه دیجیتال (DOI): 10.22080/frai.2026.30547.1031
نویسندگان
Golnoush shahraki1؛ Elias Mazrooei rad* 2؛ Behrang Rezvani Kakhki3؛ Mohammad Heidari4؛ Peyman Goli5
1Master of Biomedical Engineering, Clinical Research Development Unit, Shahid Hasheminejad Hospital, Mashhad University Of Medical Sciences, Mashhad,Iran.
2Assistant Professor, Department of biomedical Engineering, Khavaran Institute of Higher Education, Mashhad, Iran.
3Associate Professor of Emergency medicine, Department of Emergency Medicine, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
4Bachelor of Nursing, Shahid Hasheminejad Hospital, Mashhad University Of Medical Sciences, Mashhad,Iran
5Postdoctoral Researcher, Oldenburg University, Germany
تاریخ دریافت: 26 آبان 1404،  تاریخ بازنگری: 01 دی 1404،  تاریخ پذیرش: 11 دی 1404 
چکیده
Introduction: Biological age (BA) offers a more accurate measure of an individual's health status and aging rate than chronological age. This study provides a systematic review and comparative analysis of deep learning (DL) methodologies for BA estimation.
Materials and Methods: We analyzed 33 selected studies, extracting data into structured tables to compare data sources (brain MRI, X-rays, blood biomarkers, wearable sensors), model architectures (CNNs, LSTMs, Ensembles, Multimodal), and performance metrics (MAE, R², AUROC). This framework enabled a transparent, side-by-side evaluation of each approach's strengths and limitations.
Results: Our analysis confirms the superiority of advanced DL architectures. CNNs demonstrated exceptional performance on imaging data, with a lightweight SFCN model for brain MRI achieving a state-of-the-art Mean Absolute Error (MAE) of 2.14 years. Models that combined multiple data types, such as imaging with clinical information, proved to be the most robust. For instance, one multimodal ensemble model achieved an AUROC of 0.89-0.91 for predicting mortality. However, significant challenges were consistently identified, including limited model generalizability across diverse populations and the critical issue of data heterogeneity.
Conclusion: Deep learning holds immense promise for accurate biological age estimation, with complex, data-specific models like CNNs and multimodal ensembles delivering the highest performance. For successful translation into clinical practice, future efforts must prioritize overcoming barriers related to model generalizability, data standardization, and interpretability. Resolving these issues is essential for BA to realize its potential in personalized preventive medicine and health risk assessment.
کلیدواژه‌ها
Biological Age Estimation؛ Deep Learning؛ Neural Networks؛ Artificial Intelligence
آمار
تعداد مشاهده مقاله: 76
تعداد دریافت فایل اصل مقاله: 47


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب