Recognition and classification of facial expression using artificial intelligence as a key of early detection in neurological disorders

被引:2
作者
Goudarzi, Nooshin [1 ,4 ]
Taheri, Zahra [1 ,5 ]
Salari, Amir Mohammad Nezhad [1 ,6 ]
Kazemzadeh, Kimia [1 ,2 ]
Tafakhori, Abbas [1 ,2 ,3 ]
机构
[1] Universal Sci Educ & Res Network USERN, Network Neurosurg & Artificial Intelligence NONAI, Tehran, Iran
[2] Univ Tehran Med Sci, Imam Khomeini Hosp Complex, Neurosci Inst, Iranian Ctr Neurol Res, Tehran 1419733141, Iran
[3] Univ Tehran Med Sci, Sch Med, Dept Neurol, Tehran 1416634793, Iran
[4] Qazvin Univ Med Sci, Student Res Comm, Fac Med, Qazvin 1985717413, Iran
[5] Islamic Azad Univ IAUPS, Student Res Comm, Fac Pharm, Pharmaceut Sci Branch, Tehran 19395-1495, Iran
[6] Bam Univ Med Sci, Student Res Comm, Bam 7661771967, Iran
关键词
facial expression; early detection; artificial intelligence; machine learning; deep learning; neurodegenerative disorders; SUPPORT VECTOR MACHINES; PARKINSONS-DISEASE; ALZHEIMERS-DISEASE; PAIN; TOLERANCE; DIAGNOSIS; EPILEPSY; ONSET;
D O I
10.1515/revneuro-2024-0125
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
The recognition and classification of facial expressions using artificial intelligence (AI) presents a promising avenue for early detection and monitoring of neurodegenerative disorders. This narrative review critically examines the current state of AI-driven facial expression analysis in the context of neurodegenerative diseases, such as Alzheimer's and Parkinson's. We discuss the potential of AI techniques, including deep learning and computer vision, to accurately interpret and categorize subtle changes in facial expressions associated with these pathological conditions. Furthermore, we explore the role of facial expression recognition as a noninvasive, cost-effective tool for screening, disease progression tracking, and personalized intervention in neurodegenerative disorders. The review also addresses the challenges, ethical considerations, and future prospects of integrating AI-based facial expression analysis into clinical practice for early intervention and improved quality of life for individuals at risk of or affected by neurodegenerative diseases.
引用
收藏
页码:479 / 495
页数:17
相关论文
共 139 条
[1]   Automated Computer Vision Assessment of Hypomimia in Parkinson Disease: Proof-of-Principle Pilot Study [J].
Abrami, Avner ;
Gunzler, Steven ;
Kilbane, Camilla ;
Ostrand, Rachel ;
Ho, Bryan ;
Cecchi, Guillermo .
JOURNAL OF MEDICAL INTERNET RESEARCH, 2021, 23 (02)
[2]   Axial signs and magnetic resonance imaging correlates in Parkinson's disease [J].
Acharya, Hernish J. ;
Bouchard, Thomas P. ;
Emery, Derek J. ;
Camicioli, Richard M. .
CANADIAN JOURNAL OF NEUROLOGICAL SCIENCES, 2007, 34 (01) :56-61
[3]  
Adnan T., 2023, ARXIV
[4]  
Afzaal H., 2023, PRECIS AGRIC, V169, P186
[5]   Molecular diagnostics of neurodegenerative disorders [J].
Agrawal, Megha ;
Biswas, Abhijit .
FRONTIERS IN MOLECULAR BIOSCIENCES, 2015, 2
[6]   Classification of Alzheimer's Disease Stages: An Approach Using PCA-Based Algorithm [J].
Ahmad, Fayyaz ;
Dar, Waqar Mahmood .
AMERICAN JOURNAL OF ALZHEIMERS DISEASE AND OTHER DEMENTIAS, 2018, 33 (07) :433-439
[7]  
Ahmedt-Aristizabal D, 2018, IEEE ENG MED BIO, P3578, DOI 10.1109/EMBC.2018.8513031
[8]   A hierarchical multimodal system for motion analysis in patients with epilepsy [J].
Ahmedt-Aristizabal, David ;
Fookes, Clinton ;
Denman, Simon ;
Kien Nguyen ;
Fernando, Tharindu ;
Sridharan, Sridha ;
Dionisio, Sasha .
EPILEPSY & BEHAVIOR, 2018, 87 :46-58
[9]   Deep facial analysis: A new phase I epilepsy evaluation using computer vision [J].
Ahmedt-Aristizabal, David ;
Fookes, Clinton ;
Kien Nguyen ;
Denman, Simon ;
Sridharan, Sridha ;
Dionisio, Sasha .
EPILEPSY & BEHAVIOR, 2018, 82 :17-24
[10]   Automated analysis of seizure semiology and brain electrical activity in presurgery evaluation of epilepsy: A focused survey [J].
Ahmedt-Aristizabal, David ;
Fookes, Clinton ;
Dionisio, Sasha ;
Kien Nguyen ;
Cunha, Joao Paulo S. ;
Sridharan, Sridha .
EPILEPSIA, 2017, 58 (11) :1817-1831