Alzheimer’s disease (AD) is a neurodegenerative disease and the most common type of dementia in people age 65 and older. It is characterized by an insidious onset with slowly progressive impairment of behavioral and cognitive functions including memory loss, aphasia, and executive dysfunction. AD has a major impact on patients’ cognitive function and life quality, imposes heavy burdens on patients, families, society, and the health care system, and has emerged as a public health issue as the world’s population ages. However, due to the complicated pathogenesis of AD, we currently lack efficient and objective clinic diagnostic and intervention strategies. Artificial intelligence (AI) is now advancing rapidly and attracting more attention from multidisciplinary researchers throughout the world. Its powerful data mining capability is extremely useful in basic, clinical and translational studies.
Increasing studies have focused on the AI-assisted diagnosis and intervention of AD nowadays. For example, researchers have developed hierarchical classification models for AD diagnosis using a hierarchical full convolutional network (H-FCN), which can achieve a 90% accuracy rate of AD diagnosis. Another example is that a weakly supervised densely connected neural network (wiseDNN) was used for AD prognosis, and studies on 1469 subjects showed that it can efficiently predict future clinical measures of subjects. Therefore, we believe that the powerful data-mining capability of AI will bring new insights for the diagnosis and intervention of AD. However, there are still a number of obstacles in using AI for the diagnosis and intervention of AD, including reliability and reproducibility, as well as the controversy of overcomplication, interpretability, and generalization.
In this Research Topic, we focus on the application of AI in AD diagnosis and intervention, including machine learning, deep learning, as well as neural network methods and models that are applicable and suitable for AD. This Research Topic is aiming to gathering studies that investigate the application of AI techniques in the diagnosis and intervention of AD and to overcoming the challenges of standardization, interpretability, and generalization of the AI approaches in AD studies.
In this Research Topic, we welcome articles that address, but are not limited to, the following themes:
- Efficient AI-based AD recognition and intervention modulations methods
- Endeavors on the standardization, interpretability, and generalization of the AI approaches in AD diagnosis and intervention
- Meaningful discoveries and conclusions derived from the application of AI in AD pathogenic mechanisms that contribute to the AD’s diagnosis and intervention
- AI-assisted AD diagnosis and intervention modulation systems
- Positive argument and promotes on the application of AI in promoting AD diagnosis and intervention modulation
- System review of the application of AI in AD diagnosis and intervention modulations. Reviews and empirical studies of AI-assisted AD diagnosis
Alzheimer’s disease (AD) is a neurodegenerative disease and the most common type of dementia in people age 65 and older. It is characterized by an insidious onset with slowly progressive impairment of behavioral and cognitive functions including memory loss, aphasia, and executive dysfunction. AD has a major impact on patients’ cognitive function and life quality, imposes heavy burdens on patients, families, society, and the health care system, and has emerged as a public health issue as the world’s population ages. However, due to the complicated pathogenesis of AD, we currently lack efficient and objective clinic diagnostic and intervention strategies. Artificial intelligence (AI) is now advancing rapidly and attracting more attention from multidisciplinary researchers throughout the world. Its powerful data mining capability is extremely useful in basic, clinical and translational studies.
Increasing studies have focused on the AI-assisted diagnosis and intervention of AD nowadays. For example, researchers have developed hierarchical classification models for AD diagnosis using a hierarchical full convolutional network (H-FCN), which can achieve a 90% accuracy rate of AD diagnosis. Another example is that a weakly supervised densely connected neural network (wiseDNN) was used for AD prognosis, and studies on 1469 subjects showed that it can efficiently predict future clinical measures of subjects. Therefore, we believe that the powerful data-mining capability of AI will bring new insights for the diagnosis and intervention of AD. However, there are still a number of obstacles in using AI for the diagnosis and intervention of AD, including reliability and reproducibility, as well as the controversy of overcomplication, interpretability, and generalization.
In this Research Topic, we focus on the application of AI in AD diagnosis and intervention, including machine learning, deep learning, as well as neural network methods and models that are applicable and suitable for AD. This Research Topic is aiming to gathering studies that investigate the application of AI techniques in the diagnosis and intervention of AD and to overcoming the challenges of standardization, interpretability, and generalization of the AI approaches in AD studies.
In this Research Topic, we welcome articles that address, but are not limited to, the following themes:
- Efficient AI-based AD recognition and intervention modulations methods
- Endeavors on the standardization, interpretability, and generalization of the AI approaches in AD diagnosis and intervention
- Meaningful discoveries and conclusions derived from the application of AI in AD pathogenic mechanisms that contribute to the AD’s diagnosis and intervention
- AI-assisted AD diagnosis and intervention modulation systems
- Positive argument and promotes on the application of AI in promoting AD diagnosis and intervention modulation
- System review of the application of AI in AD diagnosis and intervention modulations. Reviews and empirical studies of AI-assisted AD diagnosis
