The recent pandemic triggered by a coronavirus has shaken the world. It is vital to exploit state-of-the-art technology to implement and develop real-time disease detection systems capable of telemonitoring and telediagnosis to mitigate the adverse impact of such pandemics in the future. These systems will be significant because they will help diagnose patients at home and help control the pandemic by avoiding the visits to testing centers and hospitals where subjects are exposed to the virus and have a high risk of infection.
Neurological diseases like Parkinson’s disease (PD), Alzheimer’s disease (AD), and cognitive impairment, among others, are rampant among the elderly and have a higher economic burden on healthcare systems. Automated diagnostic methods capable of early detection of such diseases may reduce the associated financial cost by controlling symptoms during the initial stages. Similarly, other diseases like hepatitis, coronary artery disease, heart failure, etc., require a high level of human expertise and equipment for their diagnosis, which are rarely available in developing and underdeveloped countries. Hence, automated methods based on advanced computational methods may offer a cheap and pertinent solution.
Recently, many computational methods based on machine learning algorithms have been developed to diagnose these diseases. However, the main problem in these methods is either a lack of availability of large-scale datasets or generalization during real-time applications. We invite researchers to present advanced computational methods and ideas to yield automated processes which demonstrate better generalization performances in real-time applications and could be deployed in clinical settings.
In this Research Topic we welcome submissions focusing on, but not limited to, the following subtopics:
• Computational methods for developing automated neurological and other disease detection systems
• Mathematical methods for optimized machine learning models for neurological and other disease detection
• Statistical methods for biomarkers evaluation of neurological and other diseases
• Deep learning methods for neurological and other disease detection
• Telemonitoring and telediagnosis of Parkinson’s disease and other neurological diseases
• Handwritten drawings and sentences based on Parkinson’s, Alzheimer and Mild Cognitive Impairment detection
• Multimodal machine learning-based methods for reliable disease detection
• Multimodal data balancing using generative adversarial networks
• Collection and analysis approaches for large scale biomedical data
• Surveys/review articles presenting state-of-the-art machine learning approaches for biomedical applications
• Prediction of stress, depression, epileptic seizures, and other neurological diseases.
The recent pandemic triggered by a coronavirus has shaken the world. It is vital to exploit state-of-the-art technology to implement and develop real-time disease detection systems capable of telemonitoring and telediagnosis to mitigate the adverse impact of such pandemics in the future. These systems will be significant because they will help diagnose patients at home and help control the pandemic by avoiding the visits to testing centers and hospitals where subjects are exposed to the virus and have a high risk of infection.
Neurological diseases like Parkinson’s disease (PD), Alzheimer’s disease (AD), and cognitive impairment, among others, are rampant among the elderly and have a higher economic burden on healthcare systems. Automated diagnostic methods capable of early detection of such diseases may reduce the associated financial cost by controlling symptoms during the initial stages. Similarly, other diseases like hepatitis, coronary artery disease, heart failure, etc., require a high level of human expertise and equipment for their diagnosis, which are rarely available in developing and underdeveloped countries. Hence, automated methods based on advanced computational methods may offer a cheap and pertinent solution.
Recently, many computational methods based on machine learning algorithms have been developed to diagnose these diseases. However, the main problem in these methods is either a lack of availability of large-scale datasets or generalization during real-time applications. We invite researchers to present advanced computational methods and ideas to yield automated processes which demonstrate better generalization performances in real-time applications and could be deployed in clinical settings.
In this Research Topic we welcome submissions focusing on, but not limited to, the following subtopics:
• Computational methods for developing automated neurological and other disease detection systems
• Mathematical methods for optimized machine learning models for neurological and other disease detection
• Statistical methods for biomarkers evaluation of neurological and other diseases
• Deep learning methods for neurological and other disease detection
• Telemonitoring and telediagnosis of Parkinson’s disease and other neurological diseases
• Handwritten drawings and sentences based on Parkinson’s, Alzheimer and Mild Cognitive Impairment detection
• Multimodal machine learning-based methods for reliable disease detection
• Multimodal data balancing using generative adversarial networks
• Collection and analysis approaches for large scale biomedical data
• Surveys/review articles presenting state-of-the-art machine learning approaches for biomedical applications
• Prediction of stress, depression, epileptic seizures, and other neurological diseases.
