Deep Learning for Chronic Disease Diagnosis, Prediction, Monitoring, and Treatment

Dear colleagues,

Chronic diseases such as dementia and diabetes, among others, immensely impact the lives of patients, their families, and societies. The wide availability of digital technologies in Healthcare 4.0 facilitates the delivery of more effective and efficient healthcare services. These technologies have the potential to reduce healthcare costs, improve user experience, and increase the quality of care. Using machine learning (ML), deep learning (DL) and other artificial intelligence (AI) technologies to automate chronic-disease management is expected to help healthcare providers (e.g., health practitioners, hospitals, and clinics) in daily practice to serve more patients in a more efficient manner. However, making personalized decisions in chronic-disease management requires the integration of huge and heterogeneous data from the hospital’s electronic health records, including neuroimaging (e.g., MRI and CT), lab tests, time series, sound waves, ECG, text, etc. DL algorithms such as CNN (convolutional neural network), RNN (recurrent neural network), RBM (restricted Boltzmann machine), autoencoder, and FFNN (feed forward neural network) have rapidly evolved and recently gained an ever-increasing role in the medical domain. They achieve superior performance compared to regular machine-learning algorithms such as SVM (support vector machine), random forest, KNN (k nearest neighbors), and decision trees. Deep-learning algorithms can automatically extract complex and deep representations from large and unstructured data such as images, sound, and text. In addition, building hybrid models and ensembles of deep-learning models even further improves modern deep-learning techniques. However, the optimization of these models is a challenging task, and implementing customized data preprocessing pipelines is another critical step for building high-performing models. The implementation of such AI-oriented diagnostic frameworks therefore requires more sophisticated approaches, which would be sustainable and inclusive in nature. This Special Issue aims to provide a platform to researchers for sharing recent novel advances in the application of DL and AI models in chronic-disease diagnosis, prediction, monitoring, and treatment.

Both theoretical and practical papers are solicited on the following related aspects: algorithms, system design, performance analysis, experimental studies, and review studies. Potential topics include, but are not limited to, the themes listed below:

• The key techniques and applications of AI-based disease diagnosis;
• The integration of DL and ontology reasoning;
• DL-based uncertainty management;
• AutoML’s role in optimizing DL models;
• Alzheimer’s disease diagnosis, progression detection, and monitoring;
• Multitask modeling using DL;
• Building hybrid DL models;
• The interpretability of DL models’ decisions;
• Image visualization for explaining DL decisions;
• Big data fusion and multimodal data;
• Ensemble deep-learning models for chronic-disease management;
• Biomarker identification using multiomics analysis;
• Secure healthcare services and applications.

Dr. Shaker El-Sappagh
Dr. Mahmud Hossain
Dr. Shahid Al Noor
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• Artificial intelligence
• Disease diagnosis
• Machine learning
• Deep learning
• Medical informatics
• Bioinformatics
• Industry 4.0
• Data analysis
• Healthcare security.