AI-Assisted Diagnostics in Telemedicine and Digital Health

Dear Colleagues,

It is expected that by 2030, telehealth services in the United States will reach USD 549.1 billion. The main drivers for this growth are (1) expanding demand for clinical services, especially in rural or underserved areas; (2) increasing complexity of medical conditions and the coexistence of multiple comorbidities necessitating input from expert clinicians; (3) expansion in wireless coverage; (4) increasing use of smartphones and digital health apps; (5) rising cost of healthcare; and (6) shortage of medical professionals and increasing preference for remote patient engagement using telehealth platforms. The rapidly expanding volume of telehealth services results in the aggregation of vast amounts of multimodal data. Big data analytics and modern artificial intelligence approaches have significant potential in optimizing telehealth delivery and reducing health disparities.

The applications of machine learning (ML) models and artificial intelligence (AI) methods in telemedicine, telehealth, and digital health are revolutionizing how healthcare services are delivered, making them more accessible, personalized, and efficient. These technologies play a crucial role in improving patient outcomes, enhancing the patient–provider interaction, and optimizing healthcare resources. This Special Issue will include articles on data in applications and data-related processes in telemedicine and digital health, including data collection and data acquisition, data processing, data analysis, data maintenance and data integrity, data curation, data management systems, and data compression. Articles from three major tracks relevant to AI applications in telemedicine and digital health will be included in this Special Issue: (1) approaches to address challenges in telehealth data quality, aggregation, and harmonization in the development of reliable and reproducible AI models for digital biomarkers and clinical diagnostics; (2) successful examples of AI and ML applications to facilitate diagnostic accuracy using telemedicine and mobile health data; (3) best practices in predictive modeling of telemonitoring data to reduce biases and achieve fairness, transparency, and explainability. These articles are expected to reflect a full spectrum of AI and ML approaches in telehealth, including supervised, unsupervised, semi-supervised, reinforcement, deep, and ensemble learning. This Special Issue is intended for a broad multi-disciplinary audience interested in the advancement of data storage and processing for telehealth services, including individuals with a background in computer science, biomedical engineering, clinical informatics, information sciences, medicine, and allied health.

The aim of this Special Issue is to accelerate the successful adoption of AI and big data analytics in telehealth applications to improve diagnostic accuracy and eliminate health disparities. Original articles, reviews, and commentaries representing current best practices and innovative approaches will be invited from broad scientific communities. We will also invite extended papers presented at the related workshop at the Artificial Intelligence in Medicine conference (https://aime24.aimedicine.info/) not published elsewhere.

The Special Issue topics will include AI applications in telemedicine and digital health at patient, provider, health system, and population levels. At the patient level, potential topics will include approaches to utilizing patient-reported and sensor-generated data for early diagnostics of incipient patient deterioration, AI-driven telerehabilitation, and chatbot-assisted remote patient engagement. At the provider level, potential topics will include approaches for real-time clinical decision support of differential diagnostics during telemedicine consultations, including image analytics and real-time AI-assisted differential diagnostics to support televisits. In the health system, potential topics will include AI methods to predict telemedicine no-shows and identify diagnostic areas of high demand. At the population level, potential topics will include AI approaches to identify subpopulations that benefit from telehealth services and identify the role of social determinants of health that affect diagnostic accuracy. Additional topics will be considered based on their merit and novelty.

Prof. Dr. Joseph Finkelstein
Guest Editor

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.

• AI
• machine learning
• deep learning
• image analysis
• digital health
• healthcare
• telemedicine
• disease diagnosis