Advances in Personalized and Intelligent Healthcare Systems Based on Artificial Intelligence

Dear Colleagues,

It is estimated that there will be a global shortfall of staff in hospitals by 2030. Artificial intelligence can help to revolutionize the way healthcare is nowadays delivered in hospitals and significantly improve healthcare medicine for several diseases, especially through empathic AI, as well as the inclusion of socially assistive humanoid robots in routine care during hospitalization since they have potential to significantly improve the landscape of nursing and routine care for both nursing staff and patients. Therefore, more healthcare systems need to be transformed in order to achieve more effective and efficient systems.

In a rapidly evolving society, psychological distress, anxiety, and depression pose significant challenges for current healthcare systems. Further, overweight and obesity rates have also reached epidemic proportions. And tools based on AI can improve the treatment of patients who have survived cancer, for example, are suffering with dementia, etc. Further, with the rise of the ageing population, several diseases becoming serious problems, and advances being made in understanding them, there is a focus on their consequences, including pain, distress, and causative links between health determinants, disease, and interventions in order to provide an evidence base for more intelligent and efficient policymaking. Obviously, on the one hand, clinical decision support systems based on novel models of health data analysis are needed, while on the other hand, systems for the remote and personalized monitoring of patients are required.

The optimal use and re-use of health data (e.g., epigenetic, biological, demographic, etc.) is also needed in order to generate novel metadata/knowledge and provide new methodologies and tools for creating and deploying such biobanks that can act as a scientific platform for research in obesity, as well as improve diagnostic and therapeutic approaches, understand the transition from metabolically healthy to unhealthy, and design advanced strategies to educate and empower citizens. Novel frameworks for data handling are also needed in order to provide more robust and transparent methodologies for operational procedures, analysis, and reporting.

Digital health interventions have the potential to improve the accessibility and effectiveness of palliative care, where novel technologies are increasingly being evaluated for, e.g., online learning, mobile applications, Virtual Reality tools, symptom management, care planning, decision-making, and interaction. E.g. professionals and caregivers using phones, internet and computer systems. In order to optimize clinical workflows, identification of holistic intervention (care and treatment) and assessment of health outcomes, innovative digital tools are needed.

To co-create interventions, co-design solutions, and assist key stakeholders, collaborative platforms and AI-based services are needed in order to facilitate the making of advanced decisions in policymaking. In this way, we can accelerate the sharing of experiences from the field and reports on the effects of clinical trials. This can also provide seamless cooperation and effective dialogue with stakeholders and ensure access to the collected information in a structured manner to foster the use of co-creative solutions.

For comprehensive digital transformation, we have to develop a common open integration platform with tools and applications based on artificial intelligence and big data in order to facilitate and measure the benefits of using digital technologies in hospitals and care facilities. Platforms of knowledge, strategies to reduce risks and increase awareness, strengthen resistance and cognitive flexibility, pilot solutions, open knowledge platforms that offer digital tools for children, adolescents, and young people, groundbreaking technologies and methodologies, and gamification concepts have to be made available in several languages.

Further, sensing networks and frameworks for multimodal risk assessment and tracking of symptoms by analyzing physiological biomarkers, by extracting and processing conversational biomarkers, are needed. Algorithms for the tracking and classification of wellbeing and health parameters are complex sensors executing multimodal signal fusion. Such sensors represent a novel source of real-world data, while their output classification can be added to the patients’ electronic data and used in an automatic patient assessment carried out under clinical decision support systems.

Fake images or videos can already simulate real events extremely closely when properly trained. AI technology can make a face move and 'speak' in a hyper-realistic way. This technology, therefore, poses a high social and health threat as models could be used—and have been—to spread fake information and disinformation within the healthcare system.

With spoken-language interfaces, chatbots, and enablers, conversational intelligence became an emerging field of research in man–machine interfaces, especially with the development of AI, large language models, etc. Conversational agents have the potential to play a significant role in healthcare, from assistants during clinical consultations to supporting positive behavior changes, or as assistants in living environments helping with daily tasks and activities, as well as the inclusion of socially assistive humanoid robots in nursing and care routine during hospitalization.

Speech-to-speech translation AI technologies can improve patient–doctor understanding, especially in cases when the patient does not speak the native language. Extensive research on the benefits of different types of training data, synthetic speech, and voice transfer for building a speech translation system for this support is, therefore, highly demanded. Many subfields of speech processing are relevant to this, including speech-to-text, speech translation, text-to-speech, unsupervised and weakly supervised learning, dialect detection, and voice adaptation.

Health AI-based platforms must be validated through large-scale pilots targeting several diseases. And proper evaluation procedures have to be developed and implemented in order to boost the development of these platforms, their tools, and technologies. They should be evaluated subjectively or objectively, and feedback should be provided for their advancement.

Dr. Matej Rojc
Dr. Izidor Mlakar
Dr. Antonis Billis
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. Applied Sciences 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 2400 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.

• healthcare systems
• artificial intelligence
• multilingual conversational chatbot systems
• social robots
• big data
• large language models
• speech-to-speech translation
• evaluation
• personal data security