Artificial Intelligence Applications in Healthcare and Precision Medicine

Dear Colleagues,

As a result of its rapid expansion, artificial intelligence (AI) is becoming a powerful tool serving numerous fields, including medicine. Its applications range from diagnostics to surgery, from drug development to rehabilitation, and from remote monitoring to patient assistance, and continue to grow exponentially.

Indeed, artificial intelligence in the medical field is now conceived as an aid to modern medicine. It is precisely in this scenario that technological tools and software used in the medical field are undergoing radical changes, with strong innovations to enable increasingly early advanced diagnoses and more and more personalized therapies, and in general to improve patients’ experience.

In the era of big-data and omics sciences, global health care is trying to move beyond the historical "one-size-fits-all" medical approach—in which one strategy fits all cases—to embrace an increasingly personalized approach uniquely designed specifically for the patient, taking advantage of each person's individual differences such as their genotype, environment and lifestyle.

In particular, in recent years, there have been tremendous advances in the applications of AI in a variety of omics studies, including genomics, transcriptomics, proteomics, metabolomics, radiomics, etc., and all multi-omics integration approaches. It is therefore highly timely to discuss the potential impact of the insights generated by new machine learning (ML) and deep learning (DL) technologies on medical support, clinical decisions, clinical research, pharmaceutical industry and the entire patient pathway, which seeks to be as personalized as possible.

From another perspective, large language models (LLMs), based on DL and trained on huge amounts of text data, allow the generation of new text close to human responses, with the goal of producing virtual assistants and chatbots to provide personalized patient support, answering medical queries, scheduling appointments, and offering basic triage services.

The goal of this Special Issue is therefore to provide a series of articles highlighting the new opportunities, challenges and perspectives of AI tools in the light of precision medicine.

Both theoretical and experimental and case studies are welcome.

Dr. Giorgio De Nunzio
Dr. Luana Conte
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.

• artificial intelligence
• machine learning
• deep learning
• omics sciences
• precision medicine
• personalized medicine
• genomics
• proteomics
• metabolomics
• radiomics
• radiogenomics
• robotic surgery
• assisting technologies
• health monitoring
• computer-assisted detection/diagnosis
• chatbots
• medical imaging
• disease prediction
• prognostics
• drug discovery

Title: Mammogram Classification with HanmanNets using Hanman Transform Classifier
Authors: Hanmandlu Madasu
Affiliation: Indian Institute of Technology Delhi
Abstract: Breast cancer is a deadly disease and radiologists recommend mammography to detect it at the early stages. This paper presents two types of HanmanNets using the information set concept for extracting the features from the Deep learning architectures and also the Hanman transform classifier for the classification of mammograms. The HanmanNets allow the modification of Kernel functions and feature maps of ResNet architectures (Type-1), and the final feature maps from AlexNet, GoogLeNet, and VGG-16 (Type-2).In this work, the type and the characteristics of the abnormality present are captured through the features from mammograms using CNN architectures and HanmanNets for a comparison of their classification performance. The highest accuracy of 100% is achieved for the multi-class classifications on the mini-MIAS database thus surpassing the results in the literature. Validation of the results is done by expert radiologists to make them clinically relevant.

Title: unsupervised learning for breast lesion segmentation
Authors: Luisa Altabella
Affiliation: Department of Diagnostics and Public Health, University of Verona

Title: Using integrated multimodal technology: a way to personalised learning in Health Sciences and Biomedical engineering Students
Authors: María Consuelo Sáiz-Manzanares
Affiliation: DATAHES Research Group, Department of Health Sciences, Faculty of Health Sciences, University of Burgos, 09001 Burgos, Spain
Abstract: Monitoring the learning process during task solving through different channels will facilitate a better understanding of the learning process. This understanding, in turn, will provide teachers with information that will help them to offer individualised education. In the present study, monitoring was carried out during the execution of a task applied in a self-regulated virtual en-vironment. The data were also analysed using data fusion techniques. The objectives were: 1) to examine whether there were significant differences between students in cognitive load (biomarkers: fixations, saccades, pupil diameter, Galvanic Skin Response-GSR-), learning outcomes and perceived student satisfaction with respect to type of degree (health sciences vs. engineering); and 2) to determine whether there were significant differences in cognitive load metrics, learning outcomes and perceived student satisfaction with respect to task presentation (visual and auditory vs. visual). We worked with a sample of 31 universities students (21 health sciences and 10 biomedical engineering). No significant differences were found in the biomarkers (fixations, saccades, pupil diameter and GSR) or in the learning outcomes with respect to the type of degree. Only, differences are detected in perceived anxiety regarding the use of virtual laboratories, being higher in biomedical engineering students. Significant differences are detected in the biomarkers of duration of use of the virtual laboratory and in some learning, outcomes related to the execution and presentation of projects with respect to the variable form of visualisation of the laboratory (visual and auditory vs. visual). Also, in general the use of tasks presented in self-regulated virtual spaces increased learning outcomes and perceived student satisfaction. Further studies will delve into the detection of different forms of information processing depending on the form of presentation of the learning tasks.