Statistical and Physics-Based Interpretation of AI and Machine Learning Methods for Biomedical Data
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Entropy and Biology".
Deadline for manuscript submissions: 28 February 2027 | Viewed by 1576
Special Issue Editor
Interests: artificial intelligence; machine learning; multiomic data; complex systems; neural networks; biophysics
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
We are assisting in the unprecedented flourishing of new AI and Machine Learning methods, which are being applied in the majority of research fields. In particular, the Biomedical field is experimenting with a huge increase in such applications in a variety of sectors, such as multi-omics science, medical imaging (including digital pathology), clinical practice, and therapy optimization for health system organizations.
The methods that are being used cover all AI techniques, such as supervised, unsupervised, and reinforcement learning. Entropy serves as a bridge connecting AI black-box models to biophysical systems, demonstrating dual significance in both algorithmic optimization and interpretability enhancement. In supervised learning, entropy-driven techniques like cross-entropy loss functions and information gain metrics refine classification accuracy while addressing biological data imbalances. Unsupervised learning leverages entropy constraints in clustering purity assessments and maximum entropy principles for synthetic medical data generation, ensuring statistical fidelity without compromising privacy. Reinforcement learning frameworks integrate entropy regularization to balance exploration–exploitation trade-offs.
A very important issue in all Biomedical applications is the transparency of the methods used, as stated in the EU AI act. This can be addressed by so-called Explainable AI (XAI), but a further step toward a more complete understanding of these techniques can be their statistical and physics-based interpretation of the learning process. Some paradigmatic examples can be the generation of synthetic data, Neural Differential Equations, clustering, and Graph Neural Networks. The integration of entropy principles bridges these AI methods and statistical physics.
This Special Issue aims to collect contributions related to AI and Machine Learning methods applied to Biomedicine with a physics-based and statistical interpretation. In particular, analyses of Biomedical data based on these methods falls within the scope of this Special Issue.
Prof. Dr. Gastone C. Castellani
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 250 words) can be sent to the Editorial Office for assessment.
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. Entropy is an international peer-reviewed open access monthly 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.
Keywords
- statistical interpretation of learning rules
- diffusion processes in AI
- complex networks
- AI methods for biomedicine
- integration of multi-omic data
- AI for medical imaging
- biophysics-inspired learning rules
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
