Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.5
4.4
Journals
Bioengineering
Special Issues
Emerging Artificial Intelligence Trends for Predictive Analytics and Personalized Healthcare
share announcement

Emerging Artificial Intelligence Trends for Predictive Analytics and Personalized Healthcare

A Special Issue of Bioengineering (ISSN 2306-5354) belonging to the section "Biosignal Processing".

Deadline for manuscript submissions: closed (31 July 2026) | Viewed by 3912

Editors

Dr. Josu Maiora

E-Mail Website
Guest Editor
Electronic Technology Department, Faculty of Engineering of Gipuzkoa, University of the Basque Country, 20018 San Sebastian, Spain
Interests: artificial intelligence; physical activity analysis; medical image analysis
Dr. Maria Begoña Sanz Echevarría

E-Mail Website
Guest Editor
1. Department of Physiology, University of the Basque Country, 48940 Leioa, Spain
2. Biobizkaia Health Research Institute, 48903 Barakaldo, Spain
Interests: physiology; aging; frailty; molecular biomarkers; sarcopenia; physical function; physical activity; bioethics
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Manuel Graña

E-Mail Website
Guest Editor
Computational Intelligence Group, Department of CCIA, University of the Basque Country, 20018 San Sebastian, Spain
Interests: hyperspectral image analysis; computational intelligence; medical imaging
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The next big technology to revolutionize healthcare will be artificial intelligence (AI). AI is increasingly present in the prevention, diagnosis, treatment and monitoring phases of subjects. The models that are being implemented allow for the implementation of personalized medicine, which aims to offer tailored strategies for defined groups of people. The use of AI includes processing data acquired through wearable sensors or medical devices; analyzing medical images; clinical decision making; algorithms designed to help monitor patients; and population health management.

With regard to AI models, in addition to the most commonly used classical methods—such as Artificial Neural Networks and Genetic Algorithms—Deep Neural Networks, emerging trends like Generative Adversarial Networks (GANs), and Federated Learning are technologies that have the capacity to improve the outcomes of these processes.  

In this context, predictive analytics has emerged as a transformative tool to enhance the healthcare sector, offering the ability to process large amounts of patient data for the prediction and prevention of diseases, the optimization of treatment plans, and the enhancement of healthcare services.

Topics of interest for this Special Issue include, but are not limited to, the following:

  • Machine learning in medicine, medically oriented human biology, and healthcare.
  • Advanced data processing for human physiology.
  • Wearable sensor data processing for the assessment of health conditions.
  • Data analytics and mining for biomedical decision support.
  • AI models leading to personalized medicine for the prediction and prevention, diagnosis, and treatment of disease.

Dr. Josu Maiora
Dr. Maria Begoña Sanz Echevarría
Prof. Dr. Manuel Graña
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 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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Bioengineering 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 2700 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

  • artificial intelligence
  • machine learning
  • deep learning
  • predictive analytics
  • wearable sensors
  • medical devices
  • medical image analysis

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.

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

22 pages, 1390 KB  
Article
Burn Extent and Fitzpatrick Skin Tone Assessment from Clinical Photographs: Systematic and Random Error in Multimodal Large Language Models
by Ibrahim Güler, Armin Kraus, Gerrit Grieb and Henrik Stelling
Bioengineering 2026, 13(9), 1000; https://doi.org/10.3390/bioengineering13091000 - 28 Aug 2026
Abstract
Background: Burn extent guides triage, transfer and fluid resuscitation, yet its clinical estimation is imprecise and observer-dependent. Multimodal large language models (MLLMs) process clinical photographs without task-specific training, but their error has rarely been separated into systematic and random components or their performance [...] Read more.
Background: Burn extent guides triage, transfer and fluid resuscitation, yet its clinical estimation is imprecise and observer-dependent. Multimodal large language models (MLLMs) process clinical photographs without task-specific training, but their error has rarely been separated into systematic and random components or their performance across skin tones characterized. Methods: Three state-of-the-art MLLMs (Gemini 3.1 Pro, GPT-5.6 Sol, and Fable 5) each assessed 153 burn photographs five times under an identical prompt. The tasks were as follows: burned proportion of the imaged field, against an expert-guided pixel-wise segmentation (tolerance ± 10 percentage points, pp); burned percentage of total body surface area (TBSA), against physician consensus (±2 pp); and binary Fitzpatrick skin tone (FST; light I–III versus dark IV–VI). The first of these was the primary endpoint. Results: The primary endpoint was in the range of 32.5–70.2%, with TBSA at 69.5–77.5%. All models compressed the estimation range (slopes 0.58–0.76, intercepts +10.0 to +22.2 pp); one multiplicative constant per model brought errors differing more than twofold into a 1.4 pp range. Across repeated queries, the median within-image range was 5.0–25.0 pp; averaging the five answers reduced error by only 0.24–2.22 pp. FST accuracy was 83.8–91.9% against a majority-class baseline of 81.0%. Conclusions: Averaging repeated answers removes only the smaller, random component; the larger, systematic one persists and requires calibration against reference data before clinical use can be considered. Full article
(This article belongs to the Special Issue Emerging Artificial Intelligence Trends for Predictive Analytics and Personalized Healthcare)
►▼ Show Figures

Figure 1

13 pages, 1825 KB  
Article
Early Sex Differences in pH, Base Excess and Lactate for the Prediction of Mortality in Trauma Patients
by Philipp Vetter, Patrik Nothdurft, Cédric Niggli, Louisa Bell, Daniel Haschtmann, Hans-Christoph Pape and Ladislav Mica
Bioengineering 2026, 13(7), 799; https://doi.org/10.3390/bioengineering13070799 - 12 Jul 2026
Viewed by 571
Abstract
Background and Objectives: In trauma patients, early correction of acid–base imbalances is crucial for survival, but time-dependent and sex-specific predictive data are limited. The aim was to analyze the time-dependent, early sex differences in pH, base excess (BE) and lactate regarding mortality in [...] Read more.
Background and Objectives: In trauma patients, early correction of acid–base imbalances is crucial for survival, but time-dependent and sex-specific predictive data are limited. The aim was to analyze the time-dependent, early sex differences in pH, base excess (BE) and lactate regarding mortality in trauma patients. Materials and Methods: Internal data of trauma patients served for retrospective analysis. pH, BE and lactate values were measured until 48 h after admission. Patients were compared according to sex and survivor status. pH < 7.25, BE < −5.5 mmol/L and lactate > 4 mmol/L were tested as time-dependent predictors for mortality, adjusted for age and Injury Severity Score (ISS). The respective area under the curve (AUC) was calculated and compared by sex. Level of significance was set at p < 0.05. Results: In the total cohort of 3653 patients (mean age: 45.8 ± 20.2 years, 73.4% male), mortality rates were comparable between females (26.7%) and males (26.9%; p = 0.931) at a similar ISS (median 25, respectively; p = 0.821). Female non-survivors had a higher rate and grade of pelvic injuries than male non-survivors (p = 0.005). At admission, males had more extreme values in pH (7.31 ± 0.13 vs. 7.32 ± 0.14; p < 0.001) and lactate (3.03 ± 2.53 vs. 2.71 ± 2.53; p < 0.001). pH and BE differed early by survivor status (within 4 h). Lactate was always higher in non-survivors. A pH < 7.25 was predictive in males at most time points (except for 0/4/8/48 h), but for females only at 12 h. BE < −5.5 mmol/L was predictive for males at 6 h and 12–48 h, and for females at 8–48 h. Lactate > 4 mmol/L was prognostic at 0–1 h and 6–48 h in males but in females at 0/12/24 h. Conclusions: Trauma patients display early differences in injury pattern and acid–base parameters according to survivor status and sex. Time- and sex-dependent referencing could aid in early risk estimation and the subsequent extent of surgical treatment. Full article
(This article belongs to the Special Issue Emerging Artificial Intelligence Trends for Predictive Analytics and Personalized Healthcare)
►▼ Show Figures

Figure 1

Review

Jump to: Research

20 pages, 1850 KB  
Review
Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review
by Bernardo G. Collaco, Srinivasagam Prabha, Cesar A. Gomez-Cabello, Syed Ali Haider, Ariana Genovese, Nadia G. Wood, Narayanan Gopala, Raghunath Raman, Erik O. Hester and Antonio Jorge Forte
Bioengineering 2026, 13(5), 513; https://doi.org/10.3390/bioengineering13050513 - 28 Apr 2026
Viewed by 2194
Abstract
Background: Agentic artificial intelligence (AI) systems, characterized by autonomous goal-directed behavior, multi-step reasoning, task decomposition, and tool use, are increasingly proposed for healthcare applications. However, their autonomy raises concerns regarding transparency, accountability, and human oversight. While explainable AI (XAI) has been widely studied [...] Read more.
Background: Agentic artificial intelligence (AI) systems, characterized by autonomous goal-directed behavior, multi-step reasoning, task decomposition, and tool use, are increasingly proposed for healthcare applications. However, their autonomy raises concerns regarding transparency, accountability, and human oversight. While explainable AI (XAI) has been widely studied in traditional predictive models, less is known about how explainability is implemented within agentic architectures. Objective: To map the emerging literature on explainable agentic AI (XAAI) in healthcare and characterize the types, scope, and forms of explainability used in these systems. Methods: A scoping review was conducted following PRISMA-ScR guidelines. PubMed, Embase, IEEE Xplore, and ACM Digital Library were searched through November 2025. Eligible studies described healthcare-related agentic AI systems incorporating explicit explainability mechanisms. Data were extracted on system architecture, explainability type (intrinsic, post hoc, hybrid), explanation scope (local, global), explanation form, and reported clinical outcomes. Results: Nine studies met the inclusion criteria. All systems demonstrated core agentic features, including autonomy, task decomposition, and tool integration, often within multi-agent frameworks. Explainability was predominantly intrinsic and workflow-native, typically delivered through textual reasoning traces and example-based grounding in retrieved clinical evidence. Feature-based and global explanations were comparatively rare and largely confined to hybrid architectures. Across domains including radiology, neurology, psychiatry, and biomedical research, XAAI systems were reported to improve performance and interpretability relative to baseline models in the included studies. However, these findings were derived from heterogeneous, predominantly experimental or retrospective studies, and structured human-in-the-loop oversight was infrequently described. Conclusions: Current XAAI systems appear to emphasize process transparency and evidence grounding rather than mechanistic model-level attribution. The available evidence remains limited and heterogeneous, and findings should be interpreted as early trends rather than established characteristics. Further progress will require standardized evaluation frameworks, clearer reporting of oversight mechanisms, and validation in real-world clinical settings to support safe and trustworthy integration of agentic AI into healthcare practice. Full article
(This article belongs to the Special Issue Emerging Artificial Intelligence Trends for Predictive Analytics and Personalized Healthcare)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop