Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.1
3.9
Journals
Life
Special Issues
Artificial Intelligence and Machine Learning for Biomedical Diagnostics and Prognostics
share announcement

Artificial Intelligence and Machine Learning for Biomedical Diagnostics and Prognostics

A special issue of Life (ISSN 2075-1729). This special issue belongs to the section "Medical Research".

Deadline for manuscript submissions: 30 November 2026 | Viewed by 6445

Editors

Dr. César Byron Guevara Maldonado

E-Mail Website
Guest Editor
Quantitative Methods Department, CUNEF Universidad, 28040 Madrid, Spain
Interests: artificial intelligence; data mining; evolutionary algorithms; computer vision; reinforcement
Dr. Victoria López

E-Mail Website
Guest Editor
Quantitative Methods Department, CUNEF Universidad, 28040 Madrid, Spain
Interests: computational mathematics; computational intelligence; artificial intelligence; algorithms
Special Issues, Collections and Topics in MDPI journals
Dr. Diego Fernando Riofrío Luzcando

E-Mail Website
Guest Editor
Quantitative Methods Department, CUNEF Universidad, 28040 Madrid, Spain
Interests: computer science; HCI; virtual reality; e-learning; inteligent tutoring systems

Special Issue Information

Dear Colleagues,

This Special Issue invites original research and reviews on the design, development, and validation of Artificial Intelligence (AI) and Machine Learning (ML) methods applied to detection, diagnosis, risk stratification, and prediction of clinical outcomes. We welcome a broad range of study designs, including individually randomized, cluster‐randomized, and stepped-wedge trials; pragmatic and adaptive trials; cohort, case–control, cross-sectional, and longitudinal studies; N-of-1 trials and interrupted time-series analyses; diagnostic and prognostic accuracy studies; clinical impact and decision-analytic evaluations; as well as systematic reviews and meta-analyses.

Submissions are encouraged across psychology and psychiatry (e.g., ecological momentary assessment, relapse prediction, suicide risk modeling, treatment response to psychotherapies and pharmacotherapies, neuroimaging, and speech/language analytics); physiotherapy and rehabilitation (e.g., telerehabilitation trials, gait analysis using inertial sensors, and exercise protocols); and nutrition (e.g., controlled dietary interventions, crossover feeding studies, nutrigenomics, and metabolomics for personalized nutrition). Additional medical domains of interest include cardiology (ECG and wearable sensors), oncology (prognosis and treatment response), sleep medicine, critical care, pediatrics, and geriatrics.

We particularly value multimodal data integration (medical imaging, omics, digital pathology, wearable sensors, and electronic health records), supervised and unsupervised learning, transfer learning, generative models, and explainable/interpretable approaches. Submissions should demonstrate clinical utility, robust calibration, multicenter generalizability, fairness, privacy and safety safeguards, and—where possible—open datasets, reproducible code, external validation, comparison to clinical standards, and prospective evaluation to accelerate the translation of AI into measurable health impact.

Dr. César Byron Guevara Maldonado
Dr. Victoria López
Dr. Diego Fernando Riofrío Luzcando
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. Life 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

  • artificial intelligence
  • machine learning
  • diagnostic and prognostic modeling
  • multimodal data integration
  • explainable AI

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 (6 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

25 pages, 10830 KB  
Article
Explainable AI for Image-Based Auxiliary Assessment of Radiation Pneumonitis on Post-Treatment CT Images Using GAN Grad-CAM and Ensemble Learning Techniques
by Tsair-Fwu Lee, Guang-Zhi Lin, Wen-Ping Yun, Yi-Lun Liao, Liyun Chang, Chao-Hong Liu, Cheng-Shie Wuu, Yu-Chang Hu, Yu-Wei Lin, Pei-Ju Chao and Yang-Wei Hsieh
Life 2026, 16(8), 1269; https://doi.org/10.3390/life16081269 - 31 Jul 2026
Viewed by 343
Abstract
Objective: This study aims to develop a preliminary explainable image-based auxiliary assessment framework for radiation pneumonitis (RP) by integrating a generative adversarial network (GAN), Gradient-weighted Class Activation Mapping (Grad-CAM), and ensemble learning to improve image-based classification performance, interpretability, and computational efficiency. Methods: Chest [...] Read more.
Objective: This study aims to develop a preliminary explainable image-based auxiliary assessment framework for radiation pneumonitis (RP) by integrating a generative adversarial network (GAN), Gradient-weighted Class Activation Mapping (Grad-CAM), and ensemble learning to improve image-based classification performance, interpretability, and computational efficiency. Methods: Chest CT images from 46 lung cancer patients who underwent VMAT were retrospectively collected, yielding 542 RP and 1857 non-RP images. Images were preprocessed using Otsu-based segmentation and standardized before being input into the RP-GAN for feature extraction. Grad-CAM was applied to qualitatively visualize attention patterns across convolutional layers and guide feature-layer selection, while PCA reduced the extracted features from 12,288 to 730 dimensions. An ensemble stacking classifier combining RF, SVM, KNN, and XGBoost with logistic regression as a meta-learner was constructed. Model performance was evaluated using AUC, accuracy, PPV, NPV, specificity, recall, and F1-score. Results: Grad-CAM highlighted conv2d_4 and conv2d_5 as the most informative layers. PCA reduced training time from 49 min to 49 s with minimal performance loss. In the internal hold-out test set, the ensemble model achieved the highest point estimates for AUC and accuracy among the evaluated classifiers (AUC = 0.921; accuracy = 87.1%). The model identified RP-positive CT slices and provided qualitative visual cues for suspected RP-related regions. Conclusions: The proposed GAN–Grad-CAM ensemble framework showed promising internal classification performance for post-treatment CT-based RP image assessment with substantially improved computational efficiency. Its qualitative visual outputs may support clinical image review, although further external validation and quantitative localization assessment are required before clinical application as an auxiliary image-review tool. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning for Biomedical Diagnostics and Prognostics)
►▼ Show Figures

Figure 1

35 pages, 1747 KB  
Article
Retrospective Validation of a Resource-Aware Assistive AI Tool for Screening Prostate Needle Biopsies and Classifying Prostate Adenocarcinoma into ISUP Grade Groups
by Sahil Ajit Saraf, Wai Po Kevin Teng, Kolangara Veetil Santosh, Sencer Karakaya, Amala Abbas, Tony Kiat Hon Lim, Kankanamage Malinda Amesh Karasinghe, Zachariah Chowdhury, Priti Singh, Anubhav Narwal, Samrat Bhattacharjee, Bidyut Bikash Gogoi, Bahoran Singh, Mohamid Afroz Khan, Daljeet Kaur, Kaveh Taghipour and Li Yan Khor
Life 2026, 16(8), 1257; https://doi.org/10.3390/life16081257 - 29 Jul 2026
Viewed by 553
Abstract
Introduction: Prostate needle biopsy reporting is time-consuming because each case typically includes 12–18 cores that require detailed assessment before a final case-level diagnosis is issued. Reporting is also influenced by pathologist expertise, particularly for tumour detection and ISUP Grade Group assignment. This study [...] Read more.
Introduction: Prostate needle biopsy reporting is time-consuming because each case typically includes 12–18 cores that require detailed assessment before a final case-level diagnosis is issued. Reporting is also influenced by pathologist expertise, particularly for tumour detection and ISUP Grade Group assignment. This study evaluated an artificial intelligence (AI)-based system designed to identify tumour and provide segmentation-based visual outputs highlighting Gleason patterns and suggesting an ISUP Grade Group. Methods: A strongly supervised approach was used to develop the algorithm. Twenty-seven pathologists annotated 2115 prostate needle biopsy whole-slide images, followed by two levels of senior pathologist reviews. An independent external test dataset of 150 prostate needle biopsy whole-slide images was then evaluated. Ground truth (GT) was established by two genitourinary pathologists, with disagreements resolved by consensus. The same slides were independently reviewed by 11 pathologists without AI assistance, while the AI system analysed the slides in parallel. AI performance and pathologist consensus were compared to GT. Results: For benign versus malignant classification, the AI identified all 109 malignant slides, with no false-negative predictions, while the pathologist consensus missed two malignant slides. The AI correctly classified 38/41 benign slides, compared to 39/41 for the pathologist consensus. For ISUP Grade Group assignment, the AI showed exact agreement with GT in 57/109 malignant cases. The AI more frequently assigned a higher Grade Group than GT. Conclusions: In this retrospective evaluation, the AI system showed high sensitivity for tumour detection and promising ordinal agreement for ISUP Grade Group assignment. These findings support further evaluation of the system within supervised prostate biopsy workflows. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning for Biomedical Diagnostics and Prognostics)
►▼ Show Figures

Graphical abstract

19 pages, 5035 KB  
Article
Green Synthesis of Silver Nanoparticles from Aloe vera: Antibacterial Potential Against Cyanobacteria from an Andean Lagoon
by Arnold Solano, Antonio Vega, José Davalos-Monteiro, Daniel Cabrera-Valle, Carlos Loyo-Dávila, Lenin Ramírez-Cando, Fernando Villalba-Meneses, Diego Almeida-Galárraga, Vladimir Bonilla, Maria Baldeon-Calisto, Raúl Dávalos Monteiro and Patricia Acosta-Vargas
Life 2026, 16(7), 1132; https://doi.org/10.3390/life16071132 - 7 Jul 2026
Viewed by 1351
Abstract
This work describes an efficient and environmentally friendly method for the synthesis of silver-based nanostructures through a green route using Aloe vera extract as a reducing agent, silver nitrate (AgNO3) as a precursor, and polyvinylpyrrolidone (PVP, 10 kDa molecular weight) as [...] Read more.
This work describes an efficient and environmentally friendly method for the synthesis of silver-based nanostructures through a green route using Aloe vera extract as a reducing agent, silver nitrate (AgNO3) as a precursor, and polyvinylpyrrolidone (PVP, 10 kDa molecular weight) as a stabilizing agent. The formation of these structures was supported by UV–Vis spectroscopy, where a surface plasmon resonance (SPR) band was observed between 425 and 460 nm. Scanning electron microscopy revealed predominantly spherical features in the 300–500 nm range; however, the distinction between primary nanoparticles and aggregates cannot be conclusively established from SEM alone. EDX analysis indicated a silver content of 59.96 wt%. Antibacterial assays performed in Z8 medium demonstrated a reduction in cyanobacterial growth with increasing dosage, with complete inhibition observed at ≥20 μL (nominal MIC = 1.77 mg mL−1, based on precursor estimation). Total dissolved solids and absorbance measurements exhibited a decreasing trend with increasing concentration (effect size = 0.87, p<0.001), supporting an inhibitory effect under the tested conditions. These findings suggest potential antibacterial activity. However, this study should be considered exploratory, and further work is required to elucidate the underlying mechanisms. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning for Biomedical Diagnostics and Prognostics)
►▼ Show Figures

Figure 1

18 pages, 1581 KB  
Article
Real-World Insights into Stage I–III Non-Small Cell Lung Cancer in Spain in the Pre-Immunotherapy Era Using AI Techniques: The IntellyLUNG Study
by Jesús Corral Jaime, Javier de Castro, Aitor Azkarate, Gema García Ledo, Antonio Calles, Raquel Marsé, Ana Sofia de Freitas Matos Parreira, Julia Villamayor, Laura Gutiérrez-Sainz, Javier-David Benítez-Fuentes, Diego Casado Elía, Natalia Gutiérrez, Marta Arregui Valles, Eduard Sarró, Noelia López and Savana Research Group
Life 2026, 16(7), 1119; https://doi.org/10.3390/life16071119 - 5 Jul 2026
Viewed by 592
Abstract
Treatment of non-small cell lung cancer (NSCLC) has been transformed by immunotherapy and targeted therapies. We aimed to characterize clinical features, treatment patterns, and healthcare resource use in patients with early and locally advanced NSCLC before incorporation of these therapies. This retrospective observational [...] Read more.
Treatment of non-small cell lung cancer (NSCLC) has been transformed by immunotherapy and targeted therapies. We aimed to characterize clinical features, treatment patterns, and healthcare resource use in patients with early and locally advanced NSCLC before incorporation of these therapies. This retrospective observational study included adults diagnosed with stage I–III NSCLC at four Spanish hospitals between 2014 and 2018, with follow-up until 2021, using artificial intelligence to extract data from electronic health records. A total of 951 patients were included (34.7% stage I, 16.7% stage II, 48.6% stage III), with a median age of 66 years and 31.9% female. Surgery was performed in 78.5% of stage I, 74.8% of stage II, and 35.5% of stage III patients. Among surgical patients, 62.5% received adjuvant chemo- and/or radiotherapy, 20.8% neoadjuvant therapy, and 15.7% both; among non-surgical patients, chemoradiotherapy was the most common treatment (50.4%). Beyond hospitalization, outpatient visits were the most frequently used healthcare resource. These findings provide a historical benchmark of NSCLC care before introduction of immunotherapy and targeted therapies in these settings, highlighting treatment variability and the need for earlier diagnosis, structured treatment pathways, and multidisciplinary management. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning for Biomedical Diagnostics and Prognostics)
►▼ Show Figures

Figure 1

17 pages, 892 KB  
Article
Artificial Intelligence for Biomedical Diagnostics: Diagnostic Accuracy and Reliability of Multimodal Large Language Models in Electrocardiogram Interpretation
by Henrik Stelling, Armin Kraus, Gerrit Grieb, David Breidung and Ibrahim Güler
Life 2026, 16(4), 681; https://doi.org/10.3390/life16040681 - 16 Apr 2026
Viewed by 1349
Abstract
The electrocardiogram (ECG) is a central tool in cardiovascular diagnostics, yet interpretation requires expertise and remains subject to variability. Multimodal large language models (MLLMs) have shown emerging capabilities in medical image analysis, but their performance in ECG interpretation remains insufficiently characterized. This study [...] Read more.
The electrocardiogram (ECG) is a central tool in cardiovascular diagnostics, yet interpretation requires expertise and remains subject to variability. Multimodal large language models (MLLMs) have shown emerging capabilities in medical image analysis, but their performance in ECG interpretation remains insufficiently characterized. This study evaluated the diagnostic accuracy and inter-run reliability of five MLLMs across ECG interpretation tasks. Thirteen standard 12-lead ECGs were presented to five models (ChatGPT-5.3, Gemini 3.1 Pro, Claude Opus 4.6, Grok 4.1, and ERNIE 5.0) across five independent runs per case, yielding 2275 task-level assessments. Six categorical interpretation tasks (rhythm, electrical axis, PR/P-wave morphology, QRS duration, ST/T-wave morphology, and QTc interval) were compared with expert-consensus ground truth, while heart rate estimation was evaluated using mean absolute error (MAE). Overall categorical accuracy ranged from 52.3% to 64.9%. QRS duration classification achieved the highest accuracy (66.2–90.8%), whereas ST/T-wave assessment showed the lowest performance (20.0–41.5%). Heart rate MAE ranged from 14.8 to 46.7 bpm. A dissociation between diagnostic accuracy and inter-run reliability was observed across models. These findings indicate that current MLLMs do not achieve clinically reliable ECG interpretation performance and highlight the importance of assessing diagnostic accuracy and inter-run reliability when evaluating artificial intelligence systems in biomedical diagnostics. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning for Biomedical Diagnostics and Prognostics)
►▼ Show Figures

Graphical abstract

25 pages, 16496 KB  
Article
MassSeg-Framework: A Breast Mass Detection and Segmentation Framework Based on Deep Learning and an Active Contour Model
by Camila Zambrano, Noel Pérez-Pérez, Miguel Coimbra, Maria Baldeon-Calisto, Ricardo Flores-Moyano, José Ramón Mora, Oscar Camacho and Diego Benítez
Life 2026, 16(4), 653; https://doi.org/10.3390/life16040653 - 12 Apr 2026
Viewed by 1182
Abstract
This work introduces the MassSeg-Framework, a fully automatic two-stage pipeline for breast mass analysis in mammography that integrates YOLOv11-based detection with Chan–Vese ACM refinement to achieve accurate mass localization and segmentation with a lightweight computational footprint. The framework was trained and evaluated [...] Read more.
This work introduces the MassSeg-Framework, a fully automatic two-stage pipeline for breast mass analysis in mammography that integrates YOLOv11-based detection with Chan–Vese ACM refinement to achieve accurate mass localization and segmentation with a lightweight computational footprint. The framework was trained and evaluated on two publicly available datasets using consistent experimental protocols. In the detection stage, YOLOv11-nano was the most effective architecture, with a confidence threshold of 0.4, achieving statistically significant mAP50 values of 0.862 and 0.709 on the dINbreast and dCBIS datasets, respectively. These results confirm that a moderate threshold preserves clinically relevant true-positive candidates, which is particularly important for screening-oriented settings where missed lesions are costly. In the segmentation stage, the proposed framework achieved mean DICE scores of 0.721 and 0.700 on the test sets of the same datasets, demonstrating consistent overlap with expert annotations. Compared with state-of-the-art approaches that commonly assume lesion-centered ROIs or rely on heavier backbones, the proposed pipeline addresses a more realistic scenario by performing automatic detection followed by segmentation while maintaining substantially lower computational requirements. This balance between performance and efficiency makes the MassSeg-Framework a promising tool for scalable mammography analysis, particularly in resource-constrained environments or high-throughput screening workflows that require rapid processing. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning for Biomedical Diagnostics and Prognostics)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop