Fabiano N. Barcellos Filho
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Fabiano N. Barcellos Filho has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Alexandre Dias Porto Chiavegatto Filho
Universidade de São Paulo, Brazil
2 shared publications - Raiza Brito Cipriano
Escola Superior de Ciências da Santa Casa de Misericórdia de Vitória (EMESCAM)
2 shared publications - Wilson Falco Neto
Faculdade de Medicina de Catanduva (FAMECA), Centro Universitário Padre Albino, Catanduva, SP, Brasil
2 shared publications - Artur José Marques Paulo
Hospital Israelita Albert Einstein São Paulo SP Brazil
1 shared publication - Bruna Garbes Goncalves Pinto
Hospital Israelita Albert Einstein
1 shared publication - Camila Silva
Hospital Israelita Albert Einstein (HIAE)
1 shared publication
Latest Publications
- Open Access
- 1 April 2026
- Published by JMIR Publications Inc. in JMIR AI
The Feature Ceiling: Recognizing Data-Driven Performance Limits as a Diagnostic Category in Clinical Machine Learning (Preprint)
- 1 April 2026
- Published by JMIR Publications Inc. in JMIR AI
Open AccessThe Feature Ceiling: Recognizing Data-Driven Performance Limits as a Diagnostic Category in Clinical Machine Learning (Preprint)
- Open Access
- 1 April 2026
- Published by JMIR Publications Inc. in JMIR Preprints
The Feature Ceiling: Recognizing Data-Driven Performance Limits as a Diagnostic Category in Clinical Machine Learning (Preprint)
UNSTRUCTURED Machine learning (ML) pipelines in health care are increasingly sophisticated, yet a recurring and underappreciated phenomenon limits their practical impact: the convergence of diverse model families to the same predictive performance ceiling, regardless of algorithmic complexity. This viewpoint introduces the feature ceiling as a formal diagnostic category in clinical ML—a condition in which the informational content of the available feature set constitutes the binding constraint on predictive performance, independently of the learning algorithm employed. When the feature ceiling is reached, even a logistic regression and a carefully tuned gradient-boosted ensemble yield statistically equivalent metrics, with overlapping confidence intervals. This convergence is not a modeling failure; it is an epistemological signal that the data cannot encode what the algorithm is being asked to predict. Recognizing this condition early redirects development effort toward meaningful interventions—feature expansion, integration of complementary data sources, and strategic redesign of data collection systems—rather than continued algorithmic iteration. Beyond its technical implications, the feature ceiling carries strategic significance for health organizations: data architecture decisions made today silently define the predictive ceiling of models to be developed years from now. Embedding feature ceiling reasoning into clinical ML project design can prevent substantial misallocation of resources and redirect investment toward the structural improvements that generate real performance gains.
- 1 April 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessThe Feature Ceiling: Recognizing Data-Driven Performance Limits as a Diagnostic Category in Clinical Machine Learning (Preprint)
UNSTRUCTURED Machine learning (ML) pipelines in health care are increasingly sophisticated, yet a recurring and underappreciated phenomenon limits their practical impact: the convergence of diverse model families to the same predictive performance ceiling, regardless of algorithmic complexity. This viewpoint introduces the feature ceiling as a formal diagnostic category in clinical ML—a condition in which the informational content of the available feature set constitutes the binding constraint on predictive performance, independently of the learning algorithm employed. When the feature ceiling is reached, even a logistic regression and a carefully tuned gradient-boosted ensemble yield statistically equivalent metrics, with overlapping confidence intervals. This convergence is not a modeling failure; it is an epistemological signal that the data cannot encode what the algorithm is being asked to predict. Recognizing this condition early redirects development effort toward meaningful interventions—feature expansion, integration of complementary data sources, and strategic redesign of data collection systems—rather than continued algorithmic iteration. Beyond its technical implications, the feature ceiling carries strategic significance for health organizations: data architecture decisions made today silently define the predictive ceiling of models to be developed years from now. Embedding feature ceiling reasoning into clinical ML project design can prevent substantial misallocation of resources and redirect investment toward the structural improvements that generate real performance gains.
- 23 February 2026
- Published by Sociedade Brasileira de Cardiologia in International Journal of Cardiovascular Sciences
- Vol. 39
The Growing Role of Simulation-Based Learning in Cardiology Education
Introduction Simulation-based learning has emerged as a cornerstone in modern medical education, offering a safe and controlled environment for trainees to acquire and refine complex clinical skills.– This pedagogical approach is particularly pertinent in dynamic and high-stakes specialties such as cardiology, where precision, rapid decision-making, and technical proficiency are paramount. The systematic review by Silva, Souza, and Santos titled “The Use of Simulation-Based Learning in Cardiology Education: A Systematic Review” provides a comprehensive overview of the current evidence supporting the
- 23 February 2026
- Published by Sociedade Brasileira de Cardiologia in International Journal of Cardiovascular Sciences
- Vol. 39
The Growing Role of Simulation-Based Learning in Cardiology Education
Introduction Simulation-based learning has emerged as a cornerstone in modern medical education, offering a safe and controlled environment for trainees to acquire and refine complex clinical skills.– This pedagogical approach is particularly pertinent in dynamic and high-stakes specialties such as cardiology, where precision, rapid decision-making, and technical proficiency are paramount. The systematic review by Silva, Souza, and Santos titled “The Use of Simulation-Based Learning in Cardiology Education: A Systematic Review” provides a comprehensive overview of the current evidence supporting the
- Open Access
- 15 August 2025
- Published by Elsevier in Anais Brasileiros de Dermatologia (Versão em Português)
- Vol. 100 (5)
Inteligência artificial para diagnóstico de doenças dermatológicas eritemato‐descamativas: contribuições tecnológicas para a atenção primária
- 15 August 2025
- Published by Elsevier in Anais Brasileiros de Dermatologia (Versão em Português)
- Vol. 100 (5)
Open AccessInteligência artificial para diagnóstico de doenças dermatológicas eritemato‐descamativas: contribuições tecnológicas para a atenção primária
- Open Access
- 13 August 2025
- Published by Elsevier in Anais Brasileiros de Dermatologia
- Vol. 100 (5) , 501169
Artificial intelligence for the diagnosis of erythematous-squamous dermatological diseases: technological contributions to primary care
- 13 August 2025
- Published by Elsevier in Anais Brasileiros de Dermatologia
- Vol. 100 (5) , 501169
Open AccessArtificial intelligence for the diagnosis of erythematous-squamous dermatological diseases: technological contributions to primary care
- 1 October 2023
- Published by Springer Nature
- p. 112-122
Brain Age Prediction Based on Head Computed Tomography Segmentation
- 1 October 2023
- Published by Springer Nature
- p. 112-122
Brain Age Prediction Based on Head Computed Tomography Segmentation