José Marcio Duarte

José Marcio Duarte

Auto-generated profile, based on publicly available information

José Marcio Duarte

Federal University of São Paulo

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 January 2023 in Artificial Intelligence Review
Verified
Journal Article
Closed access
PDF file
JDJosé Marcio Duarte
José Marcio Duarte
LBLilian Berton
Lilian Berton

10 January 2025 in SciELO Preprints
Verified
Preprint
Open access
Andre Massahiro ShimaokaAndre Massahiro Shimaoka
Andre Massahiro Shimaoka
JDJosé Marcio Duarte
José Marcio Duarte
AJAntonio Carlos Da Silva Junior
Antonio Carlos Da Silva Junior
LLLuciano Rodrigo Lopes
Luciano Rodrigo Lopes
RRRichard Alecsander Reichert
Richard Alecsander Reichert
PBPaulo Bandiera-Paiva
Paulo Bandiera-Paiva
A ansiedade tornou-se uma preocupação crescente, especialmente após a pandemia de COVID-19, que elevou os casos em 25% no mundo e a consolidou como a quarta maior causa de afastamento do trabalho no Brasil. Este estudo de abordagem quantitativa analisou as notificações de transtornos de ansiedade relacionadas ao trabalho no estado de São Paulo, com foco nas mudanças pós-pandemia. Utilizando análise de tendência, regressão linear e aprendizado de máquina não supervisionada (clusterização e regras de associação), o estudo explorou o crescimento, a mudança de padrão nas notificações e os perfis demográficos e comportamentais dos trabalhadores afetados no período de 2020 a 2023. Os resultados identificaram quatro perfis principais de indivíduos com transtorno de ansiedade. O maior cluster foi composto por trabalhadores de 30 a 39 anos, atuantes nos setores de comércio, seguido por um cluster de trabalhadores do setor administrativo com idade entre 40 a 49 anos. Embora, em sua maioria, não usuários de drogas psicoativas, álcool ou tabaco, muitos já utilizaram psicotrópicos e substâncias psicoativas e/ou psicofármacos, o que foi associado à incapacidade temporária. Assim, políticas de prevenção e suporte psicológico são essenciais para o bem-estar e a produtividade no ambiente de trabalho.

24 July 2025 in Trends in Psychology
Verified
Journal Article
Closed access
PDF file
Andre Massahiro ShimaokaAndre Massahiro Shimaoka
Andre Massahiro Shimaoka
ASAntonio Carlos da Silva
Antonio Carlos da Silva
JDJosé Marcio Duarte
José Marcio Duarte
LLLuciano Rodrigo Lopes
Luciano Rodrigo Lopes
RRRichard Reichert
Richard Reichert
PBPaulo Bandiera-Paiva
Paulo Bandiera-Paiva

12 March 2026 in Research on Biomedical Engineering
Verified
Journal Article
Open access
PDF file
Andre Massahiro ShimaokaAndre Massahiro Shimaoka
Andre Massahiro Shimaoka
ASAntonio Carlos da Silva
Antonio Carlos da Silva
JDJosé Marcio Duarte
José Marcio Duarte
TCThiago Bulhões da Silva Costa
Thiago Bulhões da Silva Costa
IPIvan Torres Pisa
Ivan Torres Pisa
PBPaulo Bandiera-Paiva
Paulo Bandiera-Paiva
Purpose: This study addresses Large Language Models (LLMs) pre-trained in Portuguese for healthcare applications, focusing on contextual embeddings. Research on LLMs for natural language processing (NLP) tasks in Portuguese is limited, especially within healthcare. Much of the existing research has focused on high-resource languages such as English. However, LLMs demonstrate potential in clinical decision support, diagnosis assistance, patient care, and other healthcare applications. In view of this, the present work assesses the current state of LLMs in Portuguese for healthcare. Methods: Our Systematic Literature Review (SLR) followed standard protocols: search, screening based on inclusion/exclusion criteria, quality assessment, data extraction, and analysis. Results: We identified 32 models, mostly based on BERTimbau, mBERT, and BioBERTpt. Adaptation strategies such as fine-tuning, domain-adaptive pre-training, training from scratch, and zero-shot learning have been the most prevalent. Several datasets have been used, including clinical records, social media, and scientific repositories. LLMs in Portuguese are being applied in mental health, general medicine, COVID-19, oncology, and other related areas, accomplishing classification tasks, followed by named entity recognition (NER), topic modeling, question answering, text generation, summarization, de-identification, and conversational agents. Conclusion: Our study identified key gaps and opportunities: (1) unexplored recent LLMs such as T5, Qwen, DeepSeek, BART, among others; (2) insufficient fine-tuning details, hindering reproducibility; (3) limited coverage of healthcare fields; (4) clinical and hospital data widely used but not shared; (5) social media data requiring caution due to potential inconsistencies; and (6) overlooked data privacy.

14 January 2026 in Asklepion: Informação em Saúde
Verified
Journal Article
Open access
PDF file
Andre Massahiro ShimaokaAndre Massahiro Shimaoka
Andre Massahiro Shimaoka
MSMaria Elisabete Salvador
Maria Elisabete Salvador
JDJosé Marcio Duarte
José Marcio Duarte
ASAntonio Carlos da Silva
Antonio Carlos da Silva
LLLuciano Rodrigo Lopes
Luciano Rodrigo Lopes
PBPaulo Bandiera-Paiva
Paulo Bandiera-Paiva
He growing availability of health data within the Brazilian Unified Health System (SUS) increases the potential for data-driven analysis. However, large datasets also introduce challenges related to volume, structure, and data integration. This study develops and evaluates an automated Extract, Transform, Load (ETL) pipeline for ingestion and preparation of data from the Ambulatory Information System (SIA-SUS). The architecture uses cloud computing infrastructure to support scalable processing. The study follows the Design Science Research approach, which focuses on the development and evaluation of technological artifacts. A pilot experiment processes data from January 2024 for three Brazilian states. The experiment includes approximately 3.2 million ambulatory records. Each execution runs five times to estimate operational variability. Results show stable pipeline performance across scenarios. The extraction stage accounts for the largest share of total execution time. Throughput remains relatively consistent despite differences in data volume. Linear regression between processed records and execution time produces a coefficient of determination of R² = 0.996. The result indicates an approximately linear relationship between data volume and processing time. The pipeline demonstrates operational feasibility and scalability potential. The architecture reduces the complexity of preparing large datasets from the SUS. The solution supports the development of analytical environments for public health data.

1 January 2026 in Ciencia & Saude Coletiva
Verified
Journal Article
Open access
Andre Massahiro ShimaokaAndre Massahiro Shimaoka
Andre Massahiro Shimaoka
ASAntonio Carlos da Silva
Antonio Carlos da Silva
JDJosé Marcio Duarte
José Marcio Duarte
KAKELSY CATHERINA NEMA ARECO
KELSY CATHERINA NEMA ARECO
MRMarcelo Batista Ribeiro
Marcelo Batista Ribeiro
PBPaulo Bandiera-Paiva
Paulo Bandiera-Paiva
Analyze patterns of association between diagnoses related to domestic violence in hospital admissions and identify clinical-demographic profiles using unsupervised machine learning. Data from the SUS Hospital Information System between 2008 and 2023 were used, covering 90,798 hospitalizations of women aged 20 to 59 years with ICD-10 codes related to violence. Frameworks for data preparation were applied, as well as algorithms for identifying association rules between diagnoses and topic modeling. The hospitalization rate stabilized after 2012, with an average between 2.6 and 3.2 per 100,000 women. States such as São Paulo, Bahia, and Minas Gerais accounted for 46% of absolute cases; Rio Grande do Norte and Pará presented the highest proportional rates. The algorithm identified significant rules between types of injury and mechanisms of aggression. Latent Dirichlet Allocation modeling revealed nine distinct profiles, highlighting young women undergoing emergency surgeries due to polytrauma. The use of machine learning identified relevant clinical-epidemiological patterns to support prediction and surveillance strategies in Primary Care, contributing to addressing gender-based violence.