Elisa Tuler
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Elisa Tuler has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Leonardo Rocha
Federal University of São João del-Rei, São João del-Rei, Brazil
18 shared publications - Diego Roberto Colombo Dias
Universidade Federal do Espírito Santo (UFES)
12 shared publications - Adriano César Machado Pereira
Universidade Federal de Minas Gerais
5 shared publications - Marcelo de Paiva Guimarães
Universidade Federal de São Paulo
4 shared publications - Nícollas Silva
Universidade Federal de Minas Gerais, Brazil
3 shared publications - Vinicius Fernandes Soares Mota
Universidade Federal do Espírito Santo (UFES)
3 shared publications
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 629-638
A Machine Learning Approach for an End-to-End Music Inpainting Pipeline
- 2 July 2026
- Published by Springer Nature
- p. 629-638
A Machine Learning Approach for an End-to-End Music Inpainting Pipeline
- 1 July 2026
- Published by Springer Nature
- p. 584-600
Evaluating Segmentation and Temporal Resolution in Highway Crash Forecasting: The BR-040 Corridor
- 1 July 2026
- Published by Springer Nature
- p. 584-600
Evaluating Segmentation and Temporal Resolution in Highway Crash Forecasting: The BR-040 Corridor
- Open Access
- 26 May 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e84444
Large Language Model–Generated Patient Instructions for Prescriptions in Primary Health Care: Preclinical Algorithm Validation
Background: The application of generative artificial intelligence to simplify medication use instructions has the potential to enhance people’s health by improving treatment adherence. Objective: We evaluated the performance of large language models (LLMs) in generating medication usage instructions to complement prescriptions in primary health care. Methods: This randomized, blinded experimental preclinical study used prescription-inducing scenarios, assigned to 62 health care professionals, to validate instructions generated by LLMs during electronic prescriptions. The instructions were generated by ChatGPT-4.0 (OpenAI), Llama3.1-8B (Meta), and Llama3.1-8B-RAG (Meta) using retrieval-augmented generation based on patient information leaflets. Performance metrics assessed adequacy, completeness, clarity, language simplification, usefulness, and errors in the generated instructions, with scores to analyze overall and individual metrics. Results: The 3 models yielded high overall scores for producing qualified instructions (ChatGPT-4.0: median 88.4, IQR 22.8; Llama3.1-8B: median 66.5, IQR 50.9; Llama3.1-8B-RAG: median 79.9, IQR 34.4; Kruskal-Wallis test P=.003). Llama3.1-8B-RAG received evaluations with similar overall scores to ChatGPT-4.0 (post hoc test, P=.05) and similar to Llama3.1-8B (post hoc test, P=.44). ChatGPT-4.0 outperformed Llama3.1-8B (Bonferroni test, P<.001). Regarding specific domains, Llama3.1-8B-RAG received scores equivalent to those of ChatGPT-4.0 for adequacy (mean 6.24, SD 2.3 vs mean 6.82, SD 2.1; post hoc test, P=.54); completeness (mean 5.94, SD 2.2 vs 6.55, SD 1.9; post hoc test P=.38), clarity (mean 5.77, SD 2.4 vs mean 6.68, SD 1.9; post hoc test P=.09), and usefulness (mean 5.42, SD 2.4 vs mean 5.96, SD 2.2; post hoc test P=.63). ChatGPT-4.0 received higher scores in the language simplification criterion than Llama3.1-8B-RAG (mean 7.05, SD 1.5 vs mean 5.44, SD 2.6; post hoc test P<.001). Interrater variability in assigning scores ranged from 4.2% (n=3) to 85.8% (n=6) among primary health care professionals. Instructions leading to incorrect use of the medication had similar frequency among the models(ChatGPT-4.0: n=15, 22.7%; Llama3.1-8B: n=19, 22.8%; Llama3.1-8B-RAG: n=19, 22.8%; chi-square test P=.71). The frequencies of hallucination were similar (ChatGPT-4.0: n=7, 10.6%; Llama3.1-8B: n=9, 13.6%; Llama3.1-8B-RAG: n=6, 9.1%; chi-square test P=.67). Conclusions: The open-source LLM enhanced with external information presented similar performance to the closed-source model, except for ChatGPT4.0, which was superior in language simplification of messages. LLM generation demonstrated potential for instructing patients on medication use. Nonetheless, the introduction of this innovation into the electronic prescribing workflow demands prescriber validation for human oversight of the technology and requires a strategy for LLM performance governance. International Registered Report Identifier (IRRID): RR2-10.12688/verixiv.1359.1
- 26 May 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e84444
Open AccessLarge Language Model–Generated Patient Instructions for Prescriptions in Primary Health Care: Preclinical Algorithm Validation
Background: The application of generative artificial intelligence to simplify medication use instructions has the potential to enhance people’s health by improving treatment adherence. Objective: We evaluated the performance of large language models (LLMs) in generating medication usage instructions to complement prescriptions in primary health care. Methods: This randomized, blinded experimental preclinical study used prescription-inducing scenarios, assigned to 62 health care professionals, to validate instructions generated by LLMs during electronic prescriptions. The instructions were generated by ChatGPT-4.0 (OpenAI), Llama3.1-8B (Meta), and Llama3.1-8B-RAG (Meta) using retrieval-augmented generation based on patient information leaflets. Performance metrics assessed adequacy, completeness, clarity, language simplification, usefulness, and errors in the generated instructions, with scores to analyze overall and individual metrics. Results: The 3 models yielded high overall scores for producing qualified instructions (ChatGPT-4.0: median 88.4, IQR 22.8; Llama3.1-8B: median 66.5, IQR 50.9; Llama3.1-8B-RAG: median 79.9, IQR 34.4; Kruskal-Wallis test P=.003). Llama3.1-8B-RAG received evaluations with similar overall scores to ChatGPT-4.0 (post hoc test, P=.05) and similar to Llama3.1-8B (post hoc test, P=.44). ChatGPT-4.0 outperformed Llama3.1-8B (Bonferroni test, P<.001). Regarding specific domains, Llama3.1-8B-RAG received scores equivalent to those of ChatGPT-4.0 for adequacy (mean 6.24, SD 2.3 vs mean 6.82, SD 2.1; post hoc test, P=.54); completeness (mean 5.94, SD 2.2 vs 6.55, SD 1.9; post hoc test P=.38), clarity (mean 5.77, SD 2.4 vs mean 6.68, SD 1.9; post hoc test P=.09), and usefulness (mean 5.42, SD 2.4 vs mean 5.96, SD 2.2; post hoc test P=.63). ChatGPT-4.0 received higher scores in the language simplification criterion than Llama3.1-8B-RAG (mean 7.05, SD 1.5 vs mean 5.44, SD 2.6; post hoc test P<.001). Interrater variability in assigning scores ranged from 4.2% (n=3) to 85.8% (n=6) among primary health care professionals. Instructions leading to incorrect use of the medication had similar frequency among the models(ChatGPT-4.0: n=15, 22.7%; Llama3.1-8B: n=19, 22.8%; Llama3.1-8B-RAG: n=19, 22.8%; chi-square test P=.71). The frequencies of hallucination were similar (ChatGPT-4.0: n=7, 10.6%; Llama3.1-8B: n=9, 13.6%; Llama3.1-8B-RAG: n=6, 9.1%; chi-square test P=.67). Conclusions: The open-source LLM enhanced with external information presented similar performance to the closed-source model, except for ChatGPT4.0, which was superior in language simplification of messages. LLM generation demonstrated potential for instructing patients on medication use. Nonetheless, the introduction of this innovation into the electronic prescribing workflow demands prescriber validation for human oversight of the technology and requires a strategy for LLM performance governance. International Registered Report Identifier (IRRID): RR2-10.12688/verixiv.1359.1
- Open Access
- 10 November 2025
- Published by Sociedade Brasileira de Computação
- p. 455-463
Uma Abordagem Híbrida para Sistemas de Recomendação com Base em Avaliações Textuais e Filtragem Colaborativa
Recommender systems are increasingly leveraging textual reviews to enhance user preference modeling. Although review-aware recommender systems (RARs) have shown advances in capturing semantic nuances, they often fall short in representing collaborative patterns among users and items. In contrast, traditional collaborative filtering methods, though limited in semantic modeling, are robust in exploiting structural relationships. In this study, we propose a hybrid approach that integrates semantic representations derived from RARs into traditional collaborative models. We evaluated this strategy across three Amazon datasets, comparing RARs, collaborative, and hybrid models in terms of preference modeling accuracy (MSE and MAE), and recommendation relevance (Hits, Precision, Recall). Our results showthat hybrid models outperform both baselines, achieving up to 2.8 times lower prediction error and 60% higher precision. These findings highlight the potential of hybrid models to deliver more robust and context-aware recommendations.
- 10 November 2025
- Published by Sociedade Brasileira de Computação
- p. 455-463
Open AccessUma Abordagem Híbrida para Sistemas de Recomendação com Base em Avaliações Textuais e Filtragem Colaborativa
Recommender systems are increasingly leveraging textual reviews to enhance user preference modeling. Although review-aware recommender systems (RARs) have shown advances in capturing semantic nuances, they often fall short in representing collaborative patterns among users and items. In contrast, traditional collaborative filtering methods, though limited in semantic modeling, are robust in exploiting structural relationships. In this study, we propose a hybrid approach that integrates semantic representations derived from RARs into traditional collaborative models. We evaluated this strategy across three Amazon datasets, comparing RARs, collaborative, and hybrid models in terms of preference modeling accuracy (MSE and MAE), and recommendation relevance (Hits, Precision, Recall). Our results showthat hybrid models outperform both baselines, achieving up to 2.8 times lower prediction error and 60% higher precision. These findings highlight the potential of hybrid models to deliver more robust and context-aware recommendations.
- Open Access
- 19 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Large Language Model–Generated Patient Instructions for Prescriptions in Primary Health Care: Preclinical Algorithm Validation (Preprint)
BACKGROUND The application of generative artificial intelligence to simplify medication use instructions has the potential to enhance people’s health by improving treatment adherence. OBJECTIVE We evaluated the performance of large language models (LLMs) in generating medication usage instructions to complement prescriptions in primary health care. METHODS This randomized, blinded experimental preclinical study used prescription-inducing scenarios, assigned to 62 health care professionals, to validate instructions generated by LLMs during electronic prescriptions. The instructions were generated by ChatGPT-4.0 (OpenAI), Llama3.1-8B (Meta), and Llama3.1-8B-RAG (Meta) using retrieval-augmented generation based on patient information leaflets. Performance metrics assessed adequacy, completeness, clarity, language simplification, usefulness, and errors in the generated instructions, with scores to analyze overall and individual metrics. RESULTS The 3 models yielded high overall scores for producing qualified instructions (ChatGPT-4.0: median 88.4, IQR 22.8; Llama3.1-8B: median 66.5, IQR 50.9; Llama3.1-8B-RAG: median 79.9, IQR 34.4; Kruskal-Wallis test P=.003). Llama3.1-8B-RAG received evaluations with similar overall scores to ChatGPT-4.0 (post hoc test, P=.05) and similar to Llama3.1-8B (post hoc test, P=.44). ChatGPT-4.0 outperformed Llama3.1-8B (Bonferroni test, P<.001). Regarding specific domains, Llama3.1-8B-RAG received scores equivalent to those of ChatGPT-4.0 for adequacy (mean 6.24, SD 2.3 vs mean 6.82, SD 2.1; post hoc test, P=.54); completeness (mean 5.94, SD 2.2 vs 6.55, SD 1.9; post hoc test P=.38), clarity (mean 5.77, SD 2.4 vs mean 6.68, SD 1.9; post hoc test P=.09), and usefulness (mean 5.42, SD 2.4 vs mean 5.96, SD 2.2; post hoc test P=.63). ChatGPT-4.0 received higher scores in the language simplification criterion than Llama3.1-8B-RAG (mean 7.05, SD 1.5 vs mean 5.44, SD 2.6; post hoc test P<.001). Interrater variability in assigning scores ranged from 4.2% (n=3) to 85.8% (n=6) among primary health care professionals. Instructions leading to incorrect use of the medication had similar frequency among the models(ChatGPT-4.0: n=15, 22.7%; Llama3.1-8B: n=19, 22.8%; Llama3.1-8B-RAG: n=19, 22.8%; chi-square test P=.71). The frequencies of hallucination were similar (ChatGPT-4.0: n=7, 10.6%; Llama3.1-8B: n=9, 13.6%; Llama3.1-8B-RAG: n=6, 9.1%; chi-square test P=.67). CONCLUSIONS The open-source LLM enhanced with external information presented similar performance to the closed-source model, except for ChatGPT4.0, which was superior in language simplification of messages. LLM generation demonstrated potential for instructing patients on medication use. Nonetheless, the introduction of this innovation into the electronic prescribing workflow demands prescriber validation for human oversight of the technology and requires a strategy for LLM performance governance. INTERNATIONAL REGISTERED REPORT RR2-10.12688/verixiv.1359.1
- 19 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessLarge Language Model–Generated Patient Instructions for Prescriptions in Primary Health Care: Preclinical Algorithm Validation (Preprint)
BACKGROUND The application of generative artificial intelligence to simplify medication use instructions has the potential to enhance people’s health by improving treatment adherence. OBJECTIVE We evaluated the performance of large language models (LLMs) in generating medication usage instructions to complement prescriptions in primary health care. METHODS This randomized, blinded experimental preclinical study used prescription-inducing scenarios, assigned to 62 health care professionals, to validate instructions generated by LLMs during electronic prescriptions. The instructions were generated by ChatGPT-4.0 (OpenAI), Llama3.1-8B (Meta), and Llama3.1-8B-RAG (Meta) using retrieval-augmented generation based on patient information leaflets. Performance metrics assessed adequacy, completeness, clarity, language simplification, usefulness, and errors in the generated instructions, with scores to analyze overall and individual metrics. RESULTS The 3 models yielded high overall scores for producing qualified instructions (ChatGPT-4.0: median 88.4, IQR 22.8; Llama3.1-8B: median 66.5, IQR 50.9; Llama3.1-8B-RAG: median 79.9, IQR 34.4; Kruskal-Wallis test P=.003). Llama3.1-8B-RAG received evaluations with similar overall scores to ChatGPT-4.0 (post hoc test, P=.05) and similar to Llama3.1-8B (post hoc test, P=.44). ChatGPT-4.0 outperformed Llama3.1-8B (Bonferroni test, P<.001). Regarding specific domains, Llama3.1-8B-RAG received scores equivalent to those of ChatGPT-4.0 for adequacy (mean 6.24, SD 2.3 vs mean 6.82, SD 2.1; post hoc test, P=.54); completeness (mean 5.94, SD 2.2 vs 6.55, SD 1.9; post hoc test P=.38), clarity (mean 5.77, SD 2.4 vs mean 6.68, SD 1.9; post hoc test P=.09), and usefulness (mean 5.42, SD 2.4 vs mean 5.96, SD 2.2; post hoc test P=.63). ChatGPT-4.0 received higher scores in the language simplification criterion than Llama3.1-8B-RAG (mean 7.05, SD 1.5 vs mean 5.44, SD 2.6; post hoc test P<.001). Interrater variability in assigning scores ranged from 4.2% (n=3) to 85.8% (n=6) among primary health care professionals. Instructions leading to incorrect use of the medication had similar frequency among the models(ChatGPT-4.0: n=15, 22.7%; Llama3.1-8B: n=19, 22.8%; Llama3.1-8B-RAG: n=19, 22.8%; chi-square test P=.71). The frequencies of hallucination were similar (ChatGPT-4.0: n=7, 10.6%; Llama3.1-8B: n=9, 13.6%; Llama3.1-8B-RAG: n=6, 9.1%; chi-square test P=.67). CONCLUSIONS The open-source LLM enhanced with external information presented similar performance to the closed-source model, except for ChatGPT4.0, which was superior in language simplification of messages. LLM generation demonstrated potential for instructing patients on medication use. Nonetheless, the introduction of this innovation into the electronic prescribing workflow demands prescriber validation for human oversight of the technology and requires a strategy for LLM performance governance. INTERNATIONAL REGISTERED REPORT RR2-10.12688/verixiv.1359.1
- 9 September 2025
- Published by Springer Nature
- p. 453-476
Enhanced Analysis of User Perceptions Through Natural Language Processing Approaches
- 9 September 2025
- Published by Springer Nature
- p. 453-476
Enhanced Analysis of User Perceptions Through Natural Language Processing Approaches
- 28 June 2025
- Published by Springer Nature
- p. 65-80
Correlating Socioeconomic Factors and Syphilis Incidence: A Case Study in Brazil
- 28 June 2025
- Published by Springer Nature
- p. 65-80
Correlating Socioeconomic Factors and Syphilis Incidence: A Case Study in Brazil
- Open Access
- 17 November 2024
- Published by Sociedade Brasileira de Computação
- p. 954-965
Adapting Large Language Models for Topic Modeling Tasks
This work presents a proposal for adapting Large Language Models (LLMs) to the unsupervised task of Topic Modeling (TM). Our proposal consists of three stages: document summarization, characterization of topics, and definition of topics. We instantiated our proposal with two LLMs, one open-source (Llama3) and the other proprietary (GPT 3.5), comparing them with four state-of-the-art (SOTA) strategies in TM. Our results demonstrated that the approach is very promising, having been able to define topics as coherent as SOTA strategies but still with room for improvement in terms of organizational structure.
- 17 November 2024
- Published by Sociedade Brasileira de Computação
- p. 954-965
Open AccessAdapting Large Language Models for Topic Modeling Tasks
This work presents a proposal for adapting Large Language Models (LLMs) to the unsupervised task of Topic Modeling (TM). Our proposal consists of three stages: document summarization, characterization of topics, and definition of topics. We instantiated our proposal with two LLMs, one open-source (Llama3) and the other proprietary (GPT 3.5), comparing them with four state-of-the-art (SOTA) strategies in TM. Our results demonstrated that the approach is very promising, having been able to define topics as coherent as SOTA strategies but still with room for improvement in terms of organizational structure.