ETElisa Tuler

Elisa Tuler

*This is an algorithmically generated author record based on publicly available information.

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:


Latest Publications

  • A Machine Learning Approach for an End-to-End Music Inpainting Pipeline

    by Gustavo Romão, Elisa T. Albergaria, Diego R. C. Dias, Marcela Alves de Almeida, Vinícius F. S. Mota, Leonardo Chaves Dutra Rocha

  • Evaluating Segmentation and Temporal Resolution in Highway Crash Forecasting: The BR-040 Corridor

    by João P. Tozetto, Isadora Nunes, Bernardo Soares, Elisa T. Albergaria, Diego R. C. Dias, Vinícius F. S. Mota, Leonardo C. D. Rocha

  • Zero-Shot LLM Sentiment Meets Market Microstructure: Parsimonious Feature Selection for High-Frequency Bitcoin Forecastings

    by Luís A. Moraes, Daniel Marques, Lucas Nojiri, Elisa T. Albergaria, Diego R. C. Dias, Vinícius F. S. Mota, Marcelo P. Guimarães, Leonardo C. D. Rocha

  • Open Access

    Large Language Model–Generated Patient Instructions for Prescriptions in Primary Health Care: Preclinical Algorithm Validation

    by Zilma Silveira Nogueira Reis, Elisa Tuler Albergaria, Adriana Silvina Pagano, Eura Martins Lage, Flávia Ribeiro de Oliveira, Cristiane dos Santos Dias, Juliana Almeida Oliveira, Gláucia Miranda Varella Pereira, Isaias Jose Ramos de Oliveira, Érico Franco Mineiro, et al.

    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

    Uma Abordagem Híbrida para Sistemas de Recomendação com Base em Avaliações Textuais e Filtragem Colaborativa

    by Yan Andrade, Naan Vasconcelos, Elisa Tuler, Adriano Pereira, Leonardo Rocha

    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

    Large Language Model–Generated Patient Instructions for Prescriptions in Primary Health Care: Preclinical Algorithm Validation (Preprint)

    by Zilma Silveira Nogueira Reis, Elisa Tuler Albergaria, Adriana Silvina Pagano, Eura Martins Lage, Flávia Ribeiro de Oliveira, Cristiane dos Santos Dias, Juliana Almeida Oliveira, Gláucia Miranda Varella Pereira, Isaias Jose Ramos de Oliveira, Érico Franco Mineiro, et al.

    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

  • Enhanced Analysis of User Perceptions Through Natural Language Processing Approaches

    by Gabriel Prenassi, Ana Machado, Davi Freitas, André Lima, Raquel O. Prates, Antonio Landim, Leonardo Rocha, Elisa Tuler


  • Correlating Socioeconomic Factors and Syphilis Incidence: A Case Study in Brazil

    by Matheus Tavares, Elias Mendes, Diego Dias, Elisa Tuler, Rodolfo Villaça, Marcelo Guimarães, Leonardo Rocha

  • “Are the current topic modeling evaluation metrics enough?” Mitigating the limitations of topic modeling evaluation metrics using a multi-perspective game theoretic approach

    by Antônio Pereira, Felipe Viegas, Diego Roberto Colombo Dias, Elisa Tuler, Ana Cláudia Machado, Guilherme Fonseca, Marcos André Gonçalves, Leonardo Rocha


  • Open Access

    Adapting Large Language Models for Topic Modeling Tasks

    by Daniel Carvalho, Antônio Pereira, Elisa Tuler, Diego Dias, Washington Cunha, Leonardo Rocha

    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.