arXiv subjects

Paulo Sergio Panse Silveira

Publications and source records attributed to Paulo Sergio Panse Silveira.

3 recordsLinked to original sources

arXiv2025

Zero-shot Performance of Generative AI in Brazilian Portuguese Medical Exam

Artificial intelligence (AI) has shown the potential to revolutionize healthcare by improving diagnostic accuracy, optimizing workflows, and personalizing treatment plans. Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have achieved notable advancements in natural language processing and medical applications. However, the evaluation of these models has focused predominantly on the English language, leading to potential biases in their performance across different languages. This study investigates the capability of six LLMs (GPT-4.0 Turbo, LLaMA-3-8B, LLaMA-3-70B, Mixtral 8x7B Instruct, Titan Text G1-Express, and Command R+) and four MLLMs (Claude-3.5-Sonnet, Claude-3-Opus, Claude-3-Sonnet, and Claude-3-Haiku) to answer questions written in Brazilian spoken portuguese from the medical residency entrance exam of the Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (HCFMUSP) - the largest health complex in South America. The performance of the models was benchmarked against human candidates, analyzing accuracy, processing time, and coherence of the generated explanations. The results show that while some models, particularly Claude-3.5-Sonnet and Claude-3-Opus, achieved accuracy levels comparable to human candidates, performance gaps persist, particularly in multimodal questions requiring image interpretation. Furthermore, the study highlights language disparities, emphasizing the need for further fine-tuning and data set augmentation for non-English medical AI applications. Our findings reinforce the importance of evaluating generative AI in various linguistic and clinical settings to ensure a fair and reliable deployment in healthcare. Future research should explore improved training methodologies, improved multimodal reasoning, and real-world clinical integration of AI-driven medical assistance.

cs.CL↗

arXiv2022

Modeling VI and VDRL feedback functions: searching normative rules through computational simulation

In this paper, we present a R script named Beak, built to simulate rates of behavior interacting with schedules of reinforcement. Using Beak, we've simulated data that allows an assessment of different reinforcement feedback functions (RFF). This was made with unparalleled precision, since simulations provide huge samples of data and, more importantly, simulated behavior isn't changed by the reinforcement it produces. Therefore, we can vary it systematically. We've compared different RFF for RI schedules, using as criteria: meaning, precision, parsimony and generality. Our results indicate that the best feedback function for the RI schedule was published by Baum (1981). We also propose that the model used by Killeen (1975) is a viable feedback function for the RDRL schedule. We argue that Beak paves the way for greater understanding of schedules of reinforcement, addressing still open questions about quantitative features of schedules. Also, they could guide future experiments that use schedules as theoretical and methodological tools.

cs.AI↗

arXiv2022

Better to be in agreement than in bad company: a critical analysis of many kappa-like tests assessing one-million 2x2 contingency tables

We assessed several agreement coefficients applied in 2x2 contingency tables, which are commonly applied in research due to dicotomization by the conditions of the subjects (e.g., male or female) or by conveniency of the classification (e.g., traditional thresholds leading to separations in healthy or diseased, exposed or non-exposed, etc.). More extreme table configurations (e.g., high agreement between raters) are also usual, but some of the coefficients have problems with imbalanced tables. Here, we not only studied some especific estimators, but also developed a general method to the study for any estimator candidate to be an agreement measurement. This method was developed in open source R codes and it is avaliable to the researchers. Here, we tested this method by verifying the performance of several traditional estimators over all 1,028,789 tables with size ranging from 1 to 68. Cohen's kappa showed handicapped behavior similar to Pearson's r, Yule's Q, and Yule's Y. Scott's pi has ambiguity to assess situations of agreement between raters. Shankar and Bangdiwala's B was mistaken in all situations of neutrality and when there is greater disagreement between raters. Dice's F1 and McNemar's chi-squared incompletely assess the information of the contingency table, showing the poorest performance among all. We concluded that Holley and Guilford's G is the best agreement estimator, closely followed by Gwet's AC1 and they should be considered as the first choices for agreement measurement in contingency 2x2 tables. All procedures and data were implemented in R and are available to download from https://sourceforge.net/projects/tables2x2.

stat.ME↗