Percorrer por autor "Pais, Ricardo Jorge"
A mostrar 1 - 3 de 3
Resultados por página
Opções de ordenação
- Exploring AI-driven machine learning approaches for optimal classification of peri-implantitis based on oral microbiome data : a feasibility studyPublication . Pais, Ricardo Jorge; Botelho, João; Machado, Vanessa; Alcoforado, Gil; Mendes, José João; Alves, Ricardo; Bessa, Lucinda J.Background: Machine learning (ML) techniques have been recently proposed as a solution for aiding in the prevention and diagnosis of microbiome-related diseases. Here, we applied auto-ML approaches on real-case metagenomic datasets from saliva and subgingival peri-implant biofilm microbiomes to explore a wide range of ML algorithms to benchmark best-performing algorithms for predicting peri-implantitis (PI). Methods: A total of 100 metagenomes from the NCBI SRA database (PRJNA1163384) were used in this study to construct biofilm and saliva metagenomes datasets. Two AI-driven auto-ML approaches were used on constructed datasets to generate 100 ML-based models for the prediction of PI. These were compared with statistically significant single-microorganism-based models. Results: Several ML algorithms were pinpointed as suitable bespoke predictive approaches to apply to metagenomic data, outperforming the single-microorganism-based classification. Auto-ML approaches rendered high-performing models with Receiver Operating Characteristic–Area Under the Curve, sensitivities and specificities between 80% and 100%. Among these, classifiers based on ML-driven scoring of combinations of 2–4 microorganisms presented top-ranked performances and can be suitable for clinical application. Moreover, models generated based on the saliva microbiome showed higher predictive performance than those from the biofilm microbiome. Conclusions: This feasibility study bridges complex AI research with practical dental applications by benchmarking ML algorithms and exploring oral microbiomes as foundations for developing intuitive, cost-effective, and clinically relevant diagnostic platforms.
- Facilitating “omics” for phenotype classification using a user-friendly AI-driven platform : application in cancer prognosticsPublication . Lima Filho, Uraquitan; Pais, Tiago Alexandre; Pais, Ricardo JorgePrecision medicine approaches often rely on complex and integrative analyses of multiple biomarkers from “omics” data to generate insights that can help with either diagnostic, prognostic, or therapeutical decisions. Such insights are often made using machine learning (ML) models that perform sample classification for a particular phenotype (yes/no). Building such models is a challenge and time-consuming, requiring advanced coding skills and mathematical modelling expertise. Artificial intelligence (AI) is a methodological solution that has the potential to facilitate, optimize, and scale model development. In this work, we developed an AI-based, user-friendly, and code-free platform that fully automated the development of predictive models from quantitative “omics” data. Here, we show the application of this tool with the development of cancer survival prognostics models using real-life data from breast, lung, and renal cancer transcriptomes. In comparison to other models, our generated models rendered performances with competitive sensitivities (72–85%), specificities (76–85%), accuracies (75–85%), and Receiver Operating Characteristic curves with superior Areas Under the Curve (ROC-AUC of 77–86%). Further, we reported the associated sets of genes (biomarkers) and their expression patterns that were predictive of cancer survival. Moreover, we made our models available as online tools to generate prognostic predictions based on the gene expressions of the biomarkers. In conclusion, we demonstrated that our tool is a robust, user-friendly solution for developing bespoke predictive tools from “omics” data, which facilitate precision medicine applications to the point-of-care.
- Visualising the truth : a composite evaluation framework for score-based predictive model selectionPublication . Lima Filho, Uraquitan; Pais, Tiago Alexandre; Pais, Ricardo JorgeBackground: The selection of machine learning (ML) models in the biomedical sciences often relies on global performance metrics. When these metrics are closely clustered among candidate models, identifying the most suitable model for real-world deployment becomes challenging. Methods: We developed a novel composite framework that integrates visual inspection of Model Scoring Distribution Analysis (MSDA) with a new scoring metric (MSDscore). The methodology was implemented within the Digital Phenomics platform as the MSDanalyser tool and tested by generating and evaluating 27 predictive models developed for breast, lung, and renal cancer prognosis. Results: Our approach enabled a detailed inspection of true-positive, false-positive, true-negative, and false-negative distributions across the scoring space, capturing local performance patterns overlooked by conventional metrics. In contrast with the minimal variation between models obtained by global metrics, the MSDA methodology revealed substantial differences in score region behaviour, allowing better discrimination between models. Conclusions: Integrating our composite framework alongside traditional performance metrics provides a complementary and more nuanced approach to model selection in clinical and biomedical settings.