RESUMO
Energy consumption of constructed educational facilities significantly impacts economic, social and environment sustainable development. It contributes to approximately 37% of the carbon dioxide emissions associated with energy use and procedures. This paper aims to introduce a study that investigates several artificial intelligence-based models to predict the energy consumption of the most important educational buildings; schools. These models include decision trees, K-nearest neighbors, gradient boosting, and long-term memory networks. The research also investigates the relationship between the input parameters and the yearly energy usage of educational buildings. It has been discovered that the school sizes and AC capacities are the most impact variable associated with higher energy consumption. While 'Type of School' is less direct or weaker correlation with 'Annual Consumption'. The four developed models were evaluated and compared in training and testing stages. The Decision Tree model demonstrates strong performance on the training data with an average prediction error of about 3.58%. The K-Nearest Neighbors model has significantly higher errors, with RMSE on training data as high as 38,429.4, which may be indicative of overfitting. In contrast, Gradient Boosting can almost perfectly predict the variations within the training dataset. The performance metrics suggest that some models manage this variability better than others, with Gradient Boosting and LSTM standing out in terms of their ability to handle diverse data ranges, from the minimum consumption of approximately 99,274.95 to the maximum of 683,191.8. This research underscores the importance of sustainable educational buildings not only as physical learning spaces but also as dynamic environments that contribute to informal educational processes. Sustainable buildings serve as real-world examples of environmental stewardship, teaching students about energy efficiency and sustainability through their design and operation. By incorporating advanced AI-driven tools to optimize energy consumption, educational facilities can become interactive learning hubs that encourage students to engage with concepts of sustainability in their everyday surroundings.
Assuntos
Inteligência Artificial , Instituições Acadêmicas , Humanos , Conservação de Recursos Energéticos/métodos , Árvores de Decisões , Modelos TeóricosRESUMO
Dengue causes approximately 10.000 deaths and 100 million symptomatic infections annually worldwide, making it a significant public health concern. To address this, artificial intelligence tools like machine learning can play a crucial role in developing more effective strategies for control, diagnosis, and treatment. This study identifies relevant variables for the screening of dengue cases through machine learning models and evaluates the accuracy of the models. Data from reported dengue cases in the states of Rio de Janeiro and Minas Gerais for the years 2016 and 2019 were obtained through the National Notifiable Diseases Surveillance System (SINAN). The mutual information technique was used to assess which variables were most related to laboratory-confirmed dengue cases. Next, a random selection of 10,000 confirmed cases and 10,000 discarded cases was performed, and the dataset was divided into training (70%) and testing (30%). Machine learning models were then tested to classify the cases. It was found that the logistic regression model with 10 variables (gender, age, fever, myalgia, headache, vomiting, nausea, back pain, rash, retro-orbital pain) and the Decision Tree and Multilayer Perceptron (MLP) models achieved the best results in decision metrics, with an accuracy of 98%. Therefore, a tree-based model would be suitable for building an application and implementing it on smartphones. This resource would be available to healthcare professionals such as doctors and nurses.
Assuntos
Dengue , Aprendizado de Máquina , Programas de Rastreamento , Dengue/diagnóstico , Programas de Rastreamento/métodos , Programas de Rastreamento/normas , Brasil , Árvores de Decisões , HumanosRESUMO
Leptospirosis is a global disease that impacts people worldwide, particularly in humid and tropical regions, and is associated with significant socio-economic deficiencies. Its symptoms are often confused with other syndromes, which can compromise clinical diagnosis and the failure to carry out specific laboratory tests. In this respect, this paper presents a study of three algorithms (Decision Tree, Random Forest and Adaboost) for predicting the outcome (cure or death) of individuals with leptospirosis. Using the records contained in the government National System of Aggressions and Notification (SINAN, in portuguese) from 2007 to 2017, for the state of Pará, Brazil, where the temporal attributes of health care, symptoms (headache, vomiting, jaundice, calf pain) and clinical evolution (renal failure and respiratory changes) were used. In the performance evaluation of the selected models, it was observed that the Random Forest exhibited an accuracy of 90.81% for the training dataset, considering the attributes of experiment 8, and the Decision Tree presented an accuracy of 74.29 for the validation database. So, this result considers the best attributes pointed out by experiment 10: time first symptoms medical attention, time first symptoms ELISA sample collection, medical attention hospital admission time, headache, calf pain, vomiting, jaundice, renal insufficiency, and respiratory alterations. The contribution of this article is the confirmation that artificial intelligence, using the Decision Tree model algorithm, depicting the best choice as the final model to be used in future data for the prediction of human leptospirosis cases, helping in the diagnosis and course of the disease, aiming to avoid the evolution to death.
Assuntos
Leptospirose , Aprendizado de Máquina , Leptospirose/diagnóstico , Humanos , Algoritmos , Árvores de Decisões , Brasil/epidemiologia , Avaliação de Resultados em Cuidados de Saúde/métodos , Masculino , Feminino , AdultoRESUMO
OBJECTIVES: To undertake a cost-effectiveness analysis of restorative treatments for a first permanent molar with severe molar incisor hypomineralization from the perspective of the Brazilian public system. MATERIALS AND METHODS: Two models were constructed: a one-year decision tree and a ten-year Markov model, each based on a hypothetical cohort of one thousand individuals through Monte Carlo simulation. Eight restorative strategies were evaluated: high viscosity glass ionomer cement (HVGIC); encapsulated GIC; etch and rinse adhesive + composite; self-etch adhesive + composite; preformed stainless steel crown; HVGIC + etch and rinse adhesive + composite; HVGIC + self-etch adhesive + composite, and encapsulated GIC + etch and rinse adhesive + composite. Effectiveness data were sourced from the literature. Micro-costing was applied using 2022 USD market averages with a 5% variation. Incremental cost-effectiveness ratio (ICER), net monetary benefit (%NMB), and the budgetary impact were obtained. RESULTS: Cost-effective treatments included HVGIC (%NMB = 0%/ 0%), encapsulated GIC (%NMB = 19.4%/ 19.7%), and encapsulated GIC + etch and rinse adhesive + composite (%NMB = 23.4%/ 24.5%) at 1 year and 10 years, respectively. The benefit gain of encapsulated GIC + etch and rinse adhesive + composite in relation to encapsulated GIC was small when compared to the cost increase at 1 year (gain of 3.28% and increase of USD 24.26) and 10 years (gain of 4% and increase of USD 15.54). CONCLUSION: Within the horizon and perspective analyzed, the most cost-effective treatment was encapsulated GIC restoration. CLINICAL RELEVANCE: This study can provide information for decision-making.
Assuntos
Hipoplasia do Esmalte Dentário , Restauração Dentária Permanente , Cimentos de Ionômeros de Vidro , Humanos , Brasil , Árvores de Decisões , Hipoplasia do Esmalte Dentário/terapia , Restauração Dentária Permanente/métodos , Restauração Dentária Permanente/economia , Cimentos de Ionômeros de Vidro/uso terapêutico , Cadeias de Markov , Dente Molar , Hipomineralização Molar , Método de Monte CarloRESUMO
PURPOSE: Machine learning (ML) models presented an excellent performance in the prognosis prediction. However, the black box characteristic of ML models limited the clinical applications. Here, we aimed to establish explainable and visualizable ML models to predict biochemical recurrence (BCR) of prostate cancer (PCa). MATERIALS AND METHODS: A total of 647 PCa patients were retrospectively evaluated. Clinical parameters were identified using LASSO regression. Then, cohort was split into training and validation datasets with a ratio of 0.75:0.25 and BCR-related features were included in Cox regression and five ML algorithm to construct BCR prediction models. The clinical utility of each model was evaluated by concordance index (C-index) values and decision curve analyses (DCA). Besides, Shapley Additive Explanation (SHAP) values were used to explain the features in the models. RESULTS: We identified 11 BCR-related features using LASSO regression, then establishing five ML-based models, including random survival forest (RSF), survival support vector machine (SSVM), survival Tree (sTree), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and a Cox regression model, C-index were 0.846 (95%CI 0.796-0.894), 0.774 (95%CI 0.712-0.834), 0.757 (95%CI 0.694-0.818), 0.820 (95%CI 0.765-0.869), 0.793 (95%CI 0.735-0.852), and 0.807 (95%CI 0.753-0.858), respectively. The DCA showed that RSF model had significant advantages over all models. In interpretability of ML models, the SHAP value demonstrated the tangible contribution of each feature in RSF model. CONCLUSIONS: Our score system provide reference for the identification for BCR, and the crafting of a framework for making therapeutic decisions for PCa on a personalized basis.
Assuntos
Aprendizado de Máquina , Recidiva Local de Neoplasia , Neoplasias da Próstata , Humanos , Masculino , Neoplasias da Próstata/sangue , Neoplasias da Próstata/patologia , Recidiva Local de Neoplasia/sangue , Recidiva Local de Neoplasia/patologia , Estudos Retrospectivos , Idoso , Pessoa de Meia-Idade , Prognóstico , Árvores de Decisões , Modelos de Riscos Proporcionais , Algoritmos , Máquina de Vetores de Suporte , Antígeno Prostático Específico/sangueRESUMO
OBJECTIVES: To evaluate cost-effective pharmacological treatment in adult kidney transplant recipients from the perspective of the Colombian health system. METHODS: A decision tree model for the induction phase and a Markov model for the maintenance phase were built. A review of the clinical literature was conducted to extract probabilities, and the life-years were used as the outcome. Costs were calculated using the administrative databases. The evaluating treatment schemes are organized by groups of evidence with direct comparisons. RESULTS: In the induction phase, anti-thymocyte immunoglobulin+ methylprednisolone is dominant, more effective, and less expensive, compared with basiliximab+methylprednisolone. In the maintenance phase, azathioprine (AZA) is dominant in contrast to mycophenolate mofetil (MFM) both with cyclosporine (CIC)+ corticosteroids (CE); CIC is dominant relative to sirolimus (SIR) and tacrolimus (TAC) (both with MFM+CE or AZA+CE), and TAC is dominant compared with SIR (in addition with MFM+CE or mycophenolate sodium [MFS]+CE); MFM is dominant in relation to MFS and everolimus, and SIR is more effective MFM but it does not exceed the threshold (in sum with TAC+CE); MFS and MFM are dominant relative to everolimus, and SIR is more effective than MFM, but it does not exceed the threshold (in addiction with CIC+CE); MFM is dominant in relation to TAC (in sum with SIR+CE), and CIC+AZA+CE is dominant in relation to TAC+MFM+CE. CONCLUSIONS: The base-case results for all evidence groups are consistent with the different sensitivity analyses.
Assuntos
Imunossupressores , Transplante de Rim , Adulto , Humanos , Corticosteroides/uso terapêutico , Corticosteroides/economia , Azatioprina/uso terapêutico , Azatioprina/economia , Colômbia , Análise de Custo-Efetividade , Ciclosporina/uso terapêutico , Ciclosporina/economia , Árvores de Decisões , Rejeição de Enxerto/prevenção & controle , Rejeição de Enxerto/economia , Imunossupressores/economia , Imunossupressores/uso terapêutico , Transplante de Rim/economia , Cadeias de Markov , Ácido Micofenólico/uso terapêutico , Ácido Micofenólico/economia , Sirolimo/uso terapêutico , Sirolimo/economia , Tacrolimo/economia , Tacrolimo/uso terapêutico , Transplantados/estatística & dados numéricosRESUMO
OBJECTIVES: The study aimed to evaluate the cost-effectiveness of the Pare de Fumar Conosco software compared with the standard of care adopted in Brazil for the treatment of smoking cessation. METHODS: In the cohort of smokers with multiple chronic conditions, we developed an decision tree model for the benefit measures of smoking cessation. We adopted the perspectives of the Brazilian Unified Health System and the service provider. Resources and costs were measured by primary and secondary sources and effectiveness by a randomized clinical trial. The incremental cost-effectiveness ratio (ICER) was calculated, followed by deterministic and probabilistic sensitivity analyses and deterministic and probabilistic sensitivity analyses. No willingness to pay threshold was adopted. RESULTS: The software had a lower cost and greater effectiveness than its comparator. The ICER was dominant in all of the benefits examined (-R$2 585 178.29 to -R$325 001.20). The cost of the standard of care followed by that of the electronic tool affected the ICER of the benefit measures. In all probabilistic analyses, the software was superior to the standard of care (53.6%-82.5%). CONCLUSION: The Pare de Fumar Conosco software is a technology that results in cost savings in treating smoking cessation.
Assuntos
Abandono do Hábito de Fumar , Padrão de Cuidado , Adulto , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Brasil , Análise de Custo-Efetividade , Tomada de Decisões , Árvores de Decisões , Abandono do Hábito de Fumar/métodos , Abandono do Hábito de Fumar/economia , Software/normas , Padrão de Cuidado/economiaRESUMO
BACKGROUND: Occupational accidents in the plumbing activity in the construction sector in developing countries have high rates of work absenteeism. The productivity of enterprises is heavily influenced by it. OBJECTIVE: To propose a model based on the Plan, Do, Check, and Act cycle and data mining for the prevention of occupational accidents in the plumbing activity in the construction sector. METHODS: This cross-sectional study was administered on a total of 200 male technical workers in plumbing. It considers biological, biomechanical, chemical, and, physical risk factors. Three data mining algorithms were compared: Logistic Regression, Naive Bayes, and Decision Trees, classifying the occurrences occupational accident. The model was validated considering 20% of the data collected, maintaining the same proportion between accidents and non-accidents. The model was applied to data collected from the last 17 years of occupational accidents in the plumbing activity in a Colombian construction company. RESULTS: The results showed that, in 90.5% of the cases, the decision tree classifier (J48) correctly identified the possible cases of occupational accidents with the biological, chemical, and, biomechanical, risk factors training variables applied in the model. CONCLUSION: The results of this study are promising in that the model is efficient in predicting the occurrence of an occupational accident in the plumbing activity in the construction sector. For the accidents identified and the associated causes, a plan of measures to mitigate the risk of occupational accidents is proposed.
Assuntos
Acidentes de Trabalho , Indústria da Construção , Mineração de Dados , Humanos , Mineração de Dados/métodos , Estudos Transversais , Acidentes de Trabalho/prevenção & controle , Acidentes de Trabalho/estatística & dados numéricos , Masculino , Adulto , Colômbia/epidemiologia , Fatores de Risco , Teorema de Bayes , Árvores de Decisões , Modelos Logísticos , AlgoritmosRESUMO
Objetivo: analisar os dados de normatização dos escores da versão brasileira do instrumento eHealth Literacy Scale (eHeals) para avaliação do letramento digital em saúde. Método: estudo transversal com 502 adultos brasileiros, realizado em 2019. Dados coletados pelo instrumento eHeals e questionário sociodemográfico. Foram aplicadas árvores de decisão e análise discriminante. Estudo aprovado pelo Comite de Ética em Pesquisa. Resultados: a análise discriminante determinou as faixas de classificação do eHeals a partir da distribuição dos escores. A árvore de decisão indicou que a escolaridade afetou de forma relevante os resultados da escala. Os indivíduos com escolaridade até o ensino fundamental II incompleto: baixo (até 10), médio (11 a 25), alto (27 a 40), e escolaridade acima: baixo (até 25), médio (25 a 32) e alto LDS (33 a 40). Conclusão: a classificação dos níveis de letramento digital em saúde de adultos pelo eHeals deve ser controlada pelos níveis de escolaridade dos participantes(AU)
Objective: to analyze the normative data of the scores of the Brazilian version of the eHealth Literacy Scale (eHeals) instrument for assessing digital health literacy. Method: cross-sectional study with 502 Brazilian adults in 2019. Data collected using the eHeals instrument and sociodemographic questionnaire. Decision trees and discriminant analysis were applied. Study approved by the Research Ethics Committee. Results: Discriminant analysis determined the eHeals classification ranges based on the distribution of scores. The decision tree indicated that education significantly affected the scale results. Thus, individuals with incomplete elementary school education up to II: low (up to 10), medium (11 to 25), high (27 to 40), and higher education: low (up to 25), medium (25 to 32) and high LDS (33 to 40). Conclusion: the classification of digital health literacy levels using eHeals in adults should be controlled by the participants' education levels(AU)
Objetivo: analizar los datos de estandarización de las puntuaciones de la versión brasileña del instrumento eHealth Literacy Scale (eHeals) para evaluar la alfabetización digital en salud. Método: estudio transversal con 502 adultos brasileños que tuvo lugar en 2019. La recolección de datos se hizo mediante el instrumento eHeals y un cuestionario sociodemográfico. Se aplicaron árboles de decisión y análisis discriminante. El Comité de Ética en Investigación aprobó el estudio. Resultados: El análisis discriminante determinó los rangos de clasificación de eHeals con base en la distribución de puntuaciones. El árbol de decisión indicó que la educación afectó significativamente los resultados de la escala. Individuos con educación primaria incompleta: baja (hasta 10), media (11 a 25), alta (27 a 40), y educación superior a esa mencionada: baja (hasta 25), media (25 a 32) y alto LDS (33 a 40). Conclusión: la clasificación de los niveles de alfabetización en salud digital en adultos con eHeals debe ser controlada por los niveles de educación de los participantes(AU)