The high incidence and prevalence of chronic kidney disease (CKD), often caused by late diagnoses, is a critical public health problem, especially in developing countries such as Brazil. CKD treatment therapies, such as dialysis and kidney transplantation, increase the morbidity and mortality rates, besides the public health costs. This study analyses the usage of machine learning techniques to assist in the early diagnosis of CKD in developing countries. Qualitative and quantitative comparative analyses are, respectively, conducted using a systematic literature review and an experiment with machine learning techniques, with the k-fold cross-validation method based on the Weka software and a CKD dataset. These analyses enable a discussion on the suitability of machine learning techniques for screening for CKD risk, focusing on low-income and hard-to-reach settings of developing countries, due to the specific problems faced by them, e.g., inadequate primary health care. The study results show that the J48 decision tree is a suitable machine learning technique for such screening in developing countries, due to the easy interpretation of its classification results, with 95.00% accuracy, reaching a nearly perfect agreement with an experienced nephrologist's opinion. Conversely, random forest, naive Bayes, support vector machine, multilayer perceptron, and k-nearest neighbor techniques, respectively, yield 93.33%, 88.33%, 76.66%, 75.00%, and 71.67% accuracy, presenting at least moderate agreement with the nephrologist, at the cost of a more difficult interpretation of the classification results. INDEX TERMS Reviews, machine learning, medical diagnosis.

No abstract

Background: Chronic Kidney Disease (CKD) is a worldwide health problem, usually diagnosed in late stages of the disease, increasing public health costs and mortality rates. The late diagnosis is even more critical in developing countries due to the high levels of poverty, a large number of hard-to-reach locations, and sometimes lack/precarious primary care.Methods: We designed and evaluated an intelligent web-based Decision Support System (DSS) using the J48 decision tree machine learning algorithm, knowledge-based system concepts, the clinical document architecture, Cohen's kappa statistic, and interviews with an experienced nephrologist.Results: We provided a DSS methodology, that guided the development of the system to assist patients, primary care physicians, and the government in identifying and monitoring the CKD in Brazilian communities. The system provides remote monitoring features. A CKD dataset enabled the evaluation of the J48 decision tree algorithm, while Cohen's kappa statistic guided the evaluation of the knowledge-based system by interviews with an experienced nephrologist. Conclusion: The DSS facilitates the identification and monitoring of the CKD considering low-income populations in Brazil. In addition, the methodology and DSS can be re-used in other developing countries with similar scenarios. Trial registration: 47350313.9.0000.5013.

RESUMOO exame clínico, a sondagem periodontal e a radiografia são os três principais métodos de avaliação de saúde oral usados pelo cirurgião-dentista. Com isso, foi elaborado uma Revisão de Literatura com pesquisa no banco de dados da PubMed, Wiley Online Library e Google Acadêmico, com lapso temporal de 1998 a 2021, com o objetivo de avaliar a aplicação da TCO como possível método auxiliar no diagnóstico de doença periodontal. A partir de 1998, a TCO passa a ser estudada como possível método de diagnóstico não invasivo na Odontologia. Entre os benefícios referentes à Periodontia, tem sido relatado: a possibilidade de visualizar estruturas importantes do periodonto, fazer sondagem periodontal, diferenciar fenótipo gengival, detectar presença de cálculo supra e subgengival, além da observação de microestrutura e vascularização gengival, auxiliando no diagnóstico e acompanhamento do tratamento periodontal. Portando, a TCO é uma tecnologia emergente de bio-imagem que gera imagens estruturais bi e tridimensionais em alta resolução dos tecidos duros e moles do periodonto. Entretanto, mais estudos são necessários para superar as limitações da técnica e desenvolver sistemas de baixo custo para impulsionar seu uso em ambiente clínico.

Background: Chronic Kidney Disease (CKD) is a worldwide public health problem, usually diagnosed in the late stages of the disease, increasing public health costs and mortality rates. The late diagnosis is even more critical in developing countries due to the high levels of poverty, a large number of hard-to-reach locations, and sometimes lack/precarious primary care. Methods: We designed and evaluated an intelligent web-based Decision Support System (DSS) using the J48 decision tree machine learning algorithm, knowledge-based system concepts, the clinical document architecture, Cohen's kappa statistic, and interviews with an experienced nephrologist. Results: We provided a DSS methodology that guided the development of the system, that provides remote monitoring features, to assist patients, primary care physicians, and the government in identifying and monitoring the CKD in Brazilian communities. A CKD dataset enabled the training and evaluation of the J48 decision tree algorithm, while Cohen's kappa statistic guided the evaluation of the knowledge-based system by interviews with an experienced nephrologist. Conclusion: The DSS facilitates the identification and monitoring of the CKD considering low-income populations in Brazil. In addition, the methodology and DSS can be reused in other developing countries with similar scenarios.