Artificial Intelligence and Communication Technologies
Application of Machine Learning on the Diagnosis of 18 Common Pediatric Disease in Central African Republic
Authors: George Wu and Bin Li
Publishing Date: 28-11-2022
ISBN: 978-81-955020-5-9
Abstract
Artificial intelligence (AI) is widely used in the medical field to improve the professional level and efficiency of clinical work. In some developing countries, the shortage of qualified healthcare providers is one of the major causes of the unavailability and low quality of healthcare. Studies have shown that the application of AI improves healthcare in developing countries. This study is inspired to develop a diagnostic promoted system that is instrumental in addressing the problem of the Central African Republic, which, by a report, has the poorest healthcare access in the world. A simulated database containing 18 common pediatric diseases in the Central African Republic was used as training and testing dataset to compare the prompt diagnostic accuracy of three models of AI, including decision tree, random forest, and neural network model. The results indicate that given the dataset with laboratory data, the average accuracy of the decision tree model is 0.971, the random forest model is 0.977, and the neural network model is 0.969. In the dataset without laboratory data, the average accuracy of the decision tree model is 0.971, the random forest model is 0.977, and the neural network model is 0.923. The results indicate that the prompt diagnostic accuracy of the three models is roughly similar, all higher than 0.9, the random forest model has the highest accuracy, and in the absence of laboratory data, a high accuracy rate of 0.977 was achieved. This study suggests that developing AI diagnostic prompt techniques may help improve the diagnostic level of medical workers in developing countries, especially in the absence of laboratory data, and may also achieve a satisfactory diagnostic accuracy.
Keywords
Machine Learning, Diagnostic Prompt, Pediatric Diseases, Central African Republic
Cite as
George Wu and Bin Li, "Application of Machine Learning on the Diagnosis of 18 Common Pediatric Disease in Central African Republic", In: Saroj Hiranwal and Garima Mathur (eds), Artificial Intelligence and Communication Technologies, SCRS, India, 2022, pp. 521-525. https://doi.org/10.52458/978-81-955020-5-9-50