Результаты исследований: Глава в книге, отчете, сборнике статей › Материалы конференции › Рецензирование
Результаты исследований: Глава в книге, отчете, сборнике статей › Материалы конференции › Рецензирование
}
TY - GEN
T1 - Predicting the Risk of Myopia Exacerbation Based on a Naive Bayesian Classification Algorithm
AU - Lina, Sun
PY - 2023/5/15
Y1 - 2023/5/15
N2 - According to the WHO report, 2.6 billion people worldwide suffer from myopia. Myopia has become a global public health problem and high levels of myopia lead to severe distortion of the retina, which increases the risk of acquiring other eye diseases. This paper focuses on building a machine learning model that takes a sample from a survey questionnaire and predicts whether the sample is at risk of increased myopia. The core algorithm of the prediction model is a Bayesian algorithm. We use the python language to build a Gaussian naïve Bayesian classification model and implement it to predict the risk of increased myopia. And we also tested the performance of the model using confusion matrices, ROC curves, accuracy, precision, recall and F1 scores. Overall, the model was able to process natural language type questionnaires and correctly predict the risk of increased myopia. Finally, we explore the advantages and disadvantages of the Naive Bayesian classifier model. A summary of future extensions to this study is also presented.
AB - According to the WHO report, 2.6 billion people worldwide suffer from myopia. Myopia has become a global public health problem and high levels of myopia lead to severe distortion of the retina, which increases the risk of acquiring other eye diseases. This paper focuses on building a machine learning model that takes a sample from a survey questionnaire and predicts whether the sample is at risk of increased myopia. The core algorithm of the prediction model is a Bayesian algorithm. We use the python language to build a Gaussian naïve Bayesian classification model and implement it to predict the risk of increased myopia. And we also tested the performance of the model using confusion matrices, ROC curves, accuracy, precision, recall and F1 scores. Overall, the model was able to process natural language type questionnaires and correctly predict the risk of increased myopia. Finally, we explore the advantages and disadvantages of the Naive Bayesian classifier model. A summary of future extensions to this study is also presented.
UR - http://www.scopus.com/inward/record.url?partnerID=8YFLogxK&scp=85164966822
U2 - 10.1109/USBEREIT58508.2023.10158818
DO - 10.1109/USBEREIT58508.2023.10158818
M3 - Conference contribution
SP - 68
EP - 71
BT - Proceedings - 2023 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)
Y2 - 15 May 2023 through 17 May 2023
ER -
ID: 41990547