透過您的圖書館登入
IP:3.227.240.72
  • Journals

APPLICATION OF MULTI-LABEL CLASSIFICATION ALGORITHM TO IMPROVE DIAGNOSTIC QUALITY OF HEART DISEASES

多標籤分類演算法於提升心臟疾病診斷品質之應用

Abstracts


Artificial intelligence (AI) and machine learning (ML) are used in most aspects of human medicine, and cardiology is no exception. AI and ML provide a set of tools to enhance the effectiveness of cardiologists. ML methods have shown improved predictive ability in various clinical contexts. As acute episodes of heart failure (HF) can be avoided by timely provision of treatment, accurate prediction of HF is crucial. Herein, we investigated different ML algorithm for creating diagnostic heart disease models. Using datasets of hospitalized patients, we evaluated multi-label classification algorithm with a random forest classifier to predict HF. Performance indicators such as exact match, precision, recall, F_1 score, Hamming loss function, and Jaccard index were used for assessment. Therefore, multi-label classification can reasonably convert the diagnosis of heart disease into a single-label classification problem, which effectively improves the accuracy of classification, assist physicians in classifying and diagnosing diseases, and facilitate timely treatment.

Parallel abstracts


人工智能(artificial Intelligence, AI)和機器學習(machine learning, ML)已廣泛應用於人類大多數的醫學領域,心臟疾病也不例外,AI和ML提供了一組工具來提升心臟專科醫師的診斷,ML在各種臨床情況下均顯示出高效能的預測能力,及時提供診治可以避免急性心臟衰竭(heart failure, HF),因此準確地預測HF至關重要。本篇文章中,我們研究了應用不同ML演算法建置心臟疾病診斷性的模型,數據集是使用住院患者的數據集,以多標籤分類器將心臟病的多類症狀合理地轉化為單標籤分類問題,再以隨機森林演算法建構HF的預測模型,評估模型之性能指標包括完全匹配、精確度、召回率、F_1分數、漢明損失函數和Jaccard指數。結果證實,本模型可有效地提高疾病分類的準確性,可協助醫師對疾病的分類和診斷,有助於病人的及時治療。

Parallel keywords

機器學習 隨機森林 多標籤分類 心臟衰竭

References


Alshurafa, N., Sideris, C., Pourhomayoun, M., Kalantarian, H., Sarrafzadeh, M. and Eastwood, J.-A., 2017, Remote health monitoring outcome success prediction using baseline and first month intervention data, IEEE Journal of Biomedical and Health Informatics, 21(2), 507-514. doi:10.1109/JBHI.2016.2518673
Fatima, M. and Pasha, M., 2017, Survey of machine learning algorithms for disease diagnostic, Journal of Intelligent Learning Systems and Applications, 9(1), 1-16. doi:10.4236/jilsa.2017.91001
Guidi, G., Pettenati, M. C., Melillo, P. and Iadanza, E., 2014, A machine learning system to improve heart failure patient assistance, IEEE Journal of Biomedical and Health Informatics, 18(6), 1750-1756. doi:10.1109/JBHI.2014.2337752
Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I. and Chouvarda, I., 2017, Machine learning and data mining methods in diabetes research, Computational and Structural Biotechnology Journal, 15, 104-116. doi:10.1016/j.csbj.2016.12.005
Peleg, M. and Tu, S., 2006, Decision support, knowledge representation and management in medicine, Yearbook of Medical Informatics, 45(1), 72-80. doi:10.1055/s-0038-1638482

Read-around