SONG Ya'nan, JIN Xinye, ZHANG Ying, CHEN Kang, YING Jun, XUE Wanguo, MU Yiming. Intelligent classification of hypoglycemia treatment plan for patients with type 2 diabetes based on ensemble learning[J]. ACADEMIC JOURNAL OF CHINESE PLA MEDICAL SCHOOL, 2019, 40(8): 719-724. DOI: 10.3969/j.issn.2095-5227.2019.08.004
Citation: SONG Ya'nan, JIN Xinye, ZHANG Ying, CHEN Kang, YING Jun, XUE Wanguo, MU Yiming. Intelligent classification of hypoglycemia treatment plan for patients with type 2 diabetes based on ensemble learning[J]. ACADEMIC JOURNAL OF CHINESE PLA MEDICAL SCHOOL, 2019, 40(8): 719-724. DOI: 10.3969/j.issn.2095-5227.2019.08.004

Intelligent classification of hypoglycemia treatment plan for patients with type 2 diabetes based on ensemble learning

Funds: Supported by Beijing Municipal Science and Technology Commission (D141107005314004)
More Information
  •   Objective  To apply Adaboost in the determination of hypoglycemia treatment plan in patients with type 2 diabetes.
      Methods  Clinical data about 3 005 patients with type 2 diabetes hospitalized in the first medical center of Chinese PLA General Hospital from 2013 to 2017 were collected, including medical prescriptions, biochemical testing results, clinical manifestations, demographic characteristics, etc. Adaboost algorithm was used to establish the machine learning model and classify the treatment plan of the patients, with 1 697 cases as training set and 1 308 cases as testing set randomly, and then accuracy and Kappa coefficient of the model were computed.
      Results  The prediction accuracy of the model by Adaboost was 64.2% and the Kappa coefficient was 0.36. After analyzing the model established by Adaboost, we found that UCr, HbA1c, CK-MB, FBG, etc. were significantly related to the treatment plan selecting.
      Conclusion  To some extent, Adaboost algorithm is feasible and accurate in predicting hypoglycemia treatment plan.
  • [1]
    王丽敏. 2型糖尿病治疗现状调查分析[D]. 郑州: 郑州大学, 2012.
    [2]
    Donsa K, Spat S, Beck P, et al. Towards Personalization of Diabetes Therapy Using Computerized Decision Support and Machine Learning: Some Open Problems and Challenges[M]//Smart Health. Springer International Publishing, 2015: 237-260.
    [3]
    Kasemthaweesab P, Kurutach W. Association analysis of diabetes mellitus(DM) with complication states based on association rules[C]. Conference: Industrial Electronics and Applications, 2012.
    [4]
    Li P, Chen K, Nie Y, et al. Association of obesity with glucose, blood pressure, and lipid goals attainment in patients with concomitant diabetes and hypertension[J]. Curr Med Res Opin, 2015, 31(9): 1623-1631. doi: 10.1185/03007995.2015.1058770
    [5]
    Jelinek HF, Yatsko A, Stranieri A, et al. Novel data mining techniques for incomplete clinical data in diabetes management[J]. British Journal of Applied Science & Technology, 2014, 4(33): 4591-460. http://www.researchgate.net/publication/265686170_Novel_Data_Mining_Techniques_for_Incomplete_Clinical_Data_in_Diabetes_Management
    [6]
    Habibi S, Ahmadi M, Alizadeh S. Type 2 Diabetes Mellitus Screening and Risk Factors Using Decision Tree: Results of Data Mining[J]. Glob J Health Sci, 2015, 7(5): 304-310. http://europepmc.org/articles/PMC4803907
    [7]
    Gregori D, Petrinco M, Bo S, et al. Using data mining techniques in monitoring diabetes care. The simpler the better?[J]. J Med Syst, 2011, 35(2): 277-281. doi: 10.1007/s10916-009-9363-9
    [8]
    Liu H, Xie G, Mei J, et al. An efficacy driven approach for medication recommendation in type 2 diabetes treatment using data mining techniques[J]. Stud Health Technol Inform, 2013, 192: 1071. http://www.ncbi.nlm.nih.gov/pubmed/23978590
    [9]
    曹莹, 苗启广, 刘家辰, 等. AdaBoost算法研究进展与展望[J]. 自动化学报, 2013, 39(6): 745-758. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201306008.htm
    [10]
    代晓彤, 谢学勤, 康晓平, 等. 基于AdaBoost和分类树的北京市高血压患者就诊机构选择的影响因素分析[J]. 中国卫生统计, 2017, 34(1): 23-26. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGWT201701006.htm
    [11]
    王莉莉, 付忠良, 陶攀, 等. 基于主动学习不平衡多分类AdaBoost算法的心脏病分类[J]. 计算机应用, 2017, 37(7): 1994-1998. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201707031.htm
    [12]
    古万荣, 谢贤芬, 何亦琛, 等. 基于AdaBoost算法的药物—靶向蛋白作用预测算法[J]. 生物医学工程学杂志, 2018, 35(6): 113-120. http://www.cnki.com.cn/Article/CJFDTotal-SWGC201806016.htm
    [13]
    中华医学会糖尿病学分会. 中国2型糖尿病防治指南(2017年版)[J]. 中国实用内科杂志, 2018, 38(4): 292-344. https://www.cnki.com.cn/Article/CJFDTOTAL-SYNK201804009.htm
    [14]
    Bo W, Ai H, Chang H, et al. Fast rotation invariant multi-view face detection based on real Adaboost[C]. IEEE International Conference on Automatic Face & Gesture Recognition, 2004.
    [15]
    Yan G, Yu M, Yu Y, et al. Real-time vehicle detection using histograms of oriented gradients and AdaBoost classification[J]. Optik-International Journal for Light and Electron Optics, 2016, 127(19): 7941-7951. doi: 10.1016/j.ijleo.2016.05.092
    [16]
    Nayak DR, Dash R, Majhi B. Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests[J]. Neurocomputing, 2015, 177(C): 188-197. doi: 10.1016/j.neucom.2015.11.034
    [17]
    Islam A, Reza S, Iftekharuddin K. Multifractal texture estimation for detection and segmentation of brain tumors[J]. IEEE Trans Biomed Eng, 2013, 60(11): 3204-3215. doi: 10.1109/TBME.2013.2271383
    [18]
    Fu Q, Jing B, He P, et al. Fault Feature Selection and Diagnosis of Rolling Bearings Based on EEMD and Optimized Elman_AdaBoost Algorithm[J]. IEEE Sensors Journal, 2018, 18(12): 5024-5034. doi: 10.1109/JSEN.2018.2830109
    [19]
    郭立新. 老年糖尿病降糖药物选择及安全性评估[J]. 中国实用内科杂志, 2008, 28(4): 243-245. doi: 10.3969/j.issn.1005-2194.2008.04.002
    [20]
    蔡林江, 沈菊. 二甲双胍和胰岛素联合用药治疗和预防2型糖尿病并发心血管疾病的临床疗效[J]. 中国医疗前沿, 2012, 7(16): 17-18. https://www.cnki.com.cn/Article/CJFDTOTAL-YLQY201216012.htm

Catalog

    Article Metrics

    Article views (521) PDF downloads (11) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return