Research on Noninvasive Risk Evaluation of Diabetes Mellitus Based on Neural Network Pattern Recognition
LI Fei1, WANG Yi-kun1, 2, ZHU Ling1, 2, ZHANG Yuan-zhi1, JI Min1, ZHANG Long1, LIU Yong1, 2*, WANG An1
1. Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China 2. Wanjiang Center for Development of Emerging Industrial Technology, Tongling 244061, China
Abstract：Advanced glycation end products (AGEs) are highly associated with hyperglycemia in human skin tissue, and they also have the autofluorescence characteristic. A self-developed optical noninvasive detection device was used to measure the autofluorescence in human skin tissue, and then a neural network pattern recognition model was used to assess the risk of diabetes mellitus of the subject under survey. After the fluorescence spectra were acquired and processed with principal component analysis, four of the leading principal components were chosen to represent a whole spectrum. The established neural network pattern recognition model has 4 input nodes, 6 hidden nodes and 1 output node. A dataset consisting of 487 cases collected in Anhui Provincial Hospital was used to train the model. Seventy percent cases were used as the training set, 15% as the validation set and 15% as the test set. The model can output subject’s risk of diabetes mellitus, or a dichotomous judgment. Receiver operating characteristic curve can be drawn with the area under curve of 0.81, with standard error of 0.02. When using 0.5 as the threshold between diabetes mellitus and non-diabetes mellitus, the sensitivity and specificity of this model is 72.4% and 77.6% respectively, and the overall accuracy is 74.9%. The method using human skin autofluorescence spectrum combined with neural network pattern recognition model is proposed for the first time, and the results show that this method has a better screening effect compared with currently used fasting plasma glucose and HbA1c.
Key words：Medical optics;Neural network;Pattern recognition;Advanced glycation end products;Fluorescence spectrum;Diabetes mellitus
[1] YANG Wen-ying, LU Ju-ming, WENG Jian-ping, et al. New England Journal of Medicine, 2010, 362(12): 1090. [2] Chinese Diabetes Society(中华医学会糖尿病学分会). China Guideline for Type 2 Diabetes(中国2型糖尿病防治指南). Beijing: Peking University Medical Press(北京大学医学出版社), 2011. [3] GUO Li-xin(郭立新). Chinese Journal of Diabetes Mellitus(中华糖尿病杂志), 2013, 5(5): 268. [4] Wang Yikun, Zhu Ling, Zhang Long, et al. Journal of Applied Spectroscopy, 2012, 79(3): 431. [5] YU Dong-ni, GUO Li-xin(于冬妮，郭立新). Chinese Journal of Practical Internal Medicine(中国实用内科杂志), 2009, 29(9): 805. [6] ZHANG Long, ZHANG Yuan-zhi, WANG Yi-kun, et al(张 龙，张元志，王贻坤，等). Acta Laser Biology Sinica(激光生物学报), 2012, 21(1): 65. [7] John D Maynard, Catriona M Nguyen, Mark Rohrscheib, et al. Diabetes Care, 2007, 30(5): 1120. [8] Tavintharan S, Chew L S W, Heng D M K. Annals of the Academy of Medicine, Singapore, 2000, 29(2): 213. [9] Stephen Colagiuri, Zafirul Hussain, Paul Zimmet, et al. Diabetes Care, 2004, 27(2): 367. [10] ZHU Ling, WANG Yi-kun, YE Shan-dong, et al(朱 灵，王贻坤，叶山东，等). Chinese Journal of Diabetes Mellitus(中华糖尿病杂志), 2013, 5(5): 293.
