Share：
Share this content in WeChat
X
[Chinese][PDF]115295
• Original Article •
Study on the method of establishing clinical evaluation model of MRI effect based on Logistic regression
ZHENG Jia  LI Qi  MENG Yan  YU Fu-rao  GAO Yue  LI Le-yi  LIANG Yi-dan  CHEN Zhi-an  FU Xi-hu  ZHAO Gu-yue  PAN Shi-nong  ZHENG Li-qiang 

DOI:10.12015/issn.1674-8034.2018.02.009.


[Abstract] Objective: MRI clinical application is extensive, but there is no corresponding clinical evaluation criteria. In this study, a set of standardized clinical efficacy evaluation criteria was established by Logistic regression model to promote the healthy development of MR industry.Materials and Methods: We collected 165 clinical MRI and ten factors influencing the T2 lipid suppression sequence in lumbar vertebrae were collected of each image. The 10 variables of MRI mass were analyzed and the MRI quality was evaluated as the dependent variable. Logistic regression was used to scientifically model and evaluate the clinical effect of MRI. We used the H-L χ2 test and the AUC (the area under the receiver-operating characteristic curve) value to test the calibration and discrimination of the model.Results: The model shows that when the total score was less than 3 points, the highest probability of good MRI was 0.02, that MRI quality was poor, didn't be used in clinical diagnosis, it was recommended that patients need to re-shoot MRI. When the total score of 5—6 points, the corresponding probability was 0.22—0.52, that the general quality of MRI, barely applied to clinical diagnosis. When the total score of 8—9, that the MRI quality was very good, can be very accurate for clinical diagnosis. The H-L value was 1.457 (P=0.962). The AUC value was 0.878 (95% CI: 0.814-0.941).Conclusions: Based on Logistic regression, the evaluation model has good calibration ability and distinguishing ability, which can be used in clinical practice to establish a standardized standard of clinical evaluation of MRI.
[Keywords] Logistic regression；Evaluation model；Magnetic resonance imaging；Clinical evaluation

ZHENG Jia Department of Clinical Epidemiology, Shengjing Hospital of China Medical University, Shenyang 110004, China

LI Qi Department of Radiology, Liaoning Provincial Electric Power Hospital, Shenyang 110000, China

MENG Yan Department of Radiology, Shengjing Hospital of China Medical University, Shenyang 110004, China

YU Fu-rao Department of Radiology, Shengjing Hospital of China Medical University, Shenyang 110004, China

GAO Yue Department of Radiology, Shengjing Hospital of China Medical University, Shenyang 110004, China

LI Le-yi Department of Radiology, Jinqiu Hospital of Liaoning Province, Shenyang 110004, China

LIANG Yi-dan Department of Radiology, Jinqiu Hospital of Liaoning Province, Shenyang 110004, China

CHEN Zhi-an Department of Radiology, Shengjing Hospital of China Medical University, Shenyang 110004, China

FU Xi-hu Department of Radiology, Shengjing Hospital of China Medical University, Shenyang 110004, China

ZHAO Gu-yue Department of Radiology, Shengjing Hospital of China Medical University, Shenyang 110004, China

PAN Shi-nong* Department of Radiology, Shengjing Hospital of China Medical University, Shenyang 110004, China

ZHENG Li-qiang* Library of Shengjing Hospital of China Medical University, Shenyang 110004, China

*Corresponding to: Zheng LQ, E-mail: zhenglq@sj-hospital.org Pan SN, E-mail: 18940256901 @vip.163.com

Conflicts of interest   None.

ACKNOWLEDGMENTS  This work was part of National Key Research and Development Program Digital Clinics Research and Development Project Fund Project No.2016YFC0107102
Received  2017-10-09
Accepted  2017-11-24
DOI: 10.12015/issn.1674-8034.2018.02.009
DOI:10.12015/issn.1674-8034.2018.02.009.

[1]
Safety EPOM, Kanal E, Barkovich AJ, et al. ACR guidance document on MR safe practices: 2013. J Magn Reson Imaging, 2013, 37(3): 501-530.
[2]
Zheng LQ. Validation and construction a hypertension risk prediction model in rural areas of fuxin county with the high incidence of hypertension：results from Liaoning province. Shenyang: China Medical University, 2014.郑黎强．辽宁省阜新县农村社会环境高血压高发区高血压发病风险预测模型的验证与建立．沈阳：中国医科大学, 2014.
[3]
Fang JQ. Health statistics. Beijing: People's Health Publishing House, 2012: 390.方积乾．卫生统计学．北京：人民卫生出版社, 2012: 390.
[4]
Yuan HS, Xu WJ. Guidance on bone muscle system imaging. Beijing: Tsinghua University Press, 2016.袁慧书，徐文坚．骨肌系统影像检查指南．北京：清华大学出版社, 2016.
[5]
Sullivan LM, Massaro JM, Sr DR. Presentation of multivariate data for clinical use: The Framingham Study risk score functions. Statistics in Medicine, 2004, 23(10): 1631-1660.
[6]
Wu Y, Liu X, Li X, et al. Estimation of 10-year risk of fatal and nonfatal ischemic cardiovascular diseases in Chinese adults. Circulation, 2006, 114(21): 2217.
[7]
Cox MAA, Plackett RL. A note on a goodness of fit test for the logistic regression model. Biometrika, 1980, 67(1): 250-251.
[8]
Zheng LQ, Zhang R. Research progress on evaluation method of risk degree of disease risk prediction model. Chin J Health Statis, 2015, 32(3): 544-546.郑黎强，张蕊．疾病发病风险预测模型拟合度评价方法的研究进展．中国卫生统计, 2015, 32(3): 544-546.
[9]
Hanley JA, Mcneil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 1982, 143(1): 29.
[10]
Zhang WT, Dong W. SPSS statistical analysis advanced course. Beijing: Higher Education Press, 2013.张文彤，董伟. SPSS统计分析高级教程．北京：高等教育出版社, 2013.
[11]
Yu HM, Luo YH, Sa J, et al. Group correlation coefficient and software implementation. Chin J Health Statis, 2011, 28(5): 497-500.余红梅，罗艳虹，萨建，等．组内相关系数及其软件实现．中国卫生统计, 2011, 28(5): 497-500.
[12]
He GJ, Zhao DD, Wei Y. New journey of domestic medical magnetic resonance device: visit to the industry leaders of domestic magnetic resonance in RSNA 2014. Chin J Magn Reson Imag, 2015, 6(6): 405-410.贺光军，赵丹丹，魏燕．国产医用磁共振设备新征程——访参加RSNA 2014的国内磁共振产业领袖．磁共振成像, 2015, 6(6): 405-410.

PREV The shortcomings of conventional MR images in the diagnosis of lumbar disc herniation: comparative study with the results of surgical operation
NEXT Preliminary research of DKI parameters in predicting the prognosis of brain acute stroke lesions
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn