口腔医学研究

口腔医学研究 ›› 2021, Vol. 37 ›› Issue (7): 646-650.DOI: 10.13701/j.cnki.kqyxyj.2021.07.015

• 口腔肿瘤与口腔影像学研究 • 上一篇    下一篇

结合增强CT影像的腮腺肿瘤良恶性预测列线图的建立与验证

闫庆涵1, 王佳俐1, 车银富2, 于涛2, 陶峰2, 陈李鑫1, 何等旗2*   

  1. 1.兰州大学口腔医学院 甘肃 兰州 730000;
    2.兰州大学第一医院 甘肃 兰州 730000
  • 收稿日期:2020-12-15 出版日期:2021-07-28 发布日期:2021-07-13
  • 通讯作者: * 何等旗,E-mail:hedengqi1975@163.com
  • 作者简介:闫庆涵(1994~ ),男,河南郑州人,硕士在读,研究方向:腮腺区肿物的术前诊断。
  • 基金资助:
    兰州市科技计划项目(编号:2018-3-55)

Development and Validation of Nomogram for Benign and Malignant Parotid Tumors Combined with Enhanced CT Image Features

YAN Qinghan1, WANG Jiali1, CHE Yinfu2, YU Tao2, TAO Feng2, CHEN Lixin1, HE Dengqi2*   

  1. 1. Stomatological Hospital of Lanzhou University, Lanzhou 730000, China;
    2. The First Hospital of Lanzhou University, Lanzhou 730000, China
  • Received:2020-12-15 Online:2021-07-28 Published:2021-07-13

PDF (PC)

342

摘要： 目的:分析多项检查指标,建立腮腺肿瘤良恶性鉴别的预测模型,以期为临床鉴别提供帮助,为腮腺肿瘤患者及时施行正确的手术治疗提供依据。方法:回顾性分析2013年3月~2019年3月在兰州大学第一医院行腮腺肿瘤切除术的200例患者资料(A组),通过logistic回归分析筛选出腮腺肿瘤良恶性鉴别的独立影响因素,建立数学预测模型,另收集2019年4月~2020年9月经手术切除且明确病理诊断的腮腺肿瘤患者资料42例(B组)进行验证。结果:通过对A组进行多因素logistic回归分析,建立数学预测模型如下:Y=ex/(1+ex),X=-0.18347+(-1.29435×肿瘤形态规则与否)+(-1.44877×肿瘤边界清楚与否)+(4.34121×周围组织受累与否),e是自然对数。利用B组数据验证该模型的有效性,结果显示敏感度为1.00,特异度为93.4%,准确率为95.2%。结论:联合肿瘤形态规则与否、肿瘤边界清楚与否及周围组织受累与否等3个指标,建立的Logistic回归预测模型可以帮助临床医生诊断腮腺肿瘤良恶性。

关键词: 腮腺肿瘤, 诊断, Logistic回归, 预测模型

Abstract: Objective: To develop the prediction models for begin and malignant parotid neoplasms by analyzing multiple examination indexes. Methods: A retrospective analysis was performed on 242 patients with parotid neoplasms who were treated with parotid neoplasms resection in the First Hospital of Lanzhou University from March 2013 to March 2019(group A). The independent predictors of malignancy in parotid tumor patients were screened out through logistic regression analysis, then a prediction model was built. Other 42 parotid neoplasm patients(group B)with definite pathological diagnosis from April 2019 to September 2020 were used to validate this model. Results: Through multivariate logistic regression analysis on group A, the prediction model was built as follows: Y=ex/ (1+ex), X=-0.18347+ (-1.29435×tumor shape) + (-1.44877×tumor boundary) + (4.34121×surrounding tissues), in which “e” was natural logarithm. The validity of this model was validated by data from group B, and the results showed that the accuracy was 95.2%, the sensitivity was 1.00, and the specificity of the model was 93.4%. Conclusion: The establishment of logistic regression prediction model can help clinicians diagnose benign and malignant parotid tumors by combining the presence or absence of regular tumor shape, clear tumor boundaries, and involvement of surrounding tissues.

Key words: parotid neoplasms, differential diagnosis, Logistic regression, prediction model