Background: Mathematical predictive model is an effective method for preliminarily identifying the malignant pulmonary nodules. As the epidemiological trend of lung cancer changes, the detection rate of ground-glass-opacity (GGO) like early stage lung cancer is increasing rapidly, timely and proper clinical management can effectively improve the patients' prognosis. Our study aims to establish a novel predictive model of malignancy for non-solid pulmonary nodules, which would provide an objective evidence for invasive procedure and avoid unnecessary operation and the consequences.
Methods: We retrospectively analyzed the basic demographics, serum tumor markers and imaging features of 362 cases of non-solid pulmonary nodule from January 2013 to April 2018. All nodules received biopsy or surgical resection, and got pathological diagnosis. Cases were randomly divided into two groups. The modeling group was used for univariate analysis and logistic regression to determine independent risk factors and establish the predictive model. Data of the validation group was used to validate the predictive value and make a comparison with other models.
Results: Of the 362 cases with non-solid pulmonary nodule, 313 (86.5%) cases were diagnosed as AAH/AIS, MIA or invasive adenocarcinoma, 49 cases were diagnosed as benign lesions. Age, serum tumor markers CEA and Cyfra21-1, consolidation tumor ratio value, lobulation and calcification were identified as independent risk factors. The AUC value of the ROC curve was 0.894, the predictive sensitivity and specificity were 87.6%, 69.7%, the positive and negative predictive value were 94.8%, 46.9%. The validated predictive value is significantly better than that of the VA, Brock and GMUFH models.
Conclusions: Proved with high predictive sensitivity and positive predictive value, this novel model could help enable preliminarily screening of "high-risk" non-solid pulmonary nodules before biopsy or surgical excision, and minimize unnecessary invasive procedure. This model achieved preferable predictive value, might have great potential for clinical application.
【中文题目：新型非实性肺小结节恶性概率预测模型 的构建与验证】 【中文摘要：背景与目的 数学预测模型是判断肺小结节恶性概率的有效工具。伴随肺癌流行病学趋势的改变，以非实性肺小结节为影像学表现的早期肺癌检出率逐年升高，准确鉴别并及时治疗干预可有效改善预后。本研究旨在专门针对非实性肺小结节构建新型恶性概率预测模型，为有创诊疗提供客观依据，并尽量避免不必要的侵袭性操作及其可能造成的严重后果。方法 回顾性分析自2013年1月-2018年4月，单中心经穿刺活检或手术切除获得明确病理诊断的362例非实性肺小结节病例资料，包括临床基本资料、血清肿瘤标记物和影像学特征等。病例分两组，应用建模组数据做单因素分析和二分类Logistic回归，判定独立危险因素，建立预测模型；应用验证组数据验证模型预测价值并与其他模型比较。结果 362例非实性肺小结节病例中，313例（86.5%）确诊为非典型腺瘤样增生（atypical adenomatous hyperplasia, AAH）/原位腺癌（adenocarcinoma in situ, AIS）、微浸润腺癌（minimally invasive adenocarcinoma, MIA）或浸润性腺癌，49例诊断为良性病变。年龄、血清肿瘤标记物癌胚抗原（carcino-embryonic antigen, CEA）和Cyfra21-1、肿瘤实性成分比值（consolidation tumor ratio, CTR）、分叶征和钙化被确定为独立危险因素。模型受试者工作曲线下面积为0.894。预测灵敏度为87.6%，特异度为69.7%，阳性预测94.8%，阴性预测值为46.9%。经验证模型预测价值显著优于VA、Brock和GMUFH模型。结论 本研究建立的新型非实性肺小结节恶性概率预测模型具备较高的诊断灵敏度和阳性预测值。经初步验证，其预测价值优于传统模型。未来经大样本验证后，可用作高危非实性肺小结节活检或手术切除前的初筛方法，具备临床应用价值。】 【中文关键词：肺小结节；肺肿瘤；预测模型；恶性概率】.
Keywords: Lung neoplasms; Predictive model; Probability of malignancy; Pulmonary nodule.