Identifying Lung Cancer Risk Factors in the Elderly Using Deep Neural Networks: Quantitative Analysis of Web-Based Survey Data
Identifying Lung Cancer Risk Factors in the Elderly Using Deep Neural Networks: Quantitative Analysis of Web-Based Survey Data
复制标题
DOI：
10.2196/17695
复制
发表时间：
2020-03-17
影响因子：
7.4
通讯作者：
Wu, Sizhu
中科院分区：
文献类型：
--
作者：
Chen, Songjing;Wu, Sizhu
背景：肺癌是世界上最危险的恶性肿瘤之一，发病率和死亡率增长最快，尤其是老年人。近年来，随着老年人口的迅速增长，肺癌的预防和控制越来越重要，但由于肺癌的发病机制是一个涉及多种危险因素的复杂过程，因此肺癌的预防和控制变得更加复杂。目的：本研究旨在确定老年人肺癌发病的关键危险因素，并利用深度问卷定量分析这些危险因素的影响程度。学习方法。方法：基于网络调查数据，我们整合了多学科的危险因素，包括行为危险因素，疾病史因素，环境因素和人口统计学因素，然后对这些综合数据进行预处理。我们在分层的老年人群中训练了深度神经网络模型。然后，我们提取了老年人肺癌的危险因素，并使用深度神经网络模型对影响程度进行了定量分析。结果：提出的模型基于235，673名成年人定量识别了危险因素。提出的4组深度神经网络模型（年龄>= 65岁，女性>= 65岁，男性>= 65岁，以及整个人群）在识别肺癌危险因素方面取得了良好的表现，准确率从0.927（95% CI 0.223-0.525; P=.002）至0.962（95% CI 0.530-0.751; P=.002），曲线下面积范围为0.913（95% CI 0.564-0.803）至0.931（95% CI 0.499-0.593）。吸烟频率是65岁及以上男性肺癌的主要危险因素。戒烟后的时间和一生中吸烟至少100支是65岁及以上女性肺癌的主要危险因素。65岁及以上的男性在分层组中肺癌发病率最高，特别是非小细胞肺癌发病率。吸烟率下降，男性肺癌发病率下降较女性明显。结论：本研究为老年人肺癌危险因素的定量分析提供了一种新的方法。所提出的模型提供了预防肺癌的干预指标，特别是老年男性。这种方法可以作为一种风险因素识别工具，应用于其他癌症，并帮助医生做出预防癌症的决定。
Background: Lung cancer is one of the most dangerous malignant tumors, with the fastest-growing morbidity and mortality, especially in the elderly. With a rapid growth of the elderly population in recent years, lung cancer prevention and control are increasingly of fundamental importance, but are complicated by the fact that the pathogenesis of lung cancer is a complex process involving a variety of risk factors.Objective: This study aimed at identifying key risk factors of lung cancer incidence in the elderly and quantitatively analyzing these risk factors' degree of influence using a deep learning method.Methods: Based on Web-based survey data, we integrated multidisciplinary risk factors, including behavioral risk factors, disease history factors, environmental factors, and demographic factors, and then preprocessed these integrated data. We trained deep neural network models in a stratified elderly population. We then extracted risk factors of lung cancer in the elderly and conducted quantitative analyses of the degree of influence using the deep neural network models.Results: The proposed model quantitatively identified risk factors based on 235,673 adults. The proposed deep neural network models of 4 groups (age >= 65 years, women >= 65 years old, men >= 65 years old, and the whole population) achieved good performance in identifying lung cancer risk factors, with accuracy ranging from 0.927 (95% CI 0.223-0.525; P=.002) to 0.962 (95% CI 0.530-0.751; P=.002) and the area under curve ranging from 0.913 (95% CI 0.564-0.803) to 0.931(95% CI 0.499-0.593). Smoking frequency was the leading risk factor for lung cancer in men 65 years and older. Time since quitting and smoking at least 100 cigarettes in their lifetime were the main risk factors for lung cancer in women 65 years and older. Men 65 years and older had the highest lung cancer incidence among the stratified groups, particularly non-small cell lung cancer incidence. Lung cancer incidence decreased more obviously in men than in women with smoking rate decline.Conclusions: This study demonstrated a quantitative method to identify risk factors of lung cancer in the elderly. The proposed models provided intervention indicators to prevent lung cancer, especially in older men. This approach might be used as a risk factor identification tool to apply in other cancers and help physicians make decisions on cancer prevention.