基于大数据的肺癌合并COPD患者的临床特征

Clinical characteristics of lung cancer patients with COPD based on big data

慢性阻塞性肺疾病(chronic obstructive pulmonary disease,COPD)和肺癌作为常见的呼吸系统疾病,共同的特点是高发病率及高病死率。而COPD与吸烟量也是肺癌发生的重要独立危险因素,两者既有部分不同的发病机制,也具有一些共同的发病机制。与非COPD患者相比,COPD患者罹患肺癌的概率可增加2~4倍。研究发现,COPD合并肺癌的风险增加与年龄较大、较低的体质量指数(body mass index,BMI)、更大的吸烟指数及胸部CT表现为肺气肿等因素有关。随着大数据及人工智能(artificial intelligence,AI)广泛应用于临床医学研究中,卷积神经网络(convolutional neural network,CNN)作为AI的一种,因其学习能力优越而被用于量化分析COPD患者的胸部CT,它较CT视觉评分可以更有效地评估COPD。使用大数据建立COPD患者更精确的肺癌风险模型,可以降低早期肺癌的病死率。

Chronic obstructive pulmonary disease(COPD)and lung cancer as common respiratory diseases are characterized by high incidence and high mortality.COPD and smoking is an important independent risk factor for lung cancer.Both of them have partly different pathogenesis,but also share some common pathogenesis.Patients with COPD are more than two-fold and up to four-fold more likely to develop lung cancer than those without COPD.Some foreign studies have found that the increased risk of lung cancer is associated with older age,lower body mass index(BMI),higher smoking index,and emphysema on computed tomography(CT).With the wide application of big data and artificial intelligence(AI)in data feature extraction and analysis in clinical medical research,convolutional neural network(CNN)as a kind of AI,has been used for quantitative analysis of chest CT of COPD patients due to its superior learning ability.It is more effective than CT visual scoring in evaluating COPD.The use of big data to establish a more accurate lung cancer risk model for COPD patients can reduce the death rate of early lung cancer.