肺癌（LC）是一种多因素疾病，遗传易感性的作用变得越来越重要。我们的目标是利用人工智能 (AI) 分析基于癌症家族史 (FHC) 的 LC 患者之间的差异。从 2016 年 8 月至 2020 年 6 月的临床信息从胸部肿瘤登记处 (TTR) 获得，该数据库是由西班牙肺癌小组。除了描述性统计分析外，还进行了人工智能辅助分析。德国技术信息图书馆支持合并电子病历和 TTR 数据库中的数据。使用知识图、统一模式以及描述性和预测性分析报告人工智能辅助分析的结果。分析分两个阶段进行：第一阶段是常规统计分析，包括 5,806 名 FHC 患者中的 11,684 名患者。全球人群中，患有 FHC 的患者的中位总生存期 (OS) 为 23 个月（CI 95%：21.39-24.61），而没有 FHC 的患者 (NFHC) 的中位总生存期为 21 个月（CI 95%：19.53-22.48），p < 0.001。第二次人工智能辅助分析包括 939 名 FHC 患者中的 5,788 名。 58.48% 患有 FHC 的女性患有 LC。 9.53% 的患者存在 EGFR 或 HER2 突变或 ALK 易位，且至少一名亲属患有癌症。 LC 家族史与吸烟相关 LC 的风险增加相关。有 LC 家族史的非吸烟者更有可能在 NSCLC 中出现 EGFR 突变。在贝叶斯网络分析中，55% 有 LC 家族史且从不吸烟的患者有 EGFR 突变。在我们的人群中，女性和年轻患者中 FHC 患者的 LC 发生率较高。 FHC 是 LC 发展的风险因素和预测因子，尤其是对于 50 岁以下的人。这些结果得到了传统统计和人工智能辅助分析的证实。版权所有 © 2024。由 Elsevier B.V. 出版。

Lung Cancer (LC) is a multifactorial disease for which the role of genetic susceptibility has become increasingly relevant. Our aim was to use artificial intelligence (AI) to analyze differences between patients with LC based on family history of cancer (FHC).From August 2016 to June 2020 clinical information was obtained from Thoracic Tumors Registry (TTR), a nationwide database sponsored by the Spanish Lung Cancer Group. In addition to descriptive statistical analysis, an AI-assisted analysis was performed. The German Technical Information Library supported the merging of data from the electronic medical records and database of the TTR. The results of the AI-assisted analysis were reported using Knowledge Graph, Unified Schema and descriptive and predictive analyses.Analyses were performed in two phases: first, conventional statistical analysis including 11,684 patients of those 5,806 had FHC. Median overall survival (OS) for the global population was 23 months (CI 95 %: 21.39-24.61) in patients with FHC versus 21 months (CI 95 %: 19.53-22.48) in patients without FHC (NFHC), p < 0.001. The second AI-assisted analysis included 5,788 patients of those 939 had FHC. 58.48 % of women with FHC had LC. 9.53 % of patients had an EGFR or HER2 mutation or ALK translocation and at least one relative with cancer. A family history of LC was associated with an increased risk of smoking-related LC. Non-smokers with a family history of LC were more likely to have an EGFR mutation in NSCLC. In Bayesian network analysis, 55 % of patients with a family history of LC and never-smokers had an EGFR mutation.In our population, the incidence of LC in patients with a FHC is higher in women and younger patients. FHC is a risk factor and predictor of LC development, especially in people ≤ 50 years. These results were confirmed by conventional statistics and AI-assisted analysis.Copyright © 2024. Published by Elsevier B.V.