摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-肿瘤学的新研究-肺癌是一篇报道的主题。根据NewsRx记者从中国成都发来的新闻报道,研究表明:“异时性第二原发肺癌(MSPLC)并不罕见,但研究很少。我们的目的是比较不同手术策略和放疗治疗MSPLC的真实生存结果。”本回顾性研究分析了1988年和2012年MSPLC B患者的监测、流行病学、流行病学和流行病学等方面的资料。结果:2451例MSPLC患者分为放疗864例(35.3%),手术759例(31%),手术加放疗89例(3.6%),手术加放疗89例(3.6%)。739例(30.2%)未予治疗。放疗和手术各470对，手术组生存率明显高于放疗组(P<0.001)和未治疗组(563对;P<0.001)。进一步分析显示楔形切除(85对;P=.004)和肺叶切除(71对;P=.002)在MSPLC患者的总生存率方面均优于放疗。机器学习模型(极端梯度提升、随机森林分类器)。基于曲线下面积(AUC)值，自适应boosting显示出较高的预测性能。最小绝对收缩和选择算子(LASSO)回归分析确定了9个影响癌症特异性生存率的重要变量，强调了手术在1至10年内的持续影响。这些变量包括确诊年龄、性别、诊断年份、初发原发性肺癌的放射治疗(IPL C)、原发部位、组织学、手术、化疗，风险分析强调女性MPSLC患者的死亡率较低(Ha zard比值[HR]=0.79,95%CI 0.71-0.87)和最近的IPLC诊断(HR=0.79,95%CI 0.73-0.85)，而IPLC的放疗增加了死亡率(HR=1.31,95%CI 1.16-1.50)。95%可信区间0.21-0.31)。这些发现为影响累积癌症特异性死亡率的因素提供了有价值的见解。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Oncology - Lung Cancer is the subject of a report. According to news reporting from Chengdu, People's Republic of China, by NewsRx journalists, research stated, "Metachronous second primary lung cancer (MSPLC) is not that rare but is seldom studied. We aim to co mpare real-world survival outcomes between different surgery strategies and radi otherapy for MSPLC." The news correspondents obtained a quote from the research from Sichuan Universi ty, "This retrospective study analyzed data collected from patients with MSPLC b etween 1988 and 2012 in the Surveillance, Epidemiology, and End Results (SEER) d atabase. Propensity score matching (PSM) analyses and machine learning were perf ormed to compare variables between patients with MSPLC. Survival curves were plo tted using the Kaplan-Meier method and were compared using log-rank tests. A tot al of 2451 MSPLC patients were categorized into the following treatment groups: 864 (35.3%) received radiotherapy, 759 (31 %) underwent surgery, 89 (3.6%) had surgery plus radiotherapy, and 739 (30.2% ) had neither treatment. After PSM, 470 pairs each for radiotherapy and surgery were generated. The surgery group had significantly better survival than the rad iotherapy group (P <.001) and the untreated group (563 pair s; P <.001). Further analysis revealed that both wedge resec tion (85 pairs; P=.004) and lobectomy (71 pairs; P=.002) outperformed radiothera py in overall survival for MSPLC patients. Machine learning models (extreme grad ient boosting, random forest classifier, adaptive boosting) demonstrated high pr edictive performance based on area under the curve (AUC) values. Least absolute shrinkage and selection operator (LASSO) regression analysis identified 9 signif icant variables impacting cancer-specific survival, emphasizing surgery's consis tent influence across 1 year to 10 years. These variables encompassed age at dia gnosis, sex, year of diagnosis, radiotherapy of initial primary lung cancer (IPL C), primary site, histology, surgery, chemotherapy, and radiotherapy of MPSLC. C ompeting risk analysis highlighted lower mortality for female MPSLC patients (ha zard ratio [HR]=0.79, 95% CI 0.71-0.87) and recent IPLC diagnoses (HR=0.79, 95 % CI 0.73-0.85), while radiotherapy for IPLC increased mortality (HR=1.31, 95% CI 1.16-1.50). Surgery alone had the lowest cancer-specific mortality (HR=0.83, 95% CI 0.81-0.85), with sublevel resection having the lowest mortality rate among th e surgical approaches (HR=0.26, 95% CI 0.21-0.31). The findings pr ovide valuable insights into the factors that influence cumulative cancer-specif ic mortality."
NETL
NSTL