Lung cancer is one of the tumors with the highest incidence rate and mortality rate in the world. It is also the malignant tumor with the fastest growing number of patients, which seriously threatens human life. How to improve the accuracy of diagnosis and treatment of lung cancer and the survival prognosis is particularly important. Machine learning is a multi-disciplinary interdisciplinary specialty, covering the knowledge of probability theory, statistics, approximate theory and complex algorithm. It uses computer as a tool and is committed to simulating human learning methods, and divides the existing content into knowledge structures to effectively improve learning efficiency and being able to integrate computer science and statistics into medical problems. Through the introduction of algorithm to absorb the input data, and the application of computer analysis to predict the output value within the acceptable accuracy range, identify the patterns and trends in the data, and finally learn from previous experience, the development of this technology brings a new direction for the diagnosis and treatment of lung cancer. This article will review the performance and application prospects of different types of machine learning algorithms in the clinical diagnosis and survival prognosis analysis of lung cancer.
Objective To investigate the tumor suppressor genes of phlegm DNA in smokers, and analyze the correlation between methylation level of tumor suppressor gene promoter and chronic mucus hypersecretion (CMH). Methods The study recruited the patients who were admitted in the respiratory department during 2013-2016 in this hospital, including 700 cases of urban smokers and 380 cases of rural smokers. Eleven genes commonly silenced by promoter methylation in lung cancer and associated with cancer risk were selected. Methylation specific PCR (MSP) was used in the sputum sample of 700 individuals in the urban smokers cohort. Replication was performed in 380 individuals from the rural smokers cohort. Results CMH was significantly associated with an overall increased number of methylated genes, with SULF2 methylation demonstrating the most consistent association. The association between SULF2 methylation and CMH was significantly increased in males but not in females both in the urban and rural groups (OR=2.73, 95%CI 1.53-4.93, P=0.001; OR=2.96, 95%CI 1.47-5.94, P=0.002, respectively). Furthermore, the association between methylation and CMH was more obvious among 139 male former smokers with persistent CMH compared with current smokers (SULF2, OR=3.64, 95%CI 1.57-8.35, P=0.002). Conclusion These findings demonstrate that especially male former smokers with persistent CMH have markedly increased promoter methylation of lung cancer risk genes and potentially could be at increased risk for lung cancer.
ObjectiveTo systematically review the association between inhaled corticosteroids (ICS) and the risk of lung cancer in patients with chronic obstructive pulmonary disease (COPD). MethodsPubMed, EMbase, Web of Science, Cochrane Library, CNKI, WanFang Data and VIP databases were electronically searched to collect cohort studies on the risk of lung cancer in COPD patients using ICS from inception to August 15, 2022. Two reviewers independently screened the literature, extracted data, and evaluated the risk of bias of the included studies. Meta-analysis was then performed by using RevMan 5.4 software. ResultsA total of 8 cohort studies involving 1 184 238 patients were included. The results of meta-analysis showed that ICS use decreased risk of lung cancer in COPD patients (HR=0.68, 95%CI 0.62 to 0.75, P<0.01). The dose of ICS was an influencing factor for the risk of lung cancer in COPD patients and a large dose of ICS could significantly reduce the risk. ConclusionCurrent evidence shows that the use of ICS can reduce the risk of lung cancer in patients with COPD, especially in high-dose patients. Due to the limited quality and quantity of the included studies, more high quality studies are needed to verify the above conclusion.
Lung cancers are highly heterogeneous and resistant to available therapeutic agents, with a five-year survival rate of less than 15%. Despite significant advances in our knowledge of the genetic alterations and aberrations in lung cancer, it has been difficult to determine the basis of lung cancer's heterogeneity and drug resistance. Cancer stem cell model has attracted a significant amount of attention in recent years as a viable explanation for the heterogeneity, drug resistance, dormancy, recurrence and metastasis of various tumors. At the same time, cancer stem cells have been relatively less characterized in lung cancers. This review summarizes the current understanding of lung cancer stem cells, including their molecular features and signaling pathways that drive their stemness. This review also discusses the prognosis of lung cancer and its relationship with lung cancer stem cell, in an effort to eradicate these cells to combat lung cancer.
Objective To summarize the diagnosis and treatment of synchronous multiple primary malignant tumors in lung. Methods The clinical and pathological data of 5 cases with intrapulmonary synchronous multiple primary cancer, who were diagnosed in recent 10 years in Xinhua Hospital, were retrospectively analyzed. Results The incidence of intrapulmonary synchronous multiple primary cancer was 0. 21%( 5 /2380) in all lung cancer cases diagnosed in respiratory department of Xinhua Hospital. There were 4 males and 1 female, with the average age of 60. 2 years old. Five patients were all treated with surgical operation. Four patients with bilateral synchronous multiple primary lung cancer underwent staging operation treatment( larger lesions on one side of lung underwent conventional thoraceotomy and lobectomy, and smaller lesions on another side underwent thoracoscopic lobectomy or wedge resection afer 1 month) . For 1 patients with ipsilateral synchronous multiple primary lung cancer, simultaneous operation was performed. There was no death during perioperative period or severe cardiopulmonary complications. They were followed up for 3 years. The survival rate was 80. 0%( 4 /5) at 1 year and 60. 0% ( 3/5) at 3 years, respectively. Conclusions With the development of medical science and awareness of pulmonary multiple primary cancer, early diagnosis improves continuously. Active treatment with operation can achieve better prognosis.
Objectives To explore the effects of curcumin and cisplatin on A549 lung cancer cell invasion and metastasis, and explore the influence of the two drugs on matrix metalloproteinase 9 (MMP-9) and E-cadherin protein. Methods MTT assay was performed to detect the effects of curcumin, cisplatin alone and the combination on A549 lung cancer cell proliferation. Transwell assay was performed to detect the effects of curcumin, cisplatin alone and the combination on the invasion and metastasis of lung cancer cells. Western blot was used to detect the protein expression of MMP-9 and E-cadherin. Results The proliferation inhibition of A549 lung cancer cell rate in 5, 10, 20, 40 μmol/L of curcumin was 6.50%±1.06%, 11.70%±0.88%, 22.97%±0.82%, 27.93%±0.94%, respectively. Compared with control group, the proliferation inhibition rates in four different curcumin groups were significantly increased (all P<0.01). The differences in the proliferation inhibition rates among four different curcumin groups were statistically significant (allP<0.05). The proliferation inhibition rates of A549 lung cancer cell in 1, 2, 4 mg/L of cisplatin were 7.12%±0.86%, 20.07%±1.14%, 26.88%±0.51%, respectively. Compared with control group, the proliferation inhibition rates in three different cisplatin groups were significantly increased (allP<0.01). The differences in the proliferation inhibition rates among three different cisplatin groups were statistically significant (allP<0.01). The proliferation inhibition rates of A549 lung cancer cell in curcumin (20 μmol/L) combined with cisplatin (1, 2, 4 mg/L respectively) were 28.37%±0.57%, 39.72%±0.64%, 46.27%±0.86%, respectively. Compared with control group and curcumin or cisplatin used alone, the proliferation inhibition rates of three combined groups were significantly increased (allP<0.01). The invasion inhibition rates of A549 lung cancer cell in curcumin group (20 μmol/L), cisplatin group (2 mg/L) and combined group (curcumin 20 μmol/L plus cisplatin 2 mg/L) were 38.62%±0.23%, 36.52%±0.33%, 63.78%±0.59%, respectively. Compared with control group and curcumin or cisplatin used alone, the invasion inhibition rates of combined group were significantly increased (allP<0.01). The protein grey values for curcumin group (20 μmol/L), cisplatin group (2 mg/L) and combined group (curcumin 20 μmol/L plus cisplatin 2 mg/L) were 0.768±0.047, 0.654±0.104, 0.684±0.008, 0.444±0.104 (MMP-9) and 0.603±0.170, 0.792±0.050, 0.784±0.045, 0.879±0.110 (E-cadherin), respectively. Compared with control group and curcumin or cisplatin used alone, the protein grey values of combined group were significantly different (allP<0.01 orP<0.05). Conclusions Curcumin and cisplatin combination can inhibit the invasion and metastasis of lung cancer A549 cells. Its mechanism may be related to downregulating MMP-9 and upregulating E-cadherin.
Objective To explore the timing and safety of limited-period lung cancer surgery in patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. Methods Clinical data of of patients infected with COVID-19 undergoing lung cancer surgery (an observation group) in the Department of Thoracic Surgery of Guangdong Provincial People's Hospital, the Department of Thoracic Surgery of General Hospital of Southern Theater Command of PLA, and the Department of Cardiothoracic Surgery of the First Affiliated Hospital of Guangdong Pharmaceutical University from December 2022 to January 2023 were retrospectively analyzed and compared with patients who underwent surgery during the same period but were not infected with COVID-19 (a control group), to explore the impact of COVID-19 infection on lung cancer surgery. Results We finally included 110 patients with 73 patients in the observation group (28 males and 45 females at age of 52.62±12.80 years) and 37 patients in the control group (22 males and 15 females at age of 56.84±11.14 years). The average operation time of the observation group was longer than that of the control group, and the incidence of anhelation was higher than that of the control group (P<0.05). There were no statistcal differences in blood loss, length of hospital stay, moderate or above fever rate, degree of cough and chest pain, or blood routine between the two groups. ConclusionIt is safe and feasible to perform lung cancer surgery early after recovery for COVID-19 patients with lung cancer.
Objective To compare outcomes after single versus bilateral lung transplantation in patients with end-stage chronic obstructive pulmonary disease (COPD) with retrospective cohort study, and to provide a reference for surgical selection. Methods One hundred and two patients with end-stage COPD who received lung transplantation in Wuxi People's Hospital affiliated to Nanjing Medical University from January 2010 to May 2019 were evaluated, including 97 males and 5 females, aged from 42 to 82 years, with an average age of (59.8±8.0) years. Recipients were divided into single lung transplantation (SLT) group (31 cases) and bilateral lung transplantation (BLT) group (71 cases). Preoperative characteristics, postoperative outcomes, postoperative complications, functional improvement and survival between the two groups were analyzed retrospectively. Results The SLT group were significantly older than the BLT group [(62.6±8.8) years vs. (58.6±7.4) years, P<0.05], which was consistent with the practice mode of single lung transplantation in the elderly patients in this center. The FEV1% predicted and the six‐minute walk distance (6-MWD) in the BLT group were better than those in the SLT group (P<0.05). The cumulative survival rate in 1, 3 and 5 years after operation in the BLT group was higher than that in the SLT group (70.4%, 63.2%, 61.5%, respectively vs. 67.7%, 58.1%, 54.6%, respectively), but there was no statistical difference (P=0.388). The two groups were comparable in other preoperative clinical data (P>0.05). The cold ischemia time and total operation time were shorter in the SLT group than in the BLT group, and the intraoperative blood loss was less than that in the BLT group, but more patients required intraoperative extracorporeal membrane oxygenation support than the BLT group (P<0.05). There were no significant differences in postoperative ventilator support, reoperation, length of intensive care unit stay, postoperative hospital stay, and perioperative mortality (P>0.05). In terms of postoperative complications, the incidence of primary graft dysfunction grades 3 was higher in the SLT group than in the BLT group (35% vs. 8%, P=0.001). There were no significant differences between the two groups in chest complications, airway complications, acute rejection, infection, and bronchial occlusion syndrome (P>0.05). Nine patients (29%) developed acute native lung hyperinflation in the SLT group. ConclusionsBilateral lung transplantation is superior to single lung transplantation in the treatment of end-stage COPD. The advantage is mainly reflected in the simple perioperative management, better functional improvement after operation. Single lung transplantation as a beneficial supplement to double lung transplantation should still be considered in selected patients.
ObjectiveTo explore the accuracy of machine learning algorithms based on SHOX2 and RASSF1A methylation levels in predicting early-stage lung adenocarcinoma pathological types. MethodsA retrospective analysis was conducted on formalin-fixed paraffin-embedded (FFPE) specimens from patients who underwent lung tumor resection surgery at Affiliated Hospital of Nantong University from January 2021 to January 2023. Based on the pathological classification of the tumors, patients were divided into three groups: a benign tumor/adenocarcinoma in situ (BT/AIS) group, a minimally invasive adenocarcinoma (MIA) group, and an invasive adenocarcinoma (IA) group. The methylation levels of SHOX2 and RASSF1A in FFPE specimens were measured using the LungMe kit through methylation-specific PCR (MS-PCR). Using the methylation levels of SHOX2 and RASSF1A as predictive variables, various machine learning algorithms (including logistic regression, XGBoost, random forest, and naive Bayes) were employed to predict different lung adenocarcinoma pathological types. ResultsA total of 272 patients were included. The average ages of patients in the BT/AIS, MIA, and IA groups were 57.97, 61.31, and 63.84 years, respectively. The proportions of female patients were 55.38%, 61.11%, and 61.36%, respectively. In the early-stage lung adenocarcinoma prediction model established based on SHOX2 and RASSF1A methylation levels, the random forest and XGBoost models performed well in predicting each pathological type. The C-statistics of the random forest model for the BT/AIS, MIA, and IA groups were 0.71, 0.72, and 0.78, respectively. The C-statistics of the XGBoost model for the BT/AIS, MIA, and IA groups were 0.70, 0.75, and 0.77, respectively. The naive Bayes model only showed robust performance in the IA group, with a C-statistic of 0.73, indicating some predictive ability. The logistic regression model performed the worst among all groups, showing no predictive ability for any group. Through decision curve analysis, the random forest model demonstrated higher net benefit in predicting BT/AIS and MIA pathological types, indicating its potential value in clinical application. ConclusionMachine learning algorithms based on SHOX2 and RASSF1A methylation levels have high accuracy in predicting early-stage lung adenocarcinoma pathological types.
With the continuous advancements in immunotherapy and targeted therapy, the treatment management and surgical resection assessment of locally advanced lung cancer have undergone significant changes. In October 2024, the Society of Thoracic Surgeons (STS) released the "STS expert consensus on the multidisciplinary management and resectability of locally advanced non-small cell lung cancer", which provides the latest insights on the evaluation of resectability and multidisciplinary management of locally advanced lung cancer, neoadjuvant (including perioperative) therapy, and adjuvant therapy. This article aims to interpret this consensus, with the goal of introducing the latest perspectives of the STS consensus to thoracic surgeons and providing a reference for the rational implementation of surgical resection, multidisciplinary management, and standardized comprehensive treatment models for non-small cell lung cancer in China.