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.
The global incidence of lung cancer ranks second among cancers, which has caused a serious burden on patients’ family and society. Chemotherapy is a common treatment for lung cancer, which often leads to a decrease in patients’ physical function and quality of life. Pulmonary rehabilitation during perioperative period of lung cancer has received extensive attention, but pulmonary rehabilitation during chemotherapy of lung cancer has not been paid much attention. This article reviews the role of rehabilitation during chemotherapy for lung cancer, and focuses on the role of rehabilitation during chemotherapy for lung cancer patients with different treatment programs. The purpose is to promote the research and promotion of rehabilitation training in lung cancer patients receiving chemotherapy, so as to further improve patients’ function and quality of life.
Objective To evaluate the clinical significance of operative indication in patients with lung cancer accompanied by lung dysfunction using cardiopulmonary exercise test (CPET). Methods Before operation, using CPET with step program, work rate(W%), maximal oxygen uptake(VO2%P), maximal oxygen uptake per kilogram(VO2/kg) and other indexes were tested in the end of load exercise in 195 patients with lung cancer accompanied by lung dysfunction. Chi-square test and logistic regression analysis were performed for the abnormal rate of indexes mentioned above in patients with or without postoperative respiratory failure. Results After pneumonectomy, W%,VO2%P, VO2/kg, metabolic equivalent (MET), minute ventilation(VE) and respiratory frequency(BF) in patients with postoperative respiratory failure were lower than those in patients with non-postoperative respiratory failure (Plt;0.05 or 0.01). Logistic regression analysis showed that VElt;30 L/min and (BFlt;30) times/min were more related to the morbidity of postoperative respiratory failure than other indexes. As for the patients with lung dysfunction treated by lobectomy, this indexes didn’t show any significant difference between patients with or without postoperative respiratory failure. However, this indexes decreased in patients with postoperative respiratory failure whose ratio of forced expiratory volume in one second to forced vital capacity (FEV1%) were lower than 60%(Plt;0.05 or 0.01). Logistic regression analysis showed that VO2%Plt;60% related to the morbidity of postoperative respiratory failure. Conclusion CPET is useful to evaluate the operative indication in patients with lung cancer accompanied by lung dysfunction. VO2%Plt;60% should be selected as a evaluating index.
Lung microbiome is defined as the specific microbiota of lung. Lung microbiome can make the lung in a state of chronic inflammation through direct destruction, activation of inflammatory cells and release of inflammatory factors, and then progress to lung cancer. There are significant differences in lung microbiome between lung cancer patients and healthy people. Some specific microbial flora can be used as a diagnostic marker of lung cancer. Specific microbial communities are related to the efficacy of immunotherapy, and microbial composition may be used as a marker of immune-related adverse events. There are both challenges and opportunities for research on the relationship between lung microbiome and lung cancer. This review will focus on the significance and value of lung microbiome in the occurrence, diagnosis and immunotherapy of lung cancer, in order to provide a reference for basic and clinical researchers in related fields.
ObjectiveTo understand variations in clinical epidemiology of lung cancer and to help with early accurate diagnosis and treatment of lung cancer.MethodsThis research was based on the Lung Cancer Database of West China Hospital of Sichuan University. Clinicopathological data of inpatients with primary lung cancer from 2011 to 2018 was collected for analysis. Information regarding sex, age, smoking history, surgical resection modalities, TNM stage of tumor, and pathological subtypes was included.ResultsA total of 23 228 inpatients with primary lung cancer were included in this research. There were 1 932, 2 029, 2 162, 2 773, 2 975, 3 318, 3 993, and 4 046 patients in every single year from 2011 to 2018, respectively. The male-to-female ratio of patients had changed significantly from 2.00∶1 in 2011 to 1.34∶1 in 2018 (P<0.001). Statistically significant difference was found in age distribution of patients in different years, while elderly always accounted for the majority of all patients. More nonsmokers were among the group of lung cancer patients, the proportion of whom rose from 41.61% in 2011 to 52.47% in 2018 (P<0.001). The proportion of adenocarcinoma in all subtypes rose from 54.04% in 2011 to 71.73% in 2018, while the proportion of squamous carcinoma dropped from 29.04% to 17.67% simultaneously. From 2011 to 2018, the proportion of stage Ⅰ lung cancer rose from 15.68% to 40.79%. Patients with stage ⅠA1 accounted for 11.82% in 2018. In 2018, 60.78% of stage ⅠA patients had gone through surgical resection modalities, forming a stark contrast with the fact that only 26.48% of stage ⅠA patients adopted surgeries in 2011.ConclusionsFrom 2011 to 2018, the total number of lung cancer patients increased year by year. The proportions of female patients and nonsmokers rose significantly. Adenocarcinoma accounted for the highest proportion of all subtypes, followed by squamous cell carcinoma. There were more patients with early lung cancer and less with advanced lung cancer diagnosed, implying a gradual accumulation of weight on the early stages according to the TNM classification of lung cancer.
ObjectiveTo analyze the surgical techniques and perioperative patient management of bronchial sleeve resection and plasty, carinal resection and reconstruction, and angioplasty in the treatment of locally advanced central type of lung cancer and summarize the experiences. MethodsWe retrospectively analyzed the clinical data of 21 locally advanced central type of lung cancer patients with bronchial sleeve resection and plasty, carinal resection and reconstruction, and angioplast in our hospital from December 2011 through November 2014. There were 17 males and 3 females with a mean age of 63.2±6.2 years. All operations were successful. The time of operation was 3.29±0.75 h. The hospitalization time was 25.48±22.31 days. No death ocurred during perioperative period. Postoperative complications were found in 3 patients, including 2 patients with atelectasis and 1 patient with bronchopleural fistula. ConclusionBronchial sleeve resection and plasty, carinal resection and reconstruction, and angioplasty apply to treat locally advanced central type of lung cancer not only maximally remove the lung cancer tissue, but also maximally reserve the healthy lung tissue.
ObjectiveTo prepare platelet-derived growth factor receptor β (PDGFRβ)-targeted near-infrared molecular probe and evaluate its potential in optical molecular imaging of lung cancer.MethodsPDGFRβ-specific affibody Z-tri was recombinantly expressed in Escherichia coli (E. coli) and purified using affinity chromatography. In vitro cell-binding of Z-tri was analyzed by flow cytometry. Cellular distribution of Z-tri in tumor grafts was determined by protein-tracing. The molecular probe CF750-Z-tri was prepared by conjugating near-infrared fluorescent dye CF750 to Z-tri. The optical images of xenografts of lung cancer were obtained by using CF750-Z-tri combined with optical imaging system.ResultsPDGFRβ-specific affibody Z-tri was highly expressed in E. coli and purified to homogeneity. Z-tri could bind PDGFRβ-positive cells but not PDGFRβ-negative cells cultured in vitro. In the tumor xenografts of human lung cancer, intravenously injected Z-tri was predominantly distributed on cells overexpressing PDGFRβ. The near infrared fluorescent dye CF750 was efficiently conjugated to Z-tri. Optical images with high contrast of lung cancer xenografts were produced by using the near-infrared fluorescent probe CF750-Z-tri combined with optical imaging system.ConclusionThe near-infrared fluorescent probe CF750-Z-tri can be used for optical imaging of human lung cancer, which takes great potential in optical imaging-guided surgery of lung cancer.
Objective Through the analysis of hospital costs of 16 866 cases of patients with lung cancer in Sichuan Province, in oder to find the main influencing factors of hospital costs of patients with lung cancer, and to provide references for reducing the hospital costs of patients with lung cancer. Methods We selected information of in-patients with lung cancer in 6 hospitals in Sichuan province from January 2008 to December 2011 based on full consideration into the local economic levels geographics distribution of different regions in Sichuan province. Then we extracted baseline data, hospitalization data and costs, and then analysis on relevant influencing factors was performed using single factor analysis of variance and multiple stepwise regression analysis. Results A total of 16 918 cases are chosen, of which, 16 866 were effective for further analysis. The results of statistical analysis showed that, the cost of western medicine accounted for the most of the average of the total hospital costs (50.79%) , followed by the cost of diagnosis and treatment (40.79%). The reuslts of multiple stepwise regression analysis showed that, the top three factors influencing hospital costs most included hospital stay, operation, and regions. Conclusion Facing daily increasing costs of hospital costs of lung cancer, effectively reducing drug expenses of patients could be a breakthrough. We could ultimately reduce the hospital costs of patients with lung cancer as well as the the economic burden of patients and society, by strengthening hospital management, shortening hospital stay, and rationally regulating drug use.
Chemotherapy-related cognitive impairment (CRCI) is one of the treatment-related side effects in cancer patients, which can reduce patients’ participation in medical decision-making and treatment, seriously affecting their daily function and quality of life. This article reviews the definition, research status, and influencing factors of CRCI in lung cancer patients, in order to provide basis and ideas for the subsequent evaluation and management of CRCI in lung cancer patients, and promote the optimization and improvement of the overall rehabilitation process of lung cancer patients.
Abstract ： Objective To evaluate the clinical validity of Physiological and Operative Severity Score for theenUmeration of Mortality and Morbidity (POSSUM) in primary lung cancer patients undergoing surgery in order to get clinical treatment reference. Methods A total of 179 patients，with 124 males and 55 females，with primary lung cancer surgery between January 2007 and October 2010 were included in the First Affiliated Hospital of Xinjiang Medical University. Their age was 59.2±11.4 years．Before the surgery，POSSUM was used to each patient to rate the results and substituted the results into Copeland equation to calculate the predicted postoperative mortality and morbidity. The actual number of complications and death were calculated after surgery and the patients were divided into one group with postoperative complications and another group without postoperative complications. The physiological score and the operative risk score were compared between the two groups. Actual number of complications and death were compared with thenumber predicted by POSSUM respectively. The clinical factors related to the actual number of complications and death were analyzed. Results Among 179 patients， there were postoperative complications in 78 patients. The physiological score and the operative severity score were significantly higher in the group in whose complications occurred compared with those without complications (16.11±2.53 points versus 14.88±1.86 points for physiological score，P=0.000 ； 13.47±2.83 points versus 12.88±2.57 points for operative severity score，P=0.000). There was no statistical difference in complication between the predicted and actual number (65/179 versus 78/179，χ2=1.968，P=0.161). There was statistical difference in death between the predicted and actual number(12/179 versus 3/179，χ2=5.636，P=0.018).Univariable analysis revealed that 5 single factors were related to the complications， only hemoglobin was related to the death. Conclusion The POSSUM gives satisfactory prediction in morbidity rate but overrates the mortality rate in primary lung cancer patients undergoing surgery， and 5 single clinical factors show a better clinical value.