scholarly journals Lung Cancer Prediction Using Ensemble Learning

2021 ◽  
pp. 477-482
Author(s):  
Vaibhav Narawade ◽  
Akash Singh ◽  
Mohit Shrivastava ◽  
Abhishek Prasad
Keyword(s):  
Lung Cancer ◽  
Ensemble Learning ◽  
Randomized Clinical Trials ◽  
Screening Methods ◽  
Cure Rate ◽  
Data Set ◽  
Medical Practitioners ◽  
Lung Cancer Patients ◽  
Detection Techniques ◽  
The Individual

Lung Cancer is the most commonly occurring type of cancer in the world. Despite all the research in the field of lung cancer is still maintains a extremely high mortality rate and a cure rate of of less than 15%. Majority of lung cancer patients are diagnosed at a very advanced stage which is why randomized clinical trials have come under intense scrutiny from the medical practitioners and have led to a new resurgence of interest in its screening methods and development of newer techniques to improve its efficiency. The existing screening and detection techniques have known to be slow, cost ineffective and have other discrepancies such as false positives. Keeping this in mind we propose to use ensemble learning methods to train our data-set to overcome the drawbacks and improve upon the individual algorithms.

scholarly journals Thermal Liquid Biopsy (TLB): A Predictive Score Derived from Serum Thermograms as a Clinical Tool for Screening Lung Cancer Patients

Cancers ◽  
2019 ◽  
Vol 11 (7) ◽  
pp. 1012 ◽  
Author(s):  
Alberto Rodrigo ◽  
Jorge L. Ojeda ◽  
Sonia Vega ◽  
Oscar Sanchez-Gracia ◽  
Angel Lanas ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Patients ◽  
Liquid Biopsy ◽  
Predictive Score ◽  
Risk Population ◽  
Lung Cancer Patients ◽  
Screening Programs ◽  
Detection Techniques ◽  
Cancer Management ◽  
Incidence And Mortality

Risk population screening programs are instrumental for advancing cancer management and reducing economic costs of therapeutic interventions and the burden of the disease, as well as increasing the survival rate and improving the quality of life for cancer patients. Lung cancer, with high incidence and mortality rates, is not excluded from this situation. The success of screening programs relies on many factors, with some of them being the appropriate definition of the risk population and the implementation of detection techniques with an optimal discrimination power and strong patient adherence. Liquid biopsy based on serum or plasma detection of circulating tumor cells or DNA/RNA is increasingly employed nowadays, but certain limitations constrain its wide application. In this work, we present a new implementation of thermal liquid biopsy (TLB) for lung cancer patients. TLB provides a prediction score based on the ability to detect plasma/serum proteome alterations through calorimetric thermograms that strongly correlates with the presence of lung cancer disease (91% accuracy rate, 90% sensitivity, 92% specificity, diagnostic odds ratio 104). TLB is a quick, minimally-invasive, low-risk technique that can be applied in clinical practice for evidencing lung cancer, and it can be used in screening and monitoring actions.

scholarly journals Sniffer dogs can identify lung cancer patients from breath and urine samples

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Charlotte Feil ◽  
Frank Staib ◽  
Martin R. Berger ◽  
Thorsten Stein ◽  
Irene Schmidtmann ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Patients ◽  
Detection Rate ◽  
Urine Samples ◽  
Screening Methods ◽  
Study Phase ◽  
Healthy Controls ◽  
Conditioned Reaction ◽  
Lung Cancer Patients ◽  
Tumor Stages

Abstract Background Lung cancer is the most common oncological cause of death in the Western world. Early diagnosis is critical for successful treatment. However, no effective screening methods exist. A promising approach could be the use of volatile organic compounds as diagnostic biomarkers. To date there are several studies, in which dogs were trained to discriminate cancer samples from controls. In this study we evaluated the abilities of specifically trained dogs to distinguish samples derived from lung cancer patients of various tumor stages from matched healthy controls. Methods This single center, double-blind clinical trial was approved by the local ethics committee, project no FF20/2016. The dog was conditioned with urine and breath samples of 36 cancer patients and 150 controls; afterwards, further 246 patients were included: 41 lung cancer patients comprising all stages and 205 healthy controls. From each patient two breath and urine samples were collected and shock frozen. Only samples from new subjects were presented to the dog during study phase randomized, double-blinded. This resulted in a specific conditioned reaction pointing to the cancer sample. Results Using a combination of urine and breath samples, the dog correctly predicted 40 out of 41 cancer samples, corresponding to an overall detection rate of cancer samples of 97.6% (95% CI [87.1, 99.9%]). Using urine samples only the dog achieved a detection rate of 87.8% (95% CI [73.8, 95.9%]). With breath samples, the dog correctly identified cancer in 32 of 41 samples, resulting in a detection rate of 78% (95% CI [62.4, 89.4%]). Conclusions It is known from current literature that breath and urine samples carry VOCs pointing to cancer growth. We conclude that olfactory detection of lung cancer by specifically trained dogs is highly suggestive to be a simple and non-invasive tool to detect lung cancer. To translate this approach into practice further target compounds need to be identified.

scholarly journals Survival and Treatment of Lung Cancer in Taiwan between 2010 and 2016

2021 ◽  
Vol 10 (20) ◽  
pp. 4675
Author(s):  
Yen-Jung Chang ◽  
Jing-Yang Huang ◽  
Ching-Hsiung Lin ◽  
Bing-Yen Wang
Keyword(s):  
Lung Cancer ◽  
Overall Survival ◽  
Multivariate Analysis ◽  
Prognostic Factors ◽  
Cancer Patients ◽  
Randomized Clinical Trials ◽  
Treatment Strategies ◽  
Stage Iv ◽  
Clinical Staging ◽  
Lung Cancer Patients

Background: Lung cancer is the leading cause of cancer-related death, and its incidence is still growing in Taiwan. This study investigated the prognostic factors of overall survival between 2010 and 2016 in Taiwan. Methods: Data from 2010 to 2016 was collected from the Taiwan Cancer Registry (TCR). The characteristics and overall survival of 71,334 lung cancer patients were analyzed according to the tumor, node, metastasis (TNM) 7th staging system. Univariate and multivariate analysis were performed to identify the prognostic factors. Results: The five-year overall survival (n = 71,334) was 25.0%, and the median survival was 25.3 months. The five-year overall survival of patients receiving any kind of treatment (n = 65,436; 91.7%) and surgical resection (n = 20,131; 28.2%) was 27.09% and 69.93%, respectively. The clinical staging distribution was as follows: stage IA (9208, 12.9%), stage IB (4087, 5.7%), stage IIA (1702, 2.4%), stage IIB (1454, 2.0%), stage IIIA (5309, 7.4%), stage IIIB (6316, 8.9%), stage IV (41458, 58.1%). Age, sex, Charlson comorbidity index, cell type, clinical T, clinical N, clinical M, grading and treatment strategy are independent prognostic factors in the multivariate analysis. Conclusion: The outcome for lung cancer patients was still poor. The identification of prognostic factors could facilitate in choosing treatment strategies and designing further randomized clinical trials.

Treatment trends with immune checkpoint inhibitor (ICI) therapy in older adults with lung cancer.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e24016-e24016
Author(s):  
Christine Marie Walko ◽  
Allison Dickey ◽  
Alison A. Motsinger-Reif ◽  
Elizabeth Scholl ◽  
Howard L. McLeod ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Overall Survival ◽  
Real World ◽  
Single Agent ◽  
Standard Of Care ◽  
The United States ◽  
Advanced Lung Cancer ◽  
Data Set ◽  
Lung Cancer Patients ◽  
Number Of Cycles

e24016 Background: ICI therapy has become the standard of care for the treatment of most types of advanced lung cancer with an average age at diagnosis of 70 years old (yo). The objectives of this study were to describe the demographics and practice patterns of real-world ICI usage in lung cancer patients > 70 yo. Methods: We conducted a retrospective, observational cohort study utilizing statistically deidentified data sourced from CancerLinQ Discovery® ( www.cancerlinq.org/solutions/researchers ): Lung Cancer (2014-2019), October, 2018 data set release, American Society of Clinical Oncology’s (ASCO’s) CancerLinQ LLC. Of the 1632 patients in this data release, only those patients who received a single agent ICI of nivolumab, pembrolizumab or atezolizumab and had a known birthdate were included in the analyses. Results: The majority of the 1632 patients in the data set were male (46.9%) and Caucasian (43.4%), although a substantial percentage of patient Gender and Race data was not known (14.5% and 43.1% respectively). The majority of the patients were treated in the southern part of the United States (52.6%) and the median ages for adenocarcinoma and squamous cell carcinoma histologies were 66 and 70, respectively, with interquartile ranges of 59-74 and 63-76. In the analyses, the major delineator was age at 70 yo, where age is based on when a patient received their first ICI dose. For patients < 70 yo, the mean (max) number of cycles in patients who received atezolizumab, nivolumab and pembrolizumab was 5.4 (24), 8.7 (62) and 7.7 (32), respectively and for patients > 70 yo was 4.6 (30), 8.1 (64) and 6.5 (23), respectively. The median overall survival for patients < 70 yo who received atezolizumab, nivolumab and pembrolizumab was 24, 12 and 24 months, respectively and for patients > 70 yo was 24, 12 and 18 months, respectively. Conclusions: The number of cycles and overall survival reported in this real-world dataset were similar between patients older and younger than 70 yo with lung cancer treated with ICI. Limitations included decreased power for multivariate analysis due to suppressed data elements which has been improved in more recent data releases.

scholarly journals Effects of magnanimous therapy on emotional, psychosomatic and immune functions of lung cancer patients

2020 ◽  
pp. 135910531990131
Author(s):  
Xuewei Huang ◽  
Qianyu Liu ◽  
Wendy Wen Li ◽  
Lanlan Wu ◽  
Anni Yan
Keyword(s):  
Lung Cancer ◽  
Cancer Patients ◽  
Killer Cell ◽  
Depression Scale ◽  
Advanced Lung Cancer ◽  
Controlled Study ◽  
Immune Functions ◽  
Lung Cancer Patients ◽  
Cell Functions ◽  
The Individual

This study was a randomised controlled study on the effects of the individual computer magnanimous therapy and group computer magnanimous therapy on emotional, psychosomatic and immune function among advanced lung cancer patients. Patients were examined at baseline and 2 weeks later using the Psychosomatic Status Scale for Cancer Patients, Hospital Anxiety Depression Scale and IgA, IgG, IgM and natural killer cell functions. The results showed that individual computer magnanimous therapy and group computer magnanimous therapy were beneficial for advanced lung cancer patients in improving depression, anxiety, psychosomatic status and immune functions. The improvements of immune functions may be related to the improvements of the participants’ emotional and psychosocial status.

scholarly journals One-Year Quality of Life Trends in Early-Stage Lung Cancer Patients After Lobectomy

2020 ◽  
Vol 11 ◽  
Author(s):  
Chiara Marzorati ◽  
Ketti Mazzocco ◽  
Dario Monzani ◽  
Francesca Pavan ◽  
Monica Casiraghi ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Lung Cancer ◽  
Cancer Patients ◽  
Perioperative Complications ◽  
Care Process ◽  
Lung Cancer Patients ◽  
The Individual ◽  
Type Of Surgery ◽  
Over Time

Objective: Quality of Life (QoL) is an important predictor of patient's recovery and survival in lung cancer patients. The aim of the present study is to identify 1-year trends of lung cancer patients' QoL after robot-assisted or traditional lobectomy and investigate whether clinical (e.g., pre-surgery QoL, type of surgery, and perioperative complications) and sociodemographic variables (e.g., age) may predict these trends.Methods: An Italian sample of 176 lung cancer patients undergoing lobectomy completed the European Organization for Research and Treatment of Cancer (EORTC) Quality of Life Questionnaire—Core 30 (QLQ-C30) at the pre-hospitalization (t0), 30 days (t1), 4 months (t2), 8 months (t3), and 12 months (t4) after surgery. Sociodemographic and clinical characteristics (age, gender, perioperative complications, and type of surgery) were also collected. The individual change over time of the 15 dimensions of the EORTC QLQ-C30 and the effects of pre-surgery scores of QoL dimensions, type of surgery, perioperative complications, and age on patients' QoL after surgery were studied with the individual growth curve (IGC) models.Results: Patients had a good recovery after lobectomy: functioning subscales improved over time, while most of the symptoms became less severe over the care process. Perioperative complications, type of surgery, pre-surgery status, and age significantly affected these trends, thus becoming predictors of patients' QoL.Conclusion: This study highlights different 1-year trends of lung cancer patients' QoL. The measurement of pre- and post-surgery QoL and its clinical and sociodemographic covariables would be necessary to better investigate patients' care process and implement personalized medicine in lung cancer hospital divisions.

scholarly journals Estimation for Survival of Lung Cancer Patients Depending on Different Attributes

2018 ◽  
pp. 145-148
Author(s):  
Tugba Sarac
Keyword(s):  
Lung Cancer ◽  
Life Expectancy ◽  
Cancer Patients ◽  
Cross Validation ◽  
Data Set ◽  
Lung Cancer Patients ◽  
Storage Cost ◽  
Meaningful Information ◽  
Electronic Storage ◽  
One Year

Nowadays, huge volumes of data are available thank to developing technology, variety of data and reduction in electronic storage cost of data. Various studies are carried out in order to transform data to meaningful information. In this paper, data set which belongs to lung cancer patients were transformed meaningful information. post-operative life expectancy within one year r operation has been estimated. It is observed that best result has been achieved by using KNN Algorithm (k=5 and Cross Validation=10).

Sign in / Sign up

Export Citation Format

Share Document