Using Naïve Bayes Algorithm to Estimate the Response to Drug in Lung Cancer Patients

2019 ◽  
Vol 21 (10) ◽  
pp. 734-748 ◽  
Author(s):  
Baoling Guo ◽  
Qiuxiang Zheng
Keyword(s):  
Lung Cancer ◽  
Side Effects ◽  
Cancer Patients ◽  
Drug Response ◽  
Treatment Options ◽  
Clinical Manifestations ◽  
Treatment Strategies ◽  
Cancer Resistance ◽  
Lung Cancer Patients ◽  
Bayes Algorithm

Aim and Objective: Lung cancer is a highly heterogeneous cancer, due to the significant differences in molecular levels, resulting in different clinical manifestations of lung cancer patients there is a big difference. Including disease characterization, drug response, the risk of recurrence, survival, etc. Method: Clinical patients with lung cancer do not have yet particularly effective treatment options, while patients with lung cancer resistance not only delayed the treatment cycle but also caused strong side effects. Therefore, if we can sum up the abnormalities of functional level from the molecular level, we can scientifically and effectively evaluate the patients' sensitivity to treatment and make the personalized treatment strategies to avoid the side effects caused by over-treatment and improve the prognosis. Result & Conclusion: According to the different sensitivities of lung cancer patients to drug response, this study screened out genes that were significantly associated with drug resistance. The bayes model was used to assess patient resistance.

scholarly journals Patient Preferences for Lung Cancer Treatment: A Qualitative Study Protocol Among Advanced Lung Cancer Patients

2021 ◽  
Vol 9 ◽  
Author(s):  
Ilaria Durosini ◽  
Rosanne Janssens ◽  
Reinhard Arnou ◽  
Jorien Veldwijk ◽  
Meredith Y. Smith ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Side Effects ◽  
Qualitative Study ◽  
Cancer Patients ◽  
Patient Preference ◽  
Treatment Options ◽  
Small Cell ◽  
Small Cell Lung ◽  
Group Discussions ◽  
Lung Cancer Patients

Introduction: Lung cancer is the deadliest and most prevalent cancer worldwide. Lung cancer treatments have different characteristics and are associated with a range of benefits and side effects for patients. Such differences may raise uncertainty among drug developers, regulators, payers, and clinicians regarding the value of these treatment effects to patients. The value of conducting patient preference studies (using qualitative and/or quantitative methods) for benefits and side effects of different treatment options has been recognized by healthcare stakeholders, such as drug developers, regulators, health technology assessment bodies, and clinicians. However, evidence-based guidelines on how and when to conduct and use these studies in drug decision-making are lacking. As part of the Innovative Medicines Initiative PREFER project, we developed a protocol for a qualitative study that aims to understand which treatment characteristics are most important to lung cancer patients and to develop attributes and levels for inclusion in a subsequent quantitative preference survey.Methods: The study protocol specifies a four-phased approach: (i) a scoping literature review of published literature, (ii) four focus group discussions with stage III and IV Non-Small Cell Lung Cancer patients, (iii) two nominal group discussions with stage III and IV Non-Small Cell Lung Cancer patients, and (iv) multi-stakeholder discussions involving clinicians and preference experts.Discussion: This protocol outlines methodological and practical steps as to how qualitative research can be applied to identify and develop attributes and levels for inclusion in patient preference studies aiming to inform decisions across the drug life cycle. The results of this study are intended to inform a subsequent quantitative preference survey that assesses patient trade-offs regarding lung cancer treatment options. This protocol may assist researchers, drug developers, and decision-makers in designing qualitative studies to understand which treatment aspects are most valued by patients in drug development, regulation, and reimbursement.

Cutaneous Side Effects in 19 Lung Cancer Patients Treated with Gefitinib (Iressa)

2004 ◽  
Vol 66 (6) ◽  
pp. 602-607 ◽  
Author(s):  
Miho UCHIHIRA ◽  
Takahiro EJIMA ◽  
Takao UCHIHIRA ◽  
Jun ARAKI ◽  
Toshiaki KAMEI
Keyword(s):  
Lung Cancer ◽  
Side Effects ◽  
Cancer Patients ◽  
Cutaneous Side Effects ◽  
Lung Cancer Patients

scholarly journals Increasing trends in the prevalence of prior cancer in newly diagnosed lung, stomach, colorectal, breast, cervical, and corpus uterine cancer patients: A population-based study

2021 ◽  
Author(s):  
Akira Sato ◽  
Keisuke Matsubayashi ◽  
Toshitaka Morishima ◽  
Kayo Nakata ◽  
Koji Kawakami ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Clinical Research ◽  
Cancer Patients ◽  
Uterine Cancer ◽  
Treatment Options ◽  
Temporal Trends ◽  
Treatment Strategies ◽  
Population Based ◽  
Trend Test ◽  
Newly Diagnosed

Abstract Background: Cancer survivors are frequently excluded from clinical research, resulting in their omission from the development of many cancer treatment strategies. Quantifying the prevalence of prior cancer in newly diagnosed cancer patients can inform research and clinical practice. This study aimed to describe the prevalence, characteristics, and trends of prior cancer in newly diagnosed cancer patients in Japan. Methods: Using Osaka Cancer Registry data, we examined the prevalence, characteristics, and temporal trends of prior cancer in patients who received new diagnoses of lung, stomach, colorectal, female breast, cervical, and corpus uterine cancer between 2004 and 2015. Site-specific prior cancers were examined for a maximum of 15 years before the new cancer was diagnosed. Temporal trends were evaluated using the Cochran-Armitage trend test. Results: Among 275,720 newly diagnosed cancer patients, 21,784 (7.9%) had prior cancer. The prevalence of prior cancer ranged from 3.3% (breast cancer) to 11.1% (lung cancer). In both sexes, the age-adjusted prevalence of prior cancer had increased in recent years (P values for trend < 0.001), especially in newly diagnosed lung cancer patients. The proportion of smoking-related prior cancers exceeded 50% in patients with newly diagnosed lung, stomach, colorectal, breast, and cervical cancer. Conclusions: The prevalence of prior cancer in newly diagnosed cancer patients is relatively high, and has increased in recent years. Our findings suggest that a deeper understanding of the prevalence and characteristics of prior cancer in cancer patients is needed to promote more inclusive clinical research and support the expansion of treatment options.

Prevalence of targetable mutations in black patients with lung cancer: A systematic review and meta-analysis.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e13105-e13105
Author(s):  
Yonette Paul ◽  
Sunil G Iyer ◽  
Leonardo Tamariz ◽  
Zsuzsanna Nemeth ◽  
Gilberto Lopes
Keyword(s):  
Lung Cancer ◽  
Cancer Patients ◽  
Fixed Effects ◽  
Tissue Sample ◽  
Meta Analysis ◽  
Treatment Options ◽  
Racial Groups ◽  
Lower Prevalence ◽  
Lung Cancer Patients ◽  
Arcsine Transformation

e13105 Background: Although poorer outcomes of lung cancer in Blacks compared to other racial groups has been strongly linked to socio-economic factors, it is important to investigate whether lower prevalence of targetable mutations limit treatment options, thereby also contributing to worse outcomes. This study examines the prevalence of EGFR, ALK, ROS-1 and BRAF lung cancer mutations in Blacks compared to other races. Methods: We conducted a meta- analysis compliant with PRISMA guidelines. Searched databases included PubMed/MEDLINE, Cochrane CENTRAL, EMBASE, Google Scholar and clinicaltrials.gov. Publication bias was mitigated by searching clinicaltrials.gov for unpublished studies. Searches were run to 11/19/2018. Two rounds of screening were performed based on title and then abstract by two independent reviewers. For the purposes of this study we defined racial groups as Black, Asian, Hispanic, and White/Caucasian. We selected studies of lung cancer patients (any stage or type) where the prevalence of at least one mutation was reported in Blacks. We calculated the pooled prevalence of mutations by racial group using fixed effects, exact binomial distributions and Freeman-Turkey double arcsine transformation to stabilize the variances. Results: Prevalence % of mutations by race reported with 95% Confidence Interval in parentheses N = number of tests performed We included 20 studies which totaled 11,867 lung cancer patients. Each mutation tested on a tissue sample was considered an event, for a total of 15,306 events. EGFR was the most prevalent mutation in Blacks (6%). Compared to other races Blacks had the lowest prevalence of all four mutations. Conclusions: In the era of targeted therapy, outcomes for metastatic lung have improved significantly. Of concern, our results show that Blacks are disproportionately ineligible for these therapies due to lower prevalence of targetable mutations. More research is needed to evaluate the unique tumor characteristics and therapeutic strategies in this sub group of patients, in the hope of achieving better disease outcomes.[Table: see text]

scholarly journals Personalized drug-response prediction model for lung cancer patients using machine learning

2020 ◽  
Author(s):  
Rizwan Qureshi
Keyword(s):  
Lung Cancer ◽  
Cancer Patients ◽  
Targeted Therapies ◽  
Drug Response ◽  
Kinase Inhibitors ◽  
Binding Free Energy ◽  
Survival Rates ◽  
Drug Binding ◽  
Geometrical Properties ◽  
Lung Cancer Patients

Lung cancer caused by mutations in the epidermal growth factor receptor (EGFR) is a major cause of cancer deaths worldwide. EGFR Tyrosine kinase inhibitors (TKIs) have been developed, and have shown increased survival rates and quality of life in clinical studies. However, drug resistance is a major issue, and treatment efficacy is lost after about an year. Therefore, predicting the response to targeted therapies for lung cancer patients is a significant research problem. In this work, we address this issue and propose a personalized model to predict the drug-response of lung cancer patients. This model uses clinical information, geometrical properties of the drug binding site, and the binding free energy of the drug-protein complex. The proposed model achieves state of the art performance with 97.5% accuracy, 100% recall, 95% precision, and 96.3% F1-score with a random forest classifier. This model can also be tested on other types of cancer and diseases, and we believe that it may help in taking optimal clinical decisions for treating patients with targeted therapies

scholarly journals Clinicopathological characteristics and treatment strategies for young lung cancer patients

2019 ◽  
Vol 7 (5) ◽  
pp. 100-100 ◽  
Author(s):  
Remi Yoneyama ◽  
Hisashi Saji ◽  
Yasufumi Kato ◽  
Yujin Kudo ◽  
Yoshihisa Shimada ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Patients ◽  
Treatment Strategies ◽  
Clinicopathological Characteristics ◽  
Lung Cancer Patients
Sign in / Sign up

Export Citation Format

Share Document