scholarly journals Early Exposure of Lung Cancer by Combining ANN and SVM Algorithms

2019 ◽  
Vol 8 (4) ◽  
pp. 10675-10680
Keyword(s):  
Lung Cancer ◽  
Research Work ◽  
World Health ◽  
Support Vector ◽  
Body Parts ◽  
Initial Stage ◽  
Svm Algorithm ◽  
Patient Health ◽  
Health Organization ◽  
Image Details

Lung cancer is a lethal type of cancers as its rate of spreading is very high compared to the other cancers. Patient who have been affected from Small Cell Lung Cancer (SCLC) has fast outspread rate. Even at initial stage, around 67-75% of cancer victims with SCLC will have fast outspreads and serious damages to the nearby physical parts. Moreover, World Health Organization (WHO) has predicted the count of lung cancer deaths will reach 9.6 million in 2020. Identifying such a lethal type of cancer early can be lifesaving one. Because, cancer cells in lungs are capable of traveling to other body parts even before the doctor detects them in lungs. In this research work, we have designed a combined approach to prognosticate lung cancer and its type using Artificial Neural Networks (ANN) and Support Vector Machine (SVM). To train both the ML algorithm, an open access patient health dataset published by cancer imaging archives is used. The dataset has the information like pretreatment CT scans, 3D image details of tumor and clinical outcomes. The results produced by ANN and SVM algorithm are compared to predict the type of the lung cancer accurately. The result holds good for a real time implementation.

scholarly journals Analisis Sentimen Twitter Kuliah Online Pasca Covid-19 Menggunakan Algoritma Support Vector Machine dan Naive Bayes

2021 ◽  
Vol 5 (1) ◽  
pp. 43-51
Author(s):  
Hendrik Setiawan ◽  
Ema Utami ◽  
Sudarmawan Sudarmawan
Keyword(s):  
Support Vector Machine ◽  
World Health ◽  
Support Vector ◽  
Online Lectures ◽  
Svm Algorithm ◽  
The World ◽  
The Government ◽  
Bayes Algorithm ◽  
Health Organization ◽  
Performance Results

The World Health Organization (WHO) COVID-19 is an infectious disease caused by the Coronavirus which originally came from an outbreak in the city of Wuhan, China in December 2019 which later became a pandemic that occurred in many countries around the world. This disease has caused the government to give a regional lockdown status to give students the status of "at home" for students to enforce online or online lectures, this has caused various sentiments given by students in responding to online lectures via social media twitter. For sentiment analysis, the researcher applies the nave Bayes algorithm and support vector machine (SVM) with the performance results obtained on the Bayes algorithm with an accuracy of 81.20%, time 9.00 seconds, recall 79.60% and precision 79.40% while for the SVM algorithm get an accuracy value of 85%, time 31.60 seconds, recall 84% and precision 83.60%, the performance results are obtained in the 1st iteration for nave Bayes and the 423th iteration for the SVM algorithm  

scholarly journals Nutrisi pada Penderita Kanker Paru

2020 ◽  
Vol 5 (3) ◽  
pp. 91
Author(s):  
Risnawati Risnawati ◽  
Isnu Pradjoko ◽  
Farah Fatma Wati
Keyword(s):  
Lung Cancer ◽  
Weight Loss ◽  
Nutritional Status ◽  
World Health ◽  
Nutritional Management ◽  
Prognostic Variables ◽  
Lung Cancer Patients ◽  
Patient Health ◽  
Health Organization ◽  
Patients Experience

World Health Organization data shows that lung cancer is the leading cause of death in the group of deaths due to malignancy. Weight loss is common in lung cancer. Known side effects of chemotherapy and those that affect nutritional status include anorexia, nausea, vomiting, satiety and mucositis. In total 40-60% of lung cancer patients experience unintentional weight loss. Weight loss and reduced nutritional status have been identified as negative prognostic variables for patients. Nutritional disorders during chemotherapy if left untreated can cause interference and delay treatment. Therefore there is a need for nutritional management in patients with lung cancer so that treatment runs smoothly and supports patient health.

scholarly journals FILM REJECT ANALYSIS AS A MEASURE OF QUALITY ASSURRANCE: A CASE STUDY OF SOME SELECTED HOSPITALS IN PLATEAU STATE, NIGERIA

2021 ◽  
Vol 9 (10) ◽  
pp. 88-93
Author(s):  
W.E Mangset ◽  
K.A Sauri ◽  
D.C Langs
Keyword(s):  
Research Work ◽  
Control Program ◽  
World Health ◽  
Body Parts ◽  
Reject Analysis ◽  
Plateau State ◽  
Health Organization ◽  
The Given

Film reject analysis is a planned and systematic action necessary to provide adequate confidence that a product or service will satisfy the given requirement for quality of image or radiographs. In this research work, reject film analysis as quality assurance element will be carried out in 3 selected hospitals in Plateau state, Nigeria for different rejected film sizes in each case respectively from December, 2018- December, 2019. Rejected radiographs were collected analyzed and categorized based on body parts such as chest, skull, knee, lumbar sacral, shoulder, neck, femur and pelvis. The reasons for rejection were categorized as: Over exposure, Under exposure, Poor processing, Poor positioning, Wrong placing of anatomical marker, Fog, Artifact and Multiple exposure. The three studied hospitals (selected by convenience), H1, H2, and H3 are located in Jos and environs. From this study, it was observed that the anatomical part mostly rejected was the chest and the highest reason for the rejected radiographs was Under exposure. The reject rates of Hospitals H1, H2, and H3 were found to be 8.85%, 6.65% and 5.6% respectively which were above the World Health Organization(WHO) but within the Conference of Radiation Control Program Directorate (CRCPD) recommended permissible values of 5% and (5-10%) respectively. The findings imply that patients may have been exposed to avoidable radiation doses

scholarly journals An Intelligent Method For Detecting the Rate of Poverty Level with Reference to Tuberculosis

2020 ◽  
Vol 8 (5) ◽  
pp. 299-306
Keyword(s):  
Support Vector Machines ◽  
World Health Organization ◽  
Research Work ◽  
Fuzzy Cognitive Maps ◽  
World Health ◽  
Support Vector ◽  
Poverty Level ◽  
Vector Machines ◽  
Artificial Neural ◽  
Health Organization

This paper represents the factors, which is important for the prediction of the population living below the poverty level as defined by world health organization through reverse engineering. The objective of this research work is to analyze how the tuberculosis detection rate can help us to predict the people living below the poverty line. The feed-forward artificial neural network and Support vector machines used for comparison. The Authors provide physical reasons behind the startling results that we obtained. This work used data collected by the World Health Organization. The data collected consisted of 202 observations of 358 variables and out of these vast numbers of variables; we selected only six variables of interest to build the model. After removing the not available rows, we get only 75 observations out of which we use only 57 observations to build our model. Although the error was a bit high, still with only these few observations both artificial neural networks and support vector machines yielded similar results, confirming our hypothesis. This paper also compares two well-known algorithms for variable importance and finally provides a solution to the problem of poverty by fuzzy cognitive maps. Various concepts related to the economy have been used to develop this model and results are astounding, based on the results solution to the present-day problems has been proposed.

Lung Cancer in Brazil

2012 ◽  
pp. 426-431
Author(s):  
Gilberto Schwartsmann
Keyword(s):  
Lung Cancer ◽  
Cause Of Death ◽  
Public Health Problem ◽  
Lung Cancer Mortality ◽  
World Health ◽  
Cancer Type ◽  
Positive Effects ◽  
Incident Cancer ◽  
Health Organization ◽  
Tremendous Challenge

Overview: Cancer is now the second leading cause of death in Brazil (after cardiovascular diseases) and a public health problem, with around 500,000 new cases in 2012. Excluding nonmelanoma skin cancer, lung cancer is the second most incident cancer type in men, with 17,210 expected new cases. In women, it is the fifth most incident cancer, with 10,110 expected new cases. The estimated age-adjusted lung cancer mortality rate is about 13/100,000 for men and 5.4/100,000 for women. Lung cancer rates in men increased until the early 1990s and decreased thereafter, especially in the younger population. In contrast, a steady upward trend was observed for women. The positive effects in men were probably due to the successful anti-tobacco campaign conducted in Brazil over the last decades, which led to a decrease in the adult smoking population, from 32% in the early 1980s to 17% in the 2000s. Although the Brazilian National Cancer Institute is strongly committed to providing excellence in multimodality care to cancer patients, limitations in availability and adequate geographic distribution of specialists and well-equipped cancer centers are evident. Major disparities in patient access to proper staging and state-of-the-art treatment still exist. Considering that World Health Organization (WHO) officials estimate that cancer will become the number one cause of death in most developing countries, including Brazil, in the next decades, it is highly recommended for government authorities to implement firm actions to face this tremendous challenge.

Mixed Adenocarcinomas of the Lung: Place in New Proposals in Classification, Mandatory for Target Therapy

2010 ◽  
Vol 134 (1) ◽  
pp. 55-65 ◽  
Author(s):  
Marco Chilosi ◽  
Bruno Murer
Keyword(s):  
Lung Cancer ◽  
Lung Adenocarcinoma ◽  
World Health Organization ◽  
Cell Biology ◽  
Small Cell ◽  
World Health ◽  
Malignant Neoplasms ◽  
New Classification ◽  
Therapeutic Decisions ◽  
Health Organization

Abstract Context.—Lung cancer is one of the most frequent and lethal malignant neoplasms, but knowledge regarding the molecular basis of its pathogenesis is far from complete due to the striking diversity of different forms. The current lung cancer classification (World Health Organization 2004) can efficiently distinguish clinically relevant major subtypes (small cell and non–small cell carcinomas), but its results are partly inadequate when facing prognostic and therapeutic decisions for non–small cell carcinomas, especially for the group of tumors classified as adenocarcinoma. Lung adenocarcinoma comprises a heterogeneous group of tumors characterized by diverse morphologic features and molecular pathogenesis. The category of mixed adenocarcinomas includes most adenocarcinomas (approximately 80%) and, according to World Health Organization criteria, is defined by the occurrence of a mixed array of different patterns (acinar, papillary, bronchioloalveolar, solid with mucin). The histologic recognition of mixed adenocarcinoma is subjective and cannot consistently discriminate between responders and nonresponders to new targeted therapies (eg, tyrosine kinase inhibitors). Diagnostic problems are mainly related to the poor reproducibility of histologic criteria, especially when applied in small biopsies and cytology, and to the difficulty in assigning each form to a precisely defined entity, as needed by updated therapeutic approaches. In this evolving scenario, pathologists face new challenging diagnostic roles that include not only the precise morphologic definition of carcinoma subtypes but also their molecular characterization. Objective.—To use a comprehensive critical analysis reconciling the overwhelming variety of biologic, morphologic, molecular, and clinical data to define new classification schemes for lung adenocarcinoma. Data Sources.—Scientific literature and personal data were used. Conclusions.—A new classification approach should redefine lung adenocarcinoma heterogeneity reconciling classic morphology, immunophenotypic and molecular features of neoplastic cells, and also relevant information provided by stem cell biology. This approach, which has been already successfully applied in World Health Organization classification of other tumors, could improve the recognition of new reproducible profiles for adenocarcinomas, more closely and reproducibly related to clinical features and response to specific therapies, limiting the use of “wastebasket” categories such as mixed adenocarcinoma.

scholarly journals Machine Learning based Human Fall Detection System

2021 ◽  
Vol 9 (VI) ◽  
pp. 2677-2682
Author(s):  
Nishanth P
Keyword(s):  
Machine Learning ◽  
Detection System ◽  
Wearable Sensors ◽  
Fall Detection ◽  
The Elderly ◽  
World Health ◽  
Support Vector ◽  
Data Output ◽  
Health Organization ◽  
Context Features

Falls have become one of the reasons for death. It is common among the elderly. According to World Health Organization (WHO), 3 out of 10 living alone elderly people of age 65 and more tend to fall. This rate may get higher in the upcoming years. In recent years, the safety of elderly residents alone has received increased attention in a number of countries. The fall detection system based on the wearable sensors has made its debut in response to the early indicator of detecting the fall and the usage of the IoT technology, but it has some drawbacks, including high infiltration, low accuracy, poor reliability. This work describes a fall detection that does not reliant on wearable sensors and is related on machine learning and image analysing in Python. The camera's high-frequency pictures are sent to the network, which uses the Convolutional Neural Network technique to identify the main points of the human. The Support Vector Machine technique uses the data output from the feature extraction to classify the fall. Relatives will be notified via mobile message. Rather than modelling individual activities, we use both motion and context information to recognize activities in a scene. This is based on the notion that actions that are spatially and temporally connected rarely occur alone and might serve as background for one another. We propose a hierarchical representation of action segments and activities using a two-layer random field model. The model allows for the simultaneous integration of motion and a variety of context features at multiple levels, as well as the automatic learning of statistics that represent the patterns of the features.

Prevalence of depression in Tunisian general population

2017 ◽  
Vol 41 (S1) ◽  
pp. S523-S523
Author(s):  
H. Belhadj ◽  
R. Jomli
Keyword(s):  
General Population ◽  
World Health ◽  
Cross Sectional ◽  
Gender Education ◽  
Prevalence Of Depression ◽  
Patient Health ◽  
Severity Of Depression ◽  
Competing Interest ◽  
Health Organization ◽  
Detection Of Depression

IntroductionDepression is a major burden for the health-care system worldwide.ObjectiveTo identify prevalence and severity of depression in Tunisian general population and define socoiodemographic characteristics of screened positive to depression participants.MethodWe undertook a cross-sectional and descriptive study. A total of 134 participants, representative of the Tunisian general population, were enrolled. Age, gender, and educational level were the major criteria for representativeness. Depression was assessed with the Patient Health Questionnaire (PHQ-9).ResultsThe cut-off score was 10. The prevalence of depression was 13.4%. There were no statistical difference in gender, education and age for the prevalence of depression.ConclusionThe World Health Organization ranks depression as the fourth leading cause of disability worldwide. Thus, the detection of depression and the dissemination of treatment in the general population are very important to reduce the burden of the disease.Disclosure of interestThe authors have not supplied their declaration of competing interest.

Front-Line Treatment of Advanced Non–Small-Cell Lung Cancer With Docetaxel and Gemcitabine: A Multicenter Phase II Trial

1999 ◽  
Vol 17 (3) ◽  
pp. 914-914 ◽  
Author(s):  
Vassilis Georgoulias ◽  
Charalambos Kouroussis ◽  
Nikos Androulakis ◽  
Stelios Kakolyris ◽  
Meletios-Athanasios Dimopoulos ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Performance Status ◽  
Stage Iv ◽  
Small Cell ◽  
World Health ◽  
Small Cell Lung ◽  
Grade 3 ◽  
Health Organization

PURPOSE: To evaluate the tolerance and efficacy of the combination of docetaxel and gemcitabine in patients with advanced non–small-cell lung cancer (NSCLC). PATIENTS AND METHODS: Fifty-one chemotherapy-naive patients with NSCLC were treated with gemcitabine 900 mg/m2 intravenously on days 1 and 8 and docetaxel 100 mg/m2 intravenously on day 8 with granulocyte colony-stimulating factor (150 μg/m2, subcutaneously) support from day 9 to day 15. Treatment was repeated every 3 weeks. RESULTS: The patients' median age was 64 years. The World Health Organization performance status was 0 to 1 in 39 patients and 2 in 12 patients. Fifteen patients (29%) had stage IIIB disease, and 36 (71%) had stage IV; histology was mainly squamous cell carcinoma (59%). A partial response was achieved in 19 patients (37.5%; 95% confidence interval, 24% to 50%); stable disease and progressive disease were each observed in 16 patients (31.4%). The median duration of response and the time to tumor progression were 5 and 6 months, respectively. The median survival was 13 months, and the actuarial 1-year survival was 50.7%. Grade 4 anemia and thrombocytopenia were rare (2%). Four patients (8%) developed grade 3 or 4 neutropenia, and all were complicated with fever; there was no treatment-related death. Grade 3 or 4 diarrhea occurred in three patients (6%), grade 2 or 3 neurotoxicity in four patients (8%), grade 2 or 3 asthenia in 10 patients (20%), and grade 2 or 3 edema in 10 patients (20%). CONCLUSION: The combination of docetaxel/gemcitabine is well tolerated, can be used for outpatients, and is active for the treatment of advanced NSCLC. This treatment merits further comparison with other cisplatin- or carboplatin-based combinations.

scholarly journals Machine learning versus logistic regression methods for 2-year mortality prognostication in a small, heterogeneous glioma database

2018 ◽  
Author(s):  
Sandip S Panesar ◽  
Rhett N D’Souza ◽  
Fang-Cheng Yeh ◽  
Juan C Fernandez-Miranda
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Machine Learning Techniques ◽  
World Health ◽  
Support Vector ◽  
Molecular Characteristics ◽  
Regression Methods ◽  
Learning Techniques ◽  
The World ◽  
Health Organization

AbstractBackgroundMachine learning (ML) is the application of specialized algorithms to datasets for trend delineation, categorization or prediction. ML techniques have been traditionally applied to large, highly-dimensional databases. Gliomas are a heterogeneous group of primary brain tumors, traditionally graded using histopathological features. Recently the World Health Organization proposed a novel grading system for gliomas incorporating molecular characteristics. We aimed to study whether ML could achieve accurate prognostication of 2-year mortality in a small, highly-dimensional database of glioma patients.MethodsWe applied three machine learning techniques: artificial neural networks (ANN), decision trees (DT), support vector machine (SVM), and classical logistic regression (LR) to a dataset consisting of 76 glioma patients of all grades. We compared the effect of applying the algorithms to the raw database, versus a database where only statistically significant features were included into the algorithmic inputs (feature selection).ResultsRaw input consisted of 21 variables, and achieved performance of (accuracy/AUC): 70.7%/0.70 for ANN, 68%/0.72 for SVM, 66.7%/0.64 for LR and 65%/0.70 for DT. Feature selected input consisted of 14 variables and achieved performance of 73.4%/0.75 for ANN, 73.3%/0.74 for SVM, 69.3%/0.73 for LR and 65.2%/0.63 for DT.ConclusionsWe demonstrate that these techniques can also be applied to small, yet highly-dimensional datasets. Our ML techniques achieved reasonable performance compared to similar studies in the literature. Though local databases may be small versus larger cancer repositories, we demonstrate that ML techniques can still be applied to their analysis, though traditional statistical methods are of similar benefit.

Sign in / Sign up

Export Citation Format

Share Document