Predicting Lung Cancer Survivability using SVM and Logistic Regression Algorithms

Hazra, Animesh; Bera, Nanigopal; Mandal, Avijit

doi:10.5120/ijca2017915325

Cited by 23 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Demographics, histology and pathological staging are among clinical indicators that have been proven in the literature [34][35][36], hence previous works on predicting survival among NSCLC patients are concentrated on mixing these readily available clinical factors with AUCs range between 0.62-0.79 [19][20][27][28]. To the best of our knowledge, this is the first study establishing the fusion of both clinical with imaging covariates, which has been proven to better predict survival (AUCs between 0.77 and 0.97).…”

Section: Discussionmentioning

confidence: 99%

Leveraging hybrid biomarkers in clinical endpoint prediction

Saad

Lee

2020

Preprint

View full text Add to dashboard Cite

Background Clinical endpoint prediction remains challenging for health providers. Although predictors such as age, gender, and disease staging are of considerable predictive value, the accuracy often ranges between 60% and 80%. An accurate prognosis assessment is required for making effective clinical decisions. Methods We proposed an extended prognostic model based on clinical covariates with adjustment for additional variables that were radio-graphically induced, termed imaging biomarkers. Eight imaging biomarkers were introduced and investigated in a cohort of 68 non-small cell lung cancer subjects with tumor internal characteristic. The subjects comprised of 40 males and 28 females with mean age at 68.7 years. The imaging biomarkers used to quantify the solid component and non-solid component of a tumor. The extended model comprises of additional frameworks that correlate these markers to the survival ends through uni- and multi-variable analysis to determine the most informative predictors, before combining them with existing clinical predictors. Performance was compared between traditional and extended approaches using Receiver Operating Characteristic (ROC) curves, Area under the ROC curves (AUC), Kaplan-Meier (KM) curves, Cox Proportional Hazard, and log-rank tests (p-value). Results The proposed hybrid model exhibited an impressive boosting pattern over the traditional approach of prognostic modelling in the survival prediction (AUC ranging from 77– 97%). Four developed imaging markers were found to be significant in distinguishing between subjects having more and less dense components: (P = 0.002–0.006). The correlation to survival analysis revealed that patients with denser composition of tumor (solid dominant) lived 1.6–2.2 years longer (mean survival) and 0.5–2.0 years longer (median survival), than those with less dense composition (non-solid dominant). Conclusion The present study provides crucial evidence that there is an added value for incorporating additional image-based predictors while predicting clinical endpoints. Though the hypotheses were confirmed in a customized case study, we believe the proposed model is easily adapted to various clinical cases, such as predictions of complications, treatment response, and disease evolution.

show abstract

Section: Discussionmentioning

confidence: 99%

Leveraging hybrid biomarkers in clinical endpoint prediction

Saad

Lee

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Demographics, histology and pathological staging are among clinical indicators that have been proven in the literature [34][35][36], hence previous works on predicting survival among NSCLC patients are concentrated on mixing these readily available clinical factors with AUCs range between 0.62-0.79 [19,20,27,28]. To the best of Table 8 Mean and median survival as calculated from Kaplan-Meier survival curves.…”

Section: Discussionmentioning

confidence: 99%

“…The predictors were fed into four off-the-shelf classifiers to predict the probability of patients survived or expired 5 years after surgery. The classifiers were chosen based on recent similar published works of predicting survival of lung cancer: Wallington et al, Logistic Regression (LR) [19], Jochems et al, Random Forest (RF) [20], Hazra et al, Support Vector Machines (SVM) [28], and Rodrigo et al, Artificial Neural Network (ANN) [29].…”

Section: Model Evaluationmentioning

confidence: 99%

Leveraging hybrid biomarkers in clinical endpoint prediction

Saad

Lee

2020

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Clinical endpoint prediction remains challenging for health providers. Although predictors such as age, gender, and disease staging are of considerable predictive value, the accuracy often ranges between 60 and 80%. An accurate prognosis assessment is required for making effective clinical decisions. Methods We proposed an extended prognostic model based on clinical covariates with adjustment for additional variables that were radio-graphically induced, termed imaging biomarkers. Eight imaging biomarkers were introduced and investigated in a cohort of 68 non-small cell lung cancer subjects with tumor internal characteristic. The subjects comprised of 40 males and 28 females with mean age at 68.7 years. The imaging biomarkers used to quantify the solid component and non-solid component of a tumor. The extended model comprises of additional frameworks that correlate these markers to the survival ends through uni- and multi-variable analysis to determine the most informative predictors, before combining them with existing clinical predictors. Performance was compared between traditional and extended approaches using Receiver Operating Characteristic (ROC) curves, Area under the ROC curves (AUC), Kaplan-Meier (KM) curves, Cox Proportional Hazard, and log-rank tests (p-value). Results The proposed hybrid model exhibited an impressive boosting pattern over the traditional approach of prognostic modelling in the survival prediction (AUC ranging from 77 to 97%). Four developed imaging markers were found to be significant in distinguishing between subjects having more and less dense components: (P = 0.002–0.006). The correlation to survival analysis revealed that patients with denser composition of tumor (solid dominant) lived 1.6–2.2 years longer (mean survival) and 0.5–2.0 years longer (median survival), than those with less dense composition (non-solid dominant). Conclusion The present study provides crucial evidence that there is an added value for incorporating additional image-based predictors while predicting clinical endpoints. Though the hypotheses were confirmed in a customized case study, we believe the proposed model is easily adapted to various clinical cases, such as predictions of complications, treatment response, and disease evolution.

show abstract

“…The accuracy of each of the1000 models was measured as the AUC of the Out-of-Bag (OOB) samples. Animesh Hazra et al, [19] logistic regression has been used to predict the death rate due to lung cancer. As the dataset has only two attribute either yes or no for which logistic regression can work more efficiently than other algorithms…”

Section: Use Of Logistic Regression In Lung Cancer Predictionmentioning

confidence: 99%

Machine Learning Techniques for Prediction of Lung Cancer

Banerjee¹,

Das²

2020

IJRTE

View full text Add to dashboard Cite

Lung cancer has been one of the deadliest diseases in today’s decades. It has become one of the causes of death in both man and woman. There are various reasons for which lung cancer occurs but classification of tumor and predicting it in the right stage is the most important part. This paper focused on the numerous approaches has been derived for lung cancer detection from different literature survey to advance the ability of detection of cancer. Digital image processing and data mining both are equally important because for prediction either image dataset or statistical dataset is used so for pre-processing the image dataset digital image processing is applied for statistical dataset data mining is applied. After pre-processing, segmentation and feature extraction we apply various machine learning algorithm for the prediction of lung cancer. So first we have provided a sketch of Machine learning and then various fields like in image data or statistical data where machine learning has been used for classification. Once the classification is done confusion matrix is generated for calculating accuracy, sensitivity, precision, these method is used to measure the rate of accuracy of the proposed model.

show abstract

Predicting Lung Cancer Survivability using SVM and Logistic Regression Algorithms

Cited by 23 publications

References 9 publications

Leveraging hybrid biomarkers in clinical endpoint prediction

Leveraging hybrid biomarkers in clinical endpoint prediction

Leveraging hybrid biomarkers in clinical endpoint prediction

Machine Learning Techniques for Prediction of Lung Cancer

Contact Info

Product

Resources

About