Prediction of lung cancer patient survival via supervised machine learning classification techniques

Abstract

Outcomes for cancer patients have been previously estimated by applying various machine learning techniques to large datasets such as the Surveillance, Epidemiology, and End Results (SEER) program database. In particular for lung cancer, it is not well understood which types of techniques would yield more predictive information, and which data attributes should be used in order to determine this information. In this study, a number of supervised learning techniques is applied to the SEER database to classify lung cancer patients in terms of survival, including linear regression, Decision Trees, Gradient Boosting Machines (GBM), Support Vector Machines (SVM), and a custom ensemble. Key data attributes in applying these methods include tumor grade, tumor size, gender, age, stage, and number of primaries, with the goal to enable comparison of predictive power between the various methods. The prediction is treated like a continuous target, rather than a classification into categories, as a first step towards improving survival prediction. The results show that the predicted values agree with actual values for low to moderate survival times, which constitute the majority of the data. The best performing technique was the custom ensemble with a Root Mean Square Error (RMSE) value of 15.05. The most influential model within the custom ensemble was GBM, while Decision Trees may be inapplicable as it had too few discrete outputs. The results further show that among the five individual models generated, the most accurate was GBM with an RMSE value of 15.32. Although SVM underperformed with an RMSE value of 15.82, statistical analysis singles the SVM as the only model that generated a distinctive output. The results of the models are consistent with a classical Cox proportional hazards model used as a reference technique. We conclude that application of these supervised learning techniques to lung cancer data in the SEER database may be of use to estimate patient survival time with the ultimate goal to inform patient care decisions, and that the performance of these techniques with this particular dataset may be on par with that of classical methods.

Performance Analysis of Predicting Survival Rates in Imbalanced Healthcare Dataset

“…Paper [5] uses rough sets for the prediction of Breast Cancer and the rough sets create decision rules which are used by a MATLAB program for future diagnosis of the disease. In [6] we see the authors discussing a number of supervised learning techniques and applying them to the SEER database to classify lung cancer patients in terms of survival, including linear regression, Decision Trees, Gradient Boosting Machines (GBM), Support Vector Machines (SVM), and a custom ensemble. Key data attributes in applying these methods include tumor grade, tumor size, gender, age, stage, and number of primaries.…”

Predicting rural patients� use of eHealth through supervised machine learning algorithms: A study on Portable Health Clinic in Bangladesh (Preprint)

“…Machine learning algorithms have been extensively using since the last two decades to build predictive models in agriculture [11]- [14], insurance and banking [15], [16], online shopping [17]- [20], travel and tourism [21], [22], marketing and consumer behavior [23]- [25], healthcare and medical science [26]- [29] along with many other industries. Calvert et al [23] described how advanced machine learning systems can be used to predict consumer behavior.…”

“…Reddy et al [28] used gradient boosting machine, regularized regression, and logistic regression to predict inflammation in Crohn's disease patients. Lynch et al [29] predicted lung cancer patient survival via supervised machine learning algorithms. Machine learning was also used in eHealth for analyzing patient's health data, predicting diseases, enhancing the productivity of technology or devices used for service providing, and so on [30], [31].…”

Using machine‐learning methods to support health‐care professionals in making admission decisions

“…Chong and colleagues built a machine‐learning model and a multivariable logistic regression model to predict moderate to severe pediatric traumatic brain injury in the emergency department (ED). Several researchers have focused on patient classification or prioritization . Zheng et al proposed a range of data mining approaches, including neural networks, random forest (RF) algorithms, a hybrid model of swarm intelligence, and support vector machines (SVM) to classify high‐ and low‐risk readmitted patients.…”

“…Several researchers have focused on patient classification or prioritization. [9][10][11][12] Zheng et al 13 Machine learning has achieved some success in medical decision making, which makes it reasonable for us to adopt machine learning to solve the problem of patient sequence in large tertiary hospitals. The priority of preadmission patients has not previously had enough attention paid to it.…”