Open Access iconOpen Access


Prognosis Analysis of Lung Cancer Patients

Yicheng Xie1,*, Jinyue Xia2

1 School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, 210044, China
2 International Business Machines Corporation (IBM), NY, 10504, USA

* Corresponding Author: Yicheng Xie. Email: email

Journal of Intelligent Medicine and Healthcare 2022, 1(1), 43-54.


Lung cancer is now the most common type of cancer worldwide, with high levels of morbidity and mortality. The cost of treatment and emotional stress put a high burden on families and society. This paper aims to collect relevant information and provide predictive analysis for the prognosis of patients with lung cancer. Using the public data of SEER database and the method of machine learning, a model is constructed to predict the five-year survival of patients with lung cancer. The re-coding method is used for data processing, the eigenvalues are re-coded to adapt to the construction of the model, and the data are balanced by a variety of sampling methods to improve the applicability of the model. The construction method of the model is based on logistic regression, fully connected neural network, random forest and XGBOOST, evaluate the performance and select the optimal model. The results show that among the four constructed models, XGBOOST is selected as the optimal model with faster training speed, higher accuracy and the highest AUC value, it has advantages in memory occupation and time-consuming. The tumor stage and whether surgery or not and treatment difficulty have certain decisive factors for the prognosis of patients.


Cite This Article

APA Style
Xie, Y., Xia, J. (2022). Prognosis analysis of lung cancer patients. Journal of Intelligent Medicine and Healthcare, 1(1), 43-54.
Vancouver Style
Xie Y, Xia J. Prognosis analysis of lung cancer patients. J Intell Medicine Healthcare . 2022;1(1):43-54
IEEE Style
Y. Xie and J. Xia, "Prognosis Analysis of Lung Cancer Patients," J. Intell. Medicine Healthcare , vol. 1, no. 1, pp. 43-54. 2022.

cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1129


  • 707


  • 0


Share Link