Short-term Lung Cancer Survival Prediction: Combining Linear Regression and Convolutional Neural Network

被引：0

作者：

Wang, Xuandi ^{[1
]}

Zeng, Kevin ^{[2
]}

Shalaginov, Mikhail Y. ^{[3
]}

Lin, Shuang Xiang ^{[4
]}

Zeng, Tingying Helen ^{[5
]}

机构：

[1] BASIS Int Sch Hangzhou, Hangzhou, Zhejiang, Peoples R China

[2] Acad Adv Res & Dev, 14th Floor,1 Broadway, Cambridge, MA 02142 USA

[3] MIT, Dept Mat Sci & Engn, 77 Massachusetts Ave, Cambridge, MA 02139 USA

[4] Zhejiang Univ, Sch Med, Dept Radiol, Affiliated Hosp 2, Hangzhou, Zhejiang, Peoples R China

[5] Acad Adv Res & Dev, Div Career Educ, 14th Floor,1 Broadway, Cambridge, MA 02142 USA

来源：

2024 IEEE CLOUD SUMMIT, CLOUD SUMMIT 2024 | 2024年

关键词：

Survival Prediction; Machine Learning; Linear Regression; Lung Cancer; Convolutional Neural Network;

D O I：

10.1109/Cloud-Summit61220.2024.00014

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Lung cancer, one of the most common and deadly cancers, could be a great financial and mental burden to patients and their families. Thus, it is important to develop a model that assesses the patients' conditions and provide insightful feedback for doctors to refer to. One such feedback that proves valuable is survival prediction, the assessment of the chances to stay alive in a given period of time. In this study, we propose to use linear regression to analyze clinical data and Convolutional Neural Network (CNN) models to analyze Computer Tomography (CT) scans data to complete the task of lung cancer survival prediction in short-term timespan, within 6 months. The linear regression and CNN model achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.654 and 0.572, respectively, while the combination of the two models yields excellent AUROC of 0.789. The improvement in combined results provides valuable insights to the feasibility of implementing hybrid models on cancer survival prediction.

引用

页码：42 / 47

页数：6

共 17 条

[1]

Aerts Hugo J W L, 2019, TCIA

[2] Predicting lung cancer survival based on clinical data using machine learning: A review [J].

Altuhaifa, Fatimah Abdulazim ;

Win, Khin Than ;

Su, Guoxin .

COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 165

[3]

[Anonymous], 2015, Tech. Rep.

[4]

Baker Q. B., 2023, 2023 4 INT C INT DAT, P35, DOI [10.1109/IDSTA58916.2023.10317871, DOI 10.1109/IDSTA58916.2023.10317871]

[5]

COX DR, 1972, J R STAT SOC B, V34, P187

[6] Lung cancer survival period prediction and understanding: Deep learning approaches [J].

Doppalapudi, Shreyesh ;

Qiu, Robin G. ;

Badr, Youakim .

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2021, 148

[7]

Dorwart L., 2022, How much does lung cancer treatment cost?

[8]

GfG, 2024, Linear regression in machine learning.

[9]

Haarburger C, 2019, I S BIOMED IMAGING, P1197, DOI [10.1109/ISBI.2019.8759499, 10.1109/isbi.2019.8759499]

[10]

Jabbari Fattaneh, 2020, Lung Cancer Survival Prediction Using InstanceSpecific Bayesian Networks, DOI [10.1007/978-3-030-59137-3_14, DOI 10.1007/978-3-030-59137-3_14]

← 1 2 →