Predicting lung cancer survival based on clinical data using machine learning: A review.
Fatimah Abdulazim Altuhaifa1, Khin Than Win2, Guoxin Su2
1School of Computing and Information Technology, University of Wollongong, NSW, 2500, Australia; Saudi Arabia Ministry of Higher Education, Riyadh, Saudi Arabia.
Computers in Biology and Medicine
|August 25, 2023
Summary
Machine learning aids lung cancer survival prediction using clinical data. However, many studies neglect crucial data pre-processing, potentially introducing bias and limiting accuracy.
Area of Science:
- Oncology and Medical Informatics
- Application of artificial intelligence in healthcare
Background:
- Machine learning (ML) is increasingly used for predicting patient survival times.
- Lung cancer survival prediction using clinical data is a critical area of research.
Approach:
- A systematic literature review of studies from 2000-2023 was conducted using MEDLINE, Scopus, and Google Scholar.
- Thirty studies predicting lung cancer survival with ML and clinical data were analyzed.
- Risk of bias was assessed using the Prediction Model Risk Of Bias Assessment Tool.
Key Points:
- Random forest was the most common ML model (56.6%).
- Age, sex, and N stage were frequently selected features.
- Only 40% of studies adequately addressed missing data; critical pre-processing steps like normalization were often overlooked.
Conclusions:
- The use of ML for lung cancer survival prediction has grown significantly since 2012.
- Inconsistent handling of missing data and lack of standardized pre-processing in most studies may introduce bias.
- Further research is needed to develop comprehensive models that address these data challenges for improved accuracy.
Related Concept Videos
01:21Cancer Survival Analysis
383
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
383
01:25Statistical Methods for Analyzing Epidemiological Data
408
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
408
01:24Kaplan-Meier Approach
179
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
179