The efficacy of machine learning models in lung cancer risk prediction with explainability

• Published in: PloS one Vol. 19; no. 6; p. e0305035
• Main Authors: Pathan, Refat Khan, Shorna, Israt Jahan, Hossain, Md. Sayem, Khandaker, Mayeen Uddin, Almohammed, Huda I., Hamd, Zuhal Y.
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 13.06.2024
• Subjects: Accuracy; Algorithms; Biology and Life Sciences; Cancer; Cancer therapies; Classification; Computer and Information Sciences; Datasets; Engineering and Technology; Health risks; Humans; Learning algorithms; Literature reviews; Lung cancer; Lung diseases; Lung Neoplasms - diagnosis; Machine Learning; Medical personnel; Medical prognosis; Medical research; Medical screening; Medicine and Health Sciences; Neural networks; Oncology, Experimental; Predictions; Research and Analysis Methods; Risk assessment; Risk Assessment - methods; Risk factors; Support vector machines; Three dimensional imaging; Womens health; United Kingdom > UK; United States > US
• DOI: 10.1371/journal.pone.0305035
• ISSN: 1932-6203

Among many types of cancers, to date, lung cancer remains one of the deadliest cancers around the world. Many researchers, scientists, doctors, and people from other fields continuously contribute to this subject regarding early prediction and diagnosis. One of the significant problems in prediction is the black-box nature of machine learning models. Though the detection rate is comparatively satisfactory, people have yet to learn how a model came to that decision, causing trust issues among patients and healthcare workers. This work uses multiple machine learning models on a numerical dataset of lung cancer-relevant parameters and compares performance and accuracy. After comparison, each model has been explained using different methods. The main contribution of this research is to give logical explanations of why the model reached a particular decision to achieve trust. This research has also been compared with a previous study that worked with a similar dataset and took expert opinions regarding their proposed model. We also showed that our research achieved better results than their proposed model and specialist opinion using hyperparameter tuning, having an improved accuracy of almost 100% in all four models.