Key result
Machine learning and deep learning advance lung disease detection, though key implementation challenges remain.
Why the study?
Artificial intelligence techniques are increasingly used for lung disease detection, but gaps and issues in conventional research methods remain to be addressed.
Systematic Review (n=20)
This systematic review outlines the current landscape of machine learning and deep learning techniques for detecting various lung diseases, identifying key gaps for future research.
ML and DL techniques for lung disease detection require prospective validation before clinical adoption; extends the field by mapping key research gaps and priorities.
Artificial Intelligence (AI) advancements have astonishingly taken place in the last decade, and it is seen their way into innumerable applications from driverless cars to medical diagnosis. AI is being highly used to identify lung diseases in the present years. Its main aim is to estimate human cognition in the analysis of complicated medical data attained from diagnostic tests for lung diseases. In this review paper, 20 research papers are studied based on different techniques of machine learning as well as deep learning employed for the detection of lung disease. In addition, research papers are reviewed on the basis of diverse kinds of lung diseases, namely tuberculosis, COVID-19, pneumonia, involving lung cancer by classifying the papers based on the methods, like Random forest, Deep CNN, voting classifier, etc. Then, gaps and issues in the research identified in conventional works are enlisted. This helps the researchers in finding a solution and progress their research. The literature review examines various factors when analyzing works, including the datasets used, metrics for evaluating performance, methods employed for detection/classification, and the performance achieved by those detection methods. By analyzing the existing literary works on lung disease detection, the review identifies research challenges that can guide researchers to enhance their work and suggests future directions for improvement.
No takes yet. Share an insight, caveat, or question.
Mamachan et al. (2023) conducted a systematic review in Lung diseases (tuberculosis, COVID-19, pneumonia, lung cancer) (n=20). Machine learning and deep learning techniques was evaluated on Performance of detection methods. A systematic review of 20 research papers evaluated machine learning and deep learning techniques for lung disease detection, identifying research challenges and future directions.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: