In this review, we zeroed in on utilizing machine learning strategies to classify lung diseases. The dataset,
which contains data from 200 occurrences and 10 attributes, was gathered from hospitals in Delhi. Using
the WEKA platform, the data underwent pre-processing that included addressing missing values and
randomizing the dataset. Data training was done using the K-Overlay Cross-Validation technique, and
classification was done using five machine learning algorithms: Bayesian networks, logistic model trees,
stowing, logistic regression, and random forests. Comparing the Random Forest method to the other
algorithms, the study discovered that it was the most accurate in classifying lung illnesses. It outperformed
the accuracy of Bayesian networks, logistic model trees, logistic regression, and stowing, with an accuracy
of almost 90.1538%. Different factual measurements were utilized to decide the algorithms' adequacy.
These included kappa insights, mean outright mistake, root mean squared blunder, relative outright blunder,
relative root mean squared mistake, explicitness, precision, review, and F-measure. Analysts found that
machine learning algorithms, and explicitly Irregular Woods, can accurately classify lung diseases. The
outcomes demonstrate the potential of these algorithms for decision-making and medical diagnosis. For
researchers and healthcare professionals working in the subject of classifying lung diseases, the study
offers useful insights.