An Analysis of the Machine Learning Algorithm for Early-Stage Prediction of Lung Cancer

Even though lung cancer poses a serious risk to people’s health, its early symptoms are comparable to those of bronchitis and the common cold. Clinical practitioners may be able to save lives and enhance patient care by utilizing machine learning techniques to customize screening and preventive strategies to each patient’s unique needs. Researchers need to preprocess the information, extract relevant clinical and demographic factors from patient records, and prepare it for machine learning model training to be able to effectively forecast the development due to lung cancer. The motive or intention of the project is to make use of clinical additionally demographic data to build a machine learning (ML) model that predicts lung cancer early and with accuracy. It also aims to contribute to the growing field of medical research ML applications that could improve patient outcomes. Both men and women are usually affected by lung cancer because of the uncontrollably growing lung cells. This seriously impairs one’s ability to breathe in and out of the chest. World Health Organization claims that cigarettes along with passive smoking are the primary reasons behind lung cancer. In contrast to other malignancies, lung cancer is killing more individuals every day—both young and old. The death rate is still not adequately under control even with the accessibility of cutting-edge health facilities regarding precise diagnosis as well as efficient health care. Early intervention is therefore essential to determine the condition’s signs and symptoms and to help with a more precise diagnosis. These days, the healthcare industry is greatly impacted by machine learning’s superior computing power for precise data analysis and early illness prediction. To categorize data on lung cancer from the machine learning repository at UCI as not harmful or cancerous, we have assessed and presented a variety of machine learning classifier approaches in our work. After converting the prepossessed input data to binary form, the Weka program applies a renowned classifier approach for data classification as either malignant or non-cancerous.