Data Mining
provides significant merit to the health care facilities in different fields such as disease diagnosis and mortality prediction. Predictive and descriptive analytics both have a vital role in health care (Tan, 2019). The following are the application areas;
Data mining- machine learning technique can be used to diagnose cancer of the breast, hypertension, heart condition, Parkinson’s disease, renal failure, asthma, and. Tan (2019) noted that researchers tried to use computers and applied theories to determine a bacterial infection. Currently, researchers have proposed to determine the biochemical characteristics in the diagnosis of cancer. In this case, they considered a feature selection algorithm and used a Support Vector Machine classification algorithm to apply the integrated feature selection technique to disease diagnosis (Polat, 2017). Regarding the systematic diagnosis of neural and heart diseases, an author connected an artificial bee colony algorithm and a modified full Bayesian network classifier to successfully predict a disorder, thereby attaining almost 100% accuracy. The Bayesian classifier is evidence of machine learning in the diagnosis of diseases. The Bayesian model and the Jelinek-Mercer smoothing method is used to predict and detect cardiac conditions. Tan (2019) noted that researchers carried out a comparative study of a classification method to detect heart conditions. The researchers then compared the four grouping methods in data mining to predict cardiovascular disorders in clients. Out of the four classifications compared, the Support Vector Machine model turned out to be the best classifier for predicting cardiovascular disorders.
Breast cancer is the most common disease in women. Several researchers conducted an experiment on the breast cancer dataset using the Weka tool and then contrasting the performance of different classification methods (Chaurasia, 2017). Health care professionals have incorporated a hybrid Support Vector Machine based strategy for evolving a predictive model for breast cancer detection.
Many other disorders are also diagnosed using the data mining-machine learning technique. Some authors used artificial neural networks for the detection of renal failure. Decision Tree algorithms such as Iterative Dichotomiser 3, Classification and Regression Trees, and C4.5 have been incorporated for medical detection of hepatitis, diabetes, and cardiac conditions (Peng, 2020). The research conducted using the Support Vector Machine model to predict the diagnosis of diabetes gave promising results. Thus, machine learning reduces the waiting time for clients and minimizes the effort and workforce required.
References
Chaurasia, V. a. (2017). “A novel approach for breast cancer detection using data mining techniques. International Journal of Innovative Research in Computer and Communication Engineering (An ISO 3297: 2007 Certified Organization) Vol 2.
Peng, J. C.-H. (2020). “A Machine-learning Approach to forecast Aggravation Risk in patients with Acute exacerbation of chronic obstructive pulmonary disease with clinical indicators.” Scientific Reports 10, no. 1.
Polat, H. H. (2017). Diagnosis of chronic kidney disease based on support vector machine by feature selection methods.” Journal of medical systems 41, no. 4, 55.
Tan, J. (2019). Adaptive Health Management Information Systems. Jones & Bartlett Learning.