Open Access Open Access  Restricted Access Subscription or Fee Access

Diabetes Prediction Using the Random Forest Algorithm and Machine Learning

P. Hari Krishna, D. Snehardhi, Y. Naveen, V. Siddhartha

Abstract


Early disease detection is crucial in the medical industry in order to prevent the disease. Diabetes is a perilous illness characterized by the body's inability to produce or properly respond to insulin, leading to abnormally high levels of sugar in the bloodstream. One of the deadliest diseases, it affects a large number of people. In order to prepare for the sickness, it is essential to understand its symptoms. This condition can be brought on by ageing, inactivity, inherited diabetes, a poor diet, high blood pressure, etc. The healthcare sector has a lot of databases, so using big data analytics, we can find knowledge in the data by looking for hidden patterns and unknown correlations, and then forecast the result appropriately. In order to improve classification prediction, we developed a diabetes prediction model in this study using a machine learning algorithm. Using a Pima Indian Dataset, this research work forecasts the presence of diabetes. To establish if a diabetes diagnosis is correct or incorrect, machine learning algorithms analyse the dataset. The training and testing portions of the dataset employed in this study are split 70:30, respectively. Based on a patient's current medical record, the model determines whether they have diabetes. With a prediction accuracy of 95.89, the recommended ML model exceeds the previously disclosed methods.


Full Text:

PDF

References


Aljumah AA, Ahamad MG, Siddiqui MK. Application of data mining: Diabetes health care in young and old patients. J King Saud Univ Comput Inf Sci. 2013; 25(2): 127–136. doi:10.1016/j.jksuci.2012.10.003.

Arora R, Suman. Comparative Analysis of Classification Algorithms on Different Datasets using WEKA. Int J Comput Appl. 2012; 54(13): 21–25. doi:10.5120/8626-2492

Bamnote MP, GR. Design of Classifier for Detection of Diabetes Mellitus Using Genetic Programming. In: Advances in Intelligent Systems and Computing. Switzerland: Springer; 2014; 1: 763–770. doi:10.1007/978-3-319-11933-5.

Choubey DK, Paul S, Kumar S, Kumar S. Classification of Pima indian diabetes dataset using naive bayes with genetic algorithm as an attribute selection. InCommunication and computing systems: proceedings of the international conference on communication and computing system (ICCCS 2016) 2017 Feb 15 (pp. 451-455).

Sisodia D, Shrivastava SK, Jain RC. ISVM for face recognition. Proceedings 2010 International Conference on Computational Intelligence and Communication Networks. 2010; 554–559.

Sneha N, Gangil T. Analysis of diabetes mellitus for early prediction using optimal features selection. Journal of Big data. 2019 Dec;6(1):1-9.

Debadri Dutta, Debpriyo Paul, Parthajeet Ghosh. Analyzing Feature Importance’s for Diabetes Prediction using Machine Learning. IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON). 2018; 924–928.

Kaur H, Kumari V. Predictive modelling and analytics for diabetes using a machine learning approach. Appl Comput Inform. 2022 Mar 1; 18(1/2): 90–100.

Vijiya Kumar K, Lavanya B, Nirmala I, Sofia Caroline S. Random Forest Algorithm for the Prediction of Diabetes. IEEE Proceeding of International Conference on Systems Computation Automation and Networking. 2019; 1–5.

Md. Faisal Faruque, Asaduzzaman, Sarker Iqbal H. Performance Analysis of Machine Learning Techniques to Predict Diabetes Mellitus. IEEE International Conference on Electrical, Computer and Communication Engineering (ECCE). 2019 Feb 7–9; 1–4.

Sisodia D, Sisodia DS. Prediction of diabetes using classification algorithms. Procedia Comput Sci. 2018 Jan 1; 132: 1578–85.

Joshi Tejas N, Chawan Pramila M. Diabetes Prediction Using Machine Learning Techniques. Int J Eng Res Appl. 2018 Jan; 8(1)(Part -II): 09–13.


Refbacks

  • There are currently no refbacks.