Inflammation of the bladder is the medical term also known as cystitis. Most of the time, the inflammation is caused by a bacterial infection, and it is called a urinary tract infection (UTI). A bladder infection can be painful and tiresome, and it can become a serious health problem if the infection spreads to kidneys in the human body. Cystitis may occur as a reaction to certain drugs, radiation therapy, or potential irritants, such as feminine hygiene spray, long-term use of a catheter. In this chapter, with the help of ensemble approach, 100% accuracy is obtained in all respects such as accuracy is 100% and precision is 100%, F1-score is 100%, sensitivity is 100%, and Kappa score is also 100% for the prediction of inflammation of urinary bladder.
Top1. Introduction
The primary objective of the dataset is to prepare the algorithm of the expert system, which will carry out the tentative diagnosis of inflammation of urinary bladder disease. Preferable understanding of the problem let us consider definition of the disease given by doctors. Surprisingly a patient feels severe pain in lower abdomen and the urination in form of constant urine pushing, micturition pains and sometimes lack of urine keeping. Temperature of the body can arise rapidly, generally it varies from 38
to 42
.
A urinate is feculent and sometimes bloody. At regular treatment, symptoms go off usually within several days. However, there is inclination to returns. At persons with acute inflammation of urinary bladder, we should expect that the infection will turn into protracted form. The data was created by a medical expert as a dataset to test the expert system, which will perform the presumptive diagnosis of inflammation of urinary bladder disease. The basis for rules detection was Data Mining approach. Each instance represents a potential patient (Khang, 2023).
Cystitis may also occur as a complication of another illness like cancer or it may happen after chemotherapy. There are various Cystitis symptoms shown in human like A strong persistent urge to urinate, A burning sensation when urinating, Passing frequent, small amounts of urine, Blood may come during the urine pass (it is also known as hematuria), Passing cloudy or strong-smelling urine, Pelvic discomfort, A feeling of pressure in the lower abdomen, Low-grade fever. The data that has been used in this paper is secondary data and collected from the UCI Machine Learning Repository and has 6 attributes.
Al-Shayea and Bahia (2010) used feed-forward neural networks model to predict the Urinary system Diseases Diagnosis and got the accuracy 99% . Jevita Dwi Fitriana, Budi Prasetiyo,Riza Arifudin, Department of Computer Science, Natural Sciences, State University of Semarang used shafer methods on this expert system of diagnosis of urinary system diseases generates an accuracy value of 87.5% (Krogstad, 2014). Kadhem and Zeki (2014) used OneR model accuracy in urinary bladder prediction shows 79.2% accuracy and 75% precision (Chaudhuri et al., 2021).
Top2. Relevant Literature
Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning algorithms use data as input to predict new output values.
| Year | Method | Classification Accuracy (%) | Sensitivity/Specificity | Kappa | ROC or AUC |
|
Al-Shayea and Bahia (2010)
| Feed-forward back propagation network. | 99% | x | x | x |
|
Kadhem and Zeki (2014)
| Ridor, OneR, and J48 classification algorithms | 79.2% | 75% | x | x |
|
Fitriana et al. (2020)
| forward chaining and dempster shafer method | 87.5% | x | x | x |
| Medjahed et al. (2015) | Support Vector Machine | 100% | 93.33/ 91.11 | x | x |