Disease Detection and Prediction Using the Liver Function Test Data: A Review of Machine Learning Algorithms

Altaf, Ifra; Butt, Muheet Ahmed; Zaman, Majid

doi:10.1007/978-981-16-2597-8_68

Cited by 15 publications

(12 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because when the regression tree is taken into account, the size of the M5 model created is relatively little. In a normal regression, the number of rules is equal to the total number of occurrences of the target variable, but in M5 model trees, the number of rules may be counted [27,28].…”

Section: Experimental Evaluationmentioning

confidence: 99%

How M5 Model Trees (M5-MT) on Continuous Data Are Used in Rainfall Prediction: An Experimental Evaluation

Fayaz¹,

Zaman²,

Kaul³

et al. 2022

RIA

Self Cite

View full text Add to dashboard Cite

When using machine learning to predict a class with a continuous numeric value, there are several issues. Only a few machine-learning approaches are capable of doing so, but it remains one of the most difficult jobs to do. In this paper, we show how to use the M5 Model Tree, an approach that can handle continuous numeric data. This method is a stepwise procedure that employs linear functions at the leaf nodes of any created decision tree inducer (such as CART). These M5 model trees provide basic practical formulas such as standard deviation (SD), standard deviation reduction (SDR), cost-complexity pruning (CCP), and so on, which may be simply applied to different benchmark data by another user. This study examines the M5 Model Tree algorithm's capabilities for analysing rainfall data in the Kashmir portion of India's Union Territory of Jammu & Kashmir. One of the best suited models was the M5 model tree, which was built using (70–30) percent training and test ratios, respectively, and predicted an RMSE of 2.593, an MAE of 1.68, and a correlation coefficient (R2) of 0.478. Furthermore, M5 model trees produce models with a minimal number of trails, requiring less computing effort and making them more practical to use.

show abstract

Section: Experimental Evaluationmentioning

confidence: 99%

How M5 Model Trees (M5-MT) on Continuous Data Are Used in Rainfall Prediction: An Experimental Evaluation

Fayaz¹,

Zaman²,

Kaul³

et al. 2022

RIA

Self Cite

View full text Add to dashboard Cite

show abstract

“…Dataset Accuracy Kabir and Simone [30] 2019 Stacked Ensemble ILPD 73.4% Bihter [31] 2020 Neural Network ILPD 73.28% Razali, et al [33] 2020 Bayesian Model ILPD 70.52% Barik [34] 2021 Hybrid XGBoost PIMA 74.10% Singh, et al [35] 2021 Coarse Gaussian SVM ILPD 71.4% Altaf, et al [8] 2022 Voting Ensemble with MDI PIMA 78.35% Altaf, et al [8] 2022 Voting Ensemble with MDI ILPD 74.03%…”

Section: Author Year Modelmentioning

confidence: 99%

“…With time it has spread into many business areas [1][2][3] and is originating in medical field too with the increase in the complication and evolution of data in biological sciences, AI is gradually being applied within the field. The AI technologies such as machine learning (ML) and deep learning (DL) [4][5][6][7] have played a foremost role in the detection and prediction of diseases [8,9] either by means of the disease symptom datasets [10,11] or medical image datasets, which have helped the doctors in a positive way.…”

Section: Introductionmentioning

confidence: 99%

Hard Voting Meta Classifier for Disease Diagnosis using Mean Decrease in Impurity for Tree Models

Altaf

Butt²,

Zaman³

2022

Self Cite

View full text Add to dashboard Cite

To predict and detect various diseases, machine learning techniques are increasingly being used in the field of medical science. This study puts forward a bagging meta-estimator and feed forward neural network based voting ensemble with mean decrease in impurity feature selection to classify the disease datasets. The work was carried out using the Jupyter notebook data analysis tool, and Python 3 is used as a programming language. In this study, two chronic disease datasets - Indian Liver Patient dataset and the PIMA Indians diabetes dataset are used for building and testing the proposed model. The datasets are split into training and testing data in the ratio of 70:30. The experimental results illustrate that our proposed voting ensemble has an improved performance compared to the individual base learners. We also compared the accuracy of the model before and after the application of feature reduction technique. The results revealed that the accuracy increased with the removal of unimportant features. By using the proposed ensemble model, the average MSE, bias and variance were calculated as 0.311, 0.217 and 0.094 respectively for ILPD dataset. Similarly for PIMA dataset, the average MSE, bias and variance were calculated as 0.233, 0.186 and 0.047 respectively. These statistical parameters record a low score for ensemble classifier as compared to the individual constituent classifiers.

show abstract

“…The collected diabetes dataset contains 3350 records with 1645 female patient records and 1696 male patient records (Figure 9). The dataset contains 20 The acquired data can be used to predict the diabetes disease from the hepatic [34] as well as lipid panel and also the major risk factors can be identified that affect the diabetes disease. The data will enhance opportunities for the diabetes prediction and can be used for comparing the predictions with those given by standard benchmark diabetes datasets.…”

Section: 1value Of the Datamentioning

confidence: 99%

ETL for disease indicators using brute force rule-based NLP algorithm and metadata exploration

2022

IJATEE

View full text Add to dashboard Cite

Healthcare data is generated at an extensive rate every single second making the healthcare data growth an exponential problem. Every type of data related to the health status of an individual is termed as health data that comprises of the clinical metrics together with behavioural, ecological, and economic and social [1] health related information. Data driven health technologies [2−6] are undoubtedly bringing the ground-breaking changes to revitalize the healthcare sector. They can even arrange for assistance in diagnosing and predicting certain diseases with the help of using the diagnostic laboratory test reports [7−10] to deliver the best results. Likewise, this can lead to improved effectiveness and lower the expenditures of carrying out the biochemical tests. The advance in operational proficiency can lead to an improved care. *Author for correspondenceThe several sources of health data consist of hospital records, medical histories of patients, administrative data, results of medical check-ups and examinations, [11] etc. Healthcare data also take account of a massive amount of medical data in the form of electronic medical record (EMR) and electronic health record (EHR). EMR is the subset of EHR [12] and are time and again used interchangeably. For diagnosis and treatment, mostly EMR is used. EHR is digital records of health data that contain a lot beyond EMR. Lab tests and diagnostic procedures are included in the EMRs. A diagnostic report is a set of biochemical tests that provide information regarding a person's health. The collected data having diagnostic labels can benefit in the automatic diagnosis of various diseases. Consequently, it can arrange for a prompt diagnostic reference for doctors other than helping to predict the disease ahead of time.

show abstract

Disease Detection and Prediction Using the Liver Function Test Data: A Review of Machine Learning Algorithms

Cited by 15 publications

References 41 publications

How M5 Model Trees (M5-MT) on Continuous Data Are Used in Rainfall Prediction: An Experimental Evaluation

How M5 Model Trees (M5-MT) on Continuous Data Are Used in Rainfall Prediction: An Experimental Evaluation

Hard Voting Meta Classifier for Disease Diagnosis using Mean Decrease in Impurity for Tree Models

ETL for disease indicators using brute force rule-based NLP algorithm and metadata exploration

Contact Info

Product

Resources

About