Impact of feature scaling on machine learning models for the diagnosis of diabetes

Ozsahin, Dilber Uzun; Mustapha, Mubarak Taiwo; Mubarak, Auwalu Saleh; Ameen, Zubaida Said; Uzun, Berna

doi:10.1109/aie57029.2022.00024

Cited by 32 publications

(14 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Data preprocessing is a crucial and common first step in any deep learning project [ 21 , 22 ]. It enables raw data to be adequately prepared in formats acceptable by the network.…”

Section: Methodsmentioning

confidence: 99%

Evaluating the Performance of Deep Learning Frameworks for Malaria Parasite Detection Using Microscopic Images of Peripheral Blood Smears

Ozsahin

Mustapha²,

Duwa³

et al. 2022

Diagnostics

View full text Add to dashboard Cite

Malaria is a significant health concern in many third-world countries, especially for pregnant women and young children. It accounted for about 229 million cases and 600,000 mortality globally in 2019. Hence, rapid and accurate detection is vital. This study is focused on achieving three goals. The first is to develop a deep learning framework capable of automating and accurately classifying malaria parasites using microscopic images of thin and thick peripheral blood smears. The second is to report which of the two peripheral blood smears is the most appropriate for use in accurately detecting malaria parasites in peripheral blood smears. Finally, we evaluate the performance of our proposed model with commonly used transfer learning models. We proposed a convolutional neural network capable of accurately predicting the presence of malaria parasites using microscopic images of thin and thick peripheral blood smears. Model evaluation was carried out using commonly used evaluation metrics, and the outcome proved satisfactory. The proposed model performed better when thick peripheral smears were used with accuracy, precision, and sensitivity of 96.97%, 97.00%, and 97.00%. Identifying the most appropriate peripheral blood smear is vital for improved accuracy, rapid smear preparation, and rapid diagnosis of patients, especially in regions where malaria is endemic.

show abstract

“…Data preprocessing is a crucial and common first step in any deep learning project [ 21 , 22 ]. It enables raw data to be adequately prepared in formats acceptable by the network.…”

Section: Methodsmentioning

confidence: 99%

Evaluating the Performance of Deep Learning Frameworks for Malaria Parasite Detection Using Microscopic Images of Peripheral Blood Smears

Ozsahin

Mustapha²,

Duwa³

et al. 2022

Diagnostics

View full text Add to dashboard Cite

show abstract

“…There are various techniques for feature scaling, and these are: standard scaler, minmaxscaler, robust scalar, and maxabsscaler [35]. In this study, 1) and (2) [37].…”

Section: Features Scalingmentioning

confidence: 98%

Multi-Category Prediction of Students’ Academic Performance Using Machine Learning: For Students Joining Higher Educational Institution in Ethiopia

Ahmed,

Tolera,

shebera

2023

Preprint

View full text Add to dashboard Cite

Following the deployment of the Learning Management System (LMS) platform in higher educational institutions in Ethiopia, a massive amount of potentially helpful but as-yet untapped educational data has been generated. Despite the fact that the data is powerful enough to contribute to reducing student dropout rates through the application of modern educational data mining techniques such as machine learning, it has not been successfully employed to tackle student academic performance problems in higher education institutions(HEIs). As a result, a machine learning model was proposed based on data from three semesters of undergraduate students at Bule Hora University. To predict students' academic achievement, five machine learning methods (SVM, Random Forest, KNN, Gradient Boosting, and Decision Tree) were used. The Decision Tree model outperformed other models with a promising result of 97.3% on test accuracy and was selected as a proposed model. Moreover, our findings suggest that academic factors (entrance result, study time, attendance, and Internet access) and socio-demographic factors (age, gender, father job, mother job, family size, and address) had a greater impact on students' academic success. However, the academic performance of students was less affected by additional features like extra classes, another job, and guidance and counselling. Moreover, we are working on improving the accuracy of the proposed model. In this study, the student entrance result is the only variable used from the pre-university data. However, a CGPA result is not sufficient to qualify a student. Therefore, in the future, the exit exam results of the students will be incorporated.

show abstract

“…The training set is used to train the models, whilst the testing set is reserved for the final model evaluation. To ensure that all the numerical variables contribute equally to our models (44), we applied the max-min scaling method to the numerical variables to bring them to a common scale before training the models. This is because some of the numerical variables were measured on different scales.…”

Section: Training and Testing Datasetsmentioning

confidence: 99%

Using machine learning to evaluate the value of genetic liabilities in classification of hypertension within the UK Biobank

MacCarthy,

Pazoki

2024

Preprint

View full text Add to dashboard Cite

Background and objective: Hypertension increases the risk of cardiovascular diseases (CVD) such as stroke, heart attack, heart failure, and kidney disease, contributing to global disease burden and premature mortality. Previous studies have utilized statistical and machine learning techniques to develop hypertension prediction models. Only a few have included genetic liabilities and evaluated their predictive values. This study aimed to develop an effective hypertension prediction model and investigate the potential influence of genetic liability for risk factors linked to CVD on hypertension risk using Random Forest (RF) and Neural Network (NN). Materials and methods: The study included 244,718 participants of European ancestry. Genetic liabilities were constructed using previously identified genetic variants associated with various cardiovascular risk factors through genome-wide association studies (GWAS). The sample was randomly split into training and testing sets at a 70:30 ratio. We used RF and NN techniques to develop prediction models in the training set with or without feature selection. We evaluated the models' discrimination performance using the area under the curve (AUC), calibration, and net reclassification improvement in the testing set. Results: The models without genetic liabilities achieved AUCs of 0.70 and 0.72 using RF and NN methods, respectively. Adding genetic liabilities resulted in a modest improvement in the AUC for RF but not for NN. The best prediction model was achieved using RF (AUC =0.71, Spiegelhalter z score= 0.10, P-value= 0.92, calibration slope=0.99) constructed in stage two. Conclusion: Incorporating genetic factors in the model may provide a modest incremental value for hypertension prediction beyond baseline characteristics. Our study highlighted the importance of genetic liabilities for both total cholesterol and LDL within the same prediction model adds value to the classification of hypertension.

show abstract

Impact of feature scaling on machine learning models for the diagnosis of diabetes

Cited by 32 publications

References 31 publications

Evaluating the Performance of Deep Learning Frameworks for Malaria Parasite Detection Using Microscopic Images of Peripheral Blood Smears

Evaluating the Performance of Deep Learning Frameworks for Malaria Parasite Detection Using Microscopic Images of Peripheral Blood Smears

Multi-Category Prediction of Students’ Academic Performance Using Machine Learning: For Students Joining Higher Educational Institution in Ethiopia

Using machine learning to evaluate the value of genetic liabilities in classification of hypertension within the UK Biobank

Contact Info

Product

Resources

About