Discriminating insulin resistance in middle-aged nondiabetic women using machine learning approaches DOI Creative Commons
Zailing Xing, Henian Chen, Amy C. Alman

et al.

AIMS Public Health, Journal Year: 2024, Volume and Issue: 11(2), P. 667 - 687

Published: Jan. 1, 2024

<abstract><sec> <title>Objective</title> <p>We employed machine learning algorithms to discriminate insulin resistance (IR) in middle-aged nondiabetic women.</p> </sec><sec> <title>Methods</title> <p>The data was from the National Health and Nutrition Examination Survey (2007–2018). The study subjects were 2084 women aged 45–64. analysis included 48 predictors. We randomly divided into training (n = 1667) testing 417) datasets. Four techniques IR: extreme gradient boosting (XGBoosting), random forest (RF), (GBM), decision tree (DT). area under curve (AUC) of receiver operating characteristic (ROC), accuracy, sensitivity, specificity, positive predictive value, negative F1 score compared as performance metrics select optimal technique.</p> <title>Results</title> XGBoosting algorithm achieved a relatively high AUC 0.93 dataset 0.86 IR using predictors followed by RF, GBM, DT models. After selecting top five build models, XGBoost with 0.90 (training dataset) (testing remained prediction model. SHapley Additive exPlanations (SHAP) values revealed associations between IR, namely BMI (strongly impact on IR), fasting glucose positive), HDL-C (medium negative), triglycerides glycohemoglobin positive). threshold for identifying 29 kg/m<sup>2</sup>, 100 mg/dL, 54.5 89 5.6% BMI, glucose, HDL-C, triglycerides, glycohemoglobin, respectively.</p> <title>Conclusion</title> demonstrated superior discriminating women, predictors.</p> </sec></abstract>

Language: Английский

Initial seizure episodes risk factors identification during hospitalization of ICU patients: A retrospective analysis of the eICU collaborative research database DOI
Nan Cheng, Zhuobiao Yi,

Jiayue Wang

et al.

Journal of Clinical Neuroscience, Journal Year: 2025, Volume and Issue: 136, P. 111266 - 111266

Published: April 21, 2025

Language: Английский

Citations

0
Improved liver disease prediction from clinical data through an evaluation of ensemble learning approaches DOI Creative Commons
Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Zhongming Zhao

et al.

BMC Medical Informatics and Decision Making, Journal Year: 2024, Volume and Issue: 24(1)

Published: June 7, 2024

Liver disease causes two million deaths annually, accounting for 4% of all globally. Prediction or early detection the via machine learning algorithms on large clinical data have become promising and potentially powerful, but such methods often some limitations due to complexity data. In this regard, ensemble has shown results. There is an urgent need evaluate different then suggest a robust algorithm in liver prediction.

Language: Английский

Citations

3
Liver disease classification using histogram-based gradient boosting classification tree with feature selection algorithm DOI
Prasannavenkatesan Theerthagiri

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 100, P. 107102 - 107102

Published: Nov. 1, 2024

Language: Английский

Citations

3
An Efficient Brain Tumor Segmentation Method Based on Adaptive Moving Self-Organizing Map and Fuzzy K-Mean Clustering DOI Creative Commons
Surjeet Dalal, Umesh Kumar Lilhore, Poongodi Manoharan

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(18), P. 7816 - 7816

Published: Sept. 12, 2023

Brain tumors in Magnetic resonance image segmentation is challenging research. With the advent of a new era and research into machine learning, tumor detection generated significant interest world. This presents an efficient technique using adaptive moving self-organizing map Fuzzyk-mean clustering (AMSOM-FKM). The proposed method mainly focused on extraction region. AMSOM artificial neural whose training unsupervised. utilized online Kaggle Brats-18 brain dataset. dataset consisted 1691 images. was partitioned 70% training, 20% testing, 10% validation. model based various phases: (a) removal noise, (b) selection feature attributes, (c) classification, (d) segmentation. At first, MR images were normalized Wiener filtering method, Gray level co-occurrences matrix (GLCM) used to extract relevant attributes. separated from non-tumor classification approach. last, FKM distinguish region surrounding tissue. AMSOM-FKM existing methods, i.e., Fuzzy-C-means K-mean (FMFCM), hybrid self-organization mapping-FKM, implemented over MATLAB compared comparison parameters, sensitivity, precision, accuracy, similarity index values. achieved more than better results methods.

Language: Английский

Citations

8
Drag force on a microrobot propelled through blood DOI Creative Commons
Chenjun Wu, Toshihiro Omori, Takuji Ishikawa

et al.

Communications Physics, Journal Year: 2024, Volume and Issue: 7(1)

Published: July 13, 2024

Abstract Controlling microrobot locomotion in vessels and capillaries is crucial for precise drug delivery minimally invasive surgeries. However, this challenging due to the complex interactions with red blood cells (RBCs) difficulty navigating within dense environment. Here, we construct a numerical framework evaluate relative resistance coefficient ( $${C}_{{{{{{{{\rm{r}}}}}}}}}^{* }$$ C r * ) of propelled through RBC suspensions. Our experiments validate results. We find that increases smaller microrobots higher hematocrit levels, while magnetic force strength weakly impacts . than macroscale robot estimated from apparent viscosity suspension. The aspect ratio prolate ellipsoidal influences along its long-axis direction. Additionally, machine learning accurately predicts These insights could enhance design control medical applications.

Language: Английский

Citations

2
Enhancing Disease Diagnosis: Leveraging Machine Learning Algorithms for Healthcare Data Analysis DOI

Monali Ramteke,

Shital Raut

IETE Journal of Research, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 22

Published: Dec. 11, 2024

Healthcare data analysis has emerged as one of the most promising fields study in recent years. There are different types healthcare industry, such medical test results, blood reports, X-rays, CT, MRI, ultrasound, clinical data, omics and sensor data. One important useful techniques for analysing this complicated is machine learning (ML). ML proving to be a artificial intelligence (AI) technique analysis. To accurately predict outcomes employs variety statistical cutting-edge algorithms. In years, approaches have been applied disease diagnosis. The paper provides comprehensive literature survey based on diagnose various diseases. importance discussed with applications. This will motivate advanced research intelligence-driven by showing its potential We also discuss challenges that arise when applying Furthermore, introduces new approach ensemble through explainable stacking. By integrating (XAI) stacking method, we aim not only enhance predictive accuracy but improve interpretability model. proposed model outperforms existing categorisation models, enhancing both performance efficiency diagnostic process. addition, suggest several future directions further work area.

Language: Английский

Citations

2
Machine learning model matters its accuracy: a comparative study of ensemble learning and AutoML using heart disease prediction DOI
Yagyanath Rimal,

Siddhartha Paudel,

Navneet Sharma

et al.

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(12), P. 35025 - 35042

Published: Sept. 28, 2023

Language: Английский

Citations

6
Driving Technologies of Industry 5.0 in the Medical Field DOI
Surjeet Dalal, Bijeta Seth, Magdalena Rădulescu

et al.

Emerald Publishing Limited eBooks, Journal Year: 2023, Volume and Issue: unknown, P. 267 - 292

Published: Oct. 12, 2023

Customers today expect businesses to cater their individual needs by tailoring the products they purchase own preferences. The term "Industry 5.0" refers a new wave of manufacturing that aims meet each customer's unique demands. Even while Industry 4.0 allowed for mass customization, wasn't good enough before, customers demand individualized at scale, and 5.0 is driving transition from customization personalization these It caters consumer meeting More specialized components use in medicine are made possible widespread 5.0. These parts included into medical care patient specific In current revolution, an enabling technology can produce implants, artificial organs, bodily fluids, transplants with pinpoint accuracy. With advent AI-enabled sensors, we now live world where data be swiftly analyzed. Machines may programmed make complex choices on fly. field, innovations allow exact measurement monitoring human body variables according individual's needs. They aid body's response training peak performance. allows digital dissemination accurate healthcare networks. order collect exchange relevant data, every equipment online.

Language: Английский

Citations

4
Early-stage stroke prediction based on Parkinson and wrinkles using deep learning DOI

Thotakura Haritha,

A.V. Santhosh Babu

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: 36(30), P. 18781 - 18805

Published: July 31, 2024

Language: Английский

Citations

1
Optimization of tree-based machine learning algorithms for improving the predictive accuracy of hepatitis C disease DOI

Femilda Josephin Joseph Shobana Bai,

R. Anita Jasmine

Elsevier eBooks, Journal Year: 2024, Volume and Issue: unknown, P. 523 - 545

Published: Jan. 1, 2024

Language: Английский

Citations

1