A Novel Active Learning Technique for Fetal Health Classification Based on Xgboost Classifier DOI
Kaushal Bhardwaj,

Niyati Goyal,

Bhavika Mittal

et al.

Published: Jan. 1, 2024

Ensuring safe pregnancy and reducing maternal infant mortality rates require addressing factors that affect fetal health. The application of machine learning algorithms in monitoring health helps to improve the chances timely intervention better outcomes case any possible issues fetuses. Existing studies offered aid this issue typically train models using a significant portion dataset, ranging mostly around 75%-80%. In work, we propose novel solution implementing an active technique identify most informative data samples for training model leading high accuracy with limited number samples. It employs query function built upon uncertainty diversity criteria which are derived based on properties XGBoost classifier. For deriving soft probabilities obtained unlabelled used while distance among feature space is utilized criteria. proposed approach shows superior performance comparison all state-of-the-art methods. Through analysis experimentation, achieves average higher than 99% by utilizing less 20% dataset training. This demonstrates its efficacy potential monitoring.

Language: Английский

Artificial Intelligence DOI
Lorella Bottino, Marzia Settino, Mario Cannataro

et al.

Published: Jan. 1, 2024

Citations

9
Early Diagnosis and Classification of Fetal Health Status from a Fetal Cardiotocography Dataset Using Ensemble Learning DOI Creative Commons
Adem Kuzu, Yunus Santur

Diagnostics, Journal Year: 2023, Volume and Issue: 13(15), P. 2471 - 2471

Published: July 25, 2023

(1) Background: According to the World Health Organization (WHO), 6.3 million intrauterine fetal deaths occur every year. The most common method of diagnosing perinatal death and taking early precautions for maternal health is a nonstress test (NST). Data on heart rate uterus contractions from an NST device are interpreted based trace printer’s output, allowing diagnosis be made by expert. (2) Methods: in this study, predictive ensemble learning proposed classification (normal, suspicious, pathology) using cardiotocography dataset movements acceleration tests. (3) Results: predictor achieved accuracy level above 99.5% dataset. (4) Conclusions: experimental results, it was observed that can during machine learning.

Language: Английский

Citations

15
Harnessing artificial intelligence for predictive modelling in oral oncology: Opportunities, challenges, and clinical Perspectives DOI Creative Commons
Vishnu Priya Veeraraghavan,

Shikhar Daniel,

Arun Kumar Dasari

et al.

Oral Oncology Reports, Journal Year: 2024, Volume and Issue: 11, P. 100591 - 100591

Published: June 29, 2024

Artificial intelligence (AI) has emerged as a promising tool in oral oncology, particularly the field of prediction. This review provides comprehensive outlook on role AI predicting cancer, covering key aspects such data collection and preprocessing, machine learning techniques, performance evaluation validation, challenges, future prospects, implications for clinical practice. Various algorithms, including supervised learning, unsupervised deep approaches, have been discussed context cancer Additionally, challenges interpretability, accessibility, regulatory compliance, legal are addressed along with research directions potential impact oncology care.

Language: Английский

Citations

5
Machine Learning Models and Applications for Early Detection DOI Creative Commons
Orlando Zapata-Cortés, Martín Darío Arango Serna, Julián Andrés Zapata-Cortés

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(14), P. 4678 - 4678

Published: July 18, 2024

From the various perspectives of machine learning (ML) and multiple models used in this discipline, there is an approach aimed at training for early detection (ED) anomalies. The anomalies crucial areas knowledge since identifying classifying them allows decision making provides a better response to mitigate negative effects caused by late any system. This article presents literature review examine which (MLMs) operate with focus on ED multidisciplinary manner and, specifically, how these work field fraud detection. A variety were found, including Logistic Regression (LR), Support Vector Machines (SVMs), trees (DTs), Random Forests (RFs), naive Bayesian classifier (NB), K-Nearest Neighbors (KNNs), artificial neural networks (ANNs), Extreme Gradient Boosting (XGB), among others. It was identified that MLMs as isolated models, categorized Single Base Models (SBMs) Stacking Ensemble (SEMs). under SBMs' SEMs' implementation achieved accuracies greater than 80% 90%, respectively. In detection, 90% reported authors. concludes applications, fraud, offer viable way identify classify robustly, high degree accuracy precision. are useful they can quickly process large amounts data detect suspicious transactions or activities, helping prevent financial losses.

Language: Английский

Citations

5
Explainable Thyroid Cancer Diagnosis Through Two-Level Machine Learning Optimization with an Improved Naked Mole-Rat Algorithm DOI Open Access
Wojciech Książek

Cancers, Journal Year: 2024, Volume and Issue: 16(24), P. 4128 - 4128

Published: Dec. 10, 2024

Modern technologies, particularly artificial intelligence methods such as machine learning, hold immense potential for supporting doctors with cancer diagnostics. This study explores the enhancement of popular learning using a bio-inspired algorithm—the naked mole-rat algorithm (NMRA)—to assess malignancy thyroid tumors. The utilized novel dataset released in 2022, containing data collected at Shengjing Hospital China Medical University. comprises 1232 records described by 19 features. In this research, 10 well-known classifiers, including XGBoost, LightGBM, and random forest, were employed to evaluate A key innovation is application parameter optimization feature selection within individual classifiers. Among models tested, LightGBM classifier demonstrated highest performance, achieving classification accuracy 81.82% an F1-score 86.62%, following two-level algorithm. Additionally, explainability analysis model was conducted SHAP values, providing insights into decision-making process model.

Language: Английский

Citations

5
The future of bone regeneration: Artificial intelligence in biomaterials discovery DOI

Jinfei Fan,

Jiazhen Xu,

Xiaobo Wen

et al.

Materials Today Communications, Journal Year: 2024, Volume and Issue: 40, P. 109982 - 109982

Published: July 28, 2024

Language: Английский

Citations

4
State-of-the-art progress on artificial intelligence and machine learning in accessing molecular coordination and adsorption of corrosion inhibitors DOI
Taiwo W. Quadri, Ekemini D. Akpan, Saheed E. Elugoke

et al.

Applied Physics Reviews, Journal Year: 2025, Volume and Issue: 12(1)

Published: Jan. 6, 2025

Artificial intelligence (AI) and machine learning (ML) have attracted the interest of research community in recent years. ML has found applications various areas, especially where relevant data that could be used for algorithm training retraining are available. In this review article, been discussed relation to its corrosion science, monitoring control. tools techniques, structure modeling methods, were thoroughly discussed. Furthermore, detailed inhibitor design/modeling coupled with associated limitations future perspectives reported.

Language: Английский

Citations

0
An exploration of distinguishing subjective cognitive decline and mild cognitive impairment based on resting-state prefrontal functional connectivity assessed by functional near-infrared spectroscopy DOI Creative Commons
Zhengping Pu,

Hongna Huang,

Man Li

et al.

Frontiers in Aging Neuroscience, Journal Year: 2025, Volume and Issue: 16

Published: Jan. 8, 2025

Functional near-infrared spectroscopy (fNIRS) has shown feasibility in evaluating cognitive function and brain functional connectivity (FC). Therefore, this fNIRS study aimed to develop a screening method for subjective decline (SCD) mild impairment (MCI) based on resting-state prefrontal FC neuropsychological tests via machine learning. data measured by were collected from 55 normal controls (NCs), 80 SCD individuals, 111 MCI individuals. Differences analyzed among the groups. strength test scores extracted as features build classification predictive models through Model performance was assessed accuracy, specificity, sensitivity, area under curve (AUC) with 95% confidence interval (CI) values. Statistical analysis revealed trend toward compensatory enhanced The showed satisfactory ability differentiate three groups, especially those employing linear discriminant analysis, logistic regression, support vector machine. Accuracies of 94.9% vs. NC, 79.4% SCD, 77.0% NC achieved, highest AUC values 97.5% (95% CI: 95.0%-100.0%) 83.7% 77.5%-89.8%) 80.6% 72.7%-88.4%) NC. developed learning may help predict early-stage impairment.

Language: Английский

Citations

0
Artificial intelligence's applicability in cardiac imaging DOI
Joel J. P. C. Rodrigues, Abdul Razak Mohamed Sikkander, Suman Lata Tripathi

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 181 - 195

Published: Jan. 1, 2025

Citations

0
Predictive Wind Turbine Power Analysis Based on SCADA Data and Machine Learning Algorithms DOI

Zouhir Iourzikene,

Fawzi Gougam,

Djamel Benazzouz

et al.

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 32 - 42

Published: Jan. 1, 2025

Language: Английский

Citations

0