AI-Enhanced Multi-Algorithm R Shiny App for Predictive Modeling and Analytics- A Case study of Alzheimer’s Disease Diagnostics (Preprint) DOI
Samuel Kakraba, Wenzheng Han, Sudesh Srivastav

и другие.

Опубликована: Дек. 18, 2024

BACKGROUND Recent studies have demonstrated that AI can surpass medical practitioners in diagnostic accuracy, underscoring the increasing importance of AI-assisted diagnosis healthcare. This research introduces SMART-Pred (Shiny Multi-Algorithm R Tool for Predictive Modeling), an innovative AI-based application Alzheimer's disease (AD) prediction utilizing handwriting analysis OBJECTIVE Our objective is to develop and evaluate a non-invasive, cost-effective, efficient tool early AD detection, addressing need accessible accurate screening methods. METHODS methodology employs comprehensive approach AI-driven prediction. We begin with Principal Component Analysis dimensionality reduction, ensuring processing complex data. followed by training evaluation ten diverse, highly optimized models, including logistic regression, Naïve Bayes, random forest, AdaBoost, Support Vector Machine, neural networks. multi-model allows robust comparison different machine learning techniques To rigorously assess model performance, we utilize range metrics sensitivity, specificity, F1-score, ROC-AUC. These provide holistic view each model's predictive capabilities. For validation, leveraged DARWIN dataset, which comprises samples from 174 participants (89 patients 85 healthy controls). balanced dataset ensures fair our models' ability distinguish between individuals based on characteristics. RESULTS The forest strong achieving accuracy 88.68% test set during analysis. Meanwhile, AdaBoost algorithm exhibited even higher reaching 92.00% after leveraging models identify most significant variables predicting disease. results current clinical tools, typically achieve around 81.00% accuracy. SMART-Pred's performance aligns recent advancements prediction, such as Cambridge scientists' 82.00% identifying progression within three years using cognitive tests MRI scans. Furthermore, revealed consistent pattern across all employed. "air_time" "paper_time" consistently stood out critical predictors (AD). two factors were repeatedly identified influential assessing probability onset, their potential detection risk assessment CONCLUSIONS Even though some limitations exist SMART-Pred, it offers several advantages, being efficient, customizable datasets diagnostics. study demonstrates transformative healthcare, particularly may contribute improved patient outcomes through intervention. Clinical validation necessary confirm whether key this are sufficient accurately real-world settings. step crucial ensure practical applicability reliability these findings practice.

Язык: Английский

Interconnections, trend analysis and forecasting of water-air temperature with water level dynamics in Blue Moon Lake Valley: A statistical and machine learning approach DOI

Shoukat Ali Shah,

Songtao Ai, Wolfgang Rack

и другие.

Journal of Environmental Management, Год журнала: 2025, Номер 379, С. 124829 - 124829

Опубликована: Март 8, 2025

Язык: Английский

Процитировано

1
Enhancing Drug Discovery with AI: Predictive Modeling of Pharmacokinetics Using Graph Neural Networks and Ensemble Learning DOI Creative Commons

R Satheeskumar

Intelligent Pharmacy, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 1, 2024

Язык: Английский

Процитировано

3
Hierarchical Power Output Prediction for Floating Photovoltaic Systems DOI
Mohd Herwan Sulaiman, Zuriani Mustaffa, Mohd Shawal Jadin

и другие.

Energy, Год журнала: 2025, Номер unknown, С. 135883 - 135883

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
A new feature extraction method for AI based classification of heart sounds: dual-frequency cepstral coefficients (DFCCs) DOI Creative Commons
Muhammed Telçeken

The European Physical Journal Special Topics, Год журнала: 2025, Номер unknown

Опубликована: Апрель 15, 2025

Язык: Английский

Процитировано

0
Short-term Air Conditioning Load Prediction Based on Improved Stacking Algorithm DOI Open Access

Liu Jia-kai,

Yongbao Chen, Tao Tang

и другие.

Journal of Physics Conference Series, Год журнала: 2025, Номер 3001(1), С. 012010 - 012010

Опубликована: Апрель 1, 2025

Abstract The heating, ventilation, and air-conditioning systems (HVAC) account for over 40% of the total energy consumption in buildings. This significant proportion highlights substantial potential conservation operational optimization HVAC systems. precise rapid prediction short-term load system is crucial achieving optimized scheduling. Utilizing robust regression capabilities inherent ensemble algorithms within field machine learning, this study has developed an enhanced three-tier stacking predictive model. accuracy generalizability model were evaluated using actual building datasets. results show that demonstrates performance, with Mean Absolute Percentage Error (MAPE) kept below 7% data Coefficient Variation Root Square (CVRMSE) maintained 9%. Compared traditional models, shows improved generalizability, making it a promising choice forecasting.

Язык: Английский

Процитировано

0
Application of machine learning models for predicting zinc oxide nanoparticle size DOI

Surafel Alayou,

Mekdes Mengesha,

Getachew Tizazu

и другие.

Measurement, Год журнала: 2025, Номер unknown, С. 117785 - 117785

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Risk warning based on GA-improved stacking ensemble learning algorithm: a case study of alcohol DOI
Cen Song,

Hanwen Shen,

Jun Zhuang

и другие.

Annals of Operations Research, Год журнала: 2025, Номер unknown

Опубликована: Май 17, 2025

Язык: Английский

Процитировано

0
Exploring Hydrochemical Drivers of Drinking Water Quality in a Tropical River Basin Using Self-Organizing Maps and Explainable AI DOI

Ajayakumar Appukuttan,

C. D. Aju,

Rajesh Reghunath

и другие.

Water Research, Год журнала: 2025, Номер 284, С. 123884 - 123884

Опубликована: Май 21, 2025

Язык: Английский

Процитировано

0
Comparative Study of Random Forest and Support Vector Machine for Land Cover Classification and Post-Wildfire Change Detection DOI Creative Commons

Yong How Jonathan Tan,

Lia Duarte, Ana Claúdia Teodoro

и другие.

Land, Год журнала: 2024, Номер 13(11), С. 1878 - 1878

Опубликована: Ноя. 10, 2024

The land use cover (LULC) map is extensively employed for different purposes. Machine learning (ML) algorithms applied in remote sensing (RS) data have been proven effective image classification, object detection, and semantic segmentation. Previous studies shown that random forest (RF) support vector machine (SVM) consistently achieve high accuracy classification. Considering the important role of Portugal’s Serra da Estrela Natural Park (PNSE) biodiversity nature conversation at an international scale, availability timely on PNSE emergency evaluation periodic assessment crucial. In this study, application RF SVM classifiers, object-based (OBIA) pixel-based (PBIA) approaches, with Sentinel-2A imagery was evaluated using Google Earth Engine (GEE) platform classification a burnt area PNSE. This aimed to detect change closely observe vegetation recovery after 2022 wildfire. combination OBIA achieved highest all metrics. At same time, comparison Normalized Difference Vegetation Index (NDVI) Conjunctural Land Occupation Map (COSc) 2023 year indicated PBIA resembled maps better.

Язык: Английский

Процитировано

2
AI-Enhanced Multi-Algorithm R Shiny App for Predictive Modeling and Analytics- A Case study of Alzheimer’s Disease Diagnostics (Preprint) DOI
Samuel Kakraba, Wenzheng Han, Sudesh Srivastav

и другие.

Опубликована: Дек. 18, 2024

BACKGROUND Recent studies have demonstrated that AI can surpass medical practitioners in diagnostic accuracy, underscoring the increasing importance of AI-assisted diagnosis healthcare. This research introduces SMART-Pred (Shiny Multi-Algorithm R Tool for Predictive Modeling), an innovative AI-based application Alzheimer's disease (AD) prediction utilizing handwriting analysis OBJECTIVE Our objective is to develop and evaluate a non-invasive, cost-effective, efficient tool early AD detection, addressing need accessible accurate screening methods. METHODS methodology employs comprehensive approach AI-driven prediction. We begin with Principal Component Analysis dimensionality reduction, ensuring processing complex data. followed by training evaluation ten diverse, highly optimized models, including logistic regression, Naïve Bayes, random forest, AdaBoost, Support Vector Machine, neural networks. multi-model allows robust comparison different machine learning techniques To rigorously assess model performance, we utilize range metrics sensitivity, specificity, F1-score, ROC-AUC. These provide holistic view each model's predictive capabilities. For validation, leveraged DARWIN dataset, which comprises samples from 174 participants (89 patients 85 healthy controls). balanced dataset ensures fair our models' ability distinguish between individuals based on characteristics. RESULTS The forest strong achieving accuracy 88.68% test set during analysis. Meanwhile, AdaBoost algorithm exhibited even higher reaching 92.00% after leveraging models identify most significant variables predicting disease. results current clinical tools, typically achieve around 81.00% accuracy. SMART-Pred's performance aligns recent advancements prediction, such as Cambridge scientists' 82.00% identifying progression within three years using cognitive tests MRI scans. Furthermore, revealed consistent pattern across all employed. "air_time" "paper_time" consistently stood out critical predictors (AD). two factors were repeatedly identified influential assessing probability onset, their potential detection risk assessment CONCLUSIONS Even though some limitations exist SMART-Pred, it offers several advantages, being efficient, customizable datasets diagnostics. study demonstrates transformative healthcare, particularly may contribute improved patient outcomes through intervention. Clinical validation necessary confirm whether key this are sufficient accurately real-world settings. step crucial ensure practical applicability reliability these findings practice.

Язык: Английский

Процитировано

1