Mortality prediction using data from wearable activity trackers and individual characteristics: An explainable artificial intelligence approach DOI Creative Commons
Byron Graham,

Mark Farrell

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: unknown, P. 126195 - 126195

Published: Dec. 1, 2024

Language: Английский

An Interpretable Machine Learning Model to Predict Hospitalizations DOI Creative Commons
Hagar Elbatanouny, Hissam Tawfik, Tarek Khater

et al.

Clinical eHealth, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
Implementation and Updating of Clinical Prediction Models: A Systematic Review DOI Creative Commons
Alexander Saelmans, Tom M Seinen, Victor Pera

et al.

Mayo Clinic Proceedings Digital Health, Journal Year: 2025, Volume and Issue: unknown, P. 100228 - 100228

Published: May 1, 2025

Language: Английский

Citations

0
A neuro-fuzzy causal approach for pandemic severity forecasting: COVID-19 case study DOI
Reza Omrani, Arash Nemati

International Journal of Data Science and Analytics, Journal Year: 2025, Volume and Issue: unknown

Published: May 31, 2025

Language: Английский

Citations

0
Dynamic multi-dose vaccination with initial immunity on higher-order networks DOI
Yilei Qian, Dawei Zhao, Chengyi Xia

et al.

Proceedings of the Royal Society A Mathematical Physical and Engineering Sciences, Journal Year: 2024, Volume and Issue: 480(2300)

Published: Oct. 1, 2024

Vaccination remains crucial during pandemics for combating disease spread. We here propose a two-layer model multi-dose vaccination policy, considering vaccine hesitancy, initial immunity, as well media-driven information dissemination concerning strategy selection. Moreover, we consider collective opinions through social networks with higher-order interactions. perform numerical simulations to analyse variations in strategies. further compare obtained outcomes the exploration of real data on behaviours. Our research indicates that can regulate vaccination, and models accounting individual immunity align more closely real-world scenarios. Furthermore, find decisions from neighbouring agents is under policies facilitation faster diffusion.

Language: Английский

Citations

2
A tri-light warning system for hospitalized COVID-19 patients: Credibility-based risk stratification for future pandemic preparedness DOI Creative Commons

Chuanjun Xu,

Qinmei Xu, Li Liu

et al.

European Journal of Radiology Open, Journal Year: 2024, Volume and Issue: 13, P. 100603 - 100603

Published: Oct. 17, 2024

Language: Английский

Citations

1
Reassessment of Corporate Credit Risk Identification: Novel Discoveries from Integrated Machine Learning Models DOI

Guoli Mo,

G Zhang,

Chunzhi Tan

et al.

Computational Economics, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 9, 2024

Language: Английский

Citations

1
Adaptive Stacking Ensemble Techniques for Early Severity Classification of COVID-19 Patients DOI Creative Commons
Gun-Woo Kim, Chan-Yang Ju, Hyeri Seok

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(7), P. 2715 - 2715

Published: March 24, 2024

During outbreaks of infectious diseases, such as COVID-19, it is critical to rapidly determine treatment priorities and identify patients requiring hospitalization based on clinical severity. Although various machine learning models have been developed predict COVID-19 severity, most limitations, small dataset sizes, the limited availability variables, or a constrained classification severity levels by single classifier. In this paper, we propose an adaptive stacking ensemble technique that identifies patient separates them into three formats: Type 1 (low high severity), 2 (mild, severe, critical), 3 (asymptomatic, mild, moderate, fatal). To enhance model’s generalizability, utilized nationwide from South Korean government, comprising data 5644 across over 100 hospitals. address our employs data-driven strategies proposed feature selection method. This ensures variables diverse hospital environments. construct optimal models, adaptively selects candidate base classifiers analyzing correlation between their predicted outcomes performance. It then automatically determines multi-layer combination meta-classifiers using greedy search algorithm. further improve performance, applied techniques, including imputation missing values oversampling. The experimental results demonstrate significantly outperform existing AutoML approaches, with improvements 6.42% 8.86% in F1 AUC scores for 1, 9.59% 6.68% 2, 11.94% 9.24% 3, respectively. Consequently, approach improves prediction potentially assists frontline healthcare providers making informed decisions.

Language: Английский

Citations

0
Predicting ICU Admission for COVID-19 Patients in Saudi Arabia: A Comparative Study of AdaBoost and Bagging Methods DOI Open Access
Hamza Ghandorh, Mohammad Zubair Khan, Mehshan Ahmed Khan

et al.

International Journal of Advanced Computer Science and Applications, Journal Year: 2024, Volume and Issue: 15(3)

Published: Jan. 1, 2024

COVID-19's high fatality rate and accurately deter-mining the mortality within a particular geographic region continue to be significant concerns. In this study, authors investigated assessed performance of two advanced machine learning approaches, Adaptive Boosting (AdaBoost) Bootstrap Aggregation (Bagging), as strong predictors COVID- 19-related intensive care unit (ICU) admissions Saudi Arabia. These models may help health-care organizations determine who is at higher risk readmission, allowing for more targeted interventions improved patient outcomes. The found AdaBoost-RF Bagging-RF methods produced most precise models, with accuracy rates 97.4% 97.2%, respectively. This work, like prior studies, illustrates viability developing, validating, using (ML) prediction forecast ICU admission in COVID-19 cases. ML that have been developed tremendous potential fight against industry.

Language: Английский

Citations

0
Predicting the transmission trends of COVID-19: an interpretable machine learning approach based on daily, death, and imported cases DOI Creative Commons
Hyeonjeong Ahn, Hyojung Lee

Mathematical Biosciences & Engineering, Journal Year: 2024, Volume and Issue: 21(5), P. 6150 - 6166

Published: Jan. 1, 2024

<abstract> <p>COVID-19 is caused by the SARS-CoV-2 virus, which has produced variants and increasing concerns about a potential resurgence since pandemic outbreak in 2019. Predicting infectious disease outbreaks crucial for effective prevention control. This study aims to predict transmission patterns of COVID-19 using machine learning, such as support vector machine, random forest, XGBoost, confirmed cases, death imported respectively. The categorizes trends into three groups: L0 (decrease), L1 (maintain), L2 (increase). We develop risk index function quantify changes trends, applied classification learning. A high accuracy achieved when estimating cases (91.5–95.5%), (85.6–91.8%), (77.7–89.4%). Notably, exhibit higher level compared data on deaths cases. predictions outperformed all important because it can lead new outbreaks. Thus, this robust prediction timely implementation control policies management dynamics.</p> </abstract>

Language: Английский

Citations

0
Mortality prediction using data from wearable activity trackers and individual characteristics: An explainable artificial intelligence approach DOI Creative Commons
Byron Graham,

Mark Farrell

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: unknown, P. 126195 - 126195

Published: Dec. 1, 2024

Language: Английский

Citations

0