Identifying and forecasting importation and asymptomatic spreaders of multi-drug resistant organisms in hospital settings DOI Creative Commons
Jiaming Cui, Jack Heavey, Eili Klein

et al.

npj Digital Medicine, Journal Year: 2025, Volume and Issue: 8(1)

Published: March 7, 2025

Healthcare-associated infections (HAIs) from multi-drug resistant organisms (MDROs) pose a significant challenge for healthcare systems. Patients can arrive at hospitals already infected ("importation") or acquire during their stay ("nosocomial infection"). Many cases, often asymptomatic, complicate rapid identification due to testing limitations and delays. Although recent advancements in mathematical modeling machine learning have aimed identify at-risk patients, these methods face challenges: transmission models overlook valuable electronic health record (EHR) data, while approaches typically lack mechanistic insights into underlying processes. To address issues, we propose NeurABM, novel framework that integrates neural networks agent-based (ABM) leverage the strengths of both methods. NeurABM simultaneously learns network patient-level importation predictions an ABM infection identification. Our findings show significantly outperforms existing methods, marking breakthrough accurately identifying cases forecasting future nosocomial clinical practice.

Language: Английский

Integrating artificial intelligence with mechanistic epidemiological modeling: a scoping review of opportunities and challenges DOI Creative Commons

Yang Ye,

Abhishek Pandey,

Carolyn E. Bawden

et al.

Nature Communications, Journal Year: 2025, Volume and Issue: 16(1)

Published: Jan. 10, 2025

Integrating prior epidemiological knowledge embedded within mechanistic models with the data-mining capabilities of artificial intelligence (AI) offers transformative potential for modeling. While fusion AI and traditional approaches is rapidly advancing, efforts remain fragmented. This scoping review provides a comprehensive overview emerging integrated applied across spectrum infectious diseases. Through systematic search strategies, we identified 245 eligible studies from 15,460 records. Our highlights practical value models, including advances in disease forecasting, model parameterization, calibration. However, key research gaps remain. These include need better incorporation realistic decision-making considerations, expanded exploration diverse datasets, further investigation into biological socio-behavioral mechanisms. Addressing these will unlock synergistic modeling to enhance understanding dynamics support more effective public health planning response. Artificial has improve diseases by incorporating data sources complex interactions. Here, authors conduct use summarise methodological advancements identify gaps.

Language: Английский

Citations

6
Advancing epidemic modeling: The role of LLMs and generative agent-based models Comment on LLMs and generative agent-based models for complex systems research by Lu et al. DOI
Gui-Quan Sun, Li Li,

Y Pei

et al.

Physics of Life Reviews, Journal Year: 2025, Volume and Issue: 52, P. 175 - 177

Published: Jan. 5, 2025

Language: Английский

Citations

1
Artificial Neural Network-Based Approach for Dynamic Analysis and Modeling of Marburg Virus Epidemics for Health Care DOI Open Access

Noreen Mustafa,

Jamshaid Ul Rahman, Umar Ishtiaq

et al.

Symmetry, Journal Year: 2025, Volume and Issue: 17(4), P. 578 - 578

Published: April 10, 2025

Artificial intelligence (AI) plays a crucial role in modern healthcare by enhancing disease modeling and outbreak prediction. In this study, we develop an epidemiological model for the Marburg virus, integrating vaccination treatment strategies while considering vaccine efficacy failure. The exhibits mathematical symmetry its equilibrium analysis, ensuring balanced assessment of dynamics across human bat reservoir populations. We compute Marburg-free endemic points, derive secondary infection threshold, conduct sensitivity analysis using PRCC method to identify key transmission parameters that are important control. To validate theory, optimized deep neural network (DNN) via grid search employed it dynamic which also validates cutting-edge application AI healthcare. compare AI-based predictions with traditional numerical solutions reproduction number humans R0h>1 R0h<1 validation approach. results demonstrate model’s stability, efficacy, predictive power, emphasizing synergy between epidemiology. This study provides valuable insights public health interventions effective control leveraging AI-driven simulations, highlighting AI’s potential revolutionize enhance early detection tailor strategies.

Language: Английский

Citations

1
Identifying and forecasting importation and asymptomatic spreaders of multi-drug resistant organisms in hospital settings DOI Creative Commons
Jiaming Cui, Jack Heavey, Eili Klein

et al.

npj Digital Medicine, Journal Year: 2025, Volume and Issue: 8(1)

Published: March 7, 2025

Healthcare-associated infections (HAIs) from multi-drug resistant organisms (MDROs) pose a significant challenge for healthcare systems. Patients can arrive at hospitals already infected ("importation") or acquire during their stay ("nosocomial infection"). Many cases, often asymptomatic, complicate rapid identification due to testing limitations and delays. Although recent advancements in mathematical modeling machine learning have aimed identify at-risk patients, these methods face challenges: transmission models overlook valuable electronic health record (EHR) data, while approaches typically lack mechanistic insights into underlying processes. To address issues, we propose NeurABM, novel framework that integrates neural networks agent-based (ABM) leverage the strengths of both methods. NeurABM simultaneously learns network patient-level importation predictions an ABM infection identification. Our findings show significantly outperforms existing methods, marking breakthrough accurately identifying cases forecasting future nosocomial clinical practice.

Language: Английский

Citations

0