1
|
El Morr C, Ozdemir D, Asdaah Y, Saab A, El-Lahib Y, Sokhn ES. AI-based epidemic and pandemic early warning systems: A systematic scoping review. Health Informatics J 2024; 30:14604582241275844. [PMID: 39172555 DOI: 10.1177/14604582241275844] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/24/2024]
Abstract
Background: Timely detection of disease outbreaks is critical in public health. Artificial Intelligence (AI) can identify patterns in data that signal the onset of epidemics and pandemics. This scoping review examines the effectiveness of AI in epidemic and pandemic early warning systems (EWS). Objective: To assess the capability of AI-based systems in predicting epidemics and pandemics and to identify challenges and strategies for improvement. Methods: A systematic scoping review was conducted. The review included studies from the last 5 years, focusing on AI and machine learning applications in EWS. After screening 1087 articles, 33 were selected for thematic analysis. Results: The review found that AI-based EWS have been effectively implemented in various contexts, using a range of algorithms. Key challenges identified include data quality, model explainability, bias, data volume, velocity, variety, availability, and granularity. Strategies for mitigating AI bias and improving system adaptability were also discussed. Conclusion: AI has shown promise in enhancing the speed and accuracy of epidemic detection. However, challenges related to data quality, bias, and model transparency need to be addressed to improve the reliability and generalizability of AI-based EWS. Continuous monitoring and improvement, as well as incorporating social and environmental data, are essential for future development.
Collapse
Affiliation(s)
- Christo El Morr
- School of Health Policy and Management, York University, Toronto, ON, Canada
| | - Deniz Ozdemir
- Department of Psychology, York University, Toronto, ON, Canada
| | - Yasmeen Asdaah
- School of Health Policy and Management, York University, Toronto, ON, Canada
| | - Antoine Saab
- Quality and Safety Department, Lebanese Hospital Geitaoui-UMC, Beirut, Lebanon
| | - Yahya El-Lahib
- Faculty of Social Work, University of Calgary, Calgary, AB, Canada
| | - Elie Salem Sokhn
- Laboratory Department, Lebanese Hospital-Geitaoui University Medical Center, Beirut, Lebanon
- Molecular testing Laboratory, Medical Laboratory Department, Faculty of Health Sciences, Beirut Arab University, Beirut, Lebanon
| |
Collapse
|
2
|
Rajendran EG, Mohd Hairi F, Krishna Supramaniam R, T Mohd TAM. Precision public health, the key for future outbreak management: A scoping review. Digit Health 2024; 10:20552076241256877. [PMID: 39139190 PMCID: PMC11320687 DOI: 10.1177/20552076241256877] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2023] [Accepted: 05/07/2024] [Indexed: 08/15/2024] Open
Abstract
Background Precision Public Health (PPH) is a newly emerging field in public health medicine. The application of various types of data allows PPH to deliver more tailored interventions to a specific population within a specific timeframe. However, the application of PPH possesses several challenges and limitations that need to be addressed. Objective We aim to provide evidence of the various use of PPH in outbreak management, the types of data that could be used in PPH application, and the limitations and barriers in the application of the PPH approach. Methods and analysis Articles were searched in PubMed, Web of Science, and Science Direct. Our selection of articles was based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) for Scoping Review guidelines. The outcome of the evidence assessment was presented in narrative format instead of quantitative. Results A total of 27 articles were included in the scoping review. Most of the articles (74.1%) focused on PPH applications in performing disease surveillance and signal detection. Furthermore, the data type mostly used in the studies was surveillance (51.9%), environment (44.4), and Internet query data. Most of the articles emphasized data quality and availability (81.5%) as the main barriers in PPH applications followed by data integration and interoperability (29.6%). Conclusions PPH applications in outbreak management utilize a wide range of data sources and analytical techniques to enhance disease surveillance, investigation, modeling, and prediction. By leveraging these tools and approaches, PPH contributes to more effective and efficient outbreak management, ultimately reducing the burden of infectious diseases on populations. The limitation and challenges in the application of PPH approaches in outbreak management emphasize the need to strengthen the surveillance systems, promote data sharing and collaboration among relevant stakeholders, and standardize data collection methods while upholding privacy and ethical principles.
Collapse
Affiliation(s)
- Ellappa Ghanthan Rajendran
- Department of Social and Preventive Medicine, Faculty of Medicine, University of Malaya, Kuala Lumpur, Malaysia
| | - Farizah Mohd Hairi
- Department of Social and Preventive Medicine, Faculty of Medicine, University of Malaya, Kuala Lumpur, Malaysia
| | - Rama Krishna Supramaniam
- Department of Social and Preventive Medicine, Faculty of Medicine, University of Malaya, Kuala Lumpur, Malaysia
| | | |
Collapse
|
3
|
Nduwayezu G, Zhao P, Kagoyire C, Eklund L, Bizimana JP, Pilesjo P, Mansourian A. Understanding the spatial non-stationarity in the relationships between malaria incidence and environmental risk factors using Geographically Weighted Random Forest: A case study in Rwanda. GEOSPATIAL HEALTH 2023; 18. [PMID: 37246535 DOI: 10.4081/gh.2023.1184] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/09/2023] [Accepted: 04/28/2023] [Indexed: 05/30/2023]
Abstract
As found in the health studies literature, the levels of climate association between epidemiological diseases have been found to vary across regions. Therefore, it seems reasonable to allow for the possibility that relationships might vary spatially within regions. We implemented the geographically weighted random forest (GWRF) machine learning method to analyze ecological disease patterns caused by spatially non-stationary processes using a malaria incidence dataset for Rwanda. We first compared the geographically weighted regression (WGR), the global random forest (GRF), and the geographically weighted random forest (GWRF) to examine the spatial non-stationarity in the non-linear relationships between malaria incidence and their risk factors. We used the Gaussian areal kriging model to disaggregate the malaria incidence at the local administrative cell level to understand the relationships at a fine scale since the model goodness of fit was not satisfactory to explain malaria incidence due to the limited number of sample values. Our results show that in terms of the coefficients of determination and prediction accuracy, the geographical random forest model performs better than the GWR and the global random forest model. The coefficients of determination of the geographically weighted regression (R2), the global RF (R2), and the GWRF (R2) were 4.74, 0.76, and 0.79, respectively. The GWRF algorithm achieves the best result and reveals that risk factors (rainfall, land surface temperature, elevation, and air temperature) have a strong non-linear relationship with the spatial distribution of malaria incidence rates, which could have implications for supporting local initiatives for malaria elimination in Rwanda.
Collapse
Affiliation(s)
- Gilbert Nduwayezu
- Department of Physical Geography and Ecosystem Science, Lund University, Lund, Sweden; Department of Civil, Environmental and Geomatics Engineering, University of Rwanda.
| | - Pengxiang Zhao
- Department of Physical Geography and Ecosystem Science, Lund University, Lund.
| | - Clarisse Kagoyire
- Department of Physical Geography and Ecosystem Science, Lund University, Lund, Sweden; Centre for Geographic Information Systems and Remote Sensing, University of Rwanda, Kigali.
| | - Lina Eklund
- Department of Physical Geography and Ecosystem Science, Lund University, Lund.
| | | | - Petter Pilesjo
- Department of Physical Geography and Ecosystem Science, Lund University, Lund.
| | - Ali Mansourian
- Department of Physical Geography and Ecosystem Science, Lund University, Lund, Sweden; Lund University's Profile Area: Nature-based Future Solutions.
| |
Collapse
|
4
|
Pourtois JD, Tallam K, Jones I, Hyde E, Chamberlin AJ, Evans MV, Ihantamalala FA, Cordier LF, Razafinjato BR, Rakotonanahary RJL, Tsirinomen'ny Aina A, Soloniaina P, Raholiarimanana SH, Razafinjato C, Bonds MH, De Leo GA, Sokolow SH, Garchitorena A. Climatic, land-use and socio-economic factors can predict malaria dynamics at fine spatial scales relevant to local health actors: Evidence from rural Madagascar. PLOS GLOBAL PUBLIC HEALTH 2023; 3:e0001607. [PMID: 36963091 PMCID: PMC10021226 DOI: 10.1371/journal.pgph.0001607] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/20/2022] [Accepted: 01/23/2023] [Indexed: 02/24/2023]
Abstract
While much progress has been achieved over the last decades, malaria surveillance and control remain a challenge in countries with limited health care access and resources. High-resolution predictions of malaria incidence using routine surveillance data could represent a powerful tool to health practitioners by targeting malaria control activities where and when they are most needed. Here, we investigate the predictors of spatio-temporal malaria dynamics in rural Madagascar, estimated from facility-based passive surveillance data. Specifically, this study integrates climate, land-use, and representative household survey data to explain and predict malaria dynamics at a high spatial resolution (i.e., by Fokontany, a cluster of villages) relevant to health care practitioners. Combining generalized linear mixed models (GLMM) and path analyses, we found that socio-economic, land use and climatic variables are all important predictors of monthly malaria incidence at fine spatial scales, via both direct and indirect effects. In addition, out-of-sample predictions from our model were able to identify 58% of the Fokontany in the top quintile for malaria incidence and account for 77% of the variation in the Fokontany incidence rank. These results suggest that it is possible to build a predictive framework using environmental and social predictors that can be complementary to standard surveillance systems and help inform control strategies by field actors at local scales.
Collapse
Affiliation(s)
- Julie D Pourtois
- Biology Department, Stanford University, Stanford, CA, United States of America
- Hopkins Marine Station, Stanford University, Pacific Grove, CA, United States of America
| | - Krti Tallam
- Biology Department, Stanford University, Stanford, CA, United States of America
| | - Isabel Jones
- Biology Department, Stanford University, Stanford, CA, United States of America
- Hopkins Marine Station, Stanford University, Pacific Grove, CA, United States of America
| | - Elizabeth Hyde
- School of Medicine, Stanford University, Stanford, CA, United States of America
| | - Andrew J Chamberlin
- Hopkins Marine Station, Stanford University, Pacific Grove, CA, United States of America
| | - Michelle V Evans
- MIVEGEC, Université de Montpellier, CNRS, IRD, Montpellier, France
| | - Felana A Ihantamalala
- Department of Global Health and Social Medicine, Harvard Medical School, Boston, MA, United States of America
- NGO Pivot, Ifanadiana, Madagascar
| | | | | | - Rado J L Rakotonanahary
- Department of Global Health and Social Medicine, Harvard Medical School, Boston, MA, United States of America
- NGO Pivot, Ifanadiana, Madagascar
| | | | | | | | - Celestin Razafinjato
- Programme National de Lutte contre le Paludisme, Ministère de la Santé Publique, Antananarivo, Madagascar
| | - Matthew H Bonds
- Department of Global Health and Social Medicine, Harvard Medical School, Boston, MA, United States of America
- NGO Pivot, Ifanadiana, Madagascar
| | - Giulio A De Leo
- Biology Department, Stanford University, Stanford, CA, United States of America
- Hopkins Marine Station, Stanford University, Pacific Grove, CA, United States of America
| | - Susanne H Sokolow
- Woods Institute for the Environment, Stanford University, Stanford, CA, United States of America
- Marine Science Institute and Department of Ecology, Evolution and Marine Biology, University of California, Santa Barbara, CA, United States of America
| | - Andres Garchitorena
- MIVEGEC, Université de Montpellier, CNRS, IRD, Montpellier, France
- NGO Pivot, Ifanadiana, Madagascar
| |
Collapse
|