1
|
Lieberman B, Kong JD, Gusinow R, Asgary A, Bragazzi NL, Choma J, Dahbi SE, Hayashi K, Kar D, Kawonga M, Mbada M, Monnakgotla K, Orbinski J, Ruan X, Stevenson F, Wu J, Mellado B. Big data- and artificial intelligence-based hot-spot analysis of COVID-19: Gauteng, South Africa, as a case study. BMC Med Inform Decis Mak 2023; 23:19. [PMID: 36703133 PMCID: PMC9879257 DOI: 10.1186/s12911-023-02098-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2022] [Accepted: 01/02/2023] [Indexed: 01/27/2023] Open
Abstract
The coronavirus disease 2019 (COVID-19) has developed into a pandemic. Data-driven techniques can be used to inform and guide public health decision- and policy-makers. In generalizing the spread of a virus over a large area, such as a province, it must be assumed that the transmission occurs as a stochastic process. It is therefore very difficult for policy and decision makers to understand and visualize the location specific dynamics of the virus on a more granular level. A primary concern is exposing local virus hot-spots, in order to inform and implement non-pharmaceutical interventions. A hot-spot is defined as an area experiencing exponential growth relative to the generalised growth of the pandemic. This paper uses the first and second waves of the COVID-19 epidemic in Gauteng Province, South Africa, as a case study. The study aims provide a data-driven methodology and comprehensive case study to expose location specific virus dynamics within a given area. The methodology uses an unsupervised Gaussian Mixture model to cluster cases at a desired granularity. This is combined with an epidemiological analysis to quantify each cluster's severity, progression and whether it can be defined as a hot-spot.
Collapse
Affiliation(s)
- Benjamin Lieberman
- grid.11951.3d0000 0004 1937 1135School of Physics and Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Jude Dzevela Kong
- grid.21100.320000 0004 1936 9430Department of Mathematics and Statistics, York University, Toronto, Canada ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Roy Gusinow
- grid.11951.3d0000 0004 1937 1135School of Physics and Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Ali Asgary
- grid.21100.320000 0004 1936 9430Disaster and Emergency Management, School of Administrative Studies and Advanced Disaster, Emergency and Rapid-response Simulation, York University, Toronto, Canada ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Nicola Luigi Bragazzi
- grid.21100.320000 0004 1936 9430Department of Mathematics and Statistics, York University, Toronto, Canada ,grid.21100.320000 0004 1936 9430Laboratory for Industrial and Applied Mathematics (LIAM), York University, Toronto, Canada ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Joshua Choma
- grid.11951.3d0000 0004 1937 1135School of Physics and Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Salah-Eddine Dahbi
- grid.11951.3d0000 0004 1937 1135School of Physics and Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Kentaro Hayashi
- grid.11951.3d0000 0004 1937 1135School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Deepak Kar
- grid.11951.3d0000 0004 1937 1135School of Physics and Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Mary Kawonga
- grid.11951.3d0000 0004 1937 1135School of Public Health, University of the Witwatersrand, Johannesburg, South Africa ,Gauteng Provincial Department of Health, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Mduduzi Mbada
- Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada ,Gauteng Office of the Premier, Johannesburg, South Africa
| | - Kgomotso Monnakgotla
- grid.11951.3d0000 0004 1937 1135School of Physics and Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - James Orbinski
- Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada ,grid.21100.320000 0004 1936 9430Dahdaleh Institute for Global Health Research, York University, Toronto, Canada
| | - Xifeng Ruan
- grid.11951.3d0000 0004 1937 1135School of Physics and Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Finn Stevenson
- grid.11951.3d0000 0004 1937 1135School of Physics and Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Jianhong Wu
- grid.21100.320000 0004 1936 9430Department of Mathematics and Statistics, York University, Toronto, Canada ,grid.21100.320000 0004 1936 9430Laboratory for Industrial and Applied Mathematics (LIAM), York University, Toronto, Canada ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada
| | - Bruce Mellado
- grid.11951.3d0000 0004 1937 1135School of Physics and Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South Africa ,Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Toronto, Canada ,grid.462638.d0000 0001 0696 719XiThemba LABS, National Research Foundation, Somerset West, South Africa
| |
Collapse
|
2
|
Alavinejad M, Mellado B, Asgary A, Mbada M, Mathaha T, Lieberman B, Stevenson F, Tripathi N, Swain AK, Orbinski J, Wu J, Kong JD. Management of hospital beds and ventilators in the Gauteng province, South Africa, during the COVID-19 pandemic. PLOS Glob Public Health 2022; 2:e0001113. [PMID: 36962677 PMCID: PMC10022393 DOI: 10.1371/journal.pgph.0001113] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/02/2022] [Accepted: 09/21/2022] [Indexed: 11/06/2022]
Abstract
We conducted an observational retrospective study on patients hospitalized with COVID-19, during March 05, 2020, to October 28, 2021, and developed an agent-based model to evaluate effectiveness of recommended healthcare resources (hospital beds and ventilators) management strategies during the COVID-19 pandemic in Gauteng, South Africa. We measured the effectiveness of these strategies by calculating the number of deaths prevented by implementing them. We observed differ ences between the epidemic waves. The length of hospital stay (LOS) during the third wave was lower than the first two waves. The median of the LOS was 6.73 days, 6.63 days and 6.78 days for the first, second and third wave, respectively. A combination of public and private sector provided hospital care to COVID-19 patients requiring ward and Intensive Care Units (ICU) beds. The private sector provided 88.4% of High care (HC)/ICU beds and 49.4% of ward beds, 73.9% and 51.4%, 71.8% and 58.3% during the first, second and third wave, respectively. Our simulation results showed that with a high maximum capacity, i.e., 10,000 general and isolation ward beds, 4,000 high care and ICU beds and 1,200 ventilators, increasing the resource capacity allocated to COVID- 19 patients by 25% was enough to maintain bed availability throughout the epidemic waves. With a medium resource capacity (8,500 general and isolation ward beds, 3,000 high care and ICU beds and 1,000 ventilators) a combination of resource management strategies and their timing and criteria were very effective in maintaining bed availability and therefore preventing excess deaths. With a low number of maximum available resources (7,000 general and isolation ward beds, 2,000 high care and ICU beds and 800 ventilators) and a severe epidemic wave, these strategies were effective in maintaining the bed availability and minimizing the number of excess deaths throughout the epidemic wave.
Collapse
Affiliation(s)
- Mahnaz Alavinejad
- Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Laboratory for Industrial and Applied Mathematics, York University, Toronto, Canada
| | - Bruce Mellado
- Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), School of Physics, Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South Africa
- iThemba LABS, National Research Foundation, Cape Town, South Africa
| | - Ali Asgary
- Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), The Advanced Disaster, Emergency and Rapid Response Program, York University, Toronto, Canada
| | - Mduduzi Mbada
- Head of Policy at Gauteng Office of the Premier, Johannesburg, South Africa
| | - Thuso Mathaha
- University of the Witwatersrand, Johannesburg, South Africa
| | | | - Finn Stevenson
- University of the Witwatersrand, Johannesburg, South Africa
| | - Nidhi Tripathi
- University of the Witwatersrand, Johannesburg, South Africa
| | | | - James Orbinski
- Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), The Dahdaleh Institute for Global Health Research, York University, Toronto, Canada
| | - Jianhong Wu
- Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Laboratory for Industrial and Applied Mathematics, York University, Toronto, Canada
| | - Jude Dzevela Kong
- Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Laboratory for Industrial and Applied Mathematics, York University, Toronto, Canada
| |
Collapse
|
3
|
Mellado B, Wu J, Kong JD, Bragazzi NL, Asgary A, Kawonga M, Choma N, Hayasi K, Lieberman B, Mathaha T, Mbada M, Ruan X, Stevenson F, Orbinski J. Leveraging Artificial Intelligence and Big Data to Optimize COVID-19 Clinical Public Health and Vaccination Roll-Out Strategies in Africa. Int J Environ Res Public Health 2021; 18:7890. [PMID: 34360183 PMCID: PMC8345600 DOI: 10.3390/ijerph18157890] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/06/2021] [Accepted: 07/13/2021] [Indexed: 11/29/2022]
Abstract
COVID-19 is imposing massive health, social and economic costs. While many developed countries have started vaccinating, most African nations are waiting for vaccine stocks to be allocated and are using clinical public health (CPH) strategies to control the pandemic. The emergence of variants of concern (VOC), unequal access to the vaccine supply and locally specific logistical and vaccine delivery parameters, add complexity to national CPH strategies and amplify the urgent need for effective CPH policies. Big data and artificial intelligence machine learning techniques and collaborations can be instrumental in an accurate, timely, locally nuanced analysis of multiple data sources to inform CPH decision-making, vaccination strategies and their staged roll-out. The Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC) has been established to develop and employ machine learning techniques to design CPH strategies in Africa, which requires ongoing collaboration, testing and development to maximize the equity and effectiveness of COVID-19-related CPH interventions.
Collapse
Affiliation(s)
- Bruce Mellado
- School of Physics, Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg 2050, South Africa; (B.M.); (N.C.); (B.L.); (T.M.); (X.R.); (F.S.)
- iThemba LABS, National Research Foundation, Old Faure Road, Faure 7129, South Africa
| | - Jianhong Wu
- Centre for Disease Modelling, York University, Toronto, ON M3J 1P3, Canada; (J.W.); (J.D.K.)
| | - Jude Dzevela Kong
- Centre for Disease Modelling, York University, Toronto, ON M3J 1P3, Canada; (J.W.); (J.D.K.)
| | - Nicola Luigi Bragazzi
- Centre for Disease Modelling, York University, Toronto, ON M3J 1P3, Canada; (J.W.); (J.D.K.)
| | - Ali Asgary
- Disaster & Emergency Management, School of Administrative Studies and Advanced Disaster, Emergency and Rapid-Response Simulation (ADERSIM), York University, Toronto, ON M3J 1P3, Canada;
| | - Mary Kawonga
- Gauteng Department of Health, Johannesburg 2107, South Africa;
| | - Nalamotse Choma
- School of Physics, Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg 2050, South Africa; (B.M.); (N.C.); (B.L.); (T.M.); (X.R.); (F.S.)
| | - Kentaro Hayasi
- School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg 2050, South Africa;
| | - Benjamin Lieberman
- School of Physics, Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg 2050, South Africa; (B.M.); (N.C.); (B.L.); (T.M.); (X.R.); (F.S.)
| | - Thuso Mathaha
- School of Physics, Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg 2050, South Africa; (B.M.); (N.C.); (B.L.); (T.M.); (X.R.); (F.S.)
| | - Mduduzi Mbada
- Head of Policy at Gauteng Office of the Premier, Johannesburg 2107, South Africa;
| | - Xifeng Ruan
- School of Physics, Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg 2050, South Africa; (B.M.); (N.C.); (B.L.); (T.M.); (X.R.); (F.S.)
| | - Finn Stevenson
- School of Physics, Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg 2050, South Africa; (B.M.); (N.C.); (B.L.); (T.M.); (X.R.); (F.S.)
| | - James Orbinski
- Dahdaleh Institute for Global Health Research, York University, Toronto, ON M3J 1P3, Canada;
| |
Collapse
|