Data-driven test strategy for COVID-19 using machine learning: A study in Lahore, Pakistan

• Published in: Socio-economic planning sciences Vol. 80; p. 101091
• Main Authors: Huang, Chuanli, Wang, Min, Rafaqat, Warda, Shabbir, Salman, Lian, Liping, Zhang, Jun, Lo, Siuming, Song, Weiguo
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2022; Elsevier Science Ltd; Published by Elsevier Ltd
• Subjects: COVID-19; COVID-19 diagnostic tests; Logistic regression; Machine learning; Pandemics; Policy making; Regression analysis; Risk factors; Spatial analysis; Strength; Test strategy; Time series; Time series analysis; Lahore Pakistan; Pakistan; COVID-19; Policy making; Logistic regression; Test strategy; Time series analysis; Machine learning; Spatial analysis
• ISSN: 0038-0121; 1873-6041; 0038-0121
• DOI: 10.1016/j.seps.2021.101091

We aimed at giving a preliminary analysis of the weakness of a current test strategy, and proposing a data-driven strategy that was self-adaptive to the dynamic change of pandemic. The effect of driven-data selection over time and space was also within the deep concern. A mathematical definition of the test strategy were given. With the real COVID-19 test data from March to July collected in Lahore, a significance analysis of the possible features was conducted. A machine learning method based on logistic regression and priority ranking were proposed for the data-driven test strategy. With performance assessed by the area under the receiver operating characteristic curve (AUC), time series analysis and spatial cross-test were conducted. The transition of risk factors accounted for the failure of the current test strategy. The proposed data-driven strategy could enhance the positive detection rate from 2.54% to 28.18%, and the recall rate from 8.05% to 89.35% under strictly limited test capacity. Much more optimal utilization of test resources could be realized where 89.35% of total positive cases could be detected with merely 48.17% of the original test amount. The strategy showed self-adaptability with the development of pandemic, while the strategy driven by local data was proved to be optimal. We recommended a generalization of such a data-driven test strategy for a better response to the global developing pandemic. Besides, the construction of the COVID-19 data system should be more refined on space for local applications. •Findings revealed the failure of a current test strategy.•A data-driven test strategy for COVID-19 based on machine learning was proposed for policy-making insights.•The proposed strategy was much more efficient under strictly limited test capacity.•Long-term data collection was not prerequisite for the conduction of the data-driven strategy.•Even for different subareas of a city, the strategy driven by local data was likely to be optimal.