Estimating the effect of realistic improvements of metformin adherence on COVID-19 mortality using targeted machine learning
Background: Type 2 diabetes elevates the risk of severe outcomes in COVID-19 patients, with multiple studies reporting higher case fatality rates. Metformin is a widely used medication for glycemic management. We hypothesize that improved adherence to metformin may lower COVID-19 post-infection mort...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | Global Epidemiology |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590113324000087 |
| _version_ | 1827225775110094848 |
|---|---|
| author | Sky Qiu Alan E. Hubbard Juan Pablo Gutiérrez Ganesh Pimpale Arturo Juárez-Flores Rakesh Ghosh Iván de Jesús Ascencio-Montiel Stefano M. Bertozzi |
| author_facet | Sky Qiu Alan E. Hubbard Juan Pablo Gutiérrez Ganesh Pimpale Arturo Juárez-Flores Rakesh Ghosh Iván de Jesús Ascencio-Montiel Stefano M. Bertozzi |
| author_sort | Sky Qiu |
| collection | DOAJ |
| description | Background: Type 2 diabetes elevates the risk of severe outcomes in COVID-19 patients, with multiple studies reporting higher case fatality rates. Metformin is a widely used medication for glycemic management. We hypothesize that improved adherence to metformin may lower COVID-19 post-infection mortality risk in this group. Utilizing data from the Mexican Social Security Institute (IMSS), we investigate the relationship between metformin adherence and mortality following COVID-19 infection in patients with chronic metformin prescriptions. Methods: This is a retrospective cohort study consisting of 61,180 IMSS beneficiaries who received a positive polymerase chain reaction (PCR) or rapid test for SARS-CoV-2 and had at least two consecutive months of metformin prescriptions prior to the positive test. The hypothetical intervention is improved adherence to metformin, measured by proportion of days covered (PDC), with the comparison being the observed metformin adherence values. The primary outcome is all-cause mortality following COVID-19 infection. We defined the causal parameter using shift intervention, an example of modified treatment policies. We used the targeted learning framework for estimation of the target estimand. Findings: Among COVID-19 positive patients with chronic metformin prescriptions, we found that a 5% and 10% absolute increase in metformin adherence is associated with a respective 0.26% (95% CI: −0.28%, 0.79%) and 1.26% (95% CI: 0.72%, 1.80%) absolute decrease in mortality risk. Interpretation: Subject to the limitations of a real-world data study, our results indicate a causal association between improved metformin adherence and reduced COVID-19 post-infection mortality risk. |
| first_indexed | 2024-04-24T14:27:33Z |
| format | Article |
| id | doaj.art-12a823997ace41deba3f1d0dc56e31af |
| institution | Directory Open Access Journal |
| issn | 2590-1133 |
| language | English |
| last_indexed | 2025-03-21T17:31:31Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Global Epidemiology |
| spelling | doaj.art-12a823997ace41deba3f1d0dc56e31af2024-06-13T04:45:44ZengElsevierGlobal Epidemiology2590-11332024-06-017100142Estimating the effect of realistic improvements of metformin adherence on COVID-19 mortality using targeted machine learningSky Qiu0Alan E. Hubbard1Juan Pablo Gutiérrez2Ganesh Pimpale3Arturo Juárez-Flores4Rakesh Ghosh5Iván de Jesús Ascencio-Montiel6Stefano M. Bertozzi7University of California, School of Public Health, Berkeley, CA, USA; Corresponding author.University of California, School of Public Health, Berkeley, CA, USACenter for Policy, Population and Health Research, School of Medicine, Universidad Nacional Autónoma de México, Mexico City, MexicoUniversity of California, Department of Mechanical Engineering, Berkeley, CA, USACenter for Policy, Population and Health Research, School of Medicine, Universidad Nacional Autónoma de México, Mexico City, MexicoInstitute for Global Health Sciences, University of California, San Francisco, CA, USAInstituto Mexicano del Seguro Social, CDMX, MexicoUniversity of California, School of Public Health, Berkeley, CA, USA; University of Washington, School of Public Health, Seattle, WA, USA; Instituto Nacional de Salud Pública, Cuernavaca, MOR, MexicoBackground: Type 2 diabetes elevates the risk of severe outcomes in COVID-19 patients, with multiple studies reporting higher case fatality rates. Metformin is a widely used medication for glycemic management. We hypothesize that improved adherence to metformin may lower COVID-19 post-infection mortality risk in this group. Utilizing data from the Mexican Social Security Institute (IMSS), we investigate the relationship between metformin adherence and mortality following COVID-19 infection in patients with chronic metformin prescriptions. Methods: This is a retrospective cohort study consisting of 61,180 IMSS beneficiaries who received a positive polymerase chain reaction (PCR) or rapid test for SARS-CoV-2 and had at least two consecutive months of metformin prescriptions prior to the positive test. The hypothetical intervention is improved adherence to metformin, measured by proportion of days covered (PDC), with the comparison being the observed metformin adherence values. The primary outcome is all-cause mortality following COVID-19 infection. We defined the causal parameter using shift intervention, an example of modified treatment policies. We used the targeted learning framework for estimation of the target estimand. Findings: Among COVID-19 positive patients with chronic metformin prescriptions, we found that a 5% and 10% absolute increase in metformin adherence is associated with a respective 0.26% (95% CI: −0.28%, 0.79%) and 1.26% (95% CI: 0.72%, 1.80%) absolute decrease in mortality risk. Interpretation: Subject to the limitations of a real-world data study, our results indicate a causal association between improved metformin adherence and reduced COVID-19 post-infection mortality risk.http://www.sciencedirect.com/science/article/pii/S2590113324000087 |
| spellingShingle | Sky Qiu Alan E. Hubbard Juan Pablo Gutiérrez Ganesh Pimpale Arturo Juárez-Flores Rakesh Ghosh Iván de Jesús Ascencio-Montiel Stefano M. Bertozzi Estimating the effect of realistic improvements of metformin adherence on COVID-19 mortality using targeted machine learning Global Epidemiology |
| title | Estimating the effect of realistic improvements of metformin adherence on COVID-19 mortality using targeted machine learning |
| title_full | Estimating the effect of realistic improvements of metformin adherence on COVID-19 mortality using targeted machine learning |
| title_fullStr | Estimating the effect of realistic improvements of metformin adherence on COVID-19 mortality using targeted machine learning |
| title_full_unstemmed | Estimating the effect of realistic improvements of metformin adherence on COVID-19 mortality using targeted machine learning |
| title_short | Estimating the effect of realistic improvements of metformin adherence on COVID-19 mortality using targeted machine learning |
| title_sort | estimating the effect of realistic improvements of metformin adherence on covid 19 mortality using targeted machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2590113324000087 |
| work_keys_str_mv | AT skyqiu estimatingtheeffectofrealisticimprovementsofmetforminadherenceoncovid19mortalityusingtargetedmachinelearning AT alanehubbard estimatingtheeffectofrealisticimprovementsofmetforminadherenceoncovid19mortalityusingtargetedmachinelearning AT juanpablogutierrez estimatingtheeffectofrealisticimprovementsofmetforminadherenceoncovid19mortalityusingtargetedmachinelearning AT ganeshpimpale estimatingtheeffectofrealisticimprovementsofmetforminadherenceoncovid19mortalityusingtargetedmachinelearning AT arturojuarezflores estimatingtheeffectofrealisticimprovementsofmetforminadherenceoncovid19mortalityusingtargetedmachinelearning AT rakeshghosh estimatingtheeffectofrealisticimprovementsofmetforminadherenceoncovid19mortalityusingtargetedmachinelearning AT ivandejesusascenciomontiel estimatingtheeffectofrealisticimprovementsofmetforminadherenceoncovid19mortalityusingtargetedmachinelearning AT stefanombertozzi estimatingtheeffectofrealisticimprovementsofmetforminadherenceoncovid19mortalityusingtargetedmachinelearning |