tetano
Editor, Senior Moderator
Epidemiology
. 2025 Jun 5.
doi: 10.1097/EDE.0000000000001882. Online ahead of print. Investigating Symptom Duration Using Current Status Data: A Case Study of Postacute COVID-19 Syndrome
Charles J Wolock[SUP] 1 [/SUP], Susan Jacob[SUP] 2 [/SUP], Julia C Bennett[SUP] 2 [/SUP], Anna Elias-Warren[SUP] 2 [/SUP], Jessica O'Hanlon[SUP] 2 [/SUP], Avi Kenny[SUP] 3 4 [/SUP], Nicholas P Jewell[SUP] 5 6 [/SUP], Andrea Rotnitzky[SUP] 7 [/SUP], Stephen R Cole[SUP] 8 [/SUP], Ana A Weil[SUP] 9 10 [/SUP], Helen Y Chu[SUP] 2 [/SUP], Marco Carone[SUP] 7 [/SUP]
Affiliations
Background: For infectious diseases, characterizing symptom duration is of clinical and public health importance. Symptom duration may be assessed by surveying infected individuals and querying symptom status at the time of survey response. For example, in a severe acute respiratory syndrome coronavirus 2 testing program at the University of Washington, participants were surveyed at least 28 days after testing positive and asked to report current symptom status. This study design yielded current status data: outcome measurements for each respondent consisted only of the time of survey response and a binary indicator of whether symptoms had resolved by that time. Such study design benefits from limited risk of recall bias, but analyzing the resulting data necessitates tailored statistical tools.
Methods: We review methods for current status data and describe a novel application of modern nonparametric techniques to this setting. The proposed approach is valid under weaker assumptions compared with existing methods, allows the use of flexible machine learning tools, and handles potential survey nonresponse. Our method relies on the assumption that the survey response time is conditionally independent of symptom resolution time within strata of measured covariates, and we propose an approach to assess the sensitivity of results to deviations from conditional independence.
Results: From the university study, we estimate that 19% of participants experienced ongoing symptoms 30 days after testing positive, decreasing to 7% at 90 days. We found the estimates to be more sensitive to violations of the conditional independence assumption at 30 days compared with 90 days. Female sex, fatigue during acute infection, and higher viral load were associated with slower symptom resolution.
Conclusion: The proposed method and accompanying sensitivity analysis procedure provide tools for investigators faced with current status data.
Keywords: Interval censoring; Long COVID; Machine learning; Nonparametric; Survival analysis.
. 2025 Jun 5.
doi: 10.1097/EDE.0000000000001882. Online ahead of print. Investigating Symptom Duration Using Current Status Data: A Case Study of Postacute COVID-19 Syndrome
Charles J Wolock[SUP] 1 [/SUP], Susan Jacob[SUP] 2 [/SUP], Julia C Bennett[SUP] 2 [/SUP], Anna Elias-Warren[SUP] 2 [/SUP], Jessica O'Hanlon[SUP] 2 [/SUP], Avi Kenny[SUP] 3 4 [/SUP], Nicholas P Jewell[SUP] 5 6 [/SUP], Andrea Rotnitzky[SUP] 7 [/SUP], Stephen R Cole[SUP] 8 [/SUP], Ana A Weil[SUP] 9 10 [/SUP], Helen Y Chu[SUP] 2 [/SUP], Marco Carone[SUP] 7 [/SUP]
Affiliations
- PMID: 40472281
- DOI: 10.1097/EDE.0000000000001882
Background: For infectious diseases, characterizing symptom duration is of clinical and public health importance. Symptom duration may be assessed by surveying infected individuals and querying symptom status at the time of survey response. For example, in a severe acute respiratory syndrome coronavirus 2 testing program at the University of Washington, participants were surveyed at least 28 days after testing positive and asked to report current symptom status. This study design yielded current status data: outcome measurements for each respondent consisted only of the time of survey response and a binary indicator of whether symptoms had resolved by that time. Such study design benefits from limited risk of recall bias, but analyzing the resulting data necessitates tailored statistical tools.
Methods: We review methods for current status data and describe a novel application of modern nonparametric techniques to this setting. The proposed approach is valid under weaker assumptions compared with existing methods, allows the use of flexible machine learning tools, and handles potential survey nonresponse. Our method relies on the assumption that the survey response time is conditionally independent of symptom resolution time within strata of measured covariates, and we propose an approach to assess the sensitivity of results to deviations from conditional independence.
Results: From the university study, we estimate that 19% of participants experienced ongoing symptoms 30 days after testing positive, decreasing to 7% at 90 days. We found the estimates to be more sensitive to violations of the conditional independence assumption at 30 days compared with 90 days. Female sex, fatigue during acute infection, and higher viral load were associated with slower symptom resolution.
Conclusion: The proposed method and accompanying sensitivity analysis procedure provide tools for investigators faced with current status data.
Keywords: Interval censoring; Long COVID; Machine learning; Nonparametric; Survival analysis.