Using causal frameworks to reduce bias in observational TB research: a comparison of model-building approaches
IJTLD Open · 2026-08 · 3 (8) · 494-501
DOI: 10.5588/ijtldopen.26.0076 ↗Kurz gefasst
Fachartikel in der Zeitschrift IJTLD Open, online erschienen am 01.08.2026. Verfasst von L Barcellini und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Paediatrics, "V. Buzzi" Children's Hospital, ASST FBF Sacco, Milan, Italy. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIAID NIH HHS.
Abstract (Originalsprache)
BACKGROUND Observational studies investigating causal (aetiological) questions often address confounding bias using data-driven predictive models where variables are selected regardless of their causal role, challenging interpretation. We compared the estimated effect of HIV co-infection on end-of-treatment outcomes among people with multidrug/rifampicin-resistant TB using a causal framework model and a data-driven predictive model. METHODS The causal framework guided confounder adjustment. Results were compared to those from models that applied alternative variable selection strategies (based on P values and change-in-estimate), which do not draw on domain knowledge to identify relevant variables. RESULTS The model informed by a causal diagram indicated that people living with HIV had a 31% lower probability of achieving a successful outcome compared to those without HIV (adjusted relative risk [aRR] 0.69, 95% confidence interval [CI]: 0.41–0.98). In contrast, data-driven models produced attenuated associations (aRR 0.78, 95% CI: 0.50–1.06 and aRR 0.80, 95% CI: 0.5–1.09 for the P value and change-in-estimate strategies, respectively), reflecting omission of key confounders, and inappropriate inclusion of mediators and colliders. DISCUSSION When the research question is aetiological, using a causal approach to guide variable selection ensures proper adjustment, improves interpretability, and establishes a stronger foundation for future observational research.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Paediatrics, "V. Buzzi" Children's Hospital, ASST FBF Sacco, Milan, Italy.
- Department of Global Health and Social Medicine, Harvard Medical School, Boston, MA, USA.
- Partners In Health, Boston, MA, USA.
- Division of Global Health Equity, Brigham and Women's Hospital, Boston, MA, USA.
- Field Epidemiology Department, Epicentre, Paris, France.
- Interactive Research and Development (IRD) Global, Singapore, Singapore.
Förderung
- NIAID NIH HHS
Zitieren
APA
Barcellini, L., Sauer, S., Romo, M., Mitnick, C. D., Huerga, H., Khan, U., Hewison, C., Rich, M. L., Franke, M. F., & Khan, P. Y. (2026). Using causal frameworks to reduce bias in observational TB research: a comparison of model-building approaches. IJTLD Open, 3(8), 494-501. https://doi.org/10.5588/ijtldopen.26.0076
Vancouver
Barcellini L, Sauer S, Romo M, Mitnick CD, Huerga H, Khan U, et al. Using causal frameworks to reduce bias in observational TB research: a comparison of model-building approaches. IJTLD Open. 2026;3(8):494-501. doi:10.5588/ijtldopen.26.0076
BibTeX
@article{Barcellini2026,
author = {Barcellini, L and Sauer, S and Romo, M and Mitnick, C D and Huerga, H and Khan, U and Hewison, C and Rich, M L and Franke, M F and Khan, P Y},
title = {Using causal frameworks to reduce bias in observational TB research: a comparison of model-building approaches},
journal = {IJTLD Open},
year = {2026},
volume = {3},
number = {8},
pages = {494--501},
doi = {10.5588/ijtldopen.26.0076}
}
EUVIMED