Abstract
Keywords
We thank Dr Wang for the thoughtful evaluation of our study and appreciate the opportunity to clarify the issues raised (Mohammadi et al 2026). The discrepancies in Table 1 stem from the suppression of categories with very small cell counts (n < 3) to protect participant confidentiality, in accordance with Swedish data‑protection standards and ethical requirements. Specifically, the categories “Registered partner” and “Doctoral education” contained very few individuals and were therefore withheld, despite being retained in all statistical analyses. This explains why the visible category counts do not appear to sum to the full cohort size.
Of the 3,361 individuals included in the study, 19 lacked socioeconomic information in the LISA register. These cases were excluded from complete‑case analyses, leaving 3,342 participants with available education and civil status data. Importantly, the suppression concerned presentation only and had no impact on coding, model specification, or study conclusions.
We hope this clarifies the rationale behind our data presentation and demonstrates that the integrity of the analyses remains intact.
Concerning E-values, these are formally defined for risk ratios. Because mortality was common in our cohort, we did not assume the rare-outcome approximation (HR ≈ RR). Instead, we applied the hazard ratio–specific transformation described by VanderWeele (2017; supplementary material, p. 3):
We then calculated the E-value as:
yielding values of 1.30 to 1.38. Direct substitution of the hazard ratio into the conventional formula produces slightly larger values (1.37 to 1.49), without affecting interpretation.
Finally, while dementia subtype and baseline cognitive severity are established prognostic factors, our objective was to evaluate tooth loss as a pragmatic marker at diagnosis. Residual confounding cannot be excluded and warrants further study.
Footnotes
Acknowledgements
None.
Authors Contribution
M. Mohammadi, contributed to conception and design, data analysis, drafted and critically revised the manuscript; J. Holmer, H. Albrektsson, M. Eriksdotter, contributed to data analysis, critically revised the manuscript; H. Imberg, contributed to conception and design, data acquisition, drafted and critically revised the manuscript; K. Buhlin, contributed to conception and design, data acquisition, drafted and critically revised the manuscript. All authors gave their final approval and agree to be accountable for all aspects of the work.
Declaration of Conflicting Interests
The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
Funding
The authors received no financial support for the research, authorship, and/or publication of this article.
Data Availability Statement
We, the authors, state that data sharing is not applicable.