著者
Masahiko Gosho Tomohiro Ohigashi Kengo Nagashima Yuri Ito Kazushi Maruo
出版者
Japan Epidemiological Association
雑誌
Journal of Epidemiology (ISSN:09175040)
巻号頁・発行日
pp.JE20210089, (Released:2021-09-25)
参考文献数
46
被引用文献数
8

Background: Logistic regression models are widely used to evaluate the association between a binary outcome and a set of covariates. However, when there are few study participants at the outcome and covariate levels, the models lead to bias of the odds ratio (OR) estimated using the maximum likelihood (ML) method. This bias is known as sparse data bias, and the estimated OR can yield impossibly large values because of data sparsity. However, this bias has been ignored in most epidemiological studies.Methods: We review several methods for reducing sparse data bias in logistic regression. The primary aim is to evaluate the Bayesian methods in comparison with the classical methods, such as the ML, Firth’s, and exact methods using a simulation study. We also apply these methods to a real data set.Results: Our simulation results indicate that the bias of the OR from the ML, Firth’s, and exact methods is considerable. Furthermore, the Bayesian methods with hyper-g prior modeling of the prior covariance matrix for regression coefficients reduced the bias under the null hypothesis, whereas the Bayesian methods with log F-type priors reduced the bias under the alternative hypothesis.Conclusion: The Bayesian methods using log F-type priors and hyper-g prior are superior to the ML, Firth’s, and exact methods when fitting logistic models to sparse data sets. The choice of a preferable method depends on the null and alternative hypothesis. Sensitivity analysis is important to understand the robustness of the results in sparse data analysis.
著者
Tomoko Machino-Ohtsuka Kentaro Minami Hiro Yamasaki Tomofumi Nakatsukasa Naoto Kawamatsu Kimi Sato Masayoshi Yamamoto Kazushi Maruo Tomoko Ishizu Yasushi Kawakami Masaki Ieda
出版者
The Japanese Circulation Society
雑誌
Circulation Journal (ISSN:13469843)
巻号頁・発行日
pp.CJ-23-0271, (Released:2023-06-30)
参考文献数
26

Background: In patients with atrial fibrillation (AF) and severe blood stasis in the left atrial appendage (LAA), dense spontaneous echo contrast (SEC) disturbs the distinct visualization of the LAA interior, thus making thrombus diagnosis inconclusive. We aimed to prospectively assess the efficacy and safety of a protocol for a low-dose isoproterenol (ISP) infusion to reduce SEC to exclude an LAA thrombus.Methods and Results: We enrolled 17 patients with AF and dense SEC (Grade 4 or sludge). ISP was infused with gradually increasing doses of 0.01, 0.02, and 0.03 μg/kg/min at 3-min intervals. After increasing the dose to 0.03 μg/kg/min for 3 min, or when the LAA interior was visible, the infusion was terminated. We reassessed the SEC grade, presence of an LAA thrombus, LAA function, and left ventricular ejection fraction (LVEF) within 1 min of ISP termination. Compared with baseline, ISP significantly increased LAA flow velocity, the LAA emptying fraction, LAA wall velocities, and LVEF (all P<0.01). ISP administration significantly reduced the SEC grade (median) from 4 to 1 (P<0.001). The SEC grade decreased to ≤2 in 15 (88%) patients, and the LAA thrombus was excluded. There were no adverse events.Conclusions: Low-dose ISP infusion may be effective and safe to reduce SEC and exclude an LAA thrombus by improving LAA function and LVEF.
著者
Yuta Nemoto Shinichiro Sato Yoshinori Kitabatake Noriko Takeda Kazushi Maruo Takashi Arao
出版者
Japan Epidemiological Association
雑誌
Journal of Epidemiology (ISSN:09175040)
巻号頁・発行日
pp.JE20210419, (Released:2022-05-14)
参考文献数
53
被引用文献数
4

Background: It has not been determined whether mentally active sedentary behavior (MASB) and passive sedentary behavior (PSB) differentially affect cognitive function and whether these associations differ according to physical activity (PA) level. We examined the comparative impacts of MASB and PSB on dementia onset and aimed to understand whether the associations differed by PA level.Methods: We conducted a 5-year longitudinal study involving all community-dwelling older adults in a rural area in Japan (n = 5,323). Dementia onset was examined using long-term care insurance data. PA was evaluated using the International Physical Activity Questionnaire and categorized as low (<2.5 metabolic equivalent of task [MET]-h/week), moderate (2.5–16.0 MET-h/week), or high (≥16.0 MET-h/week). We also assessed PSB (TV-watching time; <1 h/day, 1–3 h/day, ≥3 h/day) and MASB (Book-reading time; <10 min/day, 10–30 min/day, ≥30 min/day). To examine the associations of MASB and PSB with dementia onset, we performed the Fine-Gray models accounting for competing risk of death.Results: During the follow-up period, 606 (11.4%) participants developed dementia. MASB was independently associated with a lower risk of dementia; the magnitude of the impact was significant at higher PA levels. There was no association between PSB and developing dementia across all PA levels. Furthermore, dementia risk for individuals with high PA levels and moderate or high MASB levels was approximately 60% lower than those with low PA levels and low MASB.Conclusion: Providing interventions to promote MASB, which reduces dementia risk, and PA, which increases MASB’s effect on dementia incidence, can be beneficial in delaying or preventing dementia onset.