Flexible piecewise linear model for investigating dose-response relationship in meta-analysis: methodology, examples, and comparison

Objectives: Dose-response meta-analysis (DRMA) is widely employed to establishing the potential dose-response relationship between continuous exposures and disease outcomes. However, no method is readily available for exploring the relation between a discrete exposure and a binary or continuous outcome. We proposed a piecewise linear (PL) DRMA model as a solution to this issue. Methods: We illustrated the methodology of PL model in both one-stage DRMA approach and two-stage DRMA approach. The method by testing the equality of slopes of each piecewise was employed to judge if there is “piecewise effect” against simple linear trend. We then used sleep (continuous exposure) and parity (discrete exposure) data as examples to illustrate how to apply PL model in DRMA using the Stata code attached. We also empirically compared the slopes of PL model with simple linear as well as restricted cubic spline (RCS) model. Results: Both one-stage and two-stage PL DRMA model fitted well in our examples, and the results were similar. Obvious “piecewise effects” were detected in both the two examples by the method we used. In our example, the PL model showed better fitting effect and practical reliable results compared to simple linear model, while similar results for to RCS model. Conclusion: Piecewise linear function is a simple and valid method for DRMA and can be used for discrete exposures. It also represents a superior model to linear model in DRMA and may be an alternative model to non-linear model.

Download Full-text

Flexible piecewise linear model for investigating dose‐response relationship in meta‐analysis: Methodology, examples, and comparison

Journal of Evidence-Based Medicine ◽

10.1111/jebm.12339 ◽

2019 ◽

Cited By ~ 2

Author(s):

Chang Xu ◽

Lehana Thabane ◽

Tongzu Liu ◽

ASM Borhan ◽

Xin Sun

Keyword(s):

Linear Model ◽

Dose Response ◽

Piecewise Linear ◽

Meta Analysis ◽

Response Relationship ◽

Dose Response Relationship ◽

Analysis Methodology ◽

Piecewise Linear Model

Download Full-text

Does Glycemic Control Have A Dose-Response Relationship with Implant Outcomes? A Comprehensive Systematic Review and Meta-analysis

Journal of Evidence Based Dental Practice ◽

10.1016/j.jebdp.2021.101543 ◽

2021 ◽

pp. 101543

Author(s):

SZE JUN TAN ◽

BADIAH BAHARIN ◽

SYED NABIL ◽

NURULHUDA MOHD ◽

YINGYING ZHU

Keyword(s):

Systematic Review ◽

Glycemic Control ◽

Dose Response ◽

Meta Analysis ◽

Response Relationship ◽

Dose Response Relationship

Download Full-text

Effects of exposure to low-dose ionizing radiation on changing platelets: a prospective cohort study

Environmental Health and Preventive Medicine ◽

10.1186/s12199-021-00939-z ◽

2021 ◽

Vol 26 (1) ◽

Author(s):

Ning Liu ◽

Yang Peng ◽

Xinguang Zhong ◽

Zheng Ma ◽

Suiping He ◽

...

Keyword(s):

Radiation Dose ◽

Ionizing Radiation ◽

Dose Response ◽

Low Dose ◽

Linear Trend ◽

Hematological Parameters ◽

Response Relationship ◽

Dose Response Relationship ◽

Spline Models ◽

Cumulative Radiation Dose

Abstract Background Numerous studies have concentrated on high-dose radiation exposed accidentally or through therapy, and few involve low-dose occupational exposure, to investigate the correlation between low-dose ionizing radiation and changing hematological parameters among medical workers. Methods Using a prospective cohort study design, we collected health examination reports and personal dose monitoring data from medical workers and used Poisson regression and restricted cubic spline models to assess the correlation between changing hematological parameters and cumulative radiation dose and determine the dose-response relationship. Results We observed that changing platelet of 1265 medical workers followed up was statistically different among the cumulative dose groups (P = 0.010). Although the linear trend tested was not statistically significant (Ptrend = 0.258), the non-linear trend tested was statistically significant (Pnon-linear = 0.007). Overall, there was a correlation between changing platelets and cumulative radiation dose (a change of βa 0.008 × 109/L during biennially after adjusting for gender, age at baseline, service at baseline, occupation, medical level, and smoking habits; 95% confidence interval [CI] = 0.003,0.014 × 109/L). Moreover, we also found positive first and then negative dose-response relationships between cumulative radiation dose and changing platelets by restricted cubic spline models, while there were negative patterns of the baseline service not less than 10 years (− 0.015 × 109/L, 95% CI = − 0.024, − 0.007 × 109/L) and radiation nurses(− 0.033 × 109/L, 95% CI = − 0.049, − 0.016 × 109/L). Conclusion We concluded that although the exposure dose was below the limit, medical workers exposed to low-dose ionizing radiation for a short period of time might have increased first and then decreased platelets, and there was a dose-response relationship between the cumulative radiation dose and platelets changing.

Download Full-text

Blood Pressure, Hypertension and The Risk of Aortic Dissection Incidence and Mortality: results from the Japan-Specific Health Checkups Study, the UK Biobank Study and a Meta-analysis of Cohort Studies

Circulation ◽

10.1161/circulationaha.121.056546 ◽

2021 ◽

Author(s):

Makoto Hibino ◽

Yoichiro Otaki ◽

Elsa Kobeissi ◽

Han Pan ◽

Hiromi Hibino ◽

...

Keyword(s):

Blood Pressure ◽

Aortic Dissection ◽

Dose Response ◽

Meta Analysis ◽

Response Relationship ◽

Uk Biobank ◽

Dose Response Relationship ◽

Fractional Polynomial ◽

The Uk ◽

Specific Health

Background: Hypertension or elevated blood pressure (BP) is an important risk factor for aortic dissection (AD); however, few prospective studies concerning this topic have been published. We investigated the association between hypertension/elevated BP and AD in two cohorts and conducted a meta-analysis of published prospective studies, including these two studies. Methods: We analyzed data from the Japan Specific Health Checkups (J-SHC) Study and UK Biobank, which prospectively followed 534,378 and 502,424 participants, respectively. Multivariable Cox regression was used to estimate hazard ratios (HRs) and 95% confidence intervals (95% CIs) for the association of hypertension/elevated BP with AD incidence in the UK Biobank and AD mortality in the J-SHC Study. In the meta-analysis, summary relative risks (RRs) were calculated using random effects models. A potential nonlinear dose-response relationship between BP and AD was tested using fractional polynomial models, and the best-fitting second-order fractional polynomial regression model was determined. Results: In the J-SHC Study and UK Biobank, there were 84 and 182 ADs during 4- and 9-year follow-up, and the adjusted HRs of AD were 3.57 (95% CI, 2.17-6.11) and 2.68 (95% CI: 1.78-4.04) in hypertensive individuals, 1.33 (95% CI: 1.05-1.68) and 1.27 (95% CI: 1.11-1.48) per 20-mmHg increase in systolic BP (SBP), and 1.67 (95% CI: 1.40-2.00) and 1.66 (95% CI: 1.46-1.89) per 10-mmHg increase in diastolic BP (DBP), respectively. In the meta-analysis, the summary RRs were 3.07 (95% CI 2.15-4.38, I2=76.7%, n=7 studies, 2,818 ADs, 4,563,501 participants) for hypertension and 1.39 (95% CI: 1.16-1.66, I2=47.7%, n=3) and 1.79 (95% CI: 1.51-2.12, I2=57.0%, n=3) per 20-mmHg increase in SBP and per 10-mmHg in DBP, respectively. The AD risk showed a strong, positive dose-response relationship with SBP and even more so with DBP. The risk of AD in the nonlinear dose-response analysis was significant at SBP >132 mmHg and DBP >75 mmHg. Conclusions: Hypertension and elevated SBP and DBP are associated with a high risk of AD. The risk of AD was positively dose-dependent, even within the normal BP range. These findings provide further evidence for the optimization of BP to prevent AD.

Download Full-text

Abstract P209: Dose-Response Relationship Between Dietary Intake of Alpha-linolenic Acid and Risk of Coronary Heart Disease: A Meta-analysis of Prospective Studies

Circulation ◽

10.1161/circ.135.suppl_1.p209 ◽

2017 ◽

Vol 135 (suppl_1) ◽

Author(s):

Jingkai Wei ◽

Yuzhi Xi ◽

Ruixue Hou ◽

Alysse Kowalski ◽

Hao Sun ◽

...

Keyword(s):

Dose Response ◽

Meta Analysis ◽

Pooled Analysis ◽

Controlled Trials ◽

Response Relationship ◽

Alpha Linolenic Acid ◽

Dose Response Relationship ◽

Randomized Controlled ◽

Chd Risk ◽

Reduced Risk

Introduction: Previous studies show that alpha-linolenic acid (ALA) is associated with reduced risk of coronary heart disease (CHD). However, it remains unclear whether and how dietary ALA doses are related to CHD. Hypothesis: We hypothesized that higher dietary ALA intake is associated with a greater reduction in risk of CHD. Methods: We searched PubMed, EMBASE, and Web of Science for prospective studies examining the association between dietary ALA intake and CHD risk. Dietary ALA intake was assigned or measured by self-report. Outcomes were reported as total and fatal CHD and/or myocardial infarction, which were obtained from blinded endpoint assessments or medical records. Two-stage fixed-effects dose-response meta-analyses were conducted to estimate the association between increasing ALA intake (relative to study-specific referents) and CHD. Results: Fifteen published articles were identified and included in the meta-analysis (13 cohort studies and 2 randomized controlled trials). The pooled analysis was based on 310,768 individuals with 12,049 events with a mean length of follow-up of 9.6 years. The analysis showed a J-shaped curve between ALA intake and relative risk of total CHD (Chi-square=21.08, p<0.001). ALA intake from 0.3-1.4g/day showed reduced risk of total CHD, while intake ≥2.5g/day was associated with increased risk of CHD, compared to people without ALA intake (Figure 1A). Approximately 1g/day of ALA intake was associated with the lowest risk of total CHD. ALA intake was linearly associated with fatal CHD - every 1g/day increase in ALA intake was associated with an 11% decrease in fatal CHD risk (95% CI: -0.16, -0.05) (Figure 1B). Conclusion: The J-shaped dose-response relationship based on our pooled analysis suggests that 1g/day of dietary ALA may be optimal for total CHD prevention. Though a higher dietary ALA intake was associated with reduced risk of fatal CHD, the excess total CHD risk at higher ALA intakes warrants further investigation, especially through randomized controlled trials.

Download Full-text

Dose-Response Relationship Between Serum 2,3,7,8-Tetrachlorodibenzo-p-Dioxin and Diabetes Mellitus: A Meta-Analysis

American Journal of Epidemiology ◽

10.1093/aje/kwu307 ◽

2015 ◽

Vol 181 (6) ◽

pp. 374-384 ◽

Cited By ~ 8

Author(s):

Michael Goodman ◽

K. M. Venkat Narayan ◽

Dana Flanders ◽

Ellen T. Chang ◽

Hans-Olov Adami ◽

...

Keyword(s):

Diabetes Mellitus ◽

Dose Response ◽

Meta Analysis ◽

Response Relationship ◽

Dose Response Relationship ◽

Tetrachlorodibenzo P Dioxin

Download Full-text

The association and dose–response relationship between dietary intake of α-linolenic acid and risk of CHD: a systematic review and meta-analysis of cohort studies

British Journal Of Nutrition ◽

10.1017/s0007114517003294 ◽

2018 ◽

Vol 119 (1) ◽

pp. 83-89 ◽

Cited By ~ 9

Author(s):

Jingkai Wei ◽

Ruixue Hou ◽

Yuzhi Xi ◽

Alysse Kowalski ◽

Tiansheng Wang ◽

...

Keyword(s):

Cohort Studies ◽

Linolenic Acid ◽

Random Effects ◽

Dose Response ◽

Meta Analysis ◽

Geographic Region ◽

Response Relationship ◽

Dose Response Relationship ◽

Chd Risk ◽

Reduced Risk

AbstractPrevious studies show inconsistent associations between α-linolenic acid (ALA) and risk of CHD. We aimed to examine an aggregate association between ALA intake and risk of CHD, and assess for any dose–response relationship. We searched the PubMed, EMBASE and Web of Science databases for prospective cohort studies examining associations between ALA intake and CHD, including composite CHD and fatal CHD. Data were pooled using random-effects meta-analysis models, comparing the highest category of ALA intake with the lowest across studies. Subgroup analysis was conducted based on study design, geographic region, age and sex. For dose–response analyses, we used two-stage random-effects dose–response models. In all, fourteen studies of thirteen cohorts were identified and included in the meta-analysis. The pooled results showed that higher ALA intake was associated with modest reduced risk of composite CHD (risk ratios (RR)=0·91; 95 % CI 0·85, 0·97) and fatal CHD (RR=0·85; 95 % CI 0·75, 0·96). The analysis showed a J-shaped relationship between ALA intake and relative risk of composite CHD (χ2=21·95, P<0·001). Compared with people without ALA intake, only people with ALA intake <1·4 g/d showed reduced risk of composite CHD. ALA intake was linearly associated with fatal CHD – every 1 g/d increase in ALA intake was associated with a 12 % decrease in fatal CHD risk (95 % CI −0·21, −0·04). Though a higher dietary ALA intake was associated with reduced risk of composite and fatal CHD, the excess composite CHD risk at higher ALA intakes warrants further investigation, especially through randomised controlled trials.

Download Full-text