Meta-analysis of breast cancer risk for individuals with PALB2 pathogenic variants.

Multigene panel testing now allows efficient testing of many cancer susceptibility genes leading to a larger number of mutation carriers being identified. They need to be counseled about their cancer risk conferred by the specific gene mutation. An important cancer susceptibility gene is PALB2. Multiple studies reported risk estimates for breast cancer (BC) conferred by pathogenic variants in PALB2. Due to the diverse modalities of reported risk estimates (age-specific risk, odds ratio, relative risk, and standardized incidence ratio) and effect sizes, a meta-analysis combining these estimates is necessary to accurately counsel patients with this mutation. However, this is not trivial due to heterogeneity of studies in terms of study design and risk measure. We utilized a recently proposed Bayesian random-effects meta-analysis method that can synthesize estimates from such heterogeneous studies. We applied this method to combine estimates from 12 studies on BC risk for carriers of pathogenic PALB2 mutations. The estimated overall (meta-analysis-based) risk of BC is 12.80% (6.11%-22.59%) by age 50 and 48.47% (36.05%-61.74%) by age 80. Pathogenic mutations in PALB2 makes women more susceptible to BC. Our risk estimates can help clinically manage patients carrying pathogenic variants in PALB2.

Polygenic risk for prostate cancer: Decreasing relative risk with age but little impact on absolute risk.

Polygenic risk scores (PRSs) for a variety of diseases have recently been shown to have relative risks that depend on age, and genetic relative risks decrease with increasing age. A refined understanding of the age dependency of PRSs for a disease is important for personalized risk predictions and risk stratification. To further evaluate how the PRS relative risk for prostate cancer depends on age, we refined analyses for a validated PRS for prostate cancer by using 64,274 prostate cancer cases and 46,432 controls of diverse ancestry (82.8% European, 9.8% African American, 3.8% Latino, 2.8% Asian, and 0.8% Ghanaian). Our strategy applied a novel weighted proportional hazards model to case-control data to fully utilize age to refine how the relative risk decreased with age. We found significantly greater relative risks for younger men (age 30-55 years) compared with older men (70-88 years) for both relative risk per standard deviation of the PRS and dichotomized according to the upper 90th percentile of the PRS distribution. For the largest European ancestral group that could provide reliable resolution, the log-relative risk decreased approximately linearly from age 50 to age 75. Despite strong evidence of age-dependent genetic relative risk, our results suggest that absolute risk predictions differed little from predictions that assumed a constant relative risk over ages, from short-term to long-term predictions, simplifying implementation of risk discussions into clinical practice.

Estimating causal effects for binary outcomes using per-decision inverse probability weighting.

Micro-randomized trials are commonly conducted for optimizing mobile health interventions such as push notifications for behavior change. In analyzing such trials, causal excursion effects are often of primary interest, and their estimation typically involves inverse probability weighting (IPW). However, in a micro-randomized trial, additional treatments can often occur during the time window over which an outcome is defined, and this can greatly inflate the variance of the causal effect estimator because IPW would involve a product of numerous weights. To reduce variance and improve estimation efficiency, we propose two new estimators using a modified version of IPW, which we call "per-decision IPW." The second estimator further improves efficiency using the projection idea from the semiparametric efficiency theory. These estimators are applicable when the outcome is binary and can be expressed as the maximum of a series of sub-outcomes defined over sub-intervals of time. We establish the estimators' consistency and asymptotic normality. Through simulation studies and real data applications, we demonstrate substantial efficiency improvement of the proposed estimator over existing estimators. The new estimators can be used to improve the precision of primary and secondary analyses for micro-randomized trials with binary outcomes.

The risk of COVID-19 death is much greater and age dependent with type I IFN autoantibodies.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection fatality rate (IFR) doubles with every 5 y of age from childhood onward. Circulating autoantibodies neutralizing IFN-α, IFN-ω, and/or IFN-ß are found in ∼20% of deceased patients across age groups, and in ∼1% of individuals aged <70 y and in >4% of those >70 y old in the general population. With a sample of 1,261 unvaccinated deceased patients and 34,159 individuals of the general population sampled before the pandemic, we estimated both IFR and relative risk of death (RRD) across age groups for individuals carrying autoantibodies neutralizing type I IFNs, relative to noncarriers. The RRD associated with any combination of autoantibodies was higher in subjects under 70 y old. For autoantibodies neutralizing IFN-α2 or IFN-ω, the RRDs were 17.0 (95% CI: 11.7 to 24.7) and 5.8 (4.5 to 7.4) for individuals <70 y and ≥70 y old, respectively, whereas, for autoantibodies neutralizing both molecules, the RRDs were 188.3 (44.8 to 774.4) and 7.2 (5.0 to 10.3), respectively. In contrast, IFRs increased with age, ranging from 0.17% (0.12 to 0.31) for individuals <40 y old to 26.7% (20.3 to 35.2) for those ≥80 y old for autoantibodies neutralizing IFN-α2 or IFN-ω, and from 0.84% (0.31 to 8.28) to 40.5% (27.82 to 61.20) for autoantibodies neutralizing both. Autoantibodies against type I IFNs increase IFRs, and are associated with high RRDs, especially when neutralizing both IFN-α2 and IFN-ω. Remarkably, IFRs increase with age, whereas RRDs decrease with age. Autoimmunity to type I IFNs is a strong and common predictor of COVID-19 death.

The risk of treatment-related toxicities with PD-1/PD-L1 inhibitors in patients with lung cancer.

The risk of treatment-related toxicities with programmed cell death 1 and its ligand (PD-1/PD-L1) inhibitors in patients with lung cancer is unclear and inconclusive. PubMed, EMBASE, and the Cochrane Library databases were systematically searched without language restrictions from inception to May 31, 2024 to identify Phase 3 randomized controlled trials of lung cancer comparing PD-1/PD-L1 inhibitors versus placebo/best supportive care (alone or in combination with nontargeted chemotherapy) that had available data regarding treatment-related adverse events (TRAEs) or incidence and sample size. Random-effect models were employed to study the pooled relative risk (RR) and 95% confidence intervals (CIs). Finally, 36 trials, involving 19,693 participants, fulfilled the inclusion criteria. PD-1/PD-L1 inhibitors significantly augmented the likelihood of developing all-grade (RR, 1.03; 95% CI, 1.01-1.04, p < .01) and grade ≥3 TRAEs (RR, 1.16; 95% CI, 1.10 to 1.23, p < .01). PD-1/PD-L1 inhibitors substantially augmented the odds of developing treatment-related serious adverse events (SAEs) (RR, 1.48; 95% CI, 1.27-1.71, p < .01) and fatal adverse events (FAEs) (RR, 1.42; 95% CI, 1.11-1.82, p < .01). Subgroup analyses indicated that the RR of SAEs and FAEs were generally consistent, regardless of treatment type, tumor type, treatment setting, PD-1/PD-L1 inhibitors type and study design. The most common causes of FAEs were respiratory failure/insufficiency (33.3%), cardiac events (16.1%), and hematological disorders (10.1%). We demonstrated that PD-1/PD-L1 inhibitors were significantly correlated with higher possibility of developing treatment-related toxicities, especially SAEs and FAEs, compared with placebo/best supportive care controls.

Hematopoietic cell transplantation and cellular therapies in Switzerland. Evolution over 25 years. A report from the stem cell transplantation and cellular therapies working groups of the SBST 1997-2021.

The Swiss Blood Stem Cell Transplantation and Cellular Therapy Group (SBST) leads a mandatory national registry for all hematopoietic stem cell transplants (HCT) and cellular therapies. After 25 years, information was available for 11,226 patients receiving an HCT (4031 allogeneic and 7195 autologous), including 925 pediatric patients. We compared patient characteristics and outcome by quinquennia 1997-2001, 2002-2006, 2007-2011, 2012-2016, and 2017-2021. There were numerous changes over time. Allogeneic transplant recipients became older (median age 33.7 vs. 54.3) and had more frequently unrelated donors and reduced intensity conditioning in later quinquennia. Similarly, age increased for recipients of autologous HCT (median 48.3 vs. 59.9). We did not see a significant drop in transplant activity during the SARS-CoV-2 pandemic. Analysis of outcome showed overall survival (relative risk (RR) of death 0.664 (0.529-0.832) and progression free survival (RR 0.708 (0.577-0.870) being improved over time comparing the latest to the first quinquennium adjusting for risk factors. Non-relapse mortality decreased in recipients of allogeneic HCT (RR: 0.371 (0.270-0.509)) over time but relapse risks did not. Outcome of autologous HCT improved as well across quinquennia, this improvement was mainly due to decreased relapse risks (RR 0.681 (0.597-0.777)), possibly related to maintenance treatment or rescue treatment for relapse mainly in myeloma patients. Cellular therapies other than allogeneic or autologous HCT, particularly chimeric antigen receptor T-cells (CAR-T) treatment have started to increase after 2019, year of approval of the first commercial CAR-T product in Switzerland. Data on chimeric antigen receptor T-cell treatment are too early for comparative analyses. Detailed analyses of changes over time are presented. This study includes all HCTs, and cellular therapies, data useful for quality assurance programs, health care cost estimation and benchmarking. Between 50% and 60% of patients are long-term survivors after both types of HCT, indicating growing populations of surviving patients requiring long-term care.

Rejoinder to the discussion on "Bayesian meta-analysis of penetrance for cancer risk".

The five discussions of our paper provide several modeling alternatives, extensions, and generalizations that can potentially guide future research in meta-analysis. In this rejoinder, we briefly summarize and comment on some of those points.

Bayesian meta-analysis of penetrance for cancer risk.

Multi-gene panel testing allows many cancer susceptibility genes to be tested quickly at a lower cost making such testing accessible to a broader population. Thus, more patients carrying pathogenic germline mutations in various cancer-susceptibility genes are being identified. This creates a great opportunity, as well as an urgent need, to counsel these patients about appropriate risk-reducing management strategies. Counseling hinges on accurate estimates of age-specific risks of developing various cancers associated with mutations in a specific gene, ie, penetrance estimation. We propose a meta-analysis approach based on a Bayesian hierarchical random-effects model to obtain penetrance estimates by integrating studies reporting different types of risk measures (eg, penetrance, relative risk, odds ratio) while accounting for the associated uncertainties. After estimating posterior distributions of the parameters via a Markov chain Monte Carlo algorithm, we estimate penetrance and credible intervals. We investigate the proposed method and compare with an existing approach via simulations based on studies reporting risks for two moderate-risk breast cancer susceptibility genes, ATM and PALB2. Our proposed method is far superior in terms of coverage probability of credible intervals and mean square error of estimates. Finally, we apply our method to estimate the penetrance of breast cancer among carriers of pathogenic mutations in the ATM gene.

Sleep duration, its change, and risk of dementia among Japanese: The Japan Public Health Center-based Prospective Study.

OBJECTIVE: Previous findings on the association between sleep duration, changes in sleep duration, and long-term dementia risk were mixed. Thus, we aimed to investigate the association between midlife sleep duration, its change, and dementia. METHODS: We recruited 41,731 Japanese (40-71 years) and documented their habitual sleep duration at baseline (1990-1994) and a 5-year follow-up survey. Changes in sleep duration were calculated as differences between baseline and 5-year measurements. We identified dementia using the Long-Term Care Insurance system (2007-2016). Hazard ratios (HRs) and 95% confidence intervals (CIs) of dementia were calculated using the area-stratified Cox model. RESULTS: During 360,389 person-years, 4621 participants exhibited dementia. The multivariable HRs of dementia compared with 7 h of sleep were 1.13 (95% CI: 0.98-1.30) for 3-5 h, 0.93 (0.85-1.02) for 6 h, 1.06 (0.99-1.14) for 8 h, 1.13 (1.01-1.27) for 9 h, and 1.40 (1.21-1.63) for 10-12 h with a J-shaped fashion (p for linear < 0.001 and quadratic < 0.001). For its change, the HRs compared with no change were 1.02 (0.90-1.16) for decreased ≥2 h, 0.95 (0.88-1.03) for decreased 1 h, 1.00 (0.91-1.09) for increased 1 h, and 1.37 (1.20-1.58) for increased ≥2 h. The positive association for decreased sleep duration was observed in individuals with an initial sleep duration of ≤7 h, but not in those with ≥8 h (p for interaction = 0.007). CONCLUSIONS: Long and increased sleep duration was associated with a higher risk of dementia.

Elucidating vaccine efficacy using a correlate of protection, demographics, and logistic regression.

BACKGROUND: Vaccine efficacy (VE) assessed in a randomized controlled clinical trial can be affected by demographic, clinical, and other subject-specific characteristics evaluated as baseline covariates. Understanding the effect of covariates on efficacy is key to decisions by vaccine developers and public health authorities. METHODS: This work evaluates the impact of including correlate of protection (CoP) data in logistic regression on its performance in identifying statistically and clinically significant covariates in settings typical for a vaccine phase 3 trial. The proposed approach uses CoP data and covariate data as predictors of clinical outcome (diseased versus non-diseased) and is compared to logistic regression (without CoP data) to relate vaccination status and covariate data to clinical outcome. RESULTS: Clinical trial simulations, in which the true relationship between CoP data and clinical outcome probability is a sigmoid function, show that use of CoP data increases the positive predictive value for detection of a covariate effect. If the true relationship is characterized by a decreasing convex function, use of CoP data does not substantially change positive or negative predictive value. In either scenario, vaccine efficacy is estimated more precisely (i.e., confidence intervals are narrower) in covariate-defined subgroups if CoP data are used, implying that using CoP data increases the ability to determine clinical significance of baseline covariate effects on efficacy. CONCLUSIONS: This study proposes and evaluates a novel approach for assessing baseline demographic covariates potentially affecting VE. Results show that the proposed approach can sensitively and specifically identify potentially important covariates and provides a method for evaluating their likely clinical significance in terms of predicted impact on vaccine efficacy. It shows further that inclusion of CoP data can enable more precise VE estimation, thus enhancing study power and/or efficiency and providing even better information to support health policy and development decisions.

Excess Mortality Risk Due to Heat Stress in Different Climatic Zones of India.

India is at a high risk of heat stress-induced health impacts and economic losses owing to its tropical climate, high population density, and inadequate adaptive planning. The health impacts of heat stress across climate zones in India have not been adequately explored. Here, we examine and report the vulnerability to heat stress in India using 42 years (1979-2020) of meteorological data from ERA-5 and developed climate-zone-specific percentile-based human comfort class thresholds. We found that the heat stress is usually 1-4 °C higher on heatwave (HW) days than on nonheatwave (NHW) days. However, the stress on NHW days remains considerable and cannot be neglected. We then showed the association of a newly formulated India heat index (IHI) with daily all-cause mortality in three cities - Delhi (semiarid), Varanasi (humid subtropical), and Chennai (tropical wet and dry), using a semiparametric quasi-Poisson regression model, adjusted for nonlinear confounding effects of time and PM2.5. The all-cause mortality risk was enhanced by 8.1% (95% confidence interval, CI: 6.0-10.3), 5.9% (4.6-7.2), and 8.0% (1.7-14.2) during "sweltering" days in Varanasi, Delhi, and Chennai, respectively, relative to "comfortable" days. Across four age groups, the impact was more severe in Varanasi (ranging from a 3.2 to 7.5% increase in mortality risk for a unit rise in IHI) than in Delhi (2.6-4.2% higher risk) and Chennai (0.9-5.7% higher risk). We observed a 3-6 days lag effect of heat stress on mortality in these cities. Our results reveal heterogeneity in heat stress impact across diverse climate zones in India and call for developing an early warning system keeping in mind these regional variations.

Learning about treatment effects in a new target population under transportability assumptions for relative effect measures.

Investigators often believe that relative effect measures conditional on covariates, such as risk ratios and mean ratios, are "transportable" across populations. Here, we examine the identification of causal effects in a target population using an assumption that conditional relative effect measures are transportable from a trial to the target population. We show that transportability for relative effect measures is largely incompatible with transportability for difference effect measures, unless the treatment has no effect on average or one is willing to make even stronger transportability assumptions that imply the transportability of both relative and difference effect measures. We then describe how marginal (population-averaged) causal estimands in a target population can be identified under the assumption of transportability of relative effect measures, when we are interested in the effectiveness of a new experimental treatment in a target population where the only treatment in use is the control treatment evaluated in the trial. We extend these results to consider cases where the control treatment evaluated in the trial is only one of the treatments in use in the target population, under an additional partial exchangeability assumption in the target population (i.e., an assumption of no unmeasured confounding in the target population with respect to potential outcomes under the control treatment in the trial). We also develop identification results that allow for the covariates needed for transportability of relative effect measures to be only a small subset of the covariates needed to control confounding in the target population. Last, we propose estimators that can be easily implemented in standard statistical software and illustrate their use using data from a comprehensive cohort study of stable ischemic heart disease.

Visceral adiposity index as a predictor of type 2 diabetes mellitus risk: A systematic review and dose-response meta-analysis.

AIMS: Considering the positive association between visceral adiposity index (VAI) and type 2 diabetes mellitus (T2DM), no comprehensive assessment on the summarized and dose-response relationship between VAI and T2DM has yet been reported. Therefore, we performed a meta-analysis, including dose-response analysis, to quantitively elucidate this association. DATA SYNTHESIS: MEDLINE via PubMed and Embase databases were searched for relevant articles up to December 14, 2021. Random-effects generalized least squares regression models were used to assess the quantitative association between VAI and T2DM risk across studies. Restricted cubic splines were used to model the dose-response association. A total of 9 prospective cohort studies and 5 cross sectional studies were included in our review. Based on the meta-analysis, the pooled RR of T2DM was 2.05 (95% CI 1.74-2.41) for the highest versus reference VAI category. We found that the risk of T2DM was increased by 44% (RR, 1.44; 95% CI, 1.23-1.68) with each 1-unit increment of VAI. While, we found no evidence of a nonlinear dose-response association of VAI and T2DM (Pnon-linearity = 0.428). With the linear cubic spline model, when compared to population with VAI at 0.6, for those with VAI at 2.0, the risk of T2DM was increased by 81% (RR, 1.81; 95% CI 1.55-2.12). CONCLUSIONS: Our meta-analysis provides quantitative data suggesting that VAI is associated with an increased risk of T2DM. Public health strategies focusing on weight loss among obesity, especially the people characterized by the thin-on-the-outside--fat-on-the-inside phenotype could possibly reduce a substantial risk of T2DM. SYSTEMATIC REVIEW REGISTRATION: PROSPERO CRD42022372666.

Interval estimation of relative risks for combined unilateral and bilateral correlated data.

Measurements are generally collected as unilateral or bilateral data in clinical trials, epidemiology, or observational studies. For example, in ophthalmology studies, the primary outcome is often obtained from one eye or both eyes of an individual. In medical studies, the relative risk is usually the parameter of interest and is commonly used. In this article, we develop three confidence intervals for the relative risk for combined unilateral and bilateral correlated data under the equal dependence assumption. The proposed confidence intervals are based on maximum likelihood estimates of parameters derived using the Fisher scoring method. Simulation studies are conducted to evaluate the performance of proposed confidence intervals with respect to the empirical coverage probability, the mean interval width, and the ratio of mesial non-coverage probability to the distal non-coverage probability. We also compare the proposed methods with the confidence interval based on the method of variance estimates recovery and the confidence interval obtained from the modified Poisson regression model with correlated binary data. We recommend the score confidence interval for general applications because it best controls converge probabilities at the 95% level with reasonable mean interval width. We illustrate the methods with a real-world example.

Miettinen and Nurminen score statistics revisited.

It is commonly necessary to perform inferences on the difference, ratio, and odds ratio of two proportions p1 and p2 based on two independent samples. For this purpose, the most common asymptotic statistics are based on the score statistics (S-type statistics). As these do not correct the bias of the estimator of the product pi (1-pi), Miettinen and Nurminen proposed the MN-type statistics, which consist of multiplying the statistics S by (N-1)/N, where N is the sum of the two sample sizes. This paper demonstrates that the factor (N-1)/N is only correct in the case of the test of equality of two proportions, providing the estimation of the correct factor (AU-type statistics) and the minimum value of the same (AUM-type statistics). Moreover, this paper assesses the performance of the four-type statistics mentioned (S, MN, AU and AUM) in one and two-tailed tests, and for each of the three parameters cited (d, R and OR). We found that the AUM-type statistics are the best, followed by the MN type (whose performance was most similar to that of AU-type). Finally, this paper also provides the correct factors when the data are from a multinomial distribution, with the novelty that the MN and AU statistics are similar in the case of the test for the odds ratio.

Effects of major air pollutants on angina hospitalizations: a correlation study.

BACKGROUND: Angina is a crucial risk signal for cardiovascular disease. However, few studies have evaluated the effects of ambient air pollution exposure on angina. OBJECTIVE: We aimed to explore the short-term effects of air pollution on hospitalization for angina and its lag effects. METHODS: We collected data on air pollutant concentrations and angina hospitalizations from 2013 to 2020. Distributed lag nonlinear model (DLNM) was used to evaluate the short-term effects of air pollutants on angina hospitalization under different lag structures. Stratified analysis by sex, age and season was obtained. RESULTS: A total of 39,110 cases of angina hospitalization were included in the study. The results showed a significant positive correlation between PM2.5, SO2, NO2, and CO and angina hospitalization. Their maximum harmful effects were observed at lag0-7 (RR = 1.042; 95% CI: 1.017, 1.068), lag0-3 (RR = 1.067; 95% CI: 1.005, 1.133), lag0-6 (RR = 1.078; 95% CI: 1.041, 1.117), and lag0-6 (RR = 1.244; 95% CI: 1.109, 1.397), respectively. PM10 did not have an overall risk effect on angina hospitalization, but it did have a risk effect on women and the elderly. O3 was significantly negatively correlated with angina hospitalization, with the most pronounced effect observed at lag0-6 (RR = 0.960; 95% CI: 0.940, 0.982). Stratified analysis results showed that women and the elderly were more susceptible to pollutants, and the adverse effects of pollutants were stronger in the cold season. CONCLUSION: Short-term exposure to PM2.5, SO2, NO2, and CO increases the risk of hospitalization for angina.

Risk of central nervous system tumour incidence in a cohort of workers chronically exposed to ionising radiation.

The aim of the present study was to assess the risk of primary central nervous system (CNS) tumour incidence in a cohort of 22,377 Mayak Production Association workers chronically exposed to ionising radiation. There were 96 primary CNS tumours, including 42 cases of glioma and 44 cases of meningioma, registered during the whole follow-up period (1948-2018). The study demonstrated that the risk of primary CNS tumour incidence was associated with sex, attained age, calendar period, tall body height, age at the beginning of exposure, and facility type. There was no association found between risk of CNS tumour incidence and body mass index, smoking (males) and alcohol consumption status. The study did not find an effect of the total external gamma radiation dose absorbed in the brain on risk of CNS tumour incidence irrespective of whether an adjustment for the total external neutron dose absorbed in the brain was included or not. Excess relative risk per 1 Gy of external gamma brain dose was 0.05 (95% confidence interval (CI) -0.30; 0.70) for all CNS tumours, -0.18 (95% CI -; 0.44) for gliomas, and 0.38 (95% CI -0.32; 2.08) for meningiomas without adjustment for total neutron brain dose. There was no effect modification by sex, attained age, age at hire or facility.

Distributed lag effects and vulnerable groups of PM and active pulmonary TB in Qingdao, China.

There has been a gap regarding current knowledge of the effect of PM on pulmonary TB, such as the exposure-time-response between them. This study aimed to explore the distributed lag effects of particulate matter (PM) on active pulmonary tuberculosis (TB) and identify the vulnerable groups. A generalized additive mixed model combined with a distributed lag non-linear model was applied to quantify the association between PM and active pulmonary TB with adjustment for potential confounders. Relative risk (RR) and cumulative RR with 95% confidence interval (CI) were calculated to quantify the exposure-time-response. A total of 16,486 cases of active pulmonary TB were notified. Results suggested that a unit 10 µg/m3 increase of daily PM2.5 concentration was positively associated with active pulmonary TB morbidity at 36-115 lag day and RR reached maximum at 66 lag day (1.0076; 95%CI, 1.0031-1.0122), and the cumulative RR was 2.1940 (95%CI, 1.2292-3.9161). For PM10, this association was significantly positive at 73-117 lag day, and RR reached maximum at 100 lag day (1.0036; 95%CI, 1.0003-1.0067), and the cumulative RR was not significant. This study provides evidence that PM significantly associate with active pulmonary TB. Vulnerability to PM2.5 was identified in male, female, 0-18 ages, 19-64 ages, workers, and students. Our findings have significant implications for developing local strategies to prevent and reduce health impact in PM polluted areas.

Misuse of multinomial logistic regression in stroke related health research: A systematic review of methodology.

Multinomial logistic regression (MLR) is often used to model the association between a nominal outcome variable and one or more covariates. The results of MLR are interpreted as relative risk ratios (RRR) and warrant a more coherent interpretation than ordinary logistic regression. Some authors compare the results of MLR to ordinal logistic regression (OLR), irrespective of the fact that these estimate different quantities. We aim to investigate the time trends in the use and misuse of MLR in studies including stroke patients, specifically the extent to which (1) the results are denoted as anything other than RRR, (2) comparisons are made of results with results of OLR and (3) results have been interpreted coherently. Secondarily, we examine the use of model validation techniques in studies with predictive aims. We searched EMBASE and PubMed for articles using MLR on populations of stroke patients. Identified studies were screened, and information pertaining to our aims was extracted. A total of 285 articles were identified through a systematic literature search, and 68 of these were included in the review. Of these, 60 articles (88%) did not denote exponentiated coefficients of MLR as relative risk ratios but rather some other measure. Additionally, 63 articles (93%) interpreted the results of MLR in a non-coherent manner. Two articles attempted to compare MLR results with those of OLR. Nine studies attempted to use MLR for predictive means, and three used relevant validation techniques. From these findings, it is clear that the interpretation of MLR is often suboptimal.

A proportional incidence rate model for aggregated data to study the vaccine effectiveness against COVID-19 hospital and ICU admissions.

We develop a proportional incidence model that estimates vaccine effectiveness (VE) at the population level using conditional likelihood for aggregated data. Our model assumes that the population counts of clinical outcomes for an infectious disease arise from a superposition of Poisson processes with different vaccination statuses. The intensity function in the model is calculated as the product of per capita incidence rate and the at-risk population size, both of which are time-dependent. We formulate a log-linear regression model with respect to the relative risk, defined as the ratio between the per capita incidence rates of vaccinated and unvaccinated individuals. In the regression analysis, we treat the baseline incidence rate as a nuisance parameter, similar to the Cox proportional hazard model in survival analysis. We then apply the proposed models and methods to age-stratified weekly counts of COVID-19-related hospital and ICU admissions among adults in Ontario, Canada. The data spanned from 2021 to February 2022, encompassing the Omicron era and the rollout of booster vaccine doses. We also discuss the limitations and confounding effects while advocating for the necessity of more comprehensive and up-to-date individual-level data that document the clinical outcomes and measure potential confounders.