Category: Statistics

Psychometrika. 2022 Mar 20. doi: 10.1007/s11336-022-09854-w. Online ahead of print.

ABSTRACT

Studies with sensitive questions should include a sufficient number of respondents to adequately address the research interest. While studies with an inadequate number of respondents may not yield significant conclusions, studies with an excess of respondents become wasteful of investigators’ budget. Therefore, it is an important step in survey sampling to determine the required number of participants. In this article, we derive sample size formulas based on confidence interval estimation of prevalence for four randomized response models, namely, the Warner’s randomized response model, unrelated question model, item count technique model and cheater detection model. Specifically, our sample size formulas control, with a given assurance probability, the width of a confidence interval within the planned range. Simulation results demonstrate that all formulas are accurate in terms of empirical coverage probabilities and empirical assurance probabilities. All formulas are illustrated using a real-life application about the use of unethical tactics in negotiation.

PMID:35306631 | DOI:10.1007/s11336-022-09854-w

Eur J Epidemiol. 2022 Mar 20. doi: 10.1007/s10654-022-00853-w. Online ahead of print.

ABSTRACT

This mixed design synthesis aimed to estimate the infection fatality rate (IFR) of Coronavirus Disease 2019 (COVID-19) in community-dwelling elderly populations and other age groups from seroprevalence studies. Protocol: https://osf.io/47cgb . Eligible were seroprevalence studies done in 2020 and identified by any of four existing systematic reviews; with ≥ 500 participants aged ≥ 70 years; presenting seroprevalence in elderly people; aimed to generate samples reflecting the general population; and whose location had available data on cumulative COVID-19 deaths in elderly (primary cutoff ≥ 70 years; ≥ 65 or ≥ 60 also eligible). We extracted the most fully adjusted (if unavailable, unadjusted) seroprevalence estimates; age- and residence-stratified cumulative COVID-19 deaths (until 1 week after the seroprevalence sampling midpoint) from official reports; and population statistics, to calculate IFRs adjusted for test performance. Sample size-weighted IFRs were estimated for countries with multiple estimates. Thirteen seroprevalence surveys representing 11 high-income countries were included in the main analysis. Median IFR in community-dwelling elderly and elderly overall was 2.9% (range 1.8-9.7%) and 4.5% (range 2.5-16.7%) without accounting for seroreversion (2.2% and 4.0%, respectively, accounting for 5% monthly seroreversion). Multiple sensitivity analyses yielded similar results. IFR was higher with larger proportions of people > 85 years. The IFR of COVID-19 in community-dwelling elderly is lower than previously reported.

PMID:35306604 | DOI:10.1007/s10654-022-00853-w

Jpn J Ophthalmol. 2022 Mar 20. doi: 10.1007/s10384-022-00911-6. Online ahead of print.

ABSTRACT

PURPOSE: To investigate the characteristics of retinal detachment (RD) and compare the outcomes of surgical interventions, such as scleral buckling (SB), pars plana vitrectomy (PPV), or PPV combined with SB, conducted on holidays and on workdays to determine the optimal surgical timing for primary RD treatment in clinical practice.

STUDY DESIGN: Retrospective cohort study.

METHODS: The cohort included 3178 patients with primary RD registered in the Japan Retinal Detachment Registry between February 2016 and March 2017. Surgery data were divided into holiday and workday groups. A descriptive analysis of primary RD characteristics was performed, and the outcomes for each surgical intervention were assessed. The primary outcome was anatomical failure at 6 months post-surgery classified as follows: level 1, inoperable state; level 2, anatomical recovery with silicone-oil use; and level 3, additional surgery required for RD repair.

RESULTS: The holiday group comprised 108 and the workday, 3070 cases of primary RD. Compared with those in the workday group, surgery in the holiday group took longer (PPV, P < 0.0001; SB, P = 0.047) and was performed by less experienced surgeons (P = 0.014). However, there were no statistically significant differences in surgical failure 6 months post-surgery between the workday and holiday groups.

CONCLUSION: Although surgery conducted on holidays and workdays was not significantly different in terms of outcome, some surgery should be postponed with proper preoperative interim measures to limit RD progress until it can be conducted on workdays by a well-prepared team.

PMID:35306598 | DOI:10.1007/s10384-022-00911-6

World J Surg. 2022 Mar 19. doi: 10.1007/s00268-022-06501-4. Online ahead of print.

ABSTRACT

BACKGROUND: Recommendations regarding the timing of cholecystectomy for acute biliary pancreatitis (ABP) require a systematic summary of current evidence to guide clinical practice. We conducted a systematic review and meta-analysis of randomized controlled trials (RCTs) comparing early cholecystectomy (EC) versus delayed cholecystectomy (DC) in patients with ABP.

METHODS: We searched databases Medline, Embase, SCOPUS, Web of Science and Cochrane CENTRAL for randomized controlled trials addressing this question. Pairs of reviewers abstracted data and assessed the risk of bias in included studies. A random-effects meta-analysis was done to study the effect of the timing of cholecystectomy on outcomes of interest in patients with ABP. GRADE methodology was used to rate the quality in the body of evidence for each outcome as high, moderate, low, or very low.

RESULTS: 11 randomized trials (1176 participants) were included. High-quality evidence from seven RCTs (867 participants) showed a statistically significant reduction in the risk for recurrent biliary events in favour of early cholecystectomy (RR 0.10, 95% CI 0.05 to 0.19, I² = 0%). High-quality evidence from five trials was in favour of early cholecystectomy with a significant reduction in the risk 7of recurrent pancreatitis (RAP) in comparison to delayed cholecystectomy (RR 0.21, 95% CI 0.09 to 0.51, I² = 0%).

CONCLUSION: This review showed that EC has definite advantages over DC in terms of reducing recurrent pancreaticobiliary events and LOS following mild ABP. However, more RCTs are required to study the role of EC in patients with moderately-severe and severe ABP. Trial Registration Protocol registered on Prospero (CRD42020192823).

PMID:35306590 | DOI:10.1007/s00268-022-06501-4

J Clin Endocrinol Metab. 2022 Mar 20:dgac171. doi: 10.1210/clinem/dgac171. Online ahead of print.

ABSTRACT

BACKGROUND: Accelerated reproductive aging, in women indicated by early natural menopause, is associated with increased coronary heart disease (CHD) risk in observational studies. Conversely, an adverse CHD risk profile has been suggested to accelerate menopause.

OBJECTIVES: To study the direction and evidence for causality of the relationship between reproductive aging and (non-)fatal CHD and CHD risk factors in a bidirectional Mendelian Randomization (MR) approach, using age at natural menopause (ANM) genetic variants as a measure for genetically determined reproductive aging in women. We also studied the association of these variants with CHD risk (factors) in men.

DESIGN: Two-sample MR, using both cohort data as well as summary statistics, with four methods: simple and weighted median-based, standard inverse-variance weighted (IVW) regression, and MR-Egger regression.

PARTICIPANTS: Data from EPIC-CVD and summary statistics from UK Biobank and publicly available GWAS were pooled for the different analyses.

MAIN OUTCOME MEASURES: CHD, CHD risk factors and ANM.

RESULTS: Across different methods of MR no association was found between genetically determined reproductive aging and CHD risk in women (Relative Risk Estimate (RRE)IVW=0.99, 95% confidence interval (CI):0.97;1.01), or any of the CHD risk factors. Similarly, no associations were found in men. Neither did the reversed analyses show evidence for an association between CHD (risk factors) and reproductive aging.

CONCLUSION: Genetically determined reproductive aging is not causally associated with CHD risk (factors) in women, nor were the genetic variants associated in men. We found no evidence for a reverse association in a combined sample of women and men.

PMID:35306566 | DOI:10.1210/clinem/dgac171

J Gastrointestin Liver Dis. 2022 Mar 19;31(1):67-73. doi: 10.15403/jgld-4027.

ABSTRACT

BACKGROUND AND AIMS: The effect of linked color imaging (LCI) compared with white light imaging (WLI) is conflicting. The aim of this meta-analysis is to compare the efficacy of LCI versus WLI for the adenoma detection.

METHODS: PubMed, Embase, Google Scholar and Cochrane Library were searched up to the end of Aug 18, 2021. All randomized controlled trials (RCTs) comparing LCI with WLI were included. Dichotomous data were pooled to obtain the relative risk (RR) with a 95% confidence interval (CI), whereas continuous data were pooled using a mean difference (MD) with 95%CI.

RESULTS: A total of 10 RCTs involving 5,510 patients were included. The use of LCI was associated with a statistically significant improvement in adenoma detection rate (ADR), polyp detection rate (PDR), mean adenomas per patient (MAP) and mean polyp per patient (MPP) when compared to WLI (ADR: RR=1.15, 95%CI: 1.07-1.23, p=0.0001, PDR: RR=1.15, 95%CI: 1.08-1.22, p<0.0001; MAP: MD=0.18, 95%CI: 0.09- 0.28, p=0.0002; MPP: MD=0.13, 95%CI: 0.01, 0.25, p=0.03). When stratified by size, LCI group had a higher detection rate of small adenomas (<10 mm) than the WLI group. Besides, LCI showed a significant decrease in adenoma miss rate (AMR) when compared to WLI. There were no statistically significant differences between the two groups in advanced ADR (AADR), sessile serrated lesion detection rate (SDR), cecal intubation rate, insertion time, and withdrawal time.

CONCLUSIONS: The pooled evidence suggests that LCI can significantly improve the detection of ADR, especially for small adenomas (<10 mm). Moreover, the AMR were significantly lower using LCI compared with WLI.

PMID:35306544 | DOI:10.15403/jgld-4027

J Gastrointestin Liver Dis. 2022 Mar 19;31(1):40-47. doi: 10.15403/jgld-4034.

ABSTRACT

BACKGROUND AND AIMS: Bacterial infections are associated with high mortality rates in patients with decompensated cirrhosis. Early diagnosis with the available diagnostic tools is challenging. Metabolomics is a novel technique with a widespread application in hepatology. The aims of our study were to find new biomarkers for decompensated cirrhosis and for those with overlapping bacterial infections.

METHODS: 43 patients with compensated and 54 patients with decompensated cirrhosis were enrolled in the study. In patients with decompensation, a complete infectious workup was performed at admission. Blood and ascitic fluid were collected and stored at -80° C until performing the metabolomic analysis. Statistical analysis was performed using the Metaboanalyst 4.0 software.

RESULTS: 36 patients (66%) in the decompensated group were infected. Among them, 15 had multiple infections; thus, finally, 52 infections were diagnosed. The main metabolic pathways affected in patients with decompensated cirrhosis were those related to lipid metabolism, involving acylcarnitines, stearic acid derivatives, and 12/15 HETE-GABA. N-oleoyl ethanolamine was the most promising biomarker for bacterial infection diagnosis. Moreover, prostaglandin E2/D2/H2 and N-oleoyl alanine levels were higher in Gram- positive infections and ceramides (d16:2/18:0), in Gram-negative infections, respectively. L-phenylalanine (m/z=166.09) and lysophosphatidylethanolamine (18:3/0:0) were the two most relevant identified ascitic biomarkers for spontaneous bacterial peritonitis diagnosis.

CONCLUSIONS: The lipid and energetic metabolic pathways were the most affected in patients with decompensated cirrhosis and those with overlapping infections.

PMID:35306561 | DOI:10.15403/jgld-4034

J Gastrointestin Liver Dis. 2022 Mar 19;31(1):11-17. doi: 10.15403/jgld-4025.

ABSTRACT

AIMS: To explore if anti-gliadin antibody (AGA) positivity is associated with overall mortality or morbidity and especially with the development of coeliac disease during long-term gluten exposure.

METHODS: The study population comprised 130 persistently AGA-positive but transglutaminase-2 (anti- TG2) -negative and 52 persistently AGA- and anti-TG2 -negative subjects aged 64-88 years. HLA-typing for DQ2 and DQ8 (coeliac-type HLA) was performed on the AGA-positives. The medical records of the study population were reviewed to compare mortality and morbidity during a long-term follow-up of 12-13 years since the initial antibody analysis.

RESULTS: Mortality or cumulative prevalence of gastroenterological, autoimmune, psychiatric, cardiovascular or any malignant diseases did not differ statistically between the AGA-positives and the AGA-negatives. Neurological diseases were more common in the AGA-negative group (p=0.017), but there was no statistical difference between the prevalence of any particular neurological diseases. Coeliac-type HLA in AGA-positive subjects did not influence mortality or morbidity. However, during the last six to seven years the incidence of immunological diseases was more common in the AGA-positive subjects without coeliac-type HLA than in those with coeliac-type HLA, or in the AGA-negative group (p=0.020). None of the persistently AGA-positive subjects developed clinically diagnosed coeliac disease.

CONCLUSIONS: Gliadin antibody positivity without coeliac disease does not predict mortality or morbidity in the ageing population continuing to consume gluten for over ten years.

PMID:35306543 | DOI:10.15403/jgld-4025

Br J Cancer. 2022 Mar 19. doi: 10.1038/s41416-022-01779-6. Online ahead of print.

ABSTRACT

BACKGROUND: Serious and potentially life-threatening toxicities can occur following 5-fluorouracil/capecitabine exposure. Patients carrying Dihydropyrimidine Dehydrogenase (DPYD) variant alleles associated with decreased enzymatic function are at a greater risk of early/severe 5-fluorouracil/capecitabine toxicity. The objective of this systematic review/meta-analysis was to evaluate treatment outcomes between Pharmacogenetics Guided Dosing (PGD) versus non-PGD and within PGD (DPYD variant allele carriers versus wild type).

METHODS: A systematic review/meta-analysis of original publications indexed in Ovid Medline, Ovid Embase, and the Cochrane CENTRAL (Wiley) library from inception to 7-Dec-2020. Eligible studies evaluated at least one pre-defined treatment outcome measures (toxicity/hospitalisations/survival/overall response/quality of life).

RESULTS: Of 1090 identified publications, 17 met predefined eligibility criteria. The meta-analysis observed reduced incidence of grade 3/4 overall toxicity (Risk Ratio [RR] 0.32 [95% Cl 0.27-0.39], p < 0.00001) and grade 3/4 diarrhoea (RR 0.38 [95% Cl 0.24-0.61], p < 0.0001) among PGD versus non-PGD cohorts. Within PGD cohorts, there was no statistical differences for overall response rates (complete/partial) (RR 1.31 [95% Cl 0.93-1.85], p = 0.12). Similar results were found with stable disease (RR 1.27 [95% Cl 0.66-2.44], p = 0.47).

CONCLUSION: PGD improves patient outcomes in terms of grade 3/4 toxicity, in particular overall toxicity and diarrhoea, without impacting on treatment response.

REGISTRATION NUMBER: The study is registered with PROSPERO, registration number CRD42020223768.

PMID:35306539 | DOI:10.1038/s41416-022-01779-6

Hum Brain Mapp. 2022 Mar 19. doi: 10.1002/hbm.25838. Online ahead of print.

ABSTRACT

Multi-site MRI datasets are crucial for big data research. However, neuroimaging studies must face the batch effect. Here, we propose an approach that uses the predictive probabilities provided by Gaussian processes (GPs) to harmonize clinical-based studies. A multi-site dataset of 216 Parkinson’s disease (PD) patients and 87 healthy subjects (HS) was used. We performed a site GP classification using MRI data. The outcomes estimated from this classification, redefined like Weighted HARMonization PArameters (WHARMPA), were used as regressors in two different clinical studies: A PD versus HS machine learning classification using GP, and a VBM comparison (FWE-p < .05, k = 100). Same studies were also conducted using conventional Boolean site covariates, and without information about site belonging. The results from site GP classification provided high scores, balanced accuracy (BAC) was 98.39% for grey matter images. PD versus HS classification performed better when the WHARMPA were used to harmonize (BAC = 78.60%; AUC = 0.90) than when using the Boolean site information (BAC = 56.31%; AUC = 0.71) and without it (BAC = 57.22%; AUC = 0.73). The VBM analysis harmonized using WHARMPA provided larger and more statistically robust clusters in regions previously reported in PD than when the Boolean site covariates or no corrections were added to the model. In conclusion, WHARMPA might encode global site-effects quantitatively and allow the harmonization of data. This method is user-friendly and provides a powerful solution, without complex implementations, to clean the analyses by removing variability associated with the differences between sites.

PMID:35305545 | DOI:10.1002/hbm.25838