-
Journal of the American College of... Nov 2011Congenital heart disease (CHD) accounts for nearly one-third of all major congenital anomalies. CHD birth prevalence worldwide and over time is suggested to vary;... (Meta-Analysis)
Meta-Analysis Review
Congenital heart disease (CHD) accounts for nearly one-third of all major congenital anomalies. CHD birth prevalence worldwide and over time is suggested to vary; however, a complete overview is missing. This systematic review included 114 papers, comprising a total study population of 24,091,867 live births with CHD identified in 164,396 individuals. Birth prevalence of total CHD and the 8 most common subtypes were pooled in 5-year time periods since 1930 and in continent and income groups since 1970 using the inverse variance method. Reported total CHD birth prevalence increased substantially over time, from 0.6 per 1,000 live births (95% confidence interval [CI]: 0.4 to 0.8) in 1930 to 1934 to 9.1 per 1,000 live births (95% CI: 9.0 to 9.2) after 1995. Over the last 15 years, stabilization occurred, corresponding to 1.35 million newborns with CHD every year. Significant geographical differences were found. Asia reported the highest CHD birth prevalence, with 9.3 per 1,000 live births (95% CI: 8.9 to 9.7), with relatively more pulmonary outflow obstructions and fewer left ventricular outflow tract obstructions. Reported total CHD birth prevalence in Europe was significantly higher than in North America (8.2 per 1,000 live births [95% CI: 8.1 to 8.3] vs. 6.9 per 1,000 live births [95% CI: 6.7 to 7.1]; p < 0.001). Access to health care is still limited in many parts of the world, as are diagnostic facilities, probably accounting for differences in reported birth prevalence between high- and low-income countries. Observed differences may also be of genetic, environmental, socioeconomical, or ethnic origin, and there needs to be further investigation to tailor the management of this global health problem.
Topics: Confidence Intervals; Female; Global Health; Heart Defects, Congenital; Humans; Infant, Newborn; Prevalence
PubMed: 22078432
DOI: 10.1016/j.jacc.2011.08.025 -
European Journal of Epidemiology Apr 2016Misinterpretation and abuse of statistical tests, confidence intervals, and statistical power have been decried for decades, yet remain rampant. A key problem is that...
Misinterpretation and abuse of statistical tests, confidence intervals, and statistical power have been decried for decades, yet remain rampant. A key problem is that there are no interpretations of these concepts that are at once simple, intuitive, correct, and foolproof. Instead, correct use and interpretation of these statistics requires an attention to detail which seems to tax the patience of working scientists. This high cognitive demand has led to an epidemic of shortcut definitions and interpretations that are simply wrong, sometimes disastrously so-and yet these misinterpretations dominate much of the scientific literature. In light of this problem, we provide definitions and a discussion of basic statistics that are more general and critical than typically found in traditional introductory expositions. Our goal is to provide a resource for instructors, researchers, and consumers of statistics whose knowledge of statistical theory and technique may be limited but who wish to avoid and spot misinterpretations. We emphasize how violation of often unstated analysis protocols (such as selecting analyses for presentation based on the P values they produce) can lead to small P values even if the declared test hypothesis is correct, and can lead to large P values even if that hypothesis is incorrect. We then provide an explanatory list of 25 misinterpretations of P values, confidence intervals, and power. We conclude with guidelines for improving statistical interpretation and reporting.
Topics: Confidence Intervals; Data Interpretation, Statistical; Humans; Probability
PubMed: 27209009
DOI: 10.1007/s10654-016-0149-3 -
Journal of Biomedical Informatics Apr 2014This review provided a conceptual framework of sample size calculations in the studies of diagnostic test accuracy in various conditions and test outcomes.
OBJECTIVES
This review provided a conceptual framework of sample size calculations in the studies of diagnostic test accuracy in various conditions and test outcomes.
METHODS
The formulae of sample size calculations for estimation of adequate sensitivity/specificity, likelihood ratio and AUC as an overall index of accuracy and also for testing in single modality and comparing two diagnostic tasks have been presented for desired confidence interval.
RESULTS
The required sample sizes were calculated and tabulated with different levels of accuracies and marginal errors with 95% confidence level for estimating and for various effect sizes with 80% power for purpose of testing as well. The results show how sample size is varied with accuracy index and effect size of interest.
CONCLUSION
This would help the clinicians when designing diagnostic test studies that an adequate sample size is chosen based on statistical principles in order to guarantee the reliability of study.
Topics: Algorithms; Confidence Intervals; Diagnostic Tests, Routine; Humans; Likelihood Functions; Medical Informatics; Models, Statistical; ROC Curve; Reproducibility of Results; Research Design; Sample Size; Sensitivity and Specificity
PubMed: 24582925
DOI: 10.1016/j.jbi.2014.02.013 -
American Journal of Epidemiology Feb 2021Measures of information and surprise, such as the Shannon information value (S value), quantify the signal present in a stream of noisy data. We illustrate the use of...
Measures of information and surprise, such as the Shannon information value (S value), quantify the signal present in a stream of noisy data. We illustrate the use of such information measures in the context of interpreting P values as compatibility indices. S values help communicate the limited information supplied by conventional statistics and cast a critical light on cutoffs used to judge and construct those statistics. Misinterpretations of statistics may be reduced by interpreting P values and interval estimates using compatibility concepts and S values instead of "significance" and "confidence."
Topics: Confidence Intervals; Data Interpretation, Statistical; Epidemiologic Methods; Humans; Uncertainty
PubMed: 32648906
DOI: 10.1093/aje/kwaa136 -
International Journal of Epidemiology Apr 2019Globally, access to healthcare and diagnostic technologies are known to substantially impact the reported birth prevalence of congenital heart disease (CHD). Previous... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Globally, access to healthcare and diagnostic technologies are known to substantially impact the reported birth prevalence of congenital heart disease (CHD). Previous studies have shown marked heterogeneity between different regions, with a suggestion that CHD prevalence is rising globally, but the degree to which this reflects differences due to environmental or genetic risk factors, as opposed to improved detection, is uncertain. We performed an updated systematic review to address these issues.
METHODS
Studies reporting the birth prevalence of CHD between the years 1970-2017 were identified from searches of PubMed, EMBASE, Web of Science and Google Scholar. Data on the prevalence of total CHD and 27 anatomical subtypes of CHD were collected. Data were combined using random-effect models. Subgroup and meta-regression analyses were conducted, focused on geographical regions and levels of national income.
RESULTS
Two hundred and sixty studies met the inclusion criteria, encompassing 130 758 851 live births. The birth prevalence of CHD from 1970-2017 progressively increased to a maximum in the period 2010-17 of 9.410/1000 [95% CI (confidence interval) 8.602-10.253]. This represented a significant increase over the fifteen prior years (P = 0.031). The change in prevalence of mild CHD lesions (ventricular septal defect, atrial septal defect and patent ductus arteriosus) together explained 93.4% of the increased overall prevalence, consistent with a major role of improved postnatal detection of less severe lesions. In contrast the prevalence of lesions grouped together as left ventricular outflow tract obstruction (which includes hypoplastic left heart syndrome) decreased from 0.689/1000 (95% CI 0.607-0.776) in 1995-99, to 0.475/1000 (95% CI 0.392-0.565; P = 0.004) in 2010-17, which would be consistent with improved prenatal detection and consequent termination of pregnancy when these very severe lesions are discovered. There was marked heterogeneity among geographical regions, with Africa reporting the lowest prevalence [2.315/1000 (95% CI 0.429-5.696)] and Asia the highest [9.342/1000 (95% CI 8.072-10.704)].
CONCLUSIONS
The reported prevalence of CHD globally continues to increase, with evidence of severe unmet diagnostic need in Africa. The recent prevalence of CHD in Asia for the first time appears higher than in Europe and America, where disease ascertainment is likely to be near-complete, suggesting higher genetic or environmental susceptibility to CHD among Asian people.
Topics: Confidence Intervals; Global Health; Heart Defects, Congenital; Humans; Infant, Newborn; Prevalence
PubMed: 30783674
DOI: 10.1093/ije/dyz009 -
Statistics in Medicine Oct 2022Serial limiting dilution (SLD) assays are a widely used tool in many areas of public health research to measure the concentration of target entities. This concentration...
Serial limiting dilution (SLD) assays are a widely used tool in many areas of public health research to measure the concentration of target entities. This concentration can be estimated via maximum likelihood. Asymptotic as well as exact inference methods have been proposed for hypothesis testing and confidence interval construction in this one-sample problem. However, in many scientific applications, it may be of interest to compare the concentration of target entities between a pair of samples and construct valid confidence intervals for the difference in concentrations. In this paper, an exact, computationally efficient inferential procedure is proposed for hypothesis testing and confidence interval construction in the two-sample SLD assay problem. The proposed exact method is compared to an approach based on asymptotic approximations in simulation studies. The methods are illustrated using data from the University of North Carolina HIV Cure Center.
Topics: Biological Assay; Computer Simulation; Confidence Intervals; Humans; Models, Statistical; Research Design
PubMed: 35975729
DOI: 10.1002/sim.9537 -
Journal of the American College of... Mar 2021
Topics: Confidence Intervals; Data Interpretation, Statistical; Humans
PubMed: 33766263
DOI: 10.1016/j.jacc.2021.02.004 -
Proceedings. Biological Sciences Mar 2018The observation of behaviour is a key theoretical parameter underlying a number of models of prosociality. However, the empirical findings showing the effect of... (Meta-Analysis)
Meta-Analysis Review
The observation of behaviour is a key theoretical parameter underlying a number of models of prosociality. However, the empirical findings showing the effect of observability on prosociality are mixed. In this meta-analysis, we explore the boundary conditions that may account for this variability, by exploring key theoretical and methodological moderators of this link. We identified 117 papers yielding 134 study level effects (total = 788 164) and found a small but statistically significant, positive association between observability and prosociality ( = 0.141, 95% confidence interval = 0.106, 0.175). Moderator analysis showed that observability produced stronger effects on prosociality: (i) in the presence of passive observers (i.e. people whose role was to only observe participants) versus perceptions of being watched, (ii) when participants' decisions were consequential (versus non-consequential), (iii) when the studies were performed in the laboratory (as opposed to in the field/online), (iv) when the studies used repeated measures (instead of single games), and (v) when the studies involved social dilemmas (instead of bargaining games). These effects show the conditions under which observability effects on prosociality will be maximally observed. We describe the theoretical and practical significance of these results.
Topics: Behavior Control; Behavior Observation Techniques; Confidence Intervals; Databases, Factual; Effect Modifier, Epidemiologic; Humans; Models, Statistical; Observer Variation; Publication Bias; Social Behavior
PubMed: 29593114
DOI: 10.1098/rspb.2018.0116 -
Canadian Journal of Psychiatry. Revue... Apr 2021
Topics: Confidence Intervals; Humans; Models, Statistical; Psychotic Disorders; Substance-Related Disorders
PubMed: 32991213
DOI: 10.1177/0706743720962277 -
Frontiers in Public Health 2022This article focuses on the construction of a confidence interval for vaccine efficacy against contagious coronavirus disease-2019 (COVID-19) in a fixed number of events...
This article focuses on the construction of a confidence interval for vaccine efficacy against contagious coronavirus disease-2019 (COVID-19) in a fixed number of events design. Five different approaches are presented, and their performance is investigated in terms of the two-sided coverage probability, non-coverage probability at the lower tail, and expected confidence interval width. Furthermore, the effect of under-sensitivity of diagnosis tests on vaccine efficacy estimation was evaluated. Except for the exact conditional method, the non-coverage probability of the remaining methods may exceed the nominal significance level, e.g., 5%, even for a large number of total confirmed COVID-19 cases. The narrower confidence interval width from the Bayesian, approximate Poisson, and mid-P methods are on the cost of increased instability of coverage probability. When the sensitivity of diagnosis test in the vaccine group is lower than that in the placebo group, the reported vaccine efficacy tends to be overly optimistic. The exact conditional method is preferable to other methods in COVID-19 vaccine efficacy trials when the total number of cases reaches 60; otherwise, mid-p method can be used to obtain a narrower interval width.
Topics: Bayes Theorem; COVID-19; COVID-19 Vaccines; Confidence Intervals; Humans; Vaccine Efficacy
PubMed: 36033771
DOI: 10.3389/fpubh.2022.848120