Categories
Nevin Manimala Statistics

Addressing the issue of bias in observational studies: Using instrumental variables and a quasi-randomization trial in an ESME research project

PLoS One. 2021 Sep 15;16(9):e0255017. doi: 10.1371/journal.pone.0255017. eCollection 2021.

ABSTRACT

PURPOSE: Observational studies using routinely collected data are faced with a number of potential shortcomings that can bias their results. Many methods rely on controlling for measured and unmeasured confounders. In this work, we investigate the use of instrumental variables (IV) and quasi-trial analysis to control for unmeasured confounders in the context of a study based on the retrospective Epidemiological Strategy and Medical Economics (ESME) database, which compared overall survival (OS) with paclitaxel plus bevacizumab or paclitaxel alone as first-line treatment in patients with HER2-negative metastatic breast cancer (MBC).

PATIENTS AND METHODS: Causal interpretations and estimates can be made from observation data using IV and quasi-trial analysis. Quasi-trial analysis has the same conceptual basis as IV, however, instead of using IV in the analysis, a “superficial” or “pseudo” randomized trial is used in a Cox model. For instance, in a multicenter trial, instead of using the treatment variable, quasi-trial analysis can consider the treatment preference in each center, which can be informative, and then comparisons of results between centers or clinicians can be informative.

RESULTS: In the original analysis, the OS adjusted for major factors was significantly longer with paclitaxel and bevacizumab than with paclitaxel alone. Using the center-treatment preference as an instrument yielded to concordant results. For the quasi-trial analysis, a Cox model was used, adjusted on all factors initially used. The results consolidate those obtained with a conventional multivariate Cox model.

CONCLUSION: Unmeasured confounding is a major concern in observational studies, and IV or quasi-trial analysis can be helpful to complement analysis of studies of this nature.

PMID:34525119 | DOI:10.1371/journal.pone.0255017

Categories
Nevin Manimala Statistics

Applications of statistical experimental designs to improve statistical inference in weed management

PLoS One. 2021 Sep 15;16(9):e0257472. doi: 10.1371/journal.pone.0257472. eCollection 2021.

ABSTRACT

In a balanced design, researchers allocate the same number of units across all treatment groups. It has been believed as a rule of thumb among some researchers in agriculture. Sometimes, an unbalanced design outperforms a balanced design. Given a specific parameter of interest, researchers can design an experiment by unevenly distributing experimental units to increase statistical information about the parameter of interest. An additional way of improving an experiment is an adaptive design (e.g., spending the total sample size in multiple steps). It is helpful to have some knowledge about the parameter of interest to design an experiment. In the initial phase of an experiment, a researcher may spend a portion of the total sample size to learn about the parameter of interest. In the later phase, the remaining portion of the sample size can be distributed in order to gain more information about the parameter of interest. Though such ideas have existed in statistical literature, they have not been applied broadly in agricultural studies. In this article, we used simulations to demonstrate the superiority of the experimental designs over the balanced designs under three practical situations: comparing two groups, studying a dose-response relationship with right-censored data, and studying a synergetic effect of two treatments. The simulations showed that an objective-specific design provides smaller error in parameter estimation and higher statistical power in hypothesis testing when compared to a balanced design. We also conducted an adaptive experimental design applied to a dose-response study with right-censored data to quantify the effect of ethanol on weed control. Retrospective simulations supported the benefit of this adaptive design as well. All researchers face different practical situations, and appropriate experimental designs will help utilize available resources efficiently.

PMID:34525126 | DOI:10.1371/journal.pone.0257472

Categories
Nevin Manimala Statistics

Reconstructing contact network structure and cross-immunity patterns from multiple infection histories

PLoS Comput Biol. 2021 Sep 15;17(9):e1009375. doi: 10.1371/journal.pcbi.1009375. Online ahead of print.

ABSTRACT

Interactions within a population shape the spread of infectious diseases but contact patterns between individuals are difficult to access. We hypothesised that key properties of these patterns can be inferred from multiple infection data in longitudinal follow-ups. We developed a simulator for epidemics with multiple infections on networks and analysed the resulting individual infection time series by introducing similarity metrics between hosts based on their multiple infection histories. We find that, depending on infection multiplicity and network sampling, multiple infection summary statistics can recover network properties such as degree distribution. Furthermore, we show that by mining simulation outputs for multiple infection patterns, one can detect immunological interference between pathogens (i.e. the fact that past infections in a host condition future probability of infection). The combination of individual-based simulations and analysis of multiple infection histories opens promising perspectives to infer and validate transmission networks and immunological interference for infectious diseases from longitudinal cohort data.

PMID:34525092 | DOI:10.1371/journal.pcbi.1009375

Categories
Nevin Manimala Statistics

Comparison of machine learning methods for estimating case fatality ratios: An Ebola outbreak simulation study

PLoS One. 2021 Sep 15;16(9):e0257005. doi: 10.1371/journal.pone.0257005. eCollection 2021.

ABSTRACT

BACKGROUND: Machine learning (ML) algorithms are now increasingly used in infectious disease epidemiology. Epidemiologists should understand how ML algorithms behave within the context of outbreak data where missingness of data is almost ubiquitous.

METHODS: Using simulated data, we use a ML algorithmic framework to evaluate data imputation performance and the resulting case fatality ratio (CFR) estimates, focusing on the scale and type of data missingness (i.e., missing completely at random-MCAR, missing at random-MAR, or missing not at random-MNAR).

RESULTS: Across ML methods, dataset sizes and proportions of training data used, the area under the receiver operating characteristic curve decreased by 7% (median, range: 1%-16%) when missingness was increased from 10% to 40%. Overall reduction in CFR bias for MAR across methods, proportion of missingness, outbreak size and proportion of training data was 0.5% (median, range: 0%-11%).

CONCLUSION: ML methods could reduce bias and increase the precision in CFR estimates at low levels of missingness. However, no method is robust to high percentages of missingness. Thus, a datacentric approach is recommended in outbreak settings-patient survival outcome data should be prioritised for collection and random-sample follow-ups should be implemented to ascertain missing outcomes.

PMID:34525098 | DOI:10.1371/journal.pone.0257005

Categories
Nevin Manimala Statistics

Red-emitting InP quantum dot micro-disk lasers epitaxially grown on (001) silicon

Opt Lett. 2021 Sep 15;46(18):4514-4517. doi: 10.1364/OL.436320.

ABSTRACT

Direct epitaxy of InP quantum dot (QD) lasers on silicon (Si) provides an on-chip red laser source for integrated Si photonics with different applications. Here, we demonstrate the first, to the best of our knowledge, InP QD lasers directly grown on (001) Si. Combining highly emissive InP QDs and a GaAs/Si template with low defect density, continuous-wave (CW) lasing of micro-disk lasers (MDLs) on Si is achieved at room temperature. The lowest threshold of MDLs on Si is ∼500nW, without considering the micro-disk surface absorption efficiency of the pump power. The MDLs grown on the native GaAs substrate with the same growth and fabrication process are compared using statistical data analysis. Similar material characterization results and device performances on these two substrates further confirm the performance of QD lasers on Si. This demonstration paves the way for future realization of integrated photonic circuits with red and near-infrared (NIR) lasers on Si.

PMID:34525035 | DOI:10.1364/OL.436320

Categories
Nevin Manimala Statistics

Plasmodium vivax epidemiology in Ethiopia 2000-2020: A systematic review and meta-analysis

PLoS Negl Trop Dis. 2021 Sep 15;15(9):e0009781. doi: 10.1371/journal.pntd.0009781. Online ahead of print.

ABSTRACT

BACKGROUND: Ethiopia is one of the scarce rare African countries where Plasmodium vivax and P. falciparum co-exist. There has been no attempt to derive a robust prevalence estimate of P. vivax in the country although a clear understanding of the epidemiology of this parasite is essential for informed decisions. This systematic review and meta-analysis, therefore, is aimed to synthesize the available evidences on the distribution of P. vivax infection by different locations/regions, study years, eco-epidemiological zones, and study settings in Ethiopia.

METHODS: This study was conducted in accordance with Preferred Reposting Items for Systematic Reviews and Meta Analyses (PRISMA) guidelines. Studies conducted and published over the last two decades (2000 to 2020) that reported an estimate of P. vivax prevalence in Ethiopia were included. The Cochrane Q (χ2) and the I2 tests were used to assess heterogeneity, and the funnel plot and Egger’s test were used to examine publication bias. A p-value of the χ2 test <0.05 and an I2 value >75% were considered presence of considerable heterogeneity. Random effect models were used to obtain pooled estimate of P. vivax infection prevalence. This study is registered with PROSPERO (International Prospective Register of Systematic Reviews): ID CRD42020201761.

RESULTS: We screened 4,932 records and included 79 studies that enrolled 1,676,659 confirmed malaria cases, from which 548,214 (32.69%) were P. vivax infections and 1,116,581 (66.59%) were due to P. falciparum. The rest (11,864 or 0.7%) were due to mixed infections. The pooled estimate of P. vivax prevalence rate was 8.93% (95% CI: 7.98-9.88%) with significant heterogeneity (I2 = 100%, p<0.0001). Regional differences showed significant effects (p<0.0001, and I2 = 99.4%) on the pooled prevalence of P. vivax, while study years (before and after the scaling up of interventional activities) did not show significant differences (p = 0.9, I2 = 0%). Eco-epidemiological zones considered in the analysis did show a significant statistical effect (p<0.001, I2 = 78.5%) on the overall pooled estimate prevalence. Also, the study setting showed significant differences (p = 0.001, and I2 = 90.3%) on the overall prevalence, where significant reduction of P. vivax prevalence (4.67%, 95%CI: 1.41-7.93%, p<0.0001) was observed in studies conducted at the community level. The studies included in the review demonstrated lack of publication bias qualitatively (symmetrical funnel plot) and quantitatively [Egger’s test (coefficient) = -2.97, 95% CI: -15.06-9.13, p = 0.62].

CONCLUSION: The estimated prevalence of P. vivax malaria in Ethiopia was 8.93% with P. vivax prevailing in the central west region of Ethiopia, but steadily extending to the western part of the country. Its distribution across the nation varies according to geographical location, study setting and study years.

PMID:34525091 | DOI:10.1371/journal.pntd.0009781

Categories
Nevin Manimala Statistics

Plasma glycated CD59 predicts postpartum glucose intolerance after gestational diabetes

Eur J Endocrinol. 2021 Sep 1:EJE-21-0635.R1. doi: 10.1530/EJE-21-0635. Online ahead of print.

ABSTRACT

AIMS: To assess whether in women with gestational diabetes mellitus (GDM), postpartum plasma glycated CD59 (pGCD59) levels predict conversion to glucose intolerance diagnosed with an oral glucose tolerance test (OGTT).

METHODS: Blood levels of pGCD59 were measured in a case-control study of 105 women with GDM who underwent a 75g OGTT three months postpartum. The 35 postpartum glucose intolerant cases were individually matched for age, BMI, ethnic origin and parity with 70 women with GDM but normal postpartum OGTT (controls). The GDM cohort (105) was also matched with 105 normal glucose tolerant women during pregnancy. pGCD59 was measured by ELISA in standard peptide units (SPU).

RESULTS: Mean pGCD59 postpartum was significantly higher in cases than in controls (1.5 ± 0.6 SPU vs. 1.0 ±0.6 SPU, p<0.001). The area under the receiving operating characteristic curve (AUC) in cases versus controls was 0.72 (95% CI 0.62-0.83) for postpartum pGCD59 and 0.50 (95% CI 0.36-0.61) for postpartum HbA1c. A 0.5-unit increase in postpartum pGCD59 was associated with an OR of 3.3 (95% CI 1.82-6.16, p<0.001) for glucose intolerance postpartum. A pGCD59 cut-off postpartum of 0.9 SPU had a sensitivity of 85.7% (95% CI 69.7-95.2%), specificity of 47.8% (95% CI 35.6-60.2%), positive predictive value of 45.4% (95% CI 33.1-58.2%) and negative predictive value of 86.8% (95% CI 71.9-95.6%). pGCD59 in pregnancy was a poor predictor for glucose intolerance postpartum [AUC of 0.61 (95% CI 0.50-0.72)].

CONCLUSIONS: pGCD59 might identify women at low risk for glucose intolerance postpartum and could help to avoid an OGTT.

PMID:34524975 | DOI:10.1530/EJE-21-0635

Categories
Nevin Manimala Statistics

Reliability and Validity of the Spanish Version of the Medical Outcomes Study Pain Severity Scale in Mexican Patients With Rheumatic Diseases

J Clin Rheumatol. 2021 Sep 1;27(6S):S308-S315. doi: 10.1097/RHU.0000000000001651.

ABSTRACT

OBJECTIVE: To evaluate the reliability and validity of the Spanish version of the Medical Outcomes Study Pain Severity Scale (MOS-PSS) in patients with rheumatic diseases.

METHODS: A cross-sectional study was carried out from January 2019 to March 2020 using a nonprobabilistic sampling of consecutive cases. The internal consistency of the scale was evaluated through the Cronbach α coefficient and by the item response theory reliability coefficient. Construct validity was evaluated by factor analysis; relationships between MOS-PSS and visual numeric scale for pain, numeric rating scale for pain, and verbal rating scale for pain; and differences between relevant groups. Item response theory-based methods were used to assess item performance.

RESULTS: A clinical sample of 796 outpatients was recruited. Most patients presented moderate to severe pain. Two subscale solutions showed a good model fit in confirmatory factor analysis. The overall model fit of multidimensional generalized partial credit model showed to be adequate. The most discriminating item was “average pain intensity.” Evidence revealed disordered thresholds in 2 items. Collapsing categories resulted in ordered thresholds for all items and significantly improving the overall model fit. The MOS-PSS and modified MOS-PSS yielded high reliability. Both scales were very strongly correlated with numeric rating scale for pain, visual numeric scale for pain, and verbal rating scale for pain (ρ ≥ 0.85). All hypotheses related to subgroups comparison were fulfilled.

CONCLUSIONS: Overall, the Spanish version of the MOS-PSS showed good reliability and construct validity. Nevertheless, the statistical evidence from this study would suggest the modified MOS-PSS should be the version of choice for measuring pain in Mexican patients with rheumatic diseases.

PMID:34525003 | DOI:10.1097/RHU.0000000000001651

Categories
Nevin Manimala Statistics

Comparative Incidence of Periocular Surgical Site Infections with Increased Surgical Mask Use during the COVID-19 Pandemic

Ocul Immunol Inflamm. 2021 Sep 15:1-6. doi: 10.1080/09273948.2021.1974491. Online ahead of print.

ABSTRACT

PURPOSE: To evaluate the effect of surgical mask use on infection rates for office-based periocular surgeries during the pandemic.

METHODS: An Institutional Review Board-approved retrospective review of medical records identified patients who had an office-based oculofacial plastic surgery procedure during the pandemic between March and December 2020. Statistical analysis was used to compare this group to patients that underwent procedures between March and December 2019, prior to the pandemic when neither surgeon nor patient wore a surgical mask.

RESULTS: The study consisted of 680 patients. Thirty-one different types of procedures were encountered. The incidence of infections in 2020 compared to 2019 was not statistically significant (1.12% (n = 3) versus 1.21% (n = 5), p = 1). All patients with infections were treated with oral antibiotics and improved without long-term complications.

CONCLUSIONS: Periocular surgical site infections are uncommon, and the wearing of surgical masks by patient and surgeon during our office-based oculofacial procedures did not change the incidence of SSIs.

PMID:34524950 | DOI:10.1080/09273948.2021.1974491

Categories
Nevin Manimala Statistics

All-cause acute care hospitalization rates of immigrants and the Canadian-born population: A linkage study

Health Rep. 2021 Sep 15;32(9):3-13. doi: 10.25318/82-003-x202100900001-eng.

ABSTRACT

BACKGROUND: As Canadian immigration levels increase, knowledge concerning immigrant health becomes increasingly important for health system policy and planning. This study compares the rate of all-cause hospitalization among immigrants with that of their Canadian-born counterparts.

DATA AND METHODS: Using records from the Discharge Abstract Database (2004/2005 to 2016/2017) and the Ontario Mental Health Reporting System (2006/2007 to 2017/2018) linked to the 2016 Longitudinal Immigration Database, this study compared the age-standardized hospitalization rates (ASHRs) among immigrants with those of the Canadian-born population; the latter were obtained from a linkage based on the 2011 National Household Survey. Comparisons were made at the International Classification of Diseases chapter level by immigrant landing year, admission category and world region of birth. Quebec data were not available.

RESULTS: Overall, ASHRs among immigrants were lower than for the Canadian-born population. Immigrants in the economic class had the lowest ASHR, followed by those in the family class and among refugees. After pregnancy was excluded, leading hospitalization causes were similar for immigrants and the Canadian-born population, where top causes included digestive system and circulatory diseases, injuries, and cancer. In male and female immigrants, the ASHRs were lowest among those from East Asia. By landing year, males arriving earlier had the highest ASHR compared with the most recent arrivals. When pregnancy was excluded and while the differential in ASHRs among females by landing year remained, the magnitude was smaller.

INTERPRETATION: These results corroborate those from previous studies suggesting a healthy immigrant effect, but also reveal heterogeneity in ASHRs within the immigrant population. They provide a baseline for comparison of health status between populations, which enables further monitoring and informs health-system policy and planning.

PMID:34523869 | DOI:10.25318/82-003-x202100900001-eng