Bayesian semiparametric growth models for measurement error and missing data in CD4/CD8 ratio: Application to AIDS Study

2019 ◽  
Vol 29 (1) ◽  
pp. 178-188
Author(s):  
Getachew A Dagne
Keyword(s):  
Measurement Errors ◽  
Missing Values ◽  
Growth Models ◽  
Severe Disease ◽  
Real Data ◽  
Mixed Effect ◽  
Mixed Effect Models ◽  
Disease Condition ◽  
Fully Bayesian ◽  
Aids Study

In clinical research and practice, there is often an interest in assessing the effect of time varying predictors, such as CD4/CD8 ratio, on immune recovery following antiretroviral therapy. Such predictors are measured with errors, and ignoring those measurement errors during data analysis may lead to biased results. Though parametric methods have been used for reducing biases, they usually depend on untestable assumptions. To relax those assumptions, this paper presents semiparametric mixed-effect models which deal with predictors having measurement errors and missing values. We develop a fully Bayesian approach for fitting these models and discriminating between patients who are potentially progressors or nonprogressors to severe disease condition (AIDS). The proposed methods are demonstrated using real data from an AIDS clinical study.

scholarly journals FRI0412 DOES SEVERE ACUTE POSTOPERATIVE PAIN RESULT IN MORE LONG-TERM PAIN AFTER TOTAL HIP OR KNEE ARTHROPLASTY (THA OR TKA) FOR OSTEOARTHRITIS?

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 805.2-805
Author(s):  
D. A. J. M. Latijnhouwers ◽  
C. H. Martini ◽  
R. G. H. H. Nelissen ◽  
H. M. J. Van der Linden ◽  
T. P. M. Vliet Vlieland ◽  
...  
Keyword(s):  
Postoperative Pain ◽  
Acute Pain ◽  
Missing Values ◽  
Rating Scale ◽  
Acute Postoperative Pain ◽  
Preoperative Pain ◽  
Mixed Effect ◽  
Total Hip ◽  
Chronic Postsurgical Pain

Background:Chronic pain is a frequently reported unfavourable outcome of total hip and knee arthroplasties (THA/TKA) (7-23% and 10-34%, respectively) in osteoarthritis (OA) patients (1), which is difficult to treat as underlying mechanisms are not fully understood. Acute postoperative pain has been identified as risk factor for development of long-term pain in other surgical procedures, such as mastectomy and thoracotomy (2). However, the effect of acute postoperative pain on development of long-term pain in THA and TKA patients is unknown.Objectives:To investigate if acute pain following THA/TKA in OA patients is associated with long-term pain and if acute pain affects the course of pain up to 1-year postoperatively.Methods:From a longitudinal multicenter study, OA patients scheduled for primary THA or TKA were included. Acute pain scores, using Numeric Rating Scale (NRS), were routinely collected as part of standard care (≤72 hours after surgery). In case of ≥2 NRS scores the two highest scores were averaged (n=160), else the single score was taken. Pain was dichotomized into severe (NRS≥5) and mild (NRS<5). Pain was assessed preoperatively, at 3 (only THA), 6 and 12 months postoperatively using HOOS/KOOS subscale pain. Separate mixed-effect models for THA and TKA patients were used, with dichotomized acute pain as fixed-effect and long-term pain as outcome, while adjusting for confounders (age, sex, BMI, preoperative pain, mental component scale of the SF12 (MCS-12), and duration of the surgery and hospitalization). We included an interaction between time of measurement and acute postoperative pain to analyse whether effect modification was present. Missing values in preoperative pain and MCS-12 were imputed using multiple imputation methods.Results:81 THA and 87 TKA patients were included, of whom 32.1% and 56.3% reported severe acute pain. The results did not show an associated between severe acute pain and long term pain (THA: β=2.0, 95%-CI:-10.9-7.0; TKA: β=3.8, 95%-CI:-10.6-2.9). Furthermore, It seems that there is no effect present of difference in severity of acute pain and the course of pain over time (THA 6-months: β=6.4, 95%-CI:1.9-10.9 and 12-months: β=0.2, 95%-CI:-4.4-4.8; TKA 12-months: β=3.2, 95%-CI:-0.5-6.8).Conclusion:We did not find an association between acute pain and the development of long-term pain nor that severity of acute pain affects the course of postoperative pain in THA and TKA patients. The fact that THA and TKA patients often experience chronic preoperative pain might be a possible explanation for this finding. Nonetheless, future studies including additional measures of acute pain and pain sensitization in patients with chronic preoperative pain are necessary to draw stronger conclusions.References:[1]Beswick AD, Wylde V, Gooberman-Hill R, Blom A, Dieppe P. What proportion of patients report long-term pain after total hip or knee replacement for osteoarthritis? A systematic review of prospective studies in unselected patients. BMJ open. 2012;2(1):e000435.[2]Katz J, Seltzer Ze. Transition from acute to chronic postsurgical pain: risk factors and protective factors. Expert review of neurotherapeutics. 2009;9(5):723-44.Acknowledgments:We would like to thank the study group that consists of: B.L. Kaptein, Leiden University Medical Center, Leiden; S.B.W Vehmeijer, Reinier de Graaf Hospital, Delft; R. Onstenk, Groene Hart Hospital, Gouda; S.H.M. Verdegaal, Alrijne Hospital, Leiderdorp; H.H. Kaptijn, LangeLand Hospital, Zoetermeer; W.C.M. Marijnissen, Albert Schweitzer Hospital, Dordrecht; P.J. Damen, Waterland Hospital, Hoorn; the NetherlandsDisclosure of Interests:None declared

scholarly journals Modeling Software Fault-Detection and Fault-Correction Processes by Considering the Dependencies between Fault Amounts

2021 ◽  
Vol 11 (15) ◽  
pp. 6998
Author(s):  
Qiuying Li ◽  
Hoang Pham
Keyword(s):  
Time Delay ◽  
Fault Detection ◽  
Software Reliability ◽  
Growth Models ◽  
Predictive Performance ◽  
Real Data ◽  
Reliability Estimation ◽  
Model Parameters ◽  
Dual Processes ◽  
Correction Process

Many NHPP software reliability growth models (SRGMs) have been proposed to assess software reliability during the past 40 years, but most of them have focused on modeling the fault detection process (FDP) in two ways: one is to ignore the fault correction process (FCP), i.e., faults are assumed to be instantaneously removed after the failure caused by the faults is detected. However, in real software development, it is not always reliable as fault removal usually needs time, i.e., the faults causing failures cannot always be removed at once and the detected failures will become more and more difficult to correct as testing progresses. Another way to model the fault correction process is to consider the time delay between the fault detection and fault correction. The time delay has been assumed to be constant and function dependent on time or random variables following some kind of distribution. In this paper, some useful approaches to the modeling of dual fault detection and correction processes are discussed. The dependencies between fault amounts of dual processes are considered instead of fault correction time-delay. A model aiming to integrate fault-detection processes and fault-correction processes, along with the incorporation of a fault introduction rate and testing coverage rate into the software reliability evaluation is proposed. The model parameters are estimated using the Least Squares Estimation (LSE) method. The descriptive and predictive performance of this proposed model and other existing NHPP SRGMs are investigated by using three real data-sets based on four criteria, respectively. The results show that the new model can be significantly effective in yielding better reliability estimation and prediction.

scholarly journals OP0010 EFFECTIVENESS OF THE MAKING IT WORK™ PROGRAM AT IMPROVING PRESENTEEISM AND WORK CESSATION IN WORKERS WITH INFLAMMATORY ARTHRITIS – RESULTS OF A RANDOMIZED CONTROLLED TRIAL

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 7.1-8
Author(s):  
A. Luquini ◽  
Y. Zheng ◽  
H. Xie ◽  
C. Backman ◽  
P. Rogers ◽  
...  
Keyword(s):  
Randomized Controlled Trial ◽  
Work Disability ◽  
Inflammatory Arthritis ◽  
Missing Values ◽  
Controlled Trial ◽  
Intervention Group ◽  
Secondary Outcome ◽  
Mixed Effect ◽  
Randomized Controlled ◽  
Baseline Characteristics

Background:Arthritis often leads to presenteeism (decreased at-work productivity), missed days from work and permanent work disability, leading to reduced quality of life and high costs to individuals and society. Yet, health services addressing the employment needs of people with arthritis are lacking.Objectives:We evaluated the effectiveness of the Making-it-WorkTM(MiW) program, an online self-management program developed to help people with inflammatory arthritis (IA) deal with employment issues.Methods:A multi-center RCT evaluated the effectiveness of MiW at improving presenteeism and preventing work cessation (WC) over two years. Participants were recruited from rheumatologist practices, consumer organizations and arthritis programs, in three Canadian provinces. Eligibility criteria: diagnosis of IA, employed, age 18-59, and concerned about ability to work. Participants were randomized 1:1 to MiW or usual care plus printed material on workplace tips. MiW consists of five online self-learning modules and group meetings, and individual vocational counselling and ergonomic consultations. Questionnaires were administered every 6 months. Outcomes were presenteeism [Rheumatoid Arthritis Work Instability Scale (RA-WIS)], time to WC ≥ 6 months, and time to WC ≥ 2 months (secondary outcome). Baseline characteristics (age, gender, ethnicity, occupation, education, disease duration and self-employment) were collected. Intention-to-treat (ITT) longitudinal analysis of RA-WIS using linear mixed effect regression models with 2-year comparison as primary endpoint and survival analysis for time to WC using Kaplan-Meier and Cox Proportional Hazard models were performed. Robustness analyses were conducted by using various missing values imputation methods like last observation carried forward, imputation using worse possible outcomes and model-based multiple imputations; using square root transformation of RA-WIS outcome; and adjusting for baseline covariates. SAS version 9.4 was used.Results:A total of 564 participants were recruited, with 478 (84.75%) completing 2-year follow-up. Baseline characteristics were similar between groups. Mean RA-WIS scores were significantly lower in the intervention group from 6 months onwards, with the greatest difference observed at 2 years (-1.78, 95%CI: -2.7, -0.9, p < .0001), yielding a standardized effect size of 32%. Satisfactory robustness was observed. Work cessation occurred less often in intervention than control groups, but only reached statistical significance for WC ≥ 2 months (WC ≥ 6 months: 31 versus 44 events, aHR 0.70, 95%CI: 0.44, 1.11, p = 0.13; WC ≥ 2 months: 39 versus 61 events, aHR: 0.65, 95%CI: 0.43, 0.98, p = 0.04).Conclusion:Results of the RCT reveal the program was effective at improving presenteeism and preventing short-term WC. Effectiveness at preventing long-term work disability will be assessed at 5 years. This program fills one of the most important and costly unmet needs for people with inflammatory arthritis.References:[1]Carruthers EC, Rogers P, Backman CL, et al. “Employment and arthritis: making it work” a randomized controlled trial evaluating an online program to help people with inflammatory arthritis maintain employment (study protocol).BMC Med Inform Decis Mak. 2014;14:59. Published 2014 Jul 21. doi:10.1186/1472-6947-14-59Disclosure of Interests:Andre Luquini: None declared, Yufei Zheng: None declared, Hui Xie: None declared, Catherine Backman: None declared, Pamela Rogers: None declared, Alex Kwok: None declared, Astrid Knight: None declared, Monique Gignac: None declared, Dianne Mosher: None declared, Linda Li: None declared, John Esdaile: None declared, Carter Thorne Consultant of: Abbvie, Centocor, Janssen, Lilly, Medexus/Medac, Pfizer, Speakers bureau: Medexus/Medac, Diane Lacaille: None declared

scholarly journals A hierarchical bivariate meta-analysis of diagnostic test accuracy to provide direct comparisons of immunoassays vs. indirect immunofluorescence for initial screening of connective tissue diseases

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Michelle Elaine Orme ◽  
Carmen Andalucia ◽  
Sigrid Sjölander ◽  
Xavier Bossuyt
Keyword(s):  
Connective Tissue ◽  
Indirect Immunofluorescence ◽  
Meta Analysis ◽  
Connective Tissue Diseases ◽  
Test Accuracy ◽  
Initial Screening ◽  
Case Control Studies ◽  
Cross Sectional ◽  
Mixed Effect ◽  
Mixed Effect Models

AbstractObjectivesTo compare indirect immunofluorescence (IIF) for antinuclear antibodies (ANA) against immunoassays (IAs) as an initial screening test for connective tissue diseases (CTDs).MethodsA systematic literature review identified cross-sectional or case-control studies reporting test accuracy data for IIF and enzyme-linked immunosorbent assays (ELISA), fluorescence enzyme immunoassay (FEIA), chemiluminescent immunoassay (CLIA) or multiplex immunoassay (MIA). The meta-analysis used hierarchical, bivariate, mixed-effect models with random-effects by test.ResultsDirect comparisons of IIF with ELISA showed that both tests had good sensitivity (five studies, 2321 patients: ELISA: 90.3% [95% confidence interval (CI): 80.5%, 95.5%] vs. IIF at a cut-off of 1:80: 86.8% [95% CI: 81.8%, 90.6%]; p = 0.4) but low specificity, with considerable variance across assays (ELISA: 56.9% [95% CI: 40.9%, 71.5%] vs. IIF 1:80: 68.0% [95% CI: 39.5%, 87.4%]; p = 0.5). FEIA sensitivity was lower than IIF sensitivity (1:80: p = 0.005; 1:160: p = 0.051); however, FEIA specificity was higher (seven studies, n = 12,311, FEIA 93.6% [95% CI: 89.9%, 96.0%] vs. IIF 1:80 72.4% [95% CI: 62.2%, 80.7%]; p < 0.001; seven studies, n = 3251, FEIA 93.5% [95% CI: 91.1%, 95.3%] vs. IIF 1:160 81.1% [95% CI: 73.4%, 86.9%]; p < 0.0001). CLIA sensitivity was similar to IIF (1:80) with higher specificity (four studies, n = 1981: sensitivity 85.9% [95% CI: 64.7%, 95.3%]; p = 0.86; specificity 86.1% [95% CI: 78.3%, 91.4%]). More data are needed to make firm inferences for CLIA vs. IIF given the wide prediction region. There were too few studies for the meta-analysis of MIA vs. IIF (MIA sensitivity range 73.7%–86%; specificity 53%–91%).ConclusionsFEIA and CLIA have good specificity compared to IIF. A positive FEIA or CLIA test is useful to support the diagnosis of a CTD. A negative IIF test is useful to exclude a CTD.

scholarly journals Neurophysiological and behavioural effects of conventional and high definition tDCS

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Fabio Masina ◽  
Giorgio Arcara ◽  
Eleonora Galletti ◽  
Isabella Cinque ◽  
Luciano Gamberini ◽  
...  
Keyword(s):  
Response Times ◽  
Power Reduction ◽  
Alpha Power ◽  
High Definition ◽  
Mixed Effect ◽  
State Dependency ◽  
Mixed Effect Models ◽  
Beta Power ◽  
Neurophysiological Data ◽  
Spectrum Density

AbstractHigh-definition transcranial direct current stimulation (HD-tDCS) seems to overcome a drawback of traditional bipolar tDCS: the wide-spread diffusion of the electric field. Nevertheless, most of the differences that characterise the two techniques are based on mathematical simulations and not on real, behavioural and neurophysiological, data. The study aims to compare a widespread tDCS montage (i.e., a Conventional bipolar montage with extracephalic return electrode) and HD-tDCS, investigating differences both at a behavioural level, in terms of dexterity performance, and a neurophysiological level, as modifications of alpha and beta power as measured with EEG. Thirty participants took part in three sessions, one for each montage: Conventional tDCS, HD-tDCS, and sham. In all the conditions, the anode was placed over C4, while the cathode/s placed according to the montage. At baseline, during, and after each stimulation condition, dexterity was assessed with a Finger Tapping Task. In addition, resting-state EEG was recorded at baseline and after the stimulation. Power spectrum density was calculated, selecting two frequency bands: alpha (8–12 Hz) and beta (18–22 Hz). Linear mixed effect models (LMMs) were used to analyse the modulation induced by tDCS. To evaluate differences among the montages and consider state-dependency phenomenon, the post-stimulation measurements were covariate-adjusted for baseline levels. We observed that HD-tDCS induced an alpha power reduction in participants with lower alpha at baseline. Conversely, Conventional tDCS induced a beta power reduction in participants with higher beta at baseline. Furthermore, data showed a trend towards a behavioural effect of HD-tDCS in participants with lower beta at baseline showing faster response times. Conventional and HD-tDCS distinctively modulated cortical activity. The study highlights the importance of considering state-dependency to determine the effects of tDCS on individuals.

scholarly journals Recombining Your Way Out of Trouble: The Genetic Architecture of Hybrid Fitness under Environmental Stress

2019 ◽  
Vol 37 (1) ◽  
pp. 167-182 ◽  
Author(s):  
Zebin Zhang ◽  
Devin P Bendixsen ◽  
Thijs Janzen ◽  
Arne W Nolte ◽  
Duncan Greig ◽  
...  
Keyword(s):  
Environmental Stress ◽  
Evolutionary Potential ◽  
Genetic Trait ◽  
Hybrid Fitness ◽  
Mixed Effect ◽  
Mixed Effect Models ◽  
Hybrid Genome ◽  
Chromosome Associations ◽  
Low Coverage ◽  
Negative Epistasis

Abstract Hybridization between species can either promote or impede adaptation. But we know very little about the genetic basis of hybrid fitness, especially in nondomesticated organisms, and when populations are facing environmental stress. We made genetically variable F2 hybrid populations from two divergent Saccharomyces yeast species. We exposed populations to ten toxins and sequenced the most resilient hybrids on low coverage using ddRADseq to investigate four aspects of their genomes: 1) hybridity, 2) interspecific heterozygosity, 3) epistasis (positive or negative associations between nonhomologous chromosomes), and 4) ploidy. We used linear mixed-effect models and simulations to measure to which extent hybrid genome composition was contingent on the environment. Genomes grown in different environments varied in every aspect of hybridness measured, revealing strong genotype–environment interactions. We also found selection against heterozygosity or directional selection for one of the parental alleles, with larger fitness of genomes carrying more homozygous allelic combinations in an otherwise hybrid genomic background. In addition, individual chromosomes and chromosomal interactions showed significant species biases and pervasive aneuploidies. Against our expectations, we observed multiple beneficial, opposite-species chromosome associations, confirmed by epistasis- and selection-free computer simulations, which is surprising given the large divergence of parental genomes (∼15%). Together, these results suggest that successful, stress-resilient hybrid genomes can be assembled from the best features of both parents without paying high costs of negative epistasis. This illustrates the importance of measuring genetic trait architecture in an environmental context when determining the evolutionary potential of genetically diverse hybrid populations.

Missing values and lack of information in water management datasets: an approach based on Bayesian Networks

2021 ◽  
Author(s):  
Rosa F Ropero ◽  
M Julia Flores ◽  
Rafael Rumí
Keyword(s):  
Extreme Events ◽  
Coastal Area ◽  
Flood Risk ◽  
Missing Values ◽  
Real Data ◽  
Continuous Variables ◽  
Target Variable ◽  
River Level ◽  
Lack Of Information ◽  
Level Variable

&lt;p&gt;Environmental data often present missing values or lack of information that make modelling tasks difficult. Under the framework of SAICMA Research Project, a flood risk management system is modelled for Andalusian Mediterranean catchment using information from the Andalusian Hydrological System. Hourly data were collected from October 2011 to September 2020, and present two issues:&lt;/p&gt;&lt;ul&gt;&lt;li&gt;In Guadarranque River, for the dam level variable there is no data from May to August 2020, probably because of sensor damage.&lt;/li&gt; &lt;li&gt;No information about river level is collected in the lower part of Guadiaro River, which make difficult to estimate flood risk in the coastal area.&lt;/li&gt; &lt;/ul&gt;&lt;p&gt;In order to avoid removing dam variable from the entire model (or those missing months), or even reject modelling one river system, this abstract aims to provide modelling solutions based on Bayesian networks (BNs) that overcome this limitation.&lt;/p&gt;&lt;p&gt;&lt;em&gt;Guarranque River. Missing values.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;Dataset contains 75687 observations for 6 continuous variables. BNs regression models based on fixed structures (Na&amp;#239;ve Bayes, NB, and Tree Augmented Na&amp;#239;ve, TAN) were learnt using the complete dataset (until September 2019) with the aim of predicting the dam level variable as accurately as possible. A scenario was carried out with data from October 2019 to March 2020 and compared the prediction made for the target variable with the real data. Results show both NB (rmse: 6.29) and TAN (rmse: 5.74) are able to predict the behaviour of the target variable.&lt;/p&gt;&lt;p&gt;Besides, a BN based on expert&amp;#8217;s structural learning was learnt with real data and both datasets with imputed values by NB and TAN. Results show models learnt with imputed data (NB: 3.33; TAN: 3.07) improve the error rate of model with respect to real data (4.26).&lt;/p&gt;&lt;p&gt;&lt;em&gt;Guadairo River. Lack of information.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;Dataset contains 73636 observations with 14 continuous variables. Since rainfall variables present a high percentage of zero values (over 94%), they were discretised by Equal Frequency method with 4 intervals. The aim is to predict flooding risk in the coastal area but no data is collected from this area. Thus, an unsupervised classification based on hybrid BNs was performed. Here, target variable classifies all observations into a set of homogeneous groups and gives, for each observation, the probability of belonging to each group. Results show a total of 3 groups:&lt;/p&gt;&lt;ul&gt;&lt;li&gt;Group 0, &amp;#8220;Normal situation&amp;#8221;: with rainfall values equal to 0, and mean of river level very low.&lt;/li&gt; &lt;li&gt;Group 1, &amp;#8220;Storm situation&amp;#8221;: mean rainfall values are over 0.3 mm and all river level variables duplicate the mean with respect to group 0.&lt;/li&gt; &lt;li&gt;Group 2, &amp;#8220;Extreme situation&amp;#8221;: Both rainfall and river level means values present the highest values far away from both previous groups.&lt;/li&gt; &lt;/ul&gt;&lt;p&gt;Even when validation shows this methodology is able to identify extreme events, further work is needed. In this sense, data from autumn-winter season (from October 2020 to March 2021) will be used. Including this new information it would be possible to check if last extreme events (flooding event during December and Filomenastorm during January) are identified.&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;

Association of fine particulate matter with glucose and lipid metabolism: a longitudinal study in young adults

2021 ◽  
pp. oemed-2020-107039
Author(s):  
Jingyi Qin ◽  
Wei Xia ◽  
Gaodao Liang ◽  
Shunqing Xu ◽  
Xiuge Zhao ◽  
...  
Keyword(s):  
Body Mass Index ◽  
Lipid Metabolism ◽  
Longitudinal Study ◽  
Fine Particulate Matter ◽  
Healthy Adults ◽  
Mixed Effect ◽  
Glucose And Lipid Metabolism ◽  
Mixed Effect Models ◽  
Fine Particulate ◽  
Linear Mixed Effect Models

ObjectivesThis study aimed to evaluate whether PM2.5 exposure in a highly polluted area (>100 µg/m3) affects glucose and lipid metabolism in healthy adults.MethodsWe recruited 110 healthy adults in Baoding city, Hebei, China, and followed them up between 2017 and 2018. Personal air samplers were used to monitor personal PM2.5 levels. Eight glucose and lipid metabolism parameters were quantified. We performed the linear mixed-effect models to investigate the relationships between PM2.5 and glucose and lipid metabolism parameters. Stratified analyses were further performed according to sex and body mass index (BMI).ResultsThe concentration of PM2.5 was the highest in spring, with a median of 232 μg/m3 and the lowest in autumn (139 μg/m3). After adjusting for potential confounders, we found that for each twofold increase in PM2.5, the median of insulin concentration decreased by 5.89% (95% CI −10.91% to −0.58%; p<0.05), and ox-LDL increased by 6.43% (95% CI 2.21% to 10.82%; p<0.05). Stratified analyses indicated that the associations were more pronounced in females, overweight and obese participants.ConclusionsExposure to high PM2.5 may have deleterious effects on glucose and lipid metabolism. Females, overweight and obese participants are more vulnerable.

Sign in / Sign up

Export Citation Format

Share Document