O presente trabalho teve como objetivo estimar a confiabilidade e validade do Índice de Prioridade de Tratamento (IPT) na avaliação das alterações oclusais, através da análise de 200 modelos selecionados do Arquivo de Ortodontia da Faculdade de Odontologia de Bauru, apresentando os diferentes tipos de má oclusão. Estes modelos foram avaliados em dois momentos, o primeiro, por uma comissão formada por 16 experientes ortodontistas que os avaliou subjetivamente quanto à severidade da má oclusão, dificuldade e duração do tratamento necessário. Em um segundo momento, os modelos foram avaliados através do IPT por dois ortodontistas previamente calibrados para a utilização do índice. A confiabilidade intraexaminador foi testada a partir da reavaliação de 50 pares de modelos e foi calculada pelo coeficiente de correlação intraclasse (CCI), além do teste t dependente. A confiabilidade interexaminador foi estimada sobre os 200 pares de modelos de estudo, sendo calculada pelo CCI e pelo teste t independente. Por fim, a validade do índice foi avaliada pelo comparando-se as médias dos valores obtidos pelo IPT e as percepções subjetivas através do coeficiente de correlação de Pearson. Por motivos comparativos, os modelos também foram analisados através do índice PAR (Peer Assessment Rating), que é um instrumento válido e amplamente aceito na avaliação dos resultados oclusais. Os resultados mostraram que o IPT, assim como o PAR, é um índice altamente reprodutível, uma vez que revelou altos níveis de concordância inter (ICC=0,97) e intraexaminador (ICC1=0,97 e ICC2= 0,96), e válido para investigar a severidade da má oclusão (R=0,25), dificuldade do tratamento (R=0,24) e duração do tratamento (R=0,29). No entanto, apesar de significantes, as correlações encontradas pelo IPT durante a validação foram muito fracas, principalmente em comparação com o índice PAR. Conclui-se, portanto, que o IPT apesar de reprodutível, possui pouca validade como um instrumento de avaliação das alterações oclusais. / The present study sought to estimate the reliability and validity of the Treatment Priority Index (TPI) for assessment of occlusal changes through analysis of 200 dental casts from the files of the Department of Orthodontics at Bauru Dental School, selected as a representative sample of the various types of malocclusion. These casts were evaluated twice: first, by a panel of 16 experienced orthodontists, who carried out subjective assessments of the severity of malocclusion and predicted the difficulty and duration of the required treatment. In another moment, the casts were assessed with the TPI by two orthodontists calibrated beforehand. The intrarater reliability was tested by means of reassessment of 50 pairs of models, with an intraclass correlation coefficient (ICC) and the dependent t-test. The inter-rater reliability was estimated considering all 200 casts, through the ICC and the independent t-test. Finally, the validity of the index was assessed by comparison between average TPI scores and subjective perceptions through Pearsons correlation coefficient. For comparative purposes, dental casts were also analyzed using the PAR (Peer Assessment Rating) index, a valid and widely accepted instrument for assessment of occlusal outcomes. Results showed that the TPI is a highly reproducible index, as is the PAR, with high levels of inter-rater (ICC=0.97) and intra-rater reliability (ICC1=0.97, ICC2=0.96), and is a valid instrument for assessment of malocclusion severity (R=0.25), treatment difficulty (R=0.24) and treatment duration (R=0.29). However, despite their statistical significance, the TPI correlations were very weak, particularly on comparison with the PAR. Despite its reproducibility, the TPI has very limited validity for assessment of occlusal changes provided by the orthodontic treatment.

Examination of functional brain anatomy is a crucial step in the process of surgical removal of many brain tumors. Functional magnetic resonance imaging (fMRI) is a promising technology capable of mapping brain function non-invasively. To be successfully applied to presurgical mapping, there are questions of diagnostic accuracy that remain to be addressed. One of the greatest difficulties in implementing fMRI is the need to define an activation threshold for producing functional maps. There is as of yet no consensus on the best approach to this problem, and a priori statistical approaches are generally considered insufficient because they are not specific to individual patient data. Additionally, low signal to noise and sensitivity to magnetic susceptibility effects combine to make the production of activation maps technically demanding. This contributes to a wide range of estimates of reproducibility and validity for fMRI, as the results are sensitive to changes in acquisition and processing strategies. Test-retest fMRI imaging at the individual level, and receiver operator characteristic (ROC) analysis of the results can address both of these concerns simultaneously. In this work, it is shown that the area under the ROC curve (AUC) can be used as an indicator of reproducibility, and that this is dependent on the image thresholds used. Production of AUC profiles can thus be used to optimize the selection of individual thresholds on the basis of detecting stable activation patterns, rather than a priori significance levels. The ROC analysis framework developed provides a powerful tool for simultaneous control of protocol reproducibility and data driven threshold selection, at the individual level. This tool can be used to guide optimal acquisition and processing strategies, and as part of a quality assurance program for implementing presurgical fMRI.

Diss. (sammanfattning) Stockholm : Karol. inst., 2006. / Härtill 4 uppsatser.

Thesis (Ph. D.)--University of Missouri--Columbia, 1997. / "May 1997" Typescript. Vita. Includes bibliographical references (l. 66-71). Also available on the Internet.

Thesis (Ph. D.)--University of Washington, 1999. / Vita. Includes bibliographical references (leaves 129-135).

Part I. Claims to knowledge require justification. In science, such justification is made possible by the ability to reproduce or replicate experiments, thereby confirming their validity. Additionally, reproducibility serves as a self-correcting tool in science as it weeds out faulty experiments. It is therefore essential that experimental studies be replicated and confirmed. Recently, attempts to reproduce studies in several fields have failed, leading to what has been referred to as "a crisis of reproducibility." This crisis is largely a result of the current culture in the scientific world. Specifically, it is a result of a system that incentivizes individual success in the form of publications in high-impact journals over collaboration and careful conductance of research. This environment contributes to the crisis of reproducibility by increasing biases, incentivizing researchers to engage in manipulative statistics, decreasing quality control and transparency, and increasing the likelihood of researchers engaging in fraudulent behavior. Possible solutions to the problem of irreproducibility could tackle individual factors. A more prudent approach would be to focus on changing the current culture in the scientific world. Increased transparency had been suggested as a way to solve this problem. There is currently a movement advocating for increased transparency in science through "open science." Part II. Retraction of scientific papers due to evidence of research misconduct is on the rise, having increased tenfold from 2000 to 2009. Previous work on this topic focused on published retraction notices, using notices to identify the percent of retracted articles that were caused by research misconduct. This study utilized a different approach. Using the Office of Research Integrity database, we first identified publications that resulted from research misconduct. We then searched those articles to determine whether they were indeed retracted. Once retraction notices were identified, they were scored based on scoring elements reflecting guidelines for transparency. Lastly, we investigated whether a correlation exists between the quality of a retraction notice and journal impact factor. Our findings suggest that 21% of papers containing data derived from scientific misconduct are not retracted. Moreover, the quality of retraction notices varies, with some elements more likely to be present than others. No significant correlation between retraction notices and journal impact factor was found.

Reusability and reliability of published data are fundamental requirements for translating results from animal experiments into reliable clinical biomarkers. Current success rates for biomarker discovery are poor, and we need to develop new tools to collate, integrate and analyse datasets, such as knowledge bases, that would enable more effective translation from mouse to human or across disciplines. However, concerns about the validity, reproducibility and replicability of existing data must be addressed first. Here, I interrogate the quality of methods reporting in experimental models of infection and inflammation. Despite evidence that most of the assessed parameters, such as sex and age, can influence the experimental results, the quality of methods reporting was poor. Inadequate methods reporting means that it is not always possible to confirm whether findings were due to improper experimental conditions that biased the results. Thus, such inaccuracies would have an impact on the construction of knowledge base tools that require appropriate annotation. However, I provide reusable checklists that could improve the quality of methods reporting prior to publication and can be used to verify papers post-publication to enable researchers from different fields to interrogate published data. Another reason that biomarkers may fail is that it can be difficult to determine the causative pathways that will better predict disease outcome in a chronically inflamed tissue where multiple pathways are happening simultaneously. I conducted novel research to identify and verify whether investigating animal models long before onset of colitis would identify potentially causative biomarkers for colitis in an animal model. Previous studies have shown early influx of dendritic cells are associated with resistance to Trichuris muris-induced colitis in mice, suggesting early biomarkers may be detectable that might predict disease outcome in inflammatory diseases, such as inflammatory bowel disease (IBD).In the T. muris colitis model, I identified differences in gene expression of multiple components of the receptor for advanced glycation end-products (RAGE) activation pathway between colitis-resistant and colitis-susceptible mice, occurring just 24 hours post infection; before any observable clinical symptoms were present. RAGE is a receptor that binds products of damage, such as calprotectin, and initiates pro-inflammatory cascades. However, RAGE can be cleaved from the cell membrane to form a soluble receptor (sRAGE) that cannot mediate proinflammatory signals, yet can bind to damage products, effectively rendering them harmless. During a longer infection timecourse, colitis-resistant mice produced significantly more sRAGE during infection, consistent with an increased ability to prevent inflammatory ligands from activating membrane-bound RAGE. These findings were also supported by additional experiments using T. muris infection in Il-10-/- mice. In summary, I have carried out an analysis of methods reporting quality in immunology research that can help improve the reliability of existing data relevant to the further study of IBD and beyond. I have also identified sRAGE as a potential biomarker for the onset of colitis in the T. muris infection model, with implications for diagnosis and treatment of IBD in a clinical setting.

Absolute quantitative PCR (qPCR) is a method that determines the concentration of DNA in a sample. Accurate, and reproducible quantification is required during forensic DNA processing since the results determine the volume of sample used during STR genotyping. If too little DNA is utilized allelic dropout can occur; if too much DNA is used an increase in the number of artifacts can result. In either case, sub-optimal DNA input-masses can lead to the misinterpretation of the evidentiary profile, by increasing the probability of drop in and/or drop out. Generally, the qPCR method used during forensic DNA processing employs a set of standards, which are run with the questioned samples and used to generate a standard curve. These data are then used to establish a linear equation that is subsequently utilized to estimate the concentration of DNA in the unknown sample. However, standard curves have been shown to be prone to systematic and random error effects that impact the accuracy of the concentration estimate. This study examines two alternative methods to determine the DNA concentration for unknown samples, and compares them to the currently accepted protocol of running new dilutions/standards with every assay. The two alternative methods are: 1) using a validated standard curve, and 2) using linear regression of efficiency. To examine the feasibility of using these two methods for forensic purposes, two samples were quantified, using qPCR, in quadruplicate over the course of three years and concentrations were calculated using all three methods. Effects that time, kit lot, and instrument calibration had on the concentrations was examined for both total human and Y-DNA. Specifically, methods were compared by examining variances in concentration over the three- year period, and contrasting these results with the variances obtained within runs. The method which resulted in the smallest changes in concentration over time was regarded as the most stable. Results show that of the three methods, the use of a validated curve resulted in less variation of DNA concentration between multiple runs. Further, the factor that had the largest impact on concentration variance was the calibration of the instrument. Based on these results, recommendations are provided.

Background The inter- and intra-subject variations of scintigraphy, which are used to identify colonic transit disturbances in irritable bowel syndrome (IBS), are unclear. The relationship between colonic transit and bowel functions is incompletely understood. To assess inter- and intra-subject variations of scintigraphic colonic transit measurements in 86 IBS patients and 17 healthy subjects and to quantify the relationship between colonic transit and bowel symptoms in 147 IBS patients and 46 healthy subjects. Methods Data from participants with multiple colonic transit measurements were analysed. Primary end points were colonic filling at 6 h (CF6h) and geometric center (GC) at 24 and 48 h for colonic transit. Bowel functions were assessed by daily stool diaries. Key Results Inter- and intra-subject variations were greater for small intestinal than colonic transit. Overall, inter- and intra-subject variations were relatively narrow for colonic transit (both GC24h and GC48h, with lower COV at 48 h); there was little intra-subject variation in health and IBS-constipation over a period of ≤3 weeks and over 2.0 years (median, range 0.1, 11.0 years). Significant intra-individual differences in GC24h were observed only in IBS-D patients. Colonic transit was significantly associated with stool form (accounting for 19-27% of the variance), frequency (19%), and ease of stool passage (12%). Conclusions & Inferences Despite inter-subject variation in scintigraphic colonic transit results, the intra-subject measurements are reproducible over time in healthy volunteers and patients with IBS; significant changes in colonic transit at 24 h were observed only in IBS-D. Colonic transit is associated with stool form, frequency and ease of passage.

The reliability of biomarker discovery by means of proteomics has been called into question. It was speculated that "background noise" variation resulting from differences in preparation and handling of samples and proteome dynamics may mask subtle, yet important, differences due to the biological condition. Little is understood about complex proteomes and their variability. A critical aspect of proteomic biomarker research that is largely unexplored is the comparative reproducibility of certain methods such as two-dimensional gel electrophoresis and liquid chromatography/mass spectrometry. In particular, with liquid chromatography/mass spectrometry, it is not known whether variability in peptide quantitation is dependent on any of their several properties such as size, abundance, or hydrophobicity. Such determinations may be critical in properly assessing the value of proteomics data. The fruit fly Drosophila melanogaster was used as a well-controlled multicellular animal model to study the relationship between the background variation and expected changes induced by environmental or genetic factors. The data, gathered by two different proteomics methods, were used to compare and evaluate the reproducibility of the methods. It is reported that there was on average 15 to 18% variability in quantitative measurements of protein abundance using 2-dimensional gel electrophoresis or liquid chromatography/mass spectrometry. Using liquid chromatography/mass spectrometry, peptides with a smaller mass-to-charge ratio were shown to be measured less reproducibly than peptides with a larger ratio. Statistically significant proteomic differences between fly populations could be demonstrated between males and females. In dynamic experiments, less than 0.5% of proteins measured were shown to change after 24 hour starvation of the flies. However, no significant difference in peptide composition could be found for flies fed on a second diet consisting of the standard diet augmented with 10% ethanol. These results suggest that proteomic variability while evident allowed for biomarker discovery using either method for this model system.