Validation procedures in radiological diagnostic models. Neural network and logistic regression

The objective of this paper is to compare the performance of twopredictive radiological models, logistic regression (LR) and neural network (NN), with five different resampling methods. One hundred and sixty-seven patients with proven calvarial lesions as the only known disease were enrolled. Clinical and CT data were used for LR and NN models. Both models were developed with cross validation, leave-one-out and three different bootstrap algorithms. The final results of each model were compared with error rate and the area under receiver operating characteristic curves (Az). The neural network obtained statistically higher Az than LR with cross validation. The remaining resampling validation methods did not reveal statistically significant differences between LR and NN rules. The neural network classifier performs better than the one based on logistic regression. This advantage is well detected by three-fold cross-validation, but remains unnoticed when leave-one-out or bootstrap algorithms are used.

Fixed and random effects in Classical and Bayesian regression

This paper proposes a common and tractable framework for analyzingdifferent definitions of fixed and random effects in a contant-slopevariable-intercept model. It is shown that, regardless of whethereffects (i) are treated as parameters or as an error term, (ii) areestimated in different stages of a hierarchical model, or whether (iii)correlation between effects and regressors is allowed, when the sameinformation on effects is introduced into all estimation methods, theresulting slope estimator is also the same across methods. If differentmethods produce different results, it is ultimately because differentinformation is being used for each methods.

The importance of individual heterogeneity in the decomposition of measures of socioeconomic inequality in health: An approach based on quantile regression

This paper shows how recently developed regression-based methods for thedecomposition of health inequality can be extended to incorporateindividual heterogeneity in the responses of health to the explanatoryvariables. We illustrate our method with an application to the CanadianNPHS of 1994. Our strategy for the estimation of heterogeneous responsesis based on the quantile regression model. The results suggest that thereis an important degree of heterogeneity in the association of health toexplanatory variables which, in turn, accounts for a substantial percentageof inequality in observed health. A particularly interesting finding isthat the marginal response of health to income is zero for healthyindividuals but positive and significant for unhealthy individuals. Theheterogeneity in the income response reduces both overall health inequalityand income related health inequality.

Random measurement error and regression dilution bias.

Summary points: - The bias introduced by random measurement error will be different depending on whether the error is in an exposure variable (risk factor) or outcome variable (disease) - Random measurement error in an exposure variable will bias the estimates of regression slope coefficients towards the null - Random measurement error in an outcome variable will instead increase the standard error of the estimates and widen the corresponding confidence intervals, making results less likely to be statistically significant - Increasing sample size will help minimise the impact of measurement error in an outcome variable but will only make estimates more precisely wrong when the error is in an exposure variable

The IFNL3/4 ΔG variant increases susceptibility to cytomegalovirus retinitis among HIV-infected patients.

BACKGROUND: Cytomegalovirus (CMV) retinitis is a major cause of visual impairment and blindness among patients with uncontrolled HIV infections. Whereas polymorphisms in interferon-lambda 3 (IFNL3, previously named IL28B) strongly influence the clinical course of hepatitis C, few studies examined the role of such polymorphisms in infections due to viruses other than hepatitis C virus. OBJECTIVES: To analyze the association of newly identified IFNL3/4 variant rs368234815 with susceptibility to CMV-associated retinitis in a cohort of HIV-infected patients. DESIGN AND METHODS: This retrospective longitudinal study included 4884 white patients from the Swiss HIV Cohort Study, among whom 1134 were at risk to develop CMV retinitis (CD4 nadir <100 /μl and positive CMV serology). The association of CMV-associated retinitis with rs368234815 was assessed by cumulative incidence curves and multivariate Cox regression models, using the estimated date of HIV infection as a starting point, with censoring at death and/or lost follow-up. RESULTS: A total of 40 individuals among 1134 patients at risk developed CMV retinitis. The minor allele of rs368234815 was associated with a higher risk of CMV retinitis (log-rank test P = 0.007, recessive mode of inheritance). The association was still significant in a multivariate Cox regression model (hazard ratio 2.31, 95% confidence interval 1.09-4.92, P = 0.03), after adjustment for CD4 nadir and slope, HAART and HIV-risk groups. CONCLUSION: We reported for the first time an association between an IFNL3/4 polymorphism and susceptibility to AIDS-related CMV retinitis. IFNL3/4 may influence immunity against viruses other than HCV.

Global Genomic Diversity of Human Papillomavirus 6 Based on 724 Isolates and 190 Complete Genome Sequences.

Human papillomavirus type 6 (HPV6) is the major etiological agent of anogenital warts and laryngeal papillomas and has been included in both the quadrivalent and nonavalent prophylactic HPV vaccines. This study investigated the global genomic diversity of HPV6, using 724 isolates and 190 complete genomes from six continents, and the association of HPV6 genomic variants with geographical location, anatomical site of infection/disease, and gender. Initially, a 2,800-bp E5a-E5b-L1-LCR fragment was sequenced from 492/530 (92.8%) HPV6-positive samples collected for this study. Among them, 130 exhibited at least one single nucleotide polymorphism (SNP), indel, or amino acid change in the E5a-E5b-L1-LCR fragment and were sequenced in full. A global alignment and maximum likelihood tree of 190 complete HPV6 genomes (130 fully sequenced in this study and 60 obtained from sequence repositories) revealed two variant lineages, A and B, and five B sublineages: B1, B2, B3, B4, and B5. HPV6 (sub)lineage-specific SNPs and a 960-bp representative region for whole-genome-based phylogenetic clustering within the L2 open reading frame were identified. Multivariate logistic regression analysis revealed that lineage B predominated globally. Sublineage B3 was more common in Africa and North and South America, and lineage A was more common in Asia. Sublineages B1 and B3 were associated with anogenital infections, indicating a potential lesion-specific predilection of some HPV6 sublineages. Females had higher odds for infection with sublineage B3 than males. In conclusion, a global HPV6 phylogenetic analysis revealed the existence of two variant lineages and five sublineages, showing some degree of ethnogeographic, gender, and/or disease predilection in their distribution. IMPORTANCE: This study established the largest database of globally circulating HPV6 genomic variants and contributed a total of 130 new, complete HPV6 genome sequences to available sequence repositories. Two HPV6 variant lineages and five sublineages were identified and showed some degree of association with geographical location, anatomical site of infection/disease, and/or gender. We additionally identified several HPV6 lineage- and sublineage-specific SNPs to facilitate the identification of HPV6 variants and determined a representative region within the L2 gene that is suitable for HPV6 whole-genome-based phylogenetic analysis. This study complements and significantly expands the current knowledge of HPV6 genetic diversity and forms a comprehensive basis for future epidemiological, evolutionary, functional, pathogenicity, vaccination, and molecular assay development studies.

Use of NIR spectroscopy and multivariate process spectra calibration methodology for pharmaceutical solid samples analysis

Accomplish high quality of final products in pharmaceutical industry is a challenge that requires the control and supervision of all the manufacturing steps. This request created the necessity of developing fast and accurate analytical methods. Near infrared spectroscopy together with chemometrics, fulfill this growing demand. The high speed providing relevant information and the versatility of its application to different types of samples lead these combined techniques as one of the most appropriated. This study is focused on the development of a calibration model able to determine amounts of API from industrial granulates using NIR, chemometrics and process spectra methodology.

Predicting Adverse Events in Children with Fever and Chemotherapy-Induced Neutropenia. Results of the Prospective Multicenter SPOG 2003 FN Study

PURPOSE To develop a score predicting the risk of adverse events (AEs) in pediatric patients with cancer who experience fever and neutropenia (FN) and to evaluate its performance. PATIENTS AND METHODS Pediatric patients with cancer presenting with FN induced by nonmyeloablative chemotherapy were observed in a prospective multicenter study. A score predicting the risk of future AEs (ie, serious medical complication, microbiologically defined infection, radiologically confirmed pneumonia) was developed from a multivariate mixed logistic regression model. Its cross-validated predictive performance was compared with that of published risk prediction rules. Results An AE was reported in 122 (29%) of 423 FN episodes. In 57 episodes (13%), the first AE was known only after reassessment after 8 to 24 hours of inpatient management. Predicting AE at reassessment was better than prediction at presentation with FN. A differential leukocyte count did not increase the predictive performance. The score predicting future AE in 358 episodes without known AE at reassessment used the following four variables: preceding chemotherapy more intensive than acute lymphoblastic leukemia maintenance (weight = 4), hemoglobin > or = 90 g/L (weight = 5), leukocyte count less than 0.3 G/L (weight = 3), and platelet count less than 50 G/L (weight = 3). A score (sum of weights) > or = 9 predicted future AEs. The cross-validated performance of this score exceeded the performance of published risk prediction rules. At an overall sensitivity of 92%, 35% of the episodes were classified as low risk, with a specificity of 45% and a negative predictive value of 93%. CONCLUSION This score, based on four routinely accessible characteristics, accurately identifies pediatric patients with cancer with FN at risk for AEs after reassessment.

Medical treatments and risk factors for resection surgery in Crohn's disease: results from the Swiss IBD Cohort Study

Background: Surgery has been previously reported to be necessary in up to 80% of Crohn's disease (CD) patients, and up to 65% of patients needed reoperation after 10 years. Prevention of surgery is therefore a particularly important issue for these patients. Treatment options are controversial and data on them are scarce. This study reports medical treatments and main clinical risk factors in CD patients having undergone one or several surgeries. Risks for being free from surgery were also assessed. Methods: Retrospective cohort study, using data from patients included in the Swiss IBD cohort study from November 2006 to July 2011. History of resective surgeries, clinical characteristics and drug regimens were collected through detailed medical records. Univariate and multivariate analyses for clinical and therapeutic factors were performed. Cox regression was made to estimate free-of-surgery risks for different phenotypes and drugs. Results: Out of 1138 CD patients in the cohort, 721 (63.4%) were free of surgery at inclusion; 203 (17.8%) had 1 surgery and 214 (18.8%) >1 surgery. Main risk factors for surgery were disease duration 5-10 years (OR=2.92; p<0.001) and >10 years (OR=10.45; p<0.001), as well as stricturing (OR=8.33; p<0.001) or fistulizing disease (OR=7.34; p<0.001). Risk factors for repeated surgery was disease duration >10 years (OR=2.55; p=0.006) or fistulizing disease (OR=3.79; p<0.001). At inclusion, 107 patients (25.7%) had at least one anti-TNF alpha, 168 (40.3%) at least one immunosuppressive agent, and 41 (9.8%) at least 5-ASA or antibiotics. 64 (15.3%) were not exposed to any medical treatment. Kaplan-Meier curves showed that the risk of being free of surgery was 65% after 10 years, 42% after 20 years and 23% after 40 years. Surgical risks were four resp. five time higher for fistulizing and stricturing phenotypes (Hazard ratio (HR) =4.2; p<0.001; resp. HR=4.7; p<0.001) compared to inflammatory phenotype. Surgical risk was 4 times lower (HR=0.27; p=0.063) in CD patients under anti-TNF alpha compared to those under other or no drugs. Conclusion: The risk of having resective surgery was confirmed to be very high for CD in our cohort. Duration of disease, fistulizing and stricturing disease pattern enhance the risk of surgery. Anti-TNF alpha tends to lower this risk.

Interaction between widening of diameter of abdominal aorta and cardiovascular risk factors and atherosclerosis burden.

The aim of this study was to investigate influence of traditional cardiovascular risk factors (CVRF) and subclinical atherosclerosis (ATS) burden on early stages of abdominal aortic diameter (AAD) widening among adults. 2,052 consecutive patients (P) (39 % women), mean age 52 ± 13 years, were prospectively screened for CVRF, ATS, and AAD. B-mode ultrasound was used to evaluate the largest AAD and to detect carotid and femoral atherosclerotic plaques. Mean AAD was 15.2 ± 2.8 mm. Atherosclerotic plaques were detected in 71 % of patients. Significant univariate correlation between AAD, traditional CVRF, and ABS was found. However, multiple regression analysis showed that only seven of them were significantly and weakly correlated with AAD (R² = 0.27, p < 0.001). On the other hand, a multivariate logistic analysis was used to evaluate CVRF impact on enlarged AAD ≥25 mm (EAAD) as compared to those with AAD <25 mm. These factors did not account for more than 30 % of interaction (R² = 0.30, p = 0.001). Furthermore, despite a large proportion of patients with high number of CVRF, and subclinical ATS, rate of patients with AAD ≥25 mm was low (1 %) and scattered regardless their CHD risk score or ATS burden. In conclusion, these results suggest that although some traditional CVRF and presence of ATS are associated with early stages of EAAD, other determinants still need to be identified for a better understanding of abdominal aortic aneurysm pathogenesis.

Neuropathological analysis of lacunes and microvascular lesions in late-onset depression.

M. Santos, G. Gold, E. Kövari, F. R. Herrmann, P. R. Hof, C. Bouras and P. Giannakopoulos (2010) Neuropathology and Applied Neurobiology36, 661-672
Neuropathological analysis of lacunes and microvascular lesions in late-onset depression Aims: Previous neuropathological studies documented that small vascular and microvascular pathology is associated with cognitive decline. More recently, we showed that thalamic and basal ganglia lacunes are associated with post-stroke depression and may affect emotional regulation. The present study examines whether this is also the case for late-onset depression. Methods: We performed a detailed analysis of small macrovascular and microvascular pathology in the post mortem brains of 38 patients with late-onset major depression (LOD) and 29 healthy elderly controls. A clinical diagnosis of LOD was established while the subjects were alive using the DSM-IV criteria. Additionally, we retrospectively reviewed all charts for the presence of clinical criteria of vascular depression. Neuropathological evaluation included bilateral semi-quantitative assessment of lacunes, deep white matter and periventricular demyelination, cortical microinfarcts and both focal and diffuse gliosis. The association between vascular burden and LOD was investigated using Fisher's exact test and univariate and multivariate logistic regression models. Results: Neither the existence of lacunes nor the presence of microvascular ischaemic lesions was related to occurrence of LOD. Similarly, there was no relationship between vascular lesion scores and LOD. This was also the case within the subgroup of LOD patients fulfilling the clinical criteria for vascular depression. Conclusions: Our results challenge the vascular depression hypothesis by showing that neither deep white matter nor periventricular demyelination is associated with LOD. In conjunction with our previous observations in stroke patients, they also imply that the impact of lacunes on mood may be significant solely in the presence of acute brain compromise.

Poststroke fatigue following minor infarcts: a prospective study.

OBJECTIVE: To explore the potential relationship between fatigue following strokes and poststroke mood, cognitive dysfunction, disability, and infarct site and to determine the predictive factors in the development of poststroke fatigue (PSF) following minor infarcts. METHODS: Ninety-nine functionally active patients aged less than 70 years with a first, nondisabling stroke (NIH Stroke Scale score ≤6 in acute phase and ≤3 after 6 months, modified Rankin Scale score ≤1 at 6 months) were assessed during the acute phase and then at 6 (T1) and 12 months (T2) after their stroke. Scores in the Fatigue Assessment Inventory were described and correlated to age, gender, neurologic and functional impairment, lesion site, mood scores, neuropsychological data, laboratory data, and quality of life at T1 and T2 using a multivariate logistic regression analysis in order to determine which variables recorded at T1 best predicted fatigue at T2. RESULT: As many as 30.5% of the patients at T1 and 34.7% at T2 (11.6% new cases between T1 and T2) reported fatigue. At both 6 and 12 months, there was a significant association between fatigue and a reduction in professional activity. Attentional-executive impairment, depression, and anxiety levels remained associated with PSF throughout this time period, underlining the critical role of these variables in the genesis of PSF. There was no significant association between the lesion site and PSF. CONCLUSION: This study suggests that attentional and executive impairment, as well as depression and anxiety, may play a critical role in the development of PSF.

Eliminació d'artefactes en EGG mitjançant l'ús de la Multivariate Empirical Mode Decomposition

La tècnica de l’electroencefalograma (EEG) és una de les tècniques més utilitzades per estudiar el cervell. En aquesta tècnica s’enregistren els senyals elèctrics que es produeixen en el còrtex humà a través d’elèctrodes col•locats al cap. Aquesta tècnica, però, presenta algunes limitacions a l’hora de realitzar els enregistraments, la principal limitació es coneix com a artefactes, que són senyals indesitjats que es mesclen amb els senyals EEG. L’objectiu d’aquest treball de final de màster és presentar tres nous mètodes de neteja d’artefactes que poden ser aplicats en EEG. Aquests estan basats en l’aplicació de la Multivariate Empirical Mode Decomposition, que és una nova tècnica utilitzada per al processament de senyal. Els mètodes de neteja proposats s’apliquen a dades EEG simulades que contenen artefactes (pestanyeigs), i un cop s’han aplicat els procediments de neteja es comparen amb dades EEG que no tenen pestanyeigs, per comprovar quina millora presenten. Posteriorment, dos dels tres mètodes de neteja proposats s’apliquen sobre dades EEG reals. Les conclusions que s’han extret del treball són que dos dels nous procediments de neteja proposats es poden utilitzar per realitzar el preprocessament de dades reals per eliminar pestanyeigs.

Diagnostic value of vestibulo-ocular reflex parameters in the detection and characterization of labyrinthine lesions.

OBJECTIVE: To evaluate the power of various parameters of the vestibulo-ocular reflex (VOR) in detecting unilateral peripheral vestibular dysfunction and in characterizing certain inner ear pathologies. STUDY DESIGN: Prospective study of consecutive ambulatory patients presenting with acute onset of peripheral vertigo and spontaneous nystagmus. SETTING: Tertiary referral center. PATIENTS: Seventy-four patients (40 females, 34 males) and 22 normal subjects (11 females, 11 males) were included in the study. Patients were classified in three main diagnoses: vestibular neuritis: 40; viral labyrinthitis: 22; Meniere's disease: 12. METHODS: The VOR function was evaluated by standard caloric and impulse rotary tests (velocity step). A mathematical model of vestibular function was used to characterize the VOR response to rotational stimulation. The diagnostic value of the different VOR parameters was assessed by uni- and multivariable logistic regression. RESULTS: In univariable analysis, caloric asymmetry emerged as the most powerful VOR parameter in identifying unilateral vestibular deficit, with a boundary limit set at 20%. In multivariable analysis, the combination of caloric asymmetry and rotational time constant asymmetry significantly improved the discriminatory power over caloric alone (p&lt;0.0001) and produced a detection score with a correct classification of 92.4%. In discriminating labyrinthine diseases, different combinations of the VOR parameters were obtained for each diagnosis (p&lt;0.003) supporting that the VOR characteristics differ between the three inner ear disorders. However, the clinical usefulness of these characteristics in separating the pathologies was limited. CONCLUSION: We propose a powerful logistic model combining the indices of caloric and time constant asymmetries to detect a peripheral vestibular loss, with an accuracy of 92.4%. Based on vestibular data only, the discrimination between the different inner ear diseases is statistically possible, which supports different pathophysiologic changes in labyrinthine pathologies.

Uncertainty Quantification with Support Vector Regression Prediction Models

Uncertainty quantification of petroleum reservoir models is one of the present challenges, which is usually approached with a wide range of geostatistical tools linked with statistical optimisation or/and inference algorithms. The paper considers a data driven approach in modelling uncertainty in spatial predictions. Proposed semi-supervised Support Vector Regression (SVR) model has demonstrated its capability to represent realistic features and describe stochastic variability and non-uniqueness of spatial properties. It is able to capture and preserve key spatial dependencies such as connectivity, which is often difficult to achieve with two-point geostatistical models. Semi-supervised SVR is designed to integrate various kinds of conditioning data and learn dependences from them. A stochastic semi-supervised SVR model is integrated into a Bayesian framework to quantify uncertainty with multiple models fitted to dynamic observations. The developed approach is illustrated with a reservoir case study. The resulting probabilistic production forecasts are described by uncertainty envelopes.