Binary classification of dyslipidemia from the waist-to-hip ratio and body mass index: a comparison of linear, logistic, and CART models.

BACKGROUND: We sought to improve upon previously published statistical modeling strategies for binary classification of dyslipidemia for general population screening purposes based on the waist-to-hip circumference ratio and body mass index anthropometric measurements. METHODS: Study subjects were participants in WHO-MONICA population-based surveys conducted in two Swiss regions. Outcome variables were based on the total serum cholesterol to high density lipoprotein cholesterol ratio. The other potential predictor variables were gender, age, current cigarette smoking, and hypertension. The models investigated were: (i) linear regression; (ii) logistic classification; (iii) regression trees; (iv) classification trees (iii and iv are collectively known as "CART"). Binary classification performance of the region-specific models was externally validated by classifying the subjects from the other region. RESULTS: Waist-to-hip circumference ratio and body mass index remained modest predictors of dyslipidemia. Correct classification rates for all models were 60-80%, with marked gender differences. Gender-specific models provided only small gains in classification. The external validations provided assurance about the stability of the models. CONCLUSIONS: There were no striking differences between either the algebraic (i, ii) vs. non-algebraic (iii, iv), or the regression (i, iii) vs. classification (ii, iv) modeling approaches. Anticipated advantages of the CART vs. simple additive linear and logistic models were less than expected in this particular application with a relatively small set of predictor variables. CART models may be more useful when considering main effects and interactions between larger sets of predictor variables.

Generalized linear and generalized additive models in studies of species distributions: setting the scene

An important statistical development of the last 30 years has been the advance in regression analysis provided by generalized linear models (GLMs) and generalized additive models (GAMs). Here we introduce a series of papers prepared within the framework of an international workshop entitled: Advances in GLMs/GAMs modeling: from species distribution to environmental management, held in Riederalp, Switzerland, 6-11 August 2001.We first discuss some general uses of statistical models in ecology, as well as provide a short review of several key examples of the use of GLMs and GAMs in ecological modeling efforts. We next present an overview of GLMs and GAMs, and discuss some of their related statistics used for predictor selection, model diagnostics, and evaluation. Included is a discussion of several new approaches applicable to GLMs and GAMs, such as ridge regression, an alternative to stepwise selection of predictors, and methods for the identification of interactions by a combined use of regression trees and several other approaches. We close with an overview of the papers and how we feel they advance our understanding of their application to ecological modeling.

The ghost of past species occurrence: improving species distribution models for presence-only data

1. Model-based approaches have been used increasingly in conservation biology over recent years. Species presence data used for predictive species distribution modelling are abundant in natural history collections, whereas reliable absence data are sparse, most notably for vagrant species such as butterflies and snakes. As predictive methods such as generalized linear models (GLM) require absence data, various strategies have been proposed to select pseudo-absence data. However, only a few studies exist that compare different approaches to generating these pseudo-absence data. 2. Natural history collection data are usually available for long periods of time (decades or even centuries), thus allowing historical considerations. However, this historical dimension has rarely been assessed in studies of species distribution, although there is great potential for understanding current patterns, i.e. the past is the key to the present. 3. We used GLM to model the distributions of three 'target' butterfly species, Melitaea didyma, Coenonympha tullia and Maculinea teleius, in Switzerland. We developed and compared four strategies for defining pools of pseudo-absence data and applied them to natural history collection data from the last 10, 30 and 100 years. Pools included: (i) sites without target species records; (ii) sites where butterfly species other than the target species were present; (iii) sites without butterfly species but with habitat characteristics similar to those required by the target species; and (iv) a combination of the second and third strategies. Models were evaluated and compared by the total deviance explained, the maximized Kappa and the area under the curve (AUC). 4. Among the four strategies, model performance was best for strategy 3. Contrary to expectations, strategy 2 resulted in even lower model performance compared with models with pseudo-absence data simulated totally at random (strategy 1). 5. Independent of the strategy model, performance was enhanced when sites with historical species presence data were not considered as pseudo-absence data. Therefore, the combination of strategy 3 with species records from the last 100 years achieved the highest model performance. 6. Synthesis and applications. The protection of suitable habitat for species survival or reintroduction in rapidly changing landscapes is a high priority among conservationists. Model-based approaches offer planning authorities the possibility of delimiting priority areas for species detection or habitat protection. The performance of these models can be enhanced by fitting them with pseudo-absence data relying on large archives of natural history collection species presence data rather than using randomly sampled pseudo-absence data.

Etiology of ethnic differences in childhood spirometry.

OBJECTIVES: Age- and height-adjusted spirometric lung function of South Asian children is lower than those of white children. It is unclear whether this is purely genetic, or partly explained by the environment. In this study, we assessed whether cultural factors, socioeconomic status, intrauterine growth, environmental exposures, or a family and personal history of wheeze contribute to explaining the ethnic differences in spirometric lung function. METHODS: We studied children aged 9 to 14 years from a population-based cohort, including 1088 white children and 275 UK-born South Asians. Log-transformed spirometric data were analyzed using multiple linear regressions, adjusting for anthropometric factors. Five different additional models adjusted for (1) cultural factors, (2) indicators of socioeconomic status, (3) perinatal data reflecting intrauterine growth, (4) environmental exposures, and (5) personal and family history of wheeze. RESULTS: Height- and gender-adjusted forced vital capacity (FVC) and forced expired volume in 1 second (FEV1) were lower in South Asian than white children (relative difference -11% and -9% respectively, P < .001), but PEF and FEF50 were similar (P ≥ .5). FEV1/FVC was higher in South Asians (1.8%, P < .001). These differences remained largely unchanged in all 5 alternative models. CONCLUSIONS: Our study confirmed important differences in lung volumes between South Asian and white children. These were not attenuated after adjustment for cultural and socioeconomic factors and intrauterine growth, neither were they explained by differences in environmental exposures nor a personal or family history of wheeze. This suggests that differences in lung function may be mainly genetic in origin. The implication is that ethnicity-specific predicted values remain important specifically for South Asian children.

Multimodel inference and multimodel averaging in empirical modeling of occupational exposure levels.

Empirical modeling of exposure levels has been popular for identifying exposure determinants in occupational hygiene. Traditional data-driven methods used to choose a model on which to base inferences have typically not accounted for the uncertainty linked to the process of selecting the final model. Several new approaches propose making statistical inferences from a set of plausible models rather than from a single model regarded as 'best'. This paper introduces the multimodel averaging approach described in the monograph by Burnham and Anderson. In their approach, a set of plausible models are defined a priori by taking into account the sample size and previous knowledge of variables influent on exposure levels. The Akaike information criterion is then calculated to evaluate the relative support of the data for each model, expressed as Akaike weight, to be interpreted as the probability of the model being the best approximating model given the model set. The model weights can then be used to rank models, quantify the evidence favoring one over another, perform multimodel prediction, estimate the relative influence of the potential predictors and estimate multimodel-averaged effects of determinants. The whole approach is illustrated with the analysis of a data set of 1500 volatile organic compound exposure levels collected by the Institute for work and health (Lausanne, Switzerland) over 20 years, each concentration having been divided by the relevant Swiss occupational exposure limit and log-transformed before analysis. Multimodel inference represents a promising procedure for modeling exposure levels that incorporates the notion that several models can be supported by the data and permits to evaluate to a certain extent model selection uncertainty, which is seldom mentioned in current practice.

Evaluating the ability of habitat suitability models to predict species presences.

Models predicting species spatial distribution are increasingly applied to wildlife management issues, emphasising the need for reliable methods to evaluate the accuracy of their predictions. As many available datasets (e.g. museums, herbariums, atlas) do not provide reliable information about species absences, several presence-only based analyses have been developed. However, methods to evaluate the accuracy of their predictions are few and have never been validated. The aim of this paper is to compare existing and new presenceonly evaluators to usual presence/absence measures. We use a reliable, diverse, presence/absence dataset of 114 plant species to test how common presence/absence indices (Kappa, MaxKappa, AUC, adjusted D-2) compare to presenceonly measures (AVI, CVI, Boyce index) for evaluating generalised linear models (GLM). Moreover we propose a new, threshold-independent evaluator, which we call "continuous Boyce index". All indices were implemented in the B10MAPPER software. We show that the presence-only evaluators are fairly correlated (p > 0.7) to the presence/absence ones. The Boyce indices are closer to AUC than to MaxKappa and are fairly insensitive to species prevalence. In addition, the Boyce indices provide predicted-toexpected ratio curves that offer further insights into the model quality: robustness, habitat suitability resolution and deviation from randomness. This information helps reclassifying predicted maps into meaningful habitat suitability classes. The continuous Boyce index is thus both a complement to usual evaluation of presence/absence models and a reliable measure of presence-only based predictions.

Amplification efficiency: linking baseline and bias in the analysis of quantitative PCR data.

Despite the central role of quantitative PCR (qPCR) in the quantification of mRNA transcripts, most analyses of qPCR data are still delegated to the software that comes with the qPCR apparatus. This is especially true for the handling of the fluorescence baseline. This article shows that baseline estimation errors are directly reflected in the observed PCR efficiency values and are thus propagated exponentially in the estimated starting concentrations as well as 'fold-difference' results. Because of the unknown origin and kinetics of the baseline fluorescence, the fluorescence values monitored in the initial cycles of the PCR reaction cannot be used to estimate a useful baseline value. An algorithm that estimates the baseline by reconstructing the log-linear phase downward from the early plateau phase of the PCR reaction was developed and shown to lead to very reproducible PCR efficiency values. PCR efficiency values were determined per sample by fitting a regression line to a subset of data points in the log-linear phase. The variability, as well as the bias, in qPCR results was significantly reduced when the mean of these PCR efficiencies per amplicon was used in the calculation of an estimate of the starting concentration per sample.

The effect of patient, provider and financing regulations on the intensity of ambulatory physical therapy episodes : a multilevel analysis based on routinely available data

Background: Many studies have found considerable variations in the resource intensity of physical therapy episodes. Although they have identified several patient-and provider-related factors, few studies have examined their relative explanatory power. We sought to quantify the contribution of patients and providers to these differences and examine how effective Swiss regulations are (nine-session ceiling per prescription and bonus for first treatments). Methods: Our sample consisted of 87,866 first physical therapy episodes performed by 3,365 physiotherapists based on referrals by 6,131 physicians. We modeled the number of visits per episode using a multilevel log linear regression with crossed random effects for physiotherapists and physicians and with fixed effects for cantons. The three-level explanatory variables were patient, physiotherapist and physician characteristics. Results: The median number of sessions was nine (interquartile range 6-13). Physical therapy use increased with age, women, higher health care costs, lower deductibles, surgery and specific conditions. Use rose with the share of nine-session episodes among physiotherapists or physicians, but fell with the share of new treatments. Geographical area had no influence. Most of the variance was explained at the patient level, but the available factors explained only 4% thereof. Physiotherapists and physicians explained only 6% and 5% respectively of the variance, although the available factors explained most of this variance. Regulations were the most powerful factors. Conclusion: Against the backdrop of abundant physical therapy supply, Swiss financial regulations did not restrict utilization. Given that patient-related factors explained most of the variance, this group should be subject to closer scrutiny. Moreover, further research is needed on the determinants of patient demand.

How does the body-scale model affect back-calculated growth: the example of arctic charr Salvelinus alpinus (L.) of Lake Geneva (Switzerland)

When back-calculating fish length from scale measurements, the choice of the body-scale relationship is a fundamental step. Using data from the arctic charrSalvelinus alpinus (L.) of Lake Geneva (Switzerland) we show the need for a curvilinear model, on both statistical and biological grounds. From several 2-parameters models, the log-linear relationship appears to provide the best fit. A 3-parameters, Bertalanffy model did not improve the fit. We show moreover that using the proportional model would lead to important misinterpretations of the data.

Wear of two artificial tooth materials in vivo: a 12-month pilot study.

STATEMENT OF PROBLEM: Wear of methacrylate artificial teeth resulting in vertical loss is a problem for both dentists and patients. PURPOSE: The purpose of this study was to quantify wear of artificial teeth in vivo and to relate it to subject and tooth variables. MATERIAL AND METHODS: Twenty-eight subjects treated with complete dentures received 2 artificial tooth materials (polymethyl methacrylate (PMMA)/double-cross linked PMMA fillers; 35%/59% (SR Antaris DCL, SR Postaris DCL); experimental 48%/46%). At baseline and after 12 months, impressions of the dentures were poured with improved stone. After laser scanning, the casts were superimposed and matched. Maximal vertical loss (mm) and volumetric loss (mm(3)) were calculated for each tooth and log-transformed to reduce variability. Volumetric loss was related to the occlusally active surface area. Linear mixed models were used to study the influence of the factors jaw, tooth, and material on adjusted (residual) wear values (alpha=.05). RESULTS: Due to drop outs (n=5) and unmatchable casts (n=3), 69% of all teeth were analyzed. Volumetric loss had a strong linear relationship to surface area (P<.001); this was less pronounced for vertical loss (P=.004). The factor showing the highest influence was the subject. Wear was tooth dependent (increasing from incisors to molars). However, these differences diminished once the wear rates were adjusted for occlusal area, and only a few remained significant (anterior versus posterior maxillary teeth). Another influencing factor was the age of the subject. CONCLUSIONS: Clinical wear of artificial teeth is higher than previously measured or expected. The presented method of analyzing wear of artificial teeth using a laser-scanning device seemed suitable.

Trends in mortality from coronary heart and cerebrovascular disease in Switzerland, 1969-87.

Trends in age-specific and age-standardized death certification rates from all ischaemic heart disease and cerebrovascular disease in Switzerland have been analysed for the period 1969-87, i.e. since the introduction of the Eighth Revision of the International Classification of Diseases for coding causes of death. For coronary heart disease, overall age-standardized rates of males in the mid-late 1980's were similar to those in the late 1960's, although some upward trend was evident up to the mid 1970's (with a peak rate of 120.4/100,000, World standard, in 1978) followed by steady declines in more recent years (103.8/100,000 in 1987). These falls were larger in truncated (35 to 64 years) rates. For females, overall age-standardized rates were stable around a value of 40/100,000, while truncated rates tended to decrease, particularly over most recent years, with an overall decline of over 25%. Examination of age-specific trends showed that in both sexes declines at younger ages were already evident in the earlier calendar period, while above age 50 some fall became evident only in most recent years. Thus, in a formal log-linear age/period/cohort model, both a period and a cohort component emerged. In relation to cerebrovascular diseases, the overall declines were around 40% in males (from 67.4 to 41.2/100,000, World standard) and 45% for females (from 56.6 to 31.7/100,000), and were proportionally comparable across subsequent age groups above age 45. The estimates for the age/period/cohort model were thus downwards both for the period and the cohort component although, in such a situation, it is difficult to disentangle the major underlying component.(ABSTRACT TRUNCATED AT 250 WORDS)

Effects of age, birth cohort and period of death on Swiss cancer mortality, 1951-1984.

Swiss death certification data over the period 1951-1984 for total cancer mortality and 30 major cancer sites in the population aged 25 to 74 years were analysed using a log-linear Poisson model with arbitrary constraints on the parameters to isolate the effects of birth cohort, calendar period of death and age. The overall pattern of total cancer mortality in males was stable for period values and showed some moderate decreases in cohort values restricted to the generations born after 1930. Cancer mortality trends were more favourable in females, with steady, though moderate, declines in both cohort and period values. According to the estimates from the model, the worst affected generation for male lung cancer was that born around 1910, and a flattening of trends or some moderate decline was observed for more recent cohorts, although this decline was considerably more limited than in other European countries. There were decreases in cohort and period values for stomach, intestine and oesophageal cancer in both sexes and (cervix) uteri in females. Increases were observed in both cohort and period trends for pancreas and liver in males and for several other neoplasms, including prostate, brain, leukaemias and lymphomas, restricted, however, for the latter sites, to the earlier cohorts and hence partly attributable to improved diagnosis and certification in the elderly. Although age values for lung cancer in females were around 10-times lower than in males, upward trends in female lung cancer cohort values were observed in subsequent cohorts and for period values from the late 1960's onwards. Therefore, future trends in female lung cancer mortality should continue to be monitored. The application of these age/period/cohort models thus provides a summary guide for the reading and interpretation of cancer mortality trends, although it cannot replace careful inspection of single age-specific rates.

Stochastic models and numerical algorithms for a class of regulatory gene networks.

Regulatory gene networks contain generic modules, like those involving feedback loops, which are essential for the regulation of many biological functions (Guido et al. in Nature 439:856-860, 2006). We consider a class of self-regulated genes which are the building blocks of many regulatory gene networks, and study the steady-state distribution of the associated Gillespie algorithm by providing efficient numerical algorithms. We also study a regulatory gene network of interest in gene therapy, using mean-field models with time delays. Convergence of the related time-nonhomogeneous Markov chain is established for a class of linear catalytic networks with feedback loops.

Are niche-based species distribution models transferable in space?

Aim To assess the geographical transferability of niche-based species distribution models fitted with two modelling techniques. Location Two distinct geographical study areas in Switzerland and Austria, in the subalpine and alpine belts. Methods Generalized linear and generalized additive models (GLM and GAM) with a binomial probability distribution and a logit link were fitted for 54 plant species, based on topoclimatic predictor variables. These models were then evaluated quantitatively and used for spatially explicit predictions within (internal evaluation and prediction) and between (external evaluation and prediction) the two regions. Comparisons of evaluations and spatial predictions between regions and models were conducted in order to test if species and methods meet the criteria of full transferability. By full transferability, we mean that: (1) the internal evaluation of models fitted in region A and B must be similar; (2) a model fitted in region A must at least retain a comparable external evaluation when projected into region B, and vice-versa; and (3) internal and external spatial predictions have to match within both regions. Results The measures of model fit are, on average, 24% higher for GAMs than for GLMs in both regions. However, the differences between internal and external evaluations (AUC coefficient) are also higher for GAMs than for GLMs (a difference of 30% for models fitted in Switzerland and 54% for models fitted in Austria). Transferability, as measured with the AUC evaluation, fails for 68% of the species in Switzerland and 55% in Austria for GLMs (respectively for 67% and 53% of the species for GAMs). For both GAMs and GLMs, the agreement between internal and external predictions is rather weak on average (Kulczynski's coefficient in the range 0.3-0.4), but varies widely among individual species. The dominant pattern is an asymmetrical transferability between the two study regions (a mean decrease of 20% for the AUC coefficient when the models are transferred from Switzerland and 13% when they are transferred from Austria). Main conclusions The large inter-specific variability observed among the 54 study species underlines the need to consider more than a few species to test properly the transferability of species distribution models. The pronounced asymmetry in transferability between the two study regions may be due to peculiarities of these regions, such as differences in the ranges of environmental predictors or the varied impact of land-use history, or to species-specific reasons like differential phenotypic plasticity, existence of ecotypes or varied dependence on biotic interactions that are not properly incorporated into niche-based models. The lower variation between internal and external evaluation of GLMs compared to GAMs further suggests that overfitting may reduce transferability. Overall, a limited geographical transferability calls for caution when projecting niche-based models for assessing the fate of species in future environments.