Analysing Seasonal Health Data

Seasonal patterns have been found in a remarkable range of health conditions, including birth defects, respiratory infections and cardiovascular disease. Accurately estimating the size and timing of seasonal peaks in disease incidence is an aid to understanding the causes and possibly to developing interventions. With global warming increasing the intensity of seasonal weather patterns around the world, a review of the methods for estimating seasonal effects on health is timely. This is the first book on statistical methods for seasonal data written for a health audience. It describes methods for a range of outcomes (including continuous, count and binomial data) and demonstrates appropriate techniques for summarising and modelling these data. It has a practical focus and uses interesting examples to motivate and illustrate the methods. The statistical procedures and example data sets are available in an R package called ‘season’. Adrian Barnett is a senior research fellow at Queensland University of Technology, Australia. Annette Dobson is a Professor of Biostatistics at The University of Queensland, Australia. Both are experienced medical statisticians with a commitment to statistical education and have previously collaborated in research in the methodological developments and applications of biostatistics, especially to time series data. Among other projects, they worked together on revising the well-known textbook "An Introduction to Generalized Linear Models," third edition, Chapman Hall/CRC, 2008. In their new book they share their knowledge of statistical methods for examining seasonal patterns in health.

Cluster-based network model for time-course gene expression data

We propose a model-based approach to unify clustering and network modeling using time-course gene expression data. Specifically, our approach uses a mixture model to cluster genes. Genes within the same cluster share a similar expression profile. The network is built over cluster-specific expression profiles using state-space models. We discuss the application of our model to simulated data as well as to time-course gene expression data arising from animal models on prostate cancer progression. The latter application shows that with a combined statistical/bioinformatics analyses, we are able to extract gene-to-gene relationships supported by the literature as well as new plausible relationships.

Cancer-related symptom clusters for symptom management in outpatients after commencing adjuvant chemotherapy, at 6 months, and 12 months

Goals of work: The aim of this secondary data analysis was to investigate symptom clusters over time for symptom management of a patient group after commencing adjuvant chemotherapy. Materials and methods: A prospective longitudinal study of 219 cancer outpatients conducted within 1 month of commencing chemotherapy (T1), 6 months (T2), and 12 months (T3) later. Patients' distress levels were assessed for 42 physical symptoms on a clinician-modified Rotterdam Symptom Checklist. Symptom clusters were identified in exploratory factor analyses at each time. Symptom inclusion in clusters was determined from structure coefficients. Symptoms could be associated with multiple clusters. Stability over time was determined from symptom cluster composition and the proportion of symptoms in the initial symptom clusters replicated at later times. Main results Fatigue and daytime sleepiness were the most prevalent distressing symptoms over time. The median number of concurrent distressing symptoms approximated 7, over time. Five consistent clusters were identified at T1, 2, and T3. An additional two clusters were identified at 12 months, possibly due to less variation in distress levels. Weakness and fatigue were each associated with two, four, and five symptom clusters at T1, T2, and T3, respectively, potentially suggesting different causal mechanisms. Conclusion: Stability is a necessary attribute of symptom clusters, but definitional clarification is required. We propose that a core set of concurrent symptoms identifies each symptom cluster, signifying a common cause. Additional related symptoms may be included over time. Further longitudinal investigation is required to identify symptom clusters and the underlying causes.

Combining expert opinions in prior elicitation

A method of eliciting prior distributions for Bayesian models using expert knowledge is proposed. Elicitation is a widely studied problem, from a psychological perspective as well as from a statistical perspective. Here, we are interested in combining opinions from more than one expert using an explicitly model-based approach so that we may account for various sources of variation affecting elicited expert opinions. We use a hierarchical model to achieve this. We apply this approach to two problems. The first problem involves a food risk assessment problem involving modelling dose-response for Listeria monocytogenes contamination of mice. The second concerns the time taken by PhD students to submit their thesis in a particular school.

The impact of temperature on mortality in Tianjin, China : a case-crossover design with a distributed lag non-linear model

Background There has been increasing interest in assessing the impacts of temperature on mortality. However, few studies have used a case–crossover design to examine non-linear and distributed lag effects of temperature on mortality. Additionally, little evidence is available on the temperature-mortality relationship in China, or what temperature measure is the best predictor of mortality. Objectives To use a distributed lag non-linear model (DLNM) as a part of case–crossover design. To examine the non-linear and distributed lag effects of temperature on mortality in Tianjin, China. To explore which temperature measure is the best predictor of mortality; Methods: The DLNM was applied to a case¬−crossover design to assess the non-linear and delayed effects of temperatures (maximum, mean and minimum) on deaths (non-accidental, cardiopulmonary, cardiovascular and respiratory). Results A U-shaped relationship was consistently found between temperature and mortality. Cold effects (significantly increased mortality associated with low temperatures) were delayed by 3 days, and persisted for 10 days. Hot effects (significantly increased mortality associated with high temperatures) were acute and lasted for three days, and were followed by mortality displacement for non-accidental, cardiopulmonary, and cardiovascular deaths. Mean temperature was a better predictor of mortality (based on model fit) than maximum or minimum temperature. Conclusions In Tianjin, extreme cold and hot temperatures increased the risk of mortality. Results suggest that the effects of cold last longer than the effects of heat. It is possible to combine the case−crossover design with DLNMs. This allows the case−crossover design to flexibly estimate the non-linear and delayed effects of temperature (or air pollution) whilst controlling for season.

Improving cyclodiode - a risk factor analysis of complications

PURPOSE: The purpose of this study is to identify risk factors for developing complications following treatment of refractory glaucoma with transscleral diode laser cyclophotocoagulation (cyclodiode), to improve the safety profile of this treatment modality. METHOD: A retrospective analysis of 72 eyes from 70 patients who were treated with cyclodiode. RESULTS: The mean pre-treatment IOP was 37.0 mmHg (SD 11.0), with a mean post-treatment reduction in intraocular pressure (IOP) of 19.8 mmHg, and a mean IOP at last follow-up of 17.1 mmHg (SD 9.7). Mean total power delivered during treatment was 156.8 Joules (SD 82.7) over a mean of 1.3 treatments (SD 0.6). Sixteen eyes (22.2% of patients) developed complications from the treatment, with the most common being hypotony, occurring in 6 patients, including 4 with neovascular glaucoma. A higher pre-treatment IOP and higher mean total power delivery also were associated with higher complications. CONCLUSIONS: Cyclodiode is an effective treatment option for glaucoma that is refractory to other treatment options. By identifying risk factors for potential complications, cyclodiode can be modified accordingly for each patient to improve safety and efficacy.

Optimal image sample size for corneal nerve morphometry

Purpose Arbitrary numbers of corneal confocal microscopy images have been used for analysis of corneal subbasal nerve parameters under the implicit assumption that these are a representative sample of the central corneal nerve plexus. The purpose of this study is to present a technique for quantifying the number of random central corneal images required to achieve an acceptable level of accuracy in the measurement of corneal nerve fiber length and branch density. Methods Every possible combination of 2 to 16 images (where 16 was deemed the true mean) of the central corneal subbasal nerve plexus, not overlapping by more than 20%, were assessed for nerve fiber length and branch density in 20 subjects with type 2 diabetes and varying degrees of functional nerve deficit. Mean ratios were calculated to allow comparisons between and within subjects. Results In assessing nerve branch density, eight randomly chosen images not overlapping by more than 20% produced an average that was within 30% of the true mean 95% of the time. A similar sampling strategy of five images was 13% within the true mean 80% of the time for corneal nerve fiber length. Conclusions The “sample combination analysis” presented here can be used to determine the sample size required for a desired level of accuracy of quantification of corneal subbasal nerve parameters. This technique may have applications in other biological sampling studies.

Analysis of Cone-Beam CT using prior information

Treatment plans for conformal radiotherapy are based on an initial CT scan. The aim is to deliver the prescribed dose to the tumour, while minimising exposure to nearby organs. Recent advances make it possible to also obtain a Cone-Beam CT (CBCT) scan, once the patient has been positioned for treatment. A statistical model will be developed to compare these CBCT scans with the initial CT scan. Changes in the size, shape and position of the tumour and organs will be detected and quantified. Some progress has already been made in segmentation of prostate CBCT scans [1],[2],[3]. However, none of the existing approaches have taken full advantage of the prior information that is available. The planning CT scan is expertly annotated with contours of the tumour and nearby sensitive objects. This data is specific to the individual patient and can be viewed as a snapshot of spatial information at a point in time. There is an abundance of studies in the radiotherapy literature that describe the amount of variation in the relevant organs between treatments. The findings from these studies can form a basis for estimating the degree of uncertainty. All of this information can be incorporated as an informative prior into a Bayesian statistical model. This model will be developed using scans of CT phantoms, which are objects with known geometry. Thus, the accuracy of the model can be evaluated objectively. This will also enable comparison between alternative models.

Malaria antibody persistence correlates with duration of exposure

Background and Objectives  In Australia, the risk of transfusion-transmitted malaria is managed through the identification of ‘at-risk’ donors, antibody screening enzyme-linked immunoassay (EIA) and, if reactive, exclusion from fresh blood component manufacture. Donor management depends on the duration of exposure in malarious regions (>6 months: ‘Resident’, <6 months: ‘Visitor’) or a history of malaria diagnosis. We analysed antibody testing and demographic data to investigate antibody persistence dynamics. To assess the yield from retesting 3 years after an initial EIA reactive result, we estimated the proportion of donors who would become non-reactive over this period. Materials and Methods  Test results and demographic data from donors who were malaria EIA reactive were analysed. Time since possible exposure was estimated and antibody survival modelled. Results  Among seroreverters, the time since last possible exposure was significantly shorter in ‘Visitors’ than in ‘Residents’. The antibody survival modelling predicted 20% of previously EIA reactive ‘Visitors’, but only 2% of ‘Residents’ would become non-reactive within 3 years of their first reactive EIA. Conclusion  Antibody persistence in donors correlates with exposure category, with semi-immune ‘Residents’ maintaining detectable antibodies significantly longer than non-immune ‘Visitors’.

Prediction of age at menopause from assessment of ovarian reserve may be improved by using body mass index and smoking status

Objective: Menopause is the consequence of exhaustion of the ovarian follicular pool. AMH, an indirect hormonal marker of ovarian reserve, has been recently proposed as a predictor for age at menopause. Since BMI and smoking status are relevant independent factors associated with age at menopause we evaluated whether a model including all three of these variables could improve AMH-based prediction of age at menopause. Methods: In the present cohort study, participants were 375 eumenorrheic women aged 19–44 years and a sample of 2,635 Italian menopausal women. AMH values were obtained from the eumenorrheic women. Results: Regression analysis of the AMH data showed that a quadratic function of age provided a good description of these data plotted on a logarithmic scale, with a distribution of residual deviates that was not normal but showed significant leftskewness. Under the hypothesis that menopause can be predicted by AMH dropping below a critical threshold, a model predicting menopausal age was constructed from the AMH regression model and applied to the data on menopause. With the AMH threshold dependent on the covariates BMI and smoking status, the effects of these covariates were shown to be highly significant. Conclusions: In the present study we confirmed the good level of conformity between the distributions of observed and AMH-predicted ages at menopause, and showed that using BMI and smoking status as additional variables improves AMH-based prediction of age at menopause.

The relationship between anti-mullerian hormone in women receiving fertility assessments and age at menopause in subfertile women : evidence from large population studies

Context: Anti-Müllerian hormone (AMH) concentration reflects ovarian aging and is argued to be a useful predictor of age at menopause (AMP). It is hypothesized that AMH falling below a critical threshold corresponds to follicle depletion, which results in menopause. With this threshold, theoretical predictions of AMP can be made. Comparisons of such predictions with observed AMP from population studies support the role for AMH as a forecaster of menopause. Objective: The objective of the study was to investigate whether previous relationships between AMH and AMP are valid using a much larger data set. Setting: AMH was measured in 27 563 women attending fertility clinics. Study Design: From these data a model of age-related AMH change was constructed using a robust regression analysis. Data on AMP from subfertile women were obtained from the population-based Prospect-European Prospective Investigation into Cancer and Nutrition (Prospect- EPIC) cohort (n � 2249). By constructing a probability distribution of age at which AMH falls below a critical threshold and fitting this to Prospect-EPIC menopausal age data using maximum likelihood, such a threshold was estimated. Main Outcome: The main outcome was conformity between observed and predicted AMP. Results: To get a distribution of AMH-predicted AMP that fit the Prospect-EPIC data, we found the critical AMH threshold should vary among women in such a way that women with low age-specific AMH would have lower thresholds, whereas women with high age-specific AMH would have higher thresholds (mean 0.075 ng/mL; interquartile range 0.038–0.15 ng/mL). Such a varying AMH threshold for menopause is a novel and biologically plausible finding. AMH became undetectable (�0.2 ng/mL) approximately 5 years before the occurrence of menopause, in line with a previous report. Conclusions: The conformity of the observed and predicted distributions of AMP supports the hypothesis that declining population averages of AMH are associated with menopause, making AMH an excellent candidate biomarker for AMP prediction. Further research will help establish the accuracy of AMH levels to predict AMP within individuals.

Segmentation of cone-beam CT using a hidden Markov random field with informative priors

Purpose: Flat-detector, cone-beam computed tomography (CBCT) has enormous potential to improve the accuracy of treatment delivery in image-guided radiotherapy (IGRT). To assist radiotherapists in interpreting these images, we use a Bayesian statistical model to label each voxel according to its tissue type. Methods: The rich sources of prior information in IGRT are incorporated into a hidden Markov random field (MRF) model of the 3D image lattice. Tissue densities in the reference CT scan are estimated using inverse regression and then rescaled to approximate the corresponding CBCT intensity values. The treatment planning contours are combined with published studies of physiological variability to produce a spatial prior distribution for changes in the size, shape and position of the tumour volume and organs at risk (OAR). The voxel labels are estimated using the iterated conditional modes (ICM) algorithm. Results: The accuracy of the method has been evaluated using 27 CBCT scans of an electron density phantom (CIRS, Inc. model 062). The mean voxel-wise misclassification rate was 6.2%, with Dice similarity coefficient of 0.73 for liver, muscle, breast and adipose tissue. Conclusions: By incorporating prior information, we are able to successfully segment CBCT images. This could be a viable approach for automated, online image analysis in radiotherapy.

Segmentation of cone-beam CT using a hidden Markov random field with informative priors

Cone-beam computed tomography (CBCT) has enormous potential to improve the accuracy of treatment delivery in image-guided radiotherapy (IGRT). To assist radiotherapists in interpreting these images, we use a Bayesian statistical model to label each voxel according to its tissue type. The rich sources of prior information in IGRT are incorporated into a hidden Markov random field model of the 3D image lattice. Tissue densities in the reference CT scan are estimated using inverse regression and then rescaled to approximate the corresponding CBCT intensity values. The treatment planning contours are combined with published studies of physiological variability to produce a spatial prior distribution for changes in the size, shape and position of the tumour volume and organs at risk. The voxel labels are estimated using iterated conditional modes. The accuracy of the method has been evaluated using 27 CBCT scans of an electron density phantom. The mean voxel-wise misclassification rate was 6.2\%, with Dice similarity coefficient of 0.73 for liver, muscle, breast and adipose tissue. By incorporating prior information, we are able to successfully segment CBCT images. This could be a viable approach for automated, online image analysis in radiotherapy.

Pitfalls in the use of kappa when interpreting agreement between multiple raters in reliability studies

OBJECTIVE To compare different reliability coefficients (exact agreement, and variations of the kappa (generalised, Cohen's and Prevalence Adjusted and Biased Adjusted (PABAK))) for four physiotherapists conducting visual assessments of scapulae. DESIGN Inter-therapist reliability study. SETTING Research laboratory. PARTICIPANTS 30 individuals with no history of neck or shoulder pain were recruited with no obvious significant postural abnormalities. MAIN OUTCOME MEASURES Ratings of scapular posture were recorded in multiple biomechanical planes under four test conditions (at rest, and while under three isometric conditions) by four physiotherapists. RESULTS The magnitude of discrepancy between the two therapist pairs was 0.04 to 0.76 for Cohen's kappa, and 0.00 to 0.86 for PABAK. In comparison, the generalised kappa provided a score between the two paired kappa coefficients. The difference between mean generalised kappa coefficients and mean Cohen's kappa (0.02) and between mean generalised kappa and PABAK (0.02) were negligible, but the magnitude of difference between the generalised kappa and paired kappa within each plane and condition was substantial; 0.02 to 0.57 for Cohen's kappa and 0.02 to 0.63 for PABAK, respectively. CONCLUSIONS Calculating coefficients for therapist pairs alone may result in inconsistent findings. In contrast, the generalised kappa provided a coefficient close to the mean of the paired kappa coefficients. These findings support an assertion that generalised kappa may lead to a better representation of reliability between three or more raters and that reliability studies only calculating agreement between two raters should be interpreted with caution. However, generalised kappa may mask more extreme cases of agreement (or disagreement) that paired comparisons may reveal.

Constructing a clinical decision-making framework for image-guided radiotherapy using a Bayesian Network

A decision-making framework for image-guided radiotherapy (IGRT) is being developed using a Bayesian Network (BN) to graphically describe, and probabilistically quantify, the many interacting factors that are involved in this complex clinical process. Outputs of the BN will provide decision-support for radiation therapists to assist them to make correct inferences relating to the likelihood of treatment delivery accuracy for a given image-guided set-up correction. The framework is being developed as a dynamic object-oriented BN, allowing for complex modelling with specific sub-regions, as well as representation of the sequential decision-making and belief updating associated with IGRT. A prototype graphic structure for the BN was developed by analysing IGRT practices at a local radiotherapy department and incorporating results obtained from a literature review. Clinical stakeholders reviewed the BN to validate its structure. The BN consists of a sub-network for evaluating the accuracy of IGRT practices and technology. The directed acyclic graph (DAG) contains nodes and directional arcs representing the causal relationship between the many interacting factors such as tumour site and its associated critical organs, technology and technique, and inter-user variability. The BN was extended to support on-line and off-line decision-making with respect to treatment plan compliance. Following conceptualisation of the framework, the BN will be quantified. It is anticipated that the finalised decision-making framework will provide a foundation to develop better decision-support strategies and automated correction algorithms for IGRT.