Latent growth modeling of IRT versus CTT measured longitudinal latent variables.

Latent growth models are often used to measure individual trajectories representing change over time. The characteristics of the individual trajectories depend on the variability in the longitudinal outcomes. In many medical and epidemiological studies, the individual health outcomes cannot be observed directly and are indirectly observed through indicators (i.e. items of a questionnaire). An item response theory or a classical test theory measurement model is required, but the choice can influence the latent growth estimates. In this study, under various conditions, this influence is directly assessed by estimating latent growth parameters on a common scale for item response theory and classical test theory using a novel plausible value method in combination with Markov chain Monte Carlo. The latent outcomes are considered missing data and plausible values are generated from the corresponding posterior distribution, separately for item response theory and classical test theory. These plausible values are linearly transformed to a common scale. A Markov chain Monte Carlo method was developed to simultaneously estimate the latent growth and measurement model parameters using this plausible value technique. It is shown that estimated individual trajectories using item response theory, compared to classical test theory to measure outcomes, provide a more detailed description of individual change over time, since item response patterns (item response theory) are more informative about the health measurements than sum scores (classical test theory).

Mixture randomized item-response modeling: a smoking behavior validation study.

Misleading response behavior is expected in medical settings where incriminating behavior is negatively related to the recovery from a disease. In the present study, lung patients feel social and professional pressure concerning smoking and experience questions about smoking behavior as sensitive and tend to conceal embarrassing or threatening information. The randomized item-response survey method is expected to improve the accuracy of self-reports as individual item responses are masked and only randomized item responses are observed. We explored the validation of the randomized item-response technique in a unique experimental study. Therefore, we administered a new multi-item measure assessing smoking behavior by using a treatment-control design (randomized response (RR) or direct questioning). After the questionnaire, we administered a breath test by using a carbon monoxide (CO) monitor to determine the smoking status of the patient. We used the response data to measure the individual smoking behavior by using a mixture item-response model. It is shown that the detected smokers scored significantly higher in the RR condition compared with the directly questioned condition. We proposed a Bayesian latent variable framework to evaluate the diagnostic test accuracy of the questionnaire using the randomized-response technique, which is based on the posterior densities of the subject's smoking behavior scores together with the breath test measurements. For different diagnostic test thresholds, we obtained moderate posterior mean estimates of sensitivity and specificity by observing a limited number of discrete randomized item responses.

Bayesian tests of measurement invariance.

Random item effects models provide a natural framework for the exploration of violations of measurement invariance without the need for anchor items. Within the random item effects modelling framework, Bayesian tests (Bayes factor, deviance information criterion) are proposed which enable multiple marginal invariance hypotheses to be tested simultaneously. The performance of the tests is evaluated with a simulation study which shows that the tests have high power and low Type I error rate. Data from the European Social Survey are used to test for measurement invariance of attitude towards immigrant items and to show that background information can be used to explain cross-national variation in item functioning.

A Multivariate Multilevel Approach to the Modeling of Accuracy and Speed of Test Takers.

Response times on test items are easily collected in modern computerized testing. When collecting both (binary) responses and (continuous) response times on test items, it is possible to measure the accuracy and speed of test takers. To study the relationships between these two constructs, the model is extended with a multivariate multilevel regression structure which allows the incorporation of covariates to explain the variance in speed and accuracy between individuals and groups of test takers. A Bayesian approach with Markov chain Monte Carlo (MCMC) computation enables straightforward estimation of all model parameters. Model-specific implementations of a Bayes factor (BF) and deviance information criterium (DIC) for model selection are proposed which are easily calculated as byproducts of the MCMC computation. Both results from simulation studies and real-data examples are given to illustrate several novel analyses possible with this modeling framework.

A Box-Cox normal model for response times.

The log-transform has been a convenient choice in response time modelling on test items. However, motivated by a dataset of the Medical College Admission Test where the lognormal model violated the normality assumption, the possibilities of the broader class of Box-Cox transformations for response time modelling are investigated. After an introduction and an outline of a broader framework for analysing responses and response times simultaneously, the performance of a Box-Cox normal model for describing response times is investigated using simulation studies and a real data example. A transformation-invariant implementation of the deviance information criterium (DIC) is developed that allows for comparing model fit between models with different transformation parameters. Showing an enhanced description of the shape of the response time distributions, its application in an educational measurement context is discussed at length.

Multilevel IRT using dichotomous and polytomous response data.

A structural multilevel model is presented where some of the variables cannot be observed directly but are measured using tests or questionnaires. Observed dichotomous or ordinal polytomous response data serve to measure the latent variables using an item response theory model. The latent variables can be defined at any level of the multilevel model. A Bayesian procedure Markov chain Monte Carlo (MCMC), to estimate all parameters simultaneously is presented. It is shown that certain model checks and model comparisons can be done using the MCMC output. The techniques are illustrated using a simulation study and an application involving students' achievements on a mathematics test and test results regarding management characteristics of teachers and principles.

Methanol-water solutions: a bi-percolating liquid mixture.

An extensive series of neutron diffraction experiments and molecular dynamics simulations has shown that mixtures of methanol and water exhibit extended structures in solution despite the components being fully miscible in all proportions. Of particular interest is a concentration region (methanol mole fraction between 0.27 and 0.54) where both methanol and water appear to form separate, percolating networks. This is the concentration range where many transport properties and thermodynamic excess functions reach extremal values. The observed concentration dependence of several of these material properties of the solution may therefore have a structural origin.

Stochastic EM for estimating the parameters of a multilevel IRT model.

An item response theory (IRT) model is used as a measurement error model for the dependent variable of a multilevel model. The dependent variable is latent but can be measured indirectly by using tests or questionnaires. The advantage of using latent scores as dependent variables of a multilevel model is that it offers the possibility of modelling response variation and measurement error and separating the influence of item difficulty and ability level. The two-parameter normal ogive model is used for the IRT model. It is shown that the stochastic EM algorithm can be used to estimate the parameters which are close to the maximum likelihood estimates. This algorithm is easily implemented. The estimation procedure will be compared to an implementation of the Gibbs sampler in a Bayesian framework. Examples using real data are given.

Publets: clinical judgement on the web.

The Internet is now a major channel for publishing medical research data and documents, including clinical practice guidelines. It is now possible to capture guidelines in a computer interpretable form opening up the capability of using the internet (and intra/extranets etc.) to deliver patient-specific advice and other services. A development lifecycle and technology for publishing and delivering services at the point of care ("publets") are described. As with all new technologies, however, these new methods entail risks as well as opportunities. The paper closes with a discussion of quality requirements and an argument that publets should include a safety case as an integral part of their content.

A prospective pilot study to evaluate a new dental assessment and treatment paradigm for patients scheduled to undergo intensive chemotherapy for cancer.

BACKGROUND: Patients scheduled to receive chemotherapy frequently undergo pretherapy dental treatment to eliminate potential sources of odontogenic infection. A prospective study was conducted to assess a new protocol emphasizing minimal pretherapy dental treatment. METHODS: Forty-eight consecutive patients diagnosed with solid or hematologic neoplasms underwent dental examination prior to intensive chemotherapy. All chronic dental pathology was scored as either mild-to-moderate or severe based on the likelihood of conversion to an acute state during chemotherapy. No pretherapy dental treatment was given to patients with chronic dental disease. Intertherapy dental complications and the overall impact on chemotherapy outcomes were assessed. RESULTS: Thirty-eight patients (79%) were diagnosed with pretherapy chronic dental pathology. Twenty-one of these patients (44% of the total population) were identified as having severe pathology and considered at risk for acute intertherapy dental complications. Two patients (4%) experienced acute intertherapy episodes, each presenting as oral abscesses. In both cases, resolution was achieved with antibiotics without interruption of chemotherapy. Oncologic treatment outcomes for all patients were judged to be unaffected by either the presence of chronic pretherapy dental disease or acute intertherapy exacerbations of these disease states. CONCLUSIONS: These results demonstrate that patients with chronic dental pathology can safely proceed with chemotherapy without dental intervention, as conversion of chronic dental disease to an acute state during chemotherapy occurs infrequently. If intertherapy dental infections do arise, they can be managed effectively without interrupting therapy or adversely affecting oncologic treatment outcomes.

Artificial intelligence in molecular biology: a review and assessment.

Over the past ten years, molecular biologists and computer scientists have experimented with various computational methods developed in artificial intelligence (AI). AI research has yielded a number of novel technologies, which are typified by an emphasis on symbolic (non-numerical) programming methods aimed at problems which are not amenable to classical algorithmic solutions. Prominent examples include knowledge-based and expert systems, qualitative simulation and artificial neural networks and other automated learning techniques. These methods have been applied to problems in data analysis, construction of advanced databases and modelling of biological systems. Practical results are now being obtained, notably in the recognition of active genes in genomic sequences, the assembly of physical and genetic maps and protein structure prediction. This paper outlines the principal methods, surveys the findings to date, and identifies the promising trends and current limitations.

Serum cortisol levels predict infarct size and patient mortality.

We have investigated prospectively the serum cortisol response to acute myocardial infarction in 70 consecutive patients admitted to a coronary care unit and we have shown that the levels are significantly raised early in the course of the illness and prior to elevation of the cardiac specific enzyme fraction, creatine kinase MB. The magnitude of the cortisol response is related to the size of the ensuing infarction (rs = 0.54) as calculated from the total creatine kinase MB release (P < 0.001) and very high levels (> 2000 mumol/l) are predictive of mortality (P < 0.05). Serum cortisol levels may have a role in the early identification of myocardial infarction and in predicting those patients with a poor prognosis.

Primary leiomyosarcoma of the heart: a rare cause of obstruction of the left ventricular outflow tract.

Primary cardiac tumours are rare and frequently only diagnosed post-mortem. Recent improvements in non-invasive imaging techniques have led to an increasing number being diagnosed in life, allowing surgical resection. We report a primary leiomyosarcoma presenting with obstruction of the left ventricular outflow tract.

Microalbuminuria is an early response following acute myocardial infarction.

Ninety-six patients admitted to two coronary care units with suspected acute myocardial infarction were studied. The diagnosis was confirmed in 44, the remaining 52 were used as a control group. The first urine passed after admission, together with early morning urines on the following 3 days, were saved in all patients. Urinary albumin and IgG were measured by automated immunoturbidimetry and expressed as the protein creatinine ratio in mg.mmol-1. The log mean (SD) albumin creatinine ratios for the first urine passed in the myocardial infarction and non-myocardial infarction patient groups were 6.2(4.2) and 1.3(3.4) respectively. The difference in log mean albumin creatinine ratio was 4.9 mg.mmol-1, 95% CI 3.4 to 6.2 mg.mmol-1; t = 6.127 df = 94, P less than 0.0001. The median IgG creatinine ratio for the first urine passed after admission in myocardial infarction patients was 1.0 mg.mmol-1 (95% CI 0.5 to 1.2) and for non-myocardial infarction patients 0.3 (95% CI 0.2 to 0.4). Increased urinary protein excretion appears to be an early and proportional response to acute myocardial infarction.

Non Q wave infarction: exercise test characteristics, coronary anatomy, and prognosis.

The exercise test characteristics, coronary anatomy, and prognosis of patients discharged after non Q wave myocardial infarction were compared with those in whom Q wave infarction occurred. Of the 339 patients studied, all of whom were less than or equal to 70 years, 87 (26%) had had a non Q wave infarction. There were no significant differences in the exercise test characteristics between the two groups, and in those 149 patients in whom angiography was performed triple vessel disease was present in 36/114 (32%) of the Q wave group and 9/35 (26%) of the non Q wave group. The infarct related artery was more often patent in the non Q wave group (27/35 (77%] than in the Q wave group (53/114 (46%]. The one year mortality and the reinfarction and angina rates were similar in the two groups and the exercise test remained a good discriminator for predicting patients at risk of future cardiac events in both groups. In view of the similar outcome and severity of coronary disease in those aged less than or equal to 70 with non Q wave infarcts, the distinction between Q and non Q wave infarction need not influence management decisions in patients after myocardial infarction.

Persistent enteral infections with adenovirus types 1 and 2 in infants: no evidence of reinfection.

Isolates of adenovirus types 1 and 2, obtained from 11 infants with prolonged faecal excretion (up to 515 days), were compared by DNA restriction analysis with seven standard endonucleases which recognize hexanucleotides and two additional endonucleases which recognize tetranucleotides. In all instances identical genome types were identified in isolates obtained early and late after infection. Our interpretation of these data is that a chronic persistent infection occurred in these children, and not a reinfection with the same serotype.

Silent ischaemia following myocardial infarction: frequency, characteristics and prognosis.

Pre-discharge exercise tests were performed in 359 survivors of an acute myocardial infarction to determine the frequency, characteristics and prognostic implications of silent ischaemia. Tests were negative in 152 patients (42%), silent ischaemia was observed in 103 (29%) and painful ischaemia in 82 (23%). Heart rates at the development of ischaemia and the final double products were similar in both ischaemic groups but patients with silent ischaemia were able to exercise for longer (13.1 +/- 0.5 min) than those with painful ischaemia (9.3 +/- 0.5 min; P less than 0.0001). The 12 month mortality rose from 2% in patients with a negative test, to 4% in those with silent ischaemia and to 8% in those with painful ischaemia. Re-infarction rates increased similarly across the groups (3%, 8% and 18% respectively). Patients with silent ischaemia subsequently developed angina more frequently (47%) than those with negative tests (16%; P less than 0.001). These results suggest that exercise-induced silent ischaemia following myocardial infarction was common, occurring in 29% of patients. Although the final myocardial oxygen consumption was similar in both ischaemic groups those with silent ischaemia were able to exercise for longer. Finally silent ischaemia conferred an intermediate risk of death or re-infarction and was a strong predictor of subsequent angina pectoris.