Methodology for biomarker discovery with reproducibility in microbiome data using machine learning.

BACKGROUND: In recent years, human microbiome studies have received increasing attention as this field is considered a potential source for clinical applications. With the advancements in omics technologies and AI, research focused on the discovery for potential biomarkers in the human microbiome using machine learning tools has produced positive outcomes. Despite the promising results, several issues can still be found in these studies such as datasets with small number of samples, inconsistent results, lack of uniform processing and methodologies, and other additional factors lead to lack of reproducibility in biomedical research. In this work, we propose a methodology that combines the DADA2 pipeline for 16s rRNA sequences processing and the Recursive Ensemble Feature Selection (REFS) in multiple datasets to increase reproducibility and obtain robust and reliable results in biomedical research. RESULTS: Three experiments were performed analyzing microbiome data from patients/cases in Inflammatory Bowel Disease (IBD), Autism Spectrum Disorder (ASD), and Type 2 Diabetes (T2D). In each experiment, we found a biomarker signature in one dataset and applied to 2 other as further validation. The effectiveness of the proposed methodology was compared with other feature selection methods such as K-Best with F-score and random selection as a base line. The Area Under the Curve (AUC) was employed as a measure of diagnostic accuracy and used as a metric for comparing the results of the proposed methodology with other feature selection methods. Additionally, we use the Matthews Correlation Coefficient (MCC) as a metric to evaluate the performance of the methodology as well as for comparison with other feature selection methods. CONCLUSIONS: We developed a methodology for reproducible biomarker discovery for 16s rRNA microbiome sequence analysis, addressing the issues related with data dimensionality, inconsistent results and validation across independent datasets. The findings from the three experiments, across 9 different datasets, show that the proposed methodology achieved higher accuracy compared to other feature selection methods. This methodology is a first approach to increase reproducibility, to provide robust and reliable results.

Developing a personalized remote patient monitoring algorithm: a proof-of-concept in heart failure.

Aims: Non-invasive remote patient monitoring is an increasingly popular technique to aid clinicians in the early detection of worsening heart failure (HF) alongside regular follow-ups. However, previous studies have shown mixed results in the performance of such systems. Therefore, we developed and evaluated a personalized monitoring algorithm aimed at increasing positive-predictive-value (PPV) (i.e. alarm quality) and compared performance with simple rule-of-thumb and moving average convergence-divergence algorithms (MACD). Methods and results: In this proof-of-concept study, the developed algorithm was applied to retrospective data of daily bodyweight, heart rate, and systolic blood pressure of 74 HF-patients with a median observation period of 327 days (IQR: 183 days), during which 31 patients experienced 64 clinical worsening HF episodes. The algorithm combined information on both the monitored patients and a group of stable HF patients, and is increasingly personalized over time, using linear mixed-effect modelling and statistical process control charts. Optimized on alarm quality, heart rate showed the highest PPV (Personalized: 92%, MACD: 2%, Rule-of-thumb: 7%) with an F1 score of (Personalized: 28%, MACD: 6%, Rule-of-thumb: 8%). Bodyweight demonstrated the lowest PPV (Personalized: 16%, MACD: 0%, Rule-of-thumb: 6%) and F1 score (Personalized: 10%, MACD: 3%, Rule-of-thumb: 7%) overall compared methods. Conclusion: The personalized algorithm with flexible patient-tailored thresholds led to higher PPV, and performance was more sensitive compared to common simple monitoring methods (rule-of-thumb and MACD). However, many episodes of worsening HF remained undetected. Heart rate and systolic blood pressure monitoring outperformed bodyweight in predicting worsening HF. The algorithm source code is publicly available for future validation and improvement.

A robust mRNA signature obtained via recursive ensemble feature selection predicts the responsiveness of omalizumab in moderate-to-severe asthma.

BACKGROUND: Not being well controlled by therapy with inhaled corticosteroids and long-acting ß2 agonist bronchodilators is a major concern for severe-asthma patients. The current treatment option for these patients is the use of biologicals such as anti-IgE treatment, omalizumab, as an add-on therapy. Despite the accepted use of omalizumab, patients do not always benefit from it. Therefore, there is a need to identify reliable biomarkers as predictors of omalizumab response. METHODS: Two novel computational algorithms, machine-learning based Recursive Ensemble Feature Selection (REFS) and rule-based algorithm Logic Explainable Networks (LEN), were used on open accessible mRNA expression data from moderate-to-severe asthma patients to identify genes as predictors of omalizumab response. RESULTS: With REFS, the number of features was reduced from 28,402 genes to 5 genes while obtaining a cross-validated accuracy of 0.975. The 5 responsiveness predictive genes encode the following proteins: Coiled-coil domain- containing protein 113 (CCDC113), Solute Carrier Family 26 Member 8 (SLC26A), Protein Phosphatase 1 Regulatory Subunit 3D (PPP1R3D), C-Type lectin Domain Family 4 member C (CLEC4C) and LOC100131780 (not annotated). The LEN algorithm found 4 identical genes with REFS: CCDC113, SLC26A8 PPP1R3D and LOC100131780. Literature research showed that the 4 identified responsiveness predicting genes are associated with mucosal immunity, cell metabolism, and airway remodeling. CONCLUSION AND CLINICAL RELEVANCE: Both computational methods show 4 identical genes as predictors of omalizumab response in moderate-to-severe asthma patients. The obtained high accuracy indicates that our approach has potential in clinical settings. Future studies in relevant cohort data should validate our computational approach.

Identifying multivariate disease trajectories and potential phenotypes of early knee osteoarthritis in the CHECK cohort.

OBJECTIVE: To gain better understanding of osteoarthritis (OA) heterogeneity and its predictors for distinguishing OA phenotypes. This could provide the opportunity to tailor prevention and treatment strategies and thus improve care. DESIGN: Ten year follow-up data from CHECK (1002 early-OA subjects with first general practitioner visit for complaints ≤6 months before inclusion) was used. Data were collected on WOMAC (pain, function, stiffness), quantitative radiographic tibiofemoral (TF) OA characteristics, and semi-quantitative radiographic patellofemoral (PF) OA characteristics. Using functional data analysis, distinctive sets of trajectories were identified for WOMAC, TF and PF characteristics, based on model fit and clinical interpretation. The probabilities of knee membership to each trajectory were used in hierarchical cluster analyses to derive knee OA phenotypes. The number and composition of potential phenotypes was selected again based on model fit (silhouette score) and clinical interpretation. RESULTS: Five trajectories representing different constant levels or changing WOMAC scores were identified. For TF and PF OA, eight and six trajectories respectively were identified based on (changes in) joint space narrowing, osteophytes and sclerosis. Combining the probabilities of knees belonging to these different trajectories resulted in six clusters ('phenotypes') of knees with different degrees of functional (WOMAC) and radiographic (PF) parameters; TF parameters were found not to significantly contribute to clustering. Including baseline characteristics as well resulted in eight clusters of knees, dominated by sex, menopausal status and WOMAC scores, with only limited contribution of PF features. CONCLUSIONS: Several stable and progressive trajectories of OA symptoms and radiographic features were identified, resulting in phenotypes with relatively independent symptomatic and radiographic features. Sex and menopausal status may be especially important when phenotyping knee OA patients, while radiographic features contributed less. Possible phenotypes were identified that, after validation, could aid personalized treatments and patients selection.

Performance of active learning models for screening prioritization in systematic reviews: a simulation study into the Average Time to Discover relevant records.

BACKGROUND: Conducting a systematic review demands a significant amount of effort in screening titles and abstracts. To accelerate this process, various tools that utilize active learning have been proposed. These tools allow the reviewer to interact with machine learning software to identify relevant publications as early as possible. The goal of this study is to gain a comprehensive understanding of active learning models for reducing the workload in systematic reviews through a simulation study. METHODS: The simulation study mimics the process of a human reviewer screening records while interacting with an active learning model. Different active learning models were compared based on four classification techniques (naive Bayes, logistic regression, support vector machines, and random forest) and two feature extraction strategies (TF-IDF and doc2vec). The performance of the models was compared for six systematic review datasets from different research areas. The evaluation of the models was based on the Work Saved over Sampling (WSS) and recall. Additionally, this study introduces two new statistics, Time to Discovery (TD) and Average Time to Discovery (ATD). RESULTS: The models reduce the number of publications needed to screen by 91.7 to 63.9% while still finding 95% of all relevant records (WSS@95). Recall of the models was defined as the proportion of relevant records found after screening 10% of of all records and ranges from 53.6 to 99.8%. The ATD values range from 1.4% till 11.7%, which indicate the average proportion of labeling decisions the researcher needs to make to detect a relevant record. The ATD values display a similar ranking across the simulations as the recall and WSS values. CONCLUSIONS: Active learning models for screening prioritization demonstrate significant potential for reducing the workload in systematic reviews. The Naive Bayes + TF-IDF model yielded the best results overall. The Average Time to Discovery (ATD) measures performance of active learning models throughout the entire screening process without the need for an arbitrary cut-off point. This makes the ATD a promising metric for comparing the performance of different models across different datasets.

A Perspective on a Quality Management System for AI/ML-Based Clinical Decision Support in Hospital Care.

Although many artificial intelligence (AI) and machine learning (ML) based algorithms are being developed by researchers, only a small fraction has been implemented in clinical-decision support (CDS) systems for clinical care. Healthcare organizations experience significant barriers implementing AI/ML models for diagnostic, prognostic, and monitoring purposes. In this perspective, we delve into the numerous and diverse quality control measures and responsibilities that emerge when moving from AI/ML-model development in a research environment to deployment in clinical care. The Sleep-Well Baby project, a ML-based monitoring system, currently being tested at the neonatal intensive care unit of the University Medical Center Utrecht, serves as a use-case illustrating our personal learning journey in this field. We argue that, in addition to quality assurance measures taken by the manufacturer, user responsibilities should be embedded in a quality management system (QMS) that is focused on life-cycle management of AI/ML-CDS models in a medical routine care environment. Furthermore, we highlight the strong similarities between AI/ML-CDS models and in vitro diagnostic devices and propose to use ISO15189, the quality guideline for medical laboratories, as inspiration when building a QMS for AI/ML-CDS usage in the clinic. We finally envision a future in which healthcare institutions run or have access to a medical AI-lab that provides the necessary expertise and quality assurance for AI/ML-CDS implementation and applies a QMS that mimics the ISO15189 used in medical laboratories.

Life-threatening ventricular arrhythmia prediction in patients with dilated cardiomyopathy using explainable electrocardiogram-based deep neural networks.

AIMS: While electrocardiogram (ECG) characteristics have been associated with life-threatening ventricular arrhythmias (LTVA) in dilated cardiomyopathy (DCM), they typically rely on human-derived parameters. Deep neural networks (DNNs) can discover complex ECG patterns, but the interpretation is hampered by their 'black-box' characteristics. We aimed to detect DCM patients at risk of LTVA using an inherently explainable DNN. METHODS AND RESULTS: In this two-phase study, we first developed a variational autoencoder DNN on more than 1 million 12-lead median beat ECGs, compressing the ECG into 21 different factors (F): FactorECG. Next, we used two cohorts with a combined total of 695 DCM patients and entered these factors in a Cox regression for the composite LTVA outcome, which was defined as sudden cardiac arrest, spontaneous sustained ventricular tachycardia, or implantable cardioverter-defibrillator treated ventricular arrhythmia. Most patients were male (n = 442, 64%) with a median age of 54 years [interquartile range (IQR) 44-62], and median left ventricular ejection fraction of 30% (IQR 23-39). A total of 115 patients (16.5%) reached the study outcome. Factors F8 (prolonged PR-interval and P-wave duration, P < 0.005), F15 (reduced P-wave height, P = 0.04), F25 (increased right bundle branch delay, P = 0.02), F27 (P-wave axis P < 0.005), and F32 (reduced QRS-T voltages P = 0.03) were significantly associated with LTVA. CONCLUSION: Inherently explainable DNNs can detect patients at risk of LTVA which is mainly driven by P-wave abnormalities.

Privacy-preserving local analysis of digital trace data: A proof-of-concept.

We present PORT, a software platform for local data extraction and analysis of digital trace data. While digital trace data hold huge potential for social-scientific discovery, their most useful parts have been unattainable for scientists because of privacy concerns and prohibitive access to application programming interfaces. Recently, a workflow was introduced allowing citizens to donate their digital traces to scientists. In this workflow, citizens' digital traces are processed locally on their machines before providing informed consent to share a subset of the data with researchers. In this paper, we present the newly developed software PORT that implements the local processing part of this workflow, protecting privacy by shielding sensitive data from outside observers, including the researchers themselves. When using PORT, researchers can tailor the local processing procedure suitable to the data download package and research question. Thus, PORT enables a host of potential applications of social data science to hitherto unobtainable data.

A permutation test for assessing the presence of individual differences in treatment effects.

An important goal of personalized medicine is to identify heterogeneity in treatment effects and then use that heterogeneity to target the intervention to those most likely to benefit. Heterogeneity is assessed using the predicted individual treatment effects framework, and a permutation test is proposed to establish if significant heterogeneity is present given the covariates and predictive model or algorithm used for predicted individual treatment effects. We first show evidence for heterogeneity in the effects of treatment across an illustrative example data set. We then use simulations with two different predictive methods (linear regression model and Random Forests) to show that the permutation test has adequate type-I error control. Next, we use an example dataset as the basis for simulations to demonstrate the ability of the permutation test to find heterogeneity in treatment effects for a predicted individual treatment effects estimate as a function of both effect size and sample size. We find that the proposed test has good power for detecting heterogeneity in treatment effects when the heterogeneity was due primarily to a single predictor, or when it was spread across the predictors. Power was found to be greater for predictions from a linear model than from random forests. This non-parametric permutation test can be used to test for significant differences across individuals in predicted individual treatment effects obtained with a given set of covariates using any predictive method with no additional assumptions.

Automatic Prediction of Recurrence of Major Cardiovascular Events: A Text Mining Study Using Chest X-Ray Reports.

Methods: We used EHR data of patients included in the Second Manifestations of ARTerial disease (SMART) study. We propose a deep learning-based multimodal architecture for our text mining pipeline that integrates neural text representation with preprocessed clinical predictors for the prediction of recurrence of major cardiovascular events in cardiovascular patients. Text preprocessing, including cleaning and stemming, was first applied to filter out the unwanted texts from X-ray radiology reports. Thereafter, text representation methods were used to numerically represent unstructured radiology reports with vectors. Subsequently, these text representation methods were added to prediction models to assess their clinical relevance. In this step, we applied logistic regression, support vector machine (SVM), multilayer perceptron neural network, convolutional neural network, long short-term memory (LSTM), and bidirectional LSTM deep neural network (BiLSTM). Results: We performed various experiments to evaluate the added value of the text in the prediction of major cardiovascular events. The two main scenarios were the integration of radiology reports (1) with classical clinical predictors and (2) with only age and sex in the case of unavailable clinical predictors. In total, data of 5603 patients were used with 5-fold cross-validation to train the models. In the first scenario, the multimodal BiLSTM (MI-BiLSTM) model achieved an area under the curve (AUC) of 84.7%, misclassification rate of 14.3%, and F1 score of 83.8%. In this scenario, the SVM model, trained on clinical variables and bag-of-words representation, achieved the lowest misclassification rate of 12.2%. In the case of unavailable clinical predictors, the MI-BiLSTM model trained on radiology reports and demographic (age and sex) variables reached an AUC, F1 score, and misclassification rate of 74.5%, 70.8%, and 20.4%, respectively. Conclusions: Using the case study of routine care chest X-ray radiology reports, we demonstrated the clinical relevance of integrating text features and classical predictors in our text mining pipeline for cardiovascular risk prediction. The MI-BiLSTM model with word embedding representation appeared to have a desirable performance when trained on text data integrated with the clinical variables from the SMART study. Our results mined from chest X-ray reports showed that models using text data in addition to laboratory values outperform those using only known clinical predictors.

Automatic multilabel detection of ICD10 codes in Dutch cardiology discharge letters using neural networks.

Standard reference terminology of diagnoses and risk factors is crucial for billing, epidemiological studies, and inter/intranational comparisons of diseases. The International Classification of Disease (ICD) is a standardized and widely used method, but the manual classification is an enormously time-consuming endeavor. Natural language processing together with machine learning allows automated structuring of diagnoses using ICD-10 codes, but the limited performance of machine learning models, the necessity of gigantic datasets, and poor reliability of terminal parts of these codes restricted clinical usability. We aimed to create a high performing pipeline for automated classification of reliable ICD-10 codes in the free medical text in cardiology. We focussed on frequently used and well-defined three- and four-digit ICD-10 codes that still have enough granularity to be clinically relevant such as atrial fibrillation (I48), acute myocardial infarction (I21), or dilated cardiomyopathy (I42.0). Our pipeline uses a deep neural network known as a Bidirectional Gated Recurrent Unit Neural Network and was trained and tested with 5548 discharge letters and validated in 5089 discharge and procedural letters. As in clinical practice discharge letters may be labeled with more than one code, we assessed the single- and multilabel performance of main diagnoses and cardiovascular risk factors. We investigated using both the entire body of text and only the summary paragraph, supplemented by age and sex. Given the privacy-sensitive information included in discharge letters, we added a de-identification step. The performance was high, with F1 scores of 0.76-0.99 for three-character and 0.87-0.98 for four-character ICD-10 codes, and was best when using complete discharge letters. Adding variables age/sex did not affect results. For model interpretability, word coefficients were provided and qualitative assessment of classification was manually performed. Because of its high performance, this pipeline can be useful to decrease the administrative burden of classifying discharge diagnoses and may serve as a scaffold for reimbursement and research applications.

Propensity score-based analysis of long-term outcome of patients on HeartWare and HeartMate 3 left ventricular assist device support.

AIMS: Left ventricular assist device therapy has become the cornerstone in the treatment of end-stage heart failure and is increasingly used as destination therapy next to bridge to transplant or recovery. HeartMate 3 (HM3) and HeartWare (HVAD) are centrifugal continuous flow devices implanted intrapericardially and most commonly used worldwide. No randomized controlled trials have been performed yet. Analysis based on large registries may be considered as the best alternative but has the disadvantage of different standard of care between centres and missing data. Bias is introduced, because the decision which device to use was not random, even more so because many centres use only one type of left ventricular assist device. Therefore, we performed a propensity score (PS)-based analysis of long-term clinical outcome of patients that received HM3 or HVAD in a single centre. METHODS AND RESULTS: Between December 2010 and December 2019, 100 patients received HVAD and 81 patients HM3 as primary implantation at the University Medical Centre Utrecht. We performed PS matching with an extensive set of covariates, resulting in 112 matched patients with a median follow-up of 28 months. After PS matching, survival was not significantly different (P = 0.21) but was better for HM3. The cumulative incidences for haemorrhagic stroke (P = 0.01) and pump thrombosis (P = 0.02) were significantly higher for HVAD patients. The cumulative incidences for major bleeding, ischaemic stroke, right heart failure, and driveline infection were not different between the groups. We found no interaction between the surgeon who performed the implantation and survival (P = 0.59, P = 0.78, and P = 0.89). Sensitivity analysis was performed, by PS matching without patients on preoperative temporary support resulting in 74 matched patients. This also resulted in a non-significant difference in survival (P = 0.07). The PS-adjusted Cox regression showed a worse but non-significant (P = 0.10) survival for HVAD patients with hazard ratio 1.71 (95% confidence interval 0.91-3.24). CONCLUSIONS: Survival was not significantly different between both groups after PS matching, but was better for HM3, with a significantly lower incidence of haemorrhagic stroke and pump thrombosis for HM3. These results need to be interpreted carefully, because matching may have introduced greater imbalance on unmeasured covariates. A multicentre approach of carefully selected centres is recommended to enlarge the number of matched patients.

A data mining-based cross-industry process for predicting major bleeding in mechanical circulatory support.

Aims: Over a third of patients, treated with mechanical circulatory support (MCS) for end-stage heart failure, experience major bleeding. Currently, the prediction of a major bleeding in the near future is difficult because of many contributing factors. Predictive analytics using data mining could help calculating the risk of bleeding; however, its application is generally reserved for experienced researchers on this subject. We propose an easily applicable data mining tool to predict major bleeding in MCS patients. Methods and results: All data of electronic health records of MCS patients in the University Medical Centre Utrecht were included. Based on the cross-industry standard process for data mining (CRISP-DM) methodology, an application named Auto-Crisp was developed. Auto-Crisp was used to evaluate the predictive models for a major bleeding in the next 3, 7, and 30 days after the first 30 days post-operatively following MCS implantation. The performance of the predictive models is investigated by the area under the curve (AUC) evaluation measure. In 25.6% of 273 patients, a total of 142 major bleedings occurred during a median follow-up period of 542 [interquartile range (IQR) 205-1044] days. The best predictive models assessed by Auto-Crisp had AUC values of 0.792, 0.788, and 0.776 for bleedings in the next 3, 7, and 30 days, respectively. Conclusion: The Auto-Crisp-based predictive model created in this study had an acceptable performance to predict major bleeding in MCS patients in the near future. However, further validation of the application is needed to evaluate Auto-Crisp in other research projects.

Identification of predicted individual treatment effects in randomized clinical trials.

In most medical research, treatment effectiveness is assessed using the average treatment effect or some version of subgroup analysis. The practice of individualized or precision medicine, however, requires new approaches that predict how an individual will respond to treatment, rather than relying on aggregate measures of effect. In this study, we present a conceptual framework for estimating individual treatment effects, referred to as predicted individual treatment effects. We first apply the predicted individual treatment effect approach to a randomized controlled trial designed to improve behavioral and physical symptoms. Despite trivial average effects of the intervention, we show substantial heterogeneity in predicted individual treatment response using the predicted individual treatment effect approach. The predicted individual treatment effects can be used to predict individuals for whom the intervention may be most effective (or harmful). Next, we conduct a Monte Carlo simulation study to evaluate the accuracy of predicted individual treatment effects. We compare the performance of two methods used to obtain predictions: multiple imputation and non-parametric random decision trees. Results showed that, on average, both predictive methods produced accurate estimates at the individual level; however, the random decision trees tended to underestimate the predicted individual treatment effect for people at the extreme and showed more variability in predictions across repetitions compared to the imputation approach. Limitations and future directions are discussed.

Prior sensitivity analysis in default Bayesian structural equation modeling.

Bayesian structural equation modeling (BSEM) has recently gained popularity because it enables researchers to fit complex models and solve some of the issues often encountered in classical maximum likelihood estimation, such as nonconvergence and inadmissible solutions. An important component of any Bayesian analysis is the prior distribution of the unknown model parameters. Often, researchers rely on default priors, which are constructed in an automatic fashion without requiring substantive prior information. However, the prior can have a serious influence on the estimation of the model parameters, which affects the mean squared error, bias, coverage rates, and quantiles of the estimates. In this article, we investigate the performance of three different default priors: noninformative improper priors, vague proper priors, and empirical Bayes priors-with the latter being novel in the BSEM literature. Based on a simulation study, we find that these three default BSEM methods may perform very differently, especially with small samples. A careful prior sensitivity analysis is therefore needed when performing a default BSEM analysis. For this purpose, we provide a practical step-by-step guide for practitioners to conducting a prior sensitivity analysis in default BSEM. Our recommendations are illustrated using a well-known case study from the structural equation modeling literature, and all code for conducting the prior sensitivity analysis is available in the online supplemental materials. (PsycINFO Database Record

Big Five personality stability, change, and codevelopment across adolescence and early adulthood.

Using data from 2 large and overlapping cohorts of Dutch adolescents, containing up to 7 waves of longitudinal data each (N = 2,230), the present study examined Big Five personality trait stability, change, and codevelopment in friendship and sibling dyads from age 12 to 22. Four findings stand out. First, the 1-year rank-order stability of personality traits was already substantial at age 12, increased strongly from early through middle adolescence, and remained rather stable during late adolescence and early adulthood. Second, we found linear mean-level increases in girls' conscientiousness, in both genders' agreeableness, and in boys' openness. We also found temporal dips (i.e., U-shaped mean-level change) in boys' conscientiousness and in girls' emotional stability and extraversion. We did not find a mean-level change in boys' emotional stability and extraversion, and we found an increase followed by a decrease in girls' openness. Third, adolescents showed substantial individual differences in the degree and direction of personality trait changes, especially with respect to conscientiousness, extraversion, and emotional stability. Fourth, we found no evidence for personality trait convergence, for correlated change, or for time-lagged partner effects in dyadic friendship and sibling relationships. This lack of evidence for dyadic codevelopment suggests that adolescent friends and siblings tend to change independently from each other and that their shared experiences do not have uniform influences on their personality traits. (PsycINFO Database Record

Elevation alters ecosystem properties across temperate treelines globally.

Temperature is a primary driver of the distribution of biodiversity as well as of ecosystem boundaries. Declining temperature with increasing elevation in montane systems has long been recognized as a major factor shaping plant community biodiversity, metabolic processes, and ecosystem dynamics. Elevational gradients, as thermoclines, also enable prediction of long-term ecological responses to climate warming. One of the most striking manifestations of increasing elevation is the abrupt transitions from forest to treeless alpine tundra. However, whether there are globally consistent above- and belowground responses to these transitions remains an open question. To disentangle the direct and indirect effects of temperature on ecosystem properties, here we evaluate replicate treeline ecotones in seven temperate regions of the world. We find that declining temperatures with increasing elevation did not affect tree leaf nutrient concentrations, but did reduce ground-layer community-weighted plant nitrogen, leading to the strong stoichiometric convergence of ground-layer plant community nitrogen to phosphorus ratios across all regions. Further, elevation-driven changes in plant nutrients were associated with changes in soil organic matter content and quality (carbon to nitrogen ratios) and microbial properties. Combined, our identification of direct and indirect temperature controls over plant communities and soil properties in seven contrasting regions suggests that future warming may disrupt the functional properties of montane ecosystems, particularly where plant community reorganization outpaces treeline advance.

Hidden Markov Item Response Theory Models for Responses and Response Times.

Current approaches to model responses and response times to psychometric tests solely focus on between-subject differences in speed and ability. Within subjects, speed and ability are assumed to be constants. Violations of this assumption are generally absorbed in the residual of the model. As a result, within-subject departures from the between-subject speed and ability level remain undetected. These departures may be of interest to the researcher as they reflect differences in the response processes adopted on the items of a test. In this article, we propose a dynamic approach for responses and response times based on hidden Markov modeling to account for within-subject differences in responses and response times. A simulation study is conducted to demonstrate acceptable parameter recovery and acceptable performance of various fit indices in distinguishing between different models. In addition, both a confirmatory and an exploratory application are presented to demonstrate the practical value of the modeling approach.

Problems in detecting misfit of latent class models in diagnostic research without a gold standard were shown.

OBJECTIVES: The objective of this study was to evaluate the performance of goodness-of-fit testing to detect relevant violations of the assumptions underlying the criticized "standard" two-class latent class model. Often used to obtain sensitivity and specificity estimates for diagnostic tests in the absence of a gold reference standard, this model relies on assuming that diagnostic test errors are independent. When this assumption is violated, accuracy estimates may be biased: goodness-of-fit testing is often used to evaluate the assumption and prevent bias. STUDY DESIGN AND SETTING: We investigate the performance of goodness-of-fit testing by Monte Carlo simulation. The simulation scenarios are based on three empirical examples. RESULTS: Goodness-of-fit tests lack power to detect relevant misfit of the standard two-class latent class model at sample sizes that are typically found in empirical diagnostic studies. The goodness-of-fit tests that are based on asymptotic theory are not robust to the sparseness of data. A parametric bootstrap procedure improves the evaluation of goodness of fit in the case of sparse data. CONCLUSION: Our simulation study suggests that relevant violation of the local independence assumption underlying the standard two-class latent class model may remain undetected in empirical diagnostic studies, potentially leading to biased estimates of sensitivity and specificity.

The latent class multitrait-multimethod model.

A latent class multitrait-multimethod (MTMM) model is proposed to estimate random and systematic measurement error in categorical survey questions while making fewer assumptions than have been made so far in such evaluations, allowing for possible extreme response behavior and other nonmonotone effects. The method is a combination of the MTMM research design of Campbell and Fiske (1959), the basic response model for survey questions of Saris and Andrews (1991), and the latent class factor model of Vermunt and Magidson (2004, pp. 227-230). The latent class MTMM model thus combines an existing design, model, and method to allow for the estimation of the degree to and manner in which survey questions are affected by systematic measurement error. Starting from a general form of the response function for a survey question, we present the MTMM experimental approach to identification of the response function's parameters. A "trait-method biplot" is introduced as a means of interpreting the estimates of systematic measurement error, whereas the quality of the questions can be evaluated by item information curves and the item information function. An experiment from the European Social Survey is analyzed and the results are discussed, yielding valuable insights into the functioning of a set of example questions on the role of women in society in 2 countries.