Explore the vast range of titles available.

Background Recent studies have suggested that insulin resistance (IR) contributes to the development of cardiovascular diseases (CVD), and the estimated glucose disposal rate (eGDR) is considered to be a reliable surrogate marker of IR. However, most existing evidence stems from studies involving diabetic patients, potentially overstating the effects of eGDR on CVD. Therefore, the primary objective of this study is to examine the relationship of eGDR with incidence of CVD in non-diabetic participants. Method The current analysis included individuals from the China Health and Retirement Longitudinal Study (CHARLS) who were free of CVD and diabetes mellitus but had complete data on eGDR at baseline. The formula for calculating eGDR was as follows: eGDR (mg/kg/min) = 21.158 − (0.09 × WC) − (3.407 × hypertension) − (0.551 × HbA1c) [WC (cm), hypertension (yes = 1/no = 0), and HbA1c (%)]. The individuals were categorized into four subgroups according to the quartiles (Q) of eGDR. Crude incidence rate and hazard ratios (HRs) with 95% confidence intervals (CIs) were computed to investigate the association between eGDR and incident CVD, with the lowest quartile of eGDR (indicating the highest grade of insulin resistance) serving as the reference. Additionally, the multivariate adjusted restricted cubic spine (RCS) was employed to examine the dose–response relationship. Results We included 5512 participants in this study, with a mean age of 58.2 ± 8.8 years, and 54.1% were female. Over a median follow-up duration of 79.4 months, 1213 incident CVD cases, including 927 heart disease and 391 stroke, were recorded. The RCS curves demonstrated a significant and linear relationship between eGDR and all outcomes (all P for non-linearity > 0.05). After multivariate adjustment, the lower eGDR levels were founded to be significantly associated with a higher risk of CVD. Compared with participants with Q1 of eGDR, the HRs (95% CIs) for those with Q2 − 4 were 0.88 (0.76 − 1.02), 0.69 (0.58 − 0.82), and 0.66 (0.56 − 0.79). When assessed as a continuous variable, per 1.0-SD increase in eGDR was associated a 17% (HR: 0.83, 95% CI: 0.78 − 0.89) lower risk of CVD, with the subgroup analyses indicating that smoking status modified the association ( P for interaction = 0.012). Moreover, the mediation analysis revealed that obesity partly mediated the association. Additionally, incorporating eGDR into the basic model considerably improve the predictive ability for CVD. Conclusion A lower level of eGDR was found to be associated with increased risk of incident CVD among non-diabetic participants. This suggests that eGDR may serve as a promising and preferable predictor and intervention target for CVD.

In public discussions of the quality of forecasts, attention typically focuses on the predictive performance in cases of extreme events. However, the restriction of conventional forecast evaluation methods to subsets of extreme observations has unexpected and undesired effects, and is bound to discredit skillful forecasts when the signal-to-noise ratio in the data generating process is low. Conditioning on outcomes is incompatible with the theoretical assumptions of established forecast evaluation methods, thereby confronting forecasters with what we refer to as the forecaster's dilemma. For probabilistic forecasts, proper weighted scoring rules have been proposed as decision-theoretically justifiable alternatives for forecast evaluation with an emphasis on extreme events. Using theoretical arguments, simulation experiments and a real data study on probabilistic forecasts of U.S. inflation and gross domestic product (GDP) growth, we illustrate and discuss the forecaster's dilemma along with potential remedies.

The World Health Organization (WHO) introduced the new dengue classification in 2009. We aimed to assess the association of clinical signs and symptoms with WHO severe dengue classification in clinical practice. A systematic literature search was performed using the databases of PubMed, Embase, and Scopus between 2009 and 2018 according to PRISMA guideline. Meta-analysis was performed with the RevMan software. A random or fixed-effect model was applied to pool odds ratios and 95% confidence intervals of important signs and symptoms across studies. Thirty nine articles from 1790 records were included in this review. In our meta-analysis, signs and symptoms associated with higher risk of severe dengue were comorbidity, vomiting, persistent vomiting, abdominal pain or tenderness, pleural effusion, ascites, epistaxis, gum bleeding, GI bleeding, skin bleeding, lethargy or restlessness, hepatomegaly (>2 cm), increased HCT with decreased platelets, shock, dyspnea, impaired consciousness, thrombocytopenia, elevated AST and ALT, gall bladder wall thickening and secondary infection. This review shows new factors comorbidity, epistaxis, GI and skin bleeding, dyspnea, gall bladder wall thickening and secondary infection may be useful to refine the 2009 classification to triage severe dengue patients.

Models based on species distributions are widely used and serve important purposes in ecology, biogeography and conservation. Their continuous predictions of environmental suitability are commonly converted into a binary classification of predicted (or potential) presences and absences, whose accuracy is then evaluated through a number of measures that have been the subject of recent reviews. We propose four additional measures that analyse observation-prediction mismatch from a different angle – namely, from the perspective of the predicted rather than the observed area – and add to the existing toolset of model evaluation methods. We explain how these measures can complete the view provided by the existing measures, allowing further insights into distribution model predictions. We also describe how they can be particularly useful when using models to forecast the spread of diseases or of invasive species and to predict modifications in species' distributions under climate and land-use change.

Primary aldosteronism (PA) has two major subtypes: unilateral (uPA) and bilateral (bPA). Although several diagnostic models for subtype classification have been reported, the optimal combination of algorithms and clinical features remains unclear. This study aimed to identify machine learning models and clinical features that contribute to PA subtype prediction. A total of 274 PA patients who underwent successful adrenal venous sampling (AVS) at a single center were analyzed. Overall, 196 endocrine features were comprehensively collected and classified into four categories: A, PA-related features; B, challenge tests; C, general biochemistry; and D, urinary steroid profile. Five machine learning algorithms were applied; predictive performance of the models as well as predictive contribution of features and categories were evaluated. Among the models, the random forest (RF) model achieved the highest predictive accuracy (91.3%). The most contributing feature in the RF model was plasma aldosterone concentration after the captopril challenge test (CCT90-PAC). Category B made the greatest contribution to RF, followed by Categories A, D, and C. Combining Categories A and B improved predictive performance. These findings indicate that machine learning models, particularly RF, are effective for PA subtype prediction, with challenge test-related features in Category B making a major contribution.

The aim of this study was to quantify the impact of predictor measurement heterogeneity on prediction model performance. Predictor measurement heterogeneity refers to variation in the measurement of predictor(s) between the derivation of a prediction model and its validation or application. It arises, for instance, when predictors are measured using different measurement instruments or protocols. We examined the effects of various scenarios of predictor measurement heterogeneity in real-world clinical examples using previously developed prediction models for diagnosis of ovarian cancer, mutation carriers for Lynch syndrome, and intrauterine pregnancy. Changing the measurement procedure of a predictor influenced the performance at validation of the prediction models in nine clinical examples. Notably, it induced model miscalibration. The calibration intercept at validation ranged from −0.70 to 1.43 (0 for good calibration), whereas the calibration slope ranged from 0.50 to 1.67 (1 for good calibration). The difference in C-statistic and scaled Brier score between derivation and validation ranged from −0.08 to +0.08 and from −0.40 to +0.16, respectively. This study illustrates that predictor measurement heterogeneity can influence the performance of a prediction model substantially, underlining that predictor measurements used in research settings should resemble clinical practice. Specification of measurement heterogeneity can help researchers explaining discrepancies in predictive performance between derivation and validation setting.

Background Predicting survival of recipients after liver transplantation is regarded as one of the most important challenges in contemporary medicine. Hence, improving on current prediction models is of great interest.Nowadays, there is a strong discussion in the medical field about machine learning (ML) and whether it has greater potential than traditional regression models when dealing with complex data. Criticism to ML is related to unsuitable performance measures and lack of interpretability which is important for clinicians. Methods In this paper, ML techniques such as random forests and neural networks are applied to large data of 62294 patients from the United States with 97 predictors selected on clinical/statistical grounds, over more than 600, to predict survival from transplantation. Of particular interest is also the identification of potential risk factors. A comparison is performed between 3 different Cox models (with all variables, backward selection and LASSO) and 3 machine learning techniques: a random survival forest and 2 partial logistic artificial neural networks (PLANNs). For PLANNs, novel extensions to their original specification are tested. Emphasis is given on the advantages and pitfalls of each method and on the interpretability of the ML techniques. Results Well-established predictive measures are employed from the survival field (C-index, Brier score and Integrated Brier Score) and the strongest prognostic factors are identified for each model. Clinical endpoint is overall graft-survival defined as the time between transplantation and the date of graft-failure or death. The random survival forest shows slightly better predictive performance than Cox models based on the C-index. Neural networks show better performance than both Cox models and random survival forest based on the Integrated Brier Score at 10 years. Conclusion In this work, it is shown that machine learning techniques can be a useful tool for both prediction and interpretation in the survival context. From the ML techniques examined here, PLANN with 1 hidden layer predicts survival probabilities the most accurately, being as calibrated as the Cox model with all variables. Trial registration Retrospective data were provided by the Scientific Registry of Transplant Recipients under Data Use Agreement number 9477 for analysis of risk factors after liver transplantation.

Cyanobacterial harmful algal blooms (CyanoHABs) threaten ecosystem functioning and human health at both regional and global levels, and this threat is likely to become more frequent and severe under climate change. Predictive information can help local water managers to alleviate or manage the adverse effects posed by CyanoHABs. Previous works have led to various approaches for predicting cyanobacteria abundance by feeding various environmental variables into statistical models or neural networks. However, these models alone may have limited predictive performance owing to their inability to capture extreme situations. In this paper, we consider the possibility of a hybrid approach that leverages the merits of these methods by integrating a statistical model with a deep-learning model. In particular, the autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) were used in tandem to better capture temporal patterns of highly dynamic observations. Results show that the proposed ARIMA-LSTM model exhibited the promising potential to outperform the state-of-the-art baseline models for CyanoHAB prediction in highly variable time-series observations, characterized by nonstationarity and imbalance. The predictive error of the mean absolute error and root mean square error, compared with the best baseline model, were largely reduced by 12.4% and 15.5%, respectively. This study demonstrates the potential for the hybrid model to assist in cyanobacterial risk assessment and management, especially in shallow and eutrophic waters.