Summary Background Improvements to prognostic models in metastatic castration-resistant prostate cancer have the potential to augment clinical trial design and guide treatment strategies. In partnership with Project Data Sphere, a not-for-profit initiative allowing data from cancer clinical trials to be shared broadly with researchers, we designed an open-data, crowdsourced, DREAM (Dialogue for Reverse Engineering Assessments and Methods) challenge to not only identify a better prognostic model for prediction of survival in patients with metastatic castration-resistant prostate cancer but also engage a community of international data scientists to study this disease. Methods Data from the comparator arms of four phase 3 clinical trials in first-line metastatic castration-resistant prostate cancer were obtained from Project Data Sphere, comprising 476 patients treated with docetaxel and prednisone from the ASCENT2 trial, 526 patients treated with docetaxel, prednisone, and placebo in the MAINSAIL trial, 598 patients treated with docetaxel, prednisone or prednisolone, and placebo in the VENICE trial, and 470 patients treated with docetaxel and placebo in the ENTHUSE 33 trial. Datasets consisting of more than 150 clinical variables were curated centrally, including demographics, laboratory values, medical history, lesion sites, and previous treatments. Data from ASCENT2, MAINSAIL, and VENICE were released publicly to be used as training data to predict the outcome of interest—namely, overall survival. Clinical data were also released for ENTHUSE 33, but data for outcome variables (overall survival and event status) were hidden from the challenge participants so that ENTHUSE 33 could be used for independent validation. Methods were evaluated using the integrated time-dependent area under the curve (iAUC). The reference model, based on eight clinical variables and a penalised Cox proportional-hazards model, was used to compare method performance. Further validation was done using data from a fifth trial—ENTHUSE M1—in which 266 patients with metastatic castration-resistant prostate cancer were treated with placebo alone. Findings 50 independent methods were developed to predict overall survival and were evaluated through the DREAM challenge. The top performer was based on an ensemble of penalised Cox regression models (ePCR), which uniquely identified predictive interaction effects with immune biomarkers and markers of hepatic and renal function. Overall, ePCR outperformed all other methods (iAUC 0·791; Bayes factor >5) and surpassed the reference model (iAUC 0·743; Bayes factor >20). Both the ePCR model and reference models stratified patients in the ENTHUSE 33 trial into high-risk and low-risk groups with significantly different overall survival (ePCR: hazard ratio 3·32, 95% CI 2·39–4·62, p<0·0001; reference model: 2·56, 1·85–3·53, p<0·0001). The new model was validated further on the ENTHUSE M1 cohort with similarly high performance (iAUC 0·768). Meta-analysis across all methods confirmed previously identified...
IntroductionSerum uric acid (UA) has been known to have a positive association with blood pressure (BP). However, the relationship between serum UA and BP in different age groups is unclear.MethodsA total of 45,098 Koreans who underwent health examinations at Korea Association of Health Promotion with no history of taking drugs related with UA and/or BP were analyzed for determining the relationship between serum UA and BP.ResultsIn men <40, serum UA was significantly associated with systolic (β = 0.25, p = 0.002) and diastolic BP (β = 0.41, p < 0.001) after adjustment for age, diabetes, dyslipidemia, body mass index, and estimated glomerular filtration rate. Men between ages 40 and 59 showed similar results regarding diastolic BP. The association between serum UA and BP was stronger in women <40 (β = 0.54, p < 0.001 for systolic BP; β = 0.65, p < 0.001 for diastolic BP) and in between 40 and 59 (β = 0.51, p < 0.001 for diastolic BP). The association was not significant in men and women ≥60. The odds ratios (ORs) of hyperuricemia for hypertension were 1.25 (95% confidence interval [CI], 1.08 to 1.45; p = 0.003) and 1.33 (95% CI, 1.11 to 1.60; p = 0.002) in men <40 and in between 40 and 59, respectively, in the multivariate analysis. The OR was 2.60 (95% CI, 1.37 to 4.94; p = 0.0034) in women <40. The relationship between hyperuricemia and hypertension was not significant in other age/gender groups.DiscussionIn contrast to the elderly of 60 and over, the non-elderly showed significant associations between serum UA and BP.
Identifying accurate biomarkers of cognitive decline is essential for advancing early diagnosis and prevention therapies in Alzheimer’s Disease. The Alzheimer’s Disease DREAM Challenge was designed as a computational crowdsourced project to benchmark the current state-of-the-art in predicting cognitive outcomes in Alzheimer’s Disease based on high-dimensional, publicly available genetic and structural imaging data. This meta-analysis failed to identify a meaningful predictor developed from either data modality, suggesting that alternate approaches should be considered for to prediction of cognitive performance.
Background In the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, their application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder (ASD). However, given their complexity and potential clinical implications, there is an ongoing need for further research on their accuracy. Objective This study aimed to perform a systematic review and meta-analysis to summarize the available evidence for the accuracy of machine learning algorithms in diagnosing ASD. Methods The following databases were searched on November 28, 2018: MEDLINE, EMBASE, CINAHL Complete (with Open Dissertations), PsycINFO, and Institute of Electrical and Electronics Engineers Xplore Digital Library. Studies that used a machine learning algorithm partially or fully for distinguishing individuals with ASD from control subjects and provided accuracy measures were included in our analysis. The bivariate random effects model was applied to the pooled data in a meta-analysis. A subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false-negative, and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw Summary Receiver Operating Characteristics curves, and obtain the area under the curve (AUC) and partial AUC (pAUC). Results A total of 43 studies were included for the final analysis, of which a meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural magnetic resonance imaging (sMRI) subgroup meta-analysis (12 samples with 1776 participants) showed a sensitivity of 0.83 (95% CI 0.76-0.89), a specificity of 0.84 (95% CI 0.74-0.91), and AUC/pAUC of 0.90/0.83. A functional magnetic resonance imaging/deep neural network subgroup meta-analysis (5 samples with 1345 participants) showed a sensitivity of 0.69 (95% CI 0.62-0.75), specificity of 0.66 (95% CI 0.61-0.70), and AUC/pAUC of 0.71/0.67. Conclusions The accuracy of machine learning algorithms for diagnosis of ASD was considered acceptable by few accuracy measures only in cases of sMRI use; however, given the many limitations indicated in our study, further well-designed studies are warranted to extend the potential use of machine learning algorithms to clinical settings. Trial Registration PROSPERO CRD42018117779; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=117779
BackgroundThe association between body mass index (BMI) in late-life and dementia risk remains unclear. We investigated the association between BMI changes over a 2-year period and dementia in an elderly Korean population.MethodsWe examined 67 219 participants aged 60–79 years who underwent BMI measurement in 2002/2003 and 2004/2005 as part of the National Health Insurance Service-Health Screening Cohort. Baseline characteristics including BMI, socioeconomic status and cardiometabolic risk factors were measured at baseline (2002/2003). The difference between BMI at baseline and at the next health screening (2004/2005) was used to calculate the BMI change. After 2 years, the incidence of dementia was monitored for a mean 5.3 years from 2008 to 2013. Multivariate HRs for dementia incidence were estimated on the basis of baseline BMI and its changes after adjusting for various other risk factors. A subgroup analysis was conducted to determine the effects of baseline BMI and BMI changes.ResultsWe demonstrated a significant association between late-life BMI changes and dementia in both sexes (men: >−10% HR=1.26, 95% CI 1.08 to 1.46, >+10% HR=1.25, 95% CI 1.08 to 1.45; women: >−10% HR=1.15, 95% CI 1.03 to 1.29, >+10% HR=1.17, 95% CI 1.05 to 1.31). However, the baseline BMI was not associated with dementia, except in underweight men. After stratification based on the baseline BMI, the BMI increase over 2 years was associated with dementia in men with a BMI of <25 kg/m2 and women with a BMI of 18.5–25 kg/m2, but not in the obese subgroup in either sex. However, BMI decrease was associated with dementia in those with a BMI of ≥18.5 kg/m2, but not in the underweight subgroup in either sex.ConclusionBoth weight gain and weight loss may be significant risk factors associated with dementia. Continuous weight control and careful monitoring of weight changes are necessary to prevent dementia development.
Background/objectivesWeight perception, especially misperception, might affect health-related quality of life (HRQoL); however, related research is scarce and results remain equivocal. We examined the association between HRQoL and weight misperception by comparing obesity level as measured by body mass index (BMI) and weight perception in Korean adults.MethodsStudy subjects were 43 883 adults aged 19 years or older from cycles IV (2007–2009), V (2010–2012) and VI (2013–2014) of the Korean National Health and Nutrition Examination Survey. Multiple regression analyses comprising both logit and tobit models were conducted to evaluate the independent effect of obesity level as measured by BMI, weight perception and weight misperception on HRQoL after adjusting for demographics, socioeconomic status and number of chronic diseases. We also performed multiple regressions to explore the association between weight misperception and HRQoL stratified by BMI status.ResultsObesity level as measured by BMI and weight perception were independently associated with low HRQoL in both separate and combined analyses. Weight misperception, including underestimation and overestimation, had a significantly negative impact on HRQoL. In subgroup analysis, subjects with BMI ranges from normal to overweight who misperceived their weight also had a high risk of low HRQoL. Overestimation of weight among obese subjects associated with low HRQoL, whereas underestimation of weight showed no significant association.ConclusionsBoth obesity level as measured by BMI and perceiving weight as fat were significant risk factors for low HRQoL. Subjects who incorrectly perceived their weight relative to their BMI status were more likely to report impaired HRQoL, particularly subjects with BMI in the normal to overweight range. Based on these findings, we recommend political and clinical efforts to better inform individuals about healthy weight status and promote accurate weight perception.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.