Dataset Information

A Prediction Model with Lifestyle in Addition to Previously Known Risk Factors Improves Its Predictive Ability for Cardiovascular Death.

ABSTRACT: This longitudinal cohort study aimed to create a novel prediction model for cardiovascular death with lifestyle factors. Subjects aged 40-74 years in the Japanese nationwide Specific Health Checkup Database in 2008 were included. Subjects were randomly assigned to the derivation and validation cohorts by a 2:1 ratio. Points for the prediction model were determined using regression coefficients that were derived from the Cox proportional hazards model in the derivation cohort. Models 1 and 2 were developed using known risk factors and known factors with lifestyle factors, respectively. The models were validated by comparing Kaplan-Meier curves between the derivation and validation cohorts, and by calibration plots in the validation cohort. Among 295,297 subjects, data for 120,823 were available. There were 310 cardiovascular deaths during a mean follow-up of 3.6 years. Model 1 included known risk factors. In model 2, weight gain, exercise habit, gait speed, and drinking alcohol were additionally included as protective factors. Kaplan-Meier curves matched better between the derivation and validation cohorts in model 2, and model 2 was better calibrated. In conclusion, our prediction model with lifestyle factors improved the predictive ability for cardiovascular death.

SUBMITTER: Nishimoto M

PROVIDER: S-EPMC6736867 | biostudies-literature | 2019 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Prediction Model with Lifestyle in Addition to Previously Known Risk Factors Improves Its Predictive Ability for Cardiovascular Death.

Nishimoto Masatoshi M Tagawa Miho M Matsui Masaru M Eriguchi Masahiro M Samejima Ken-Ichi KI Iseki Kunitoshi K Iseki Chiho C Asahi Koichi K Yamagata Kunihiro K Konta Tsuneo T Fujimoto Shouichi S Narita Ichiei I Kasahara Masato M Shibagaki Yugo Y Moriyama Toshiki T Kondo Masahide M Watanabe Tsuyoshi T Tsuruya Kazuhiko K

Scientific reports 20190910 1

This longitudinal cohort study aimed to create a novel prediction model for cardiovascular death with lifestyle factors. Subjects aged 40-74 years in the Japanese nationwide Specific Health Checkup Database in 2008 were included. Subjects were randomly assigned to the derivation and validation cohorts by a 2:1 ratio. Points for the prediction model were determined using regression coefficients that were derived from the Cox proportional hazards model in the derivation cohort. Models 1 and 2 were ...[more]

PMID: 31506478

Similar Datasets

Project description:In perennial ryegrass (Lolium perenne L), annual and seasonal dry matter yield (DMY) and nutritive quality of herbage are high-priority traits targeted for improvement through selective breeding. Genomic prediction (GP) has proven to be a valuable tool for improving complex traits and may be further enhanced through the use of multi-trait (MT) prediction models. In this study, we evaluated the relative performance of MT prediction models to improve predictive ability for DMY and key nutritive quality traits, using two different training populations (TP1, n = 463 and TP2, n = 517) phenotyped at multiple locations. MT models outperformed single-trait (ST) models by 24% to 59% for DMY and 67% to 105% for nutritive quality traits, such as low, high, and total WSC, when a correlated secondary trait was included in both the training and test set (MT-CV2) or in the test set alone (MT-CV3) (trait-assisted genomic selection). However, when a secondary trait was included in training set and not the test set (MT-CV1), the predictive ability was not statistically significant (p > 0.05) compared to the ST model. We evaluated the impact of training set size when using a MT-CV2 model. Using a highly correlated trait (rg = 0.88) as the secondary trait in the MT-CV2 model, there was no loss in predictive ability for DMY even when the training set was reduced to 50% of its original size. In contrast, using a weakly correlated secondary trait (rg = 0.56) in the MT-CV2 model, predictive ability began to decline when the training set size was reduced by only 11% from its original size. Using a ST model, genomic predictive ability in a population unrelated to the training set was poor (rp = -0.06). However, when using an MT-CV2 model, the predictive ability was positive and high (rp = 0.76) for the same population. Our results demonstrate the first assessment of MT models in forage species and illustrate the prospects of using MT genomic selection in forages, and other outcrossing plant species, to accelerate genetic gains for complex agronomical traits, such as DMY and nutritive quality characteristics.

Project description:BackgroundTo establish a clinical prediction model of acute bilirubin encephalopathy (ABE) using amplitude-integrated electroencephalography (aEEG).MethodsA total of 114 neonatal hyperbilirubinemia patients in the Beijing Chaoyang Hospital from August 2015 to October 2018 were enrolled in this study. There were 62 (54.38%) males, and the age of patients undergoing aEEG examination was 2-23 days, with an average of 7.61±4.08 days. Participant clinical information, peak bilirubin value, albumin value, hyperbilirubinemia, and the graphic indicators of aEEG were extracted from medical records, and ABE was diagnosed according to a bilirubin-induced neurological dysfunction (BIND) score >0. Multivariable logistic regression was used to establish a clinical prediction model of ABE. Furthermore, decision curve analysis (DCA) was performed to evaluate the model's predictive value.ResultsAccording to the BIND score, there were a total of 23 (20.18%) ABE cases. The multivariable logistic regression analysis showed that the value of bilirubin/albumin (B/A), presence of hyperbilirubinemia risk factors, number of sleep-wake cycling (SWC) within 3 hours, widest bandwidth, duration of SWC, and type of SWC were significantly associated with ABE. A clinical prediction model was developed as: p=ex/ (1+ex), X=0.278+0.713*B/A+2.602*with risk factors (with risk factors equals 1) - 1.500*SWC number within 3 hours + 0.219*the widest bandwidth-0.065*the duration of one SWC + 1.491* SWC (mature SWC equals 0, immature SWC equals 1). The area under the curve (AUC) was 0.85 [95% confidence interval (CI): 0.75-0.94], which was significantly higher than the AUC only based on conventional clinical information of B/A (AUC: 0.58, 95% CI: 0.45-0.72). The DCA also showed good predictive ability compared to B/A.ConclusionsA clinical prediction model can be established based on the patients' B/A, presence of risk factors for hyperbilirubinemia, number of SWC within 3 hours, widest bandwidth, duration of 1 SWC, and the type of SWC. It has good predictive ability and may improve the diagnostic accuracy of ABE.

Project description:BackgroundBlood metabolic profiles can be used to assess metabolic disorders and to evaluate the health status of dairy cows. Given that these analyses are time-consuming, expensive, and stressful for the cows, there has been increased interest in Fourier transform infrared (FTIR) spectroscopy of milk samples as a rapid, cost-effective alternative for predicting metabolic disturbances. The integration of FTIR data with other layers of information such as genomic and on-farm data (days in milk (DIM) and parity) has been proposed to further enhance the predictive ability of statistical methods. Here, we developed a phenotype prediction approach for a panel of blood metabolites based on a combination of milk FTIR data, on-farm data, and genomic information recorded on 1150 Holstein cows, using BayesB and gradient boosting machine (GBM) models, with tenfold, batch-out and herd-out cross-validation (CV) scenarios.ResultsThe predictive ability of these approaches was measured by the coefficient of determination (R2). The results show that, compared to the model that includes only FTIR data, integration of both on-farm (DIM and parity) and genomic information with FTIR data improves the R2 for blood metabolites across the three CV scenarios, especially with the herd-out CV: R2 values ranged from 5.9 to 17.8% for BayesB, from 8.2 to 16.9% for GBM with the tenfold random CV, from 3.8 to 13.5% for BayesB and from 8.6 to 17.5% for GBM with the batch-out CV, and from 8.4 to 23.0% for BayesB and from 8.1 to 23.8% for GBM with the herd-out CV. Overall, with the model that includes the three sources of data, GBM was more accurate than BayesB with accuracies across the CV scenarios increasing by 7.1% for energy-related metabolites, 10.7% for liver function/hepatic damage, 9.6% for oxidative stress, 6.1% for inflammation/innate immunity, and 11.4% for mineral indicators.ConclusionsOur results show that, compared to using only milk FTIR data, a model integrating milk FTIR spectra with on-farm and genomic information improves the prediction of blood metabolic traits in Holstein cattle and that GBM is more accurate in predicting blood metabolites than BayesB, especially for the batch-out CV and herd-out CV scenarios.

Dataset Information

A Prediction Model with Lifestyle in Addition to Previously Known Risk Factors Improves Its Predictive Ability for Cardiovascular Death.

Publications

A Prediction Model with Lifestyle in Addition to Previously Known Risk Factors Improves Its Predictive Ability for Cardiovascular Death.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets