Dataset Information

Prediction model for high glycated hemoglobin concentration among ethnic Chinese in Taiwan.

ABSTRACT: BACKGROUND: This study aimed to construct a prediction model to identify subjects with high glycated hemoglobin (HbA1c) levels by incorporating anthropometric, lifestyle, clinical, and biochemical information in a large cross-sectional ethnic Chinese population in Taiwan from a health checkup center. METHODS: The prediction model was derived from multivariate logistic regression, and we evaluated the performance of the model in identifying the cases with high HbA1c levels (> = 7.0%). In total 17,773 participants (age > = 30 years) were recruited and 323 participants (1.8%) had high HbA1c levels. The study population was divided randomly into two parts, with 80% as the derivation data and 20% as the validation data. RESULTS: The point-based clinical model, including age (maximal 8 points), sex (1 point), family history (3 points), body mass index (2 points), waist circumference (4 points), and systolic blood pressure (3 points) reached an area under the receiver operating characteristic curve (AUC) of 0.723 (95% confidence interval, 0.677- 0.769) in the validation data. Adding biochemical measures such as triglycerides and HDL cholesterol improved the prediction power (AUC, 0.770 [0.723 - 0.817], P = < 0.001 compared with the clinical model). A cutoff point of 7 had a sensitivity of 0.76 to 0.96 and a specificity of 0.39 to 0.63 for the prediction model. CONCLUSIONS: A prediction model was constructed for the prevalent risk of high HbA1c, which could be useful in identifying high risk subjects for diabetes among ethnic Chinese in Taiwan.

SUBMITTER: Chien KL

PROVIDER: S-EPMC2955643 | biostudies-literature | 2010

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction model for high glycated hemoglobin concentration among ethnic Chinese in Taiwan.

Chien Kuo-Liong KL Lin Hung-Ju HJ Lee Bai-Chin BC Hsu Hsiu-Ching HC Chen Ming-Fong MF

Cardiovascular diabetology 20100927

<h4>Background</h4>This study aimed to construct a prediction model to identify subjects with high glycated hemoglobin (HbA1c) levels by incorporating anthropometric, lifestyle, clinical, and biochemical information in a large cross-sectional ethnic Chinese population in Taiwan from a health checkup center.<h4>Methods</h4>The prediction model was derived from multivariate logistic regression, and we evaluated the performance of the model in identifying the cases with high HbA1c levels (> = 7.0%) ...[more]

PMID: 20875098

Similar Datasets

Project description:ImportanceThe value of measuring levels of glycated hemoglobin (HbA1c) for the prediction of first cardiovascular events is uncertain.ObjectiveTo determine whether adding information on HbA1c values to conventional cardiovascular risk factors is associated with improvement in prediction of cardiovascular disease (CVD) risk.Design, setting, and participantsAnalysis of individual-participant data available from 73 prospective studies involving 294,998 participants without a known history of diabetes mellitus or CVD at the baseline assessment.Main outcomes and measuresMeasures of risk discrimination for CVD outcomes (eg, C-index) and reclassification (eg, net reclassification improvement) of participants across predicted 10-year risk categories of low (<5%), intermediate (5% to <7.5%), and high (≥ 7.5%) risk.ResultsDuring a median follow-up of 9.9 (interquartile range, 7.6-13.2) years, 20,840 incident fatal and nonfatal CVD outcomes (13,237 coronary heart disease and 7603 stroke outcomes) were recorded. In analyses adjusted for several conventional cardiovascular risk factors, there was an approximately J-shaped association between HbA1c values and CVD risk. The association between HbA1c values and CVD risk changed only slightly after adjustment for total cholesterol and triglyceride concentrations or estimated glomerular filtration rate, but this association attenuated somewhat after adjustment for concentrations of high-density lipoprotein cholesterol and C-reactive protein. The C-index for a CVD risk prediction model containing conventional cardiovascular risk factors alone was 0.7434 (95% CI, 0.7350 to 0.7517). The addition of information on HbA1c was associated with a C-index change of 0.0018 (0.0003 to 0.0033) and a net reclassification improvement of 0.42 (-0.63 to 1.48) for the categories of predicted 10-year CVD risk. The improvement provided by HbA1c assessment in prediction of CVD risk was equal to or better than estimated improvements for measurement of fasting, random, or postload plasma glucose levels.Conclusions and relevanceIn a study of individuals without known CVD or diabetes, additional assessment of HbA1c values in the context of CVD risk assessment provided little incremental benefit for prediction of CVD risk.

Project description:BackgroundPredicting the risk of glycated hemoglobin (HbA1c) elevation can help identify patients with the potential for developing serious chronic health problems, such as diabetes. Early preventive interventions based upon advanced predictive models using electronic health records data for identifying such patients can ultimately help provide better health outcomes.ObjectiveOur study investigated the performance of predictive models to forecast HbA1c elevation levels by employing several machine learning models. We also examined the use of patient electronic health record longitudinal data in the performance of the predictive models. Explainable methods were employed to interpret the decisions made by the black box models.MethodsThis study employed multiple logistic regression, random forest, support vector machine, and logistic regression models, as well as a deep learning model (multilayer perceptron) to classify patients with normal (<5.7%) and elevated (≥5.7%) levels of HbA1c. We also integrated current visit data with historical (longitudinal) data from previous visits. Explainable machine learning methods were used to interrogate the models and provide an understanding of the reasons behind the decisions made by the models. All models were trained and tested using a large data set from Saudi Arabia with 18,844 unique patient records.ResultsThe machine learning models achieved promising results for predicting current HbA1c elevation risk. When coupled with longitudinal data, the machine learning models outperformed the multiple logistic regression model used in the comparative study. The multilayer perceptron model achieved an accuracy of 83.22% for the area under receiver operating characteristic curve when used with historical data. All models showed a close level of agreement on the contribution of random blood sugar and age variables with and without longitudinal data.ConclusionsThis study shows that machine learning models can provide promising results for the task of predicting current HbA1c levels (≥5.7% or less). Using patients' longitudinal data improved the performance and affected the relative importance for the predictors used. The models showed results that are consistent with comparable studies.

Project description:Anemia, defined as a low hemoglobin concentration, has a large impact on the health of the world's population. We describe the use of a ubiquitous device, the smartphone, to predict hemoglobin concentration and screen for anemia. This was a prospective convenience sample study conducted in Emergency Department (ED) patients of an academic teaching hospital. In an algorithm derivation phase, images of both conjunctiva were obtained from 142 patients in Phase 1 using a smartphone. A region of interest targeting the palpebral conjunctiva was selected from each image. Image-based parameters were extracted and used in stepwise regression analyses to develop a prediction model of estimated hemoglobin (HBc). In Phase 2, a validation model was constructed using data from 202 new ED patients. The final model based on all 344 patients was tested for accuracy in anemia and transfusion thresholds. Hemoglobin concentration ranged from 4.7 to 19.6 g/dL (mean 12.5). In Phase 1, there was a significant association between HBc and laboratory-predicted hemoglobin (HBl) slope = 1.07 (CI = 0.98-1.15), p<0.001. Accuracy, sensitivity, and specificity of HBc for predicting anemia was 82.9 [79.3, 86.4], 90.7 [87.0, 94.4], and 73.3 [67.1, 79.5], respectively. In Phase 2, accuracy, sensitivity and specificity decreased to 72.6 [71.4, 73.8], 72.8 [71, 74.6], and 72.5 [70.8, 74.1]. Accuracy for low (<7 g/dL) and high (<9 g/dL) transfusion thresholds was 94.4 [93.7, 95] and 86 [85, 86.9] respectively. Error trended with increasing HBl values (slope 0.27 [0.19, 0.36] and intercept -3.14 [-4.21, -2.07] (p<0.001) such that HBc tended to underestimate hemoglobin in higher ranges and overestimate in lower ranges. Higher quality images had a smaller bias trend than lower quality images. When separated by skin tone results were unaffected. A smartphone can be used in screening for anemia and transfusion thresholds. Improvements in image quality and computational corrections can further enhance estimates of hemoglobin.

Dataset Information

Prediction model for high glycated hemoglobin concentration among ethnic Chinese in Taiwan.

Publications

Prediction model for high glycated hemoglobin concentration among ethnic Chinese in Taiwan.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets