Dataset Information

Dynamic risk prediction for diabetes using biomarker change measurements.

ABSTRACT:

Background

Dynamic risk models, which incorporate disease-free survival and repeated measurements over time, might yield more accurate predictions of future health status compared to static models. The objective of this study was to develop and apply a dynamic prediction model to estimate the risk of developing type 2 diabetes mellitus.

Methods

Both a static prediction model and a dynamic landmark model were used to provide predictions of a 2-year horizon time for diabetes-free survival, updated at 1, 2, and 3?years post-baseline i.e., predicting diabetes-free survival to 2?years and predicting diabetes-free survival to 3?years, 4?years, and 5?years post-baseline, given the patient already survived past 1?year, 2?years, and 3?years post-baseline, respectively. Prediction accuracy was evaluated at each time point using robust non-parametric procedures. Data from 2057 participants of the Diabetes Prevention Program (DPP) study (1027 in metformin arm, 1030 in placebo arm) were analyzed.

Results

The dynamic landmark model demonstrated good prediction accuracy with area under curve (AUC) estimates ranging from 0.645 to 0.752 and Brier Score estimates ranging from 0.088 to 0.135. Relative to a static risk model, the dynamic landmark model did not significantly differ in terms of AUC but had significantly lower (i.e., better) Brier Score estimates for predictions at 1, 2, and 3?years (e.g. 0.167 versus 0.099; difference?-?0.068 95% CI -?0.083 to -?0.053, at 3?years in placebo group) post-baseline.

Conclusions

Dynamic prediction models based on longitudinal, repeated risk factor measurements have the potential to improve the accuracy of future health status predictions.

SUBMITTER: Parast L

PROVIDER: S-EPMC6694545 | biostudies-literature | 2019 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Dynamic risk prediction for diabetes using biomarker change measurements.

Parast Layla L Mathews Megan M Friedberg Mark W MW

BMC medical research methodology 20190814 1

<h4>Background</h4>Dynamic risk models, which incorporate disease-free survival and repeated measurements over time, might yield more accurate predictions of future health status compared to static models. The objective of this study was to develop and apply a dynamic prediction model to estimate the risk of developing type 2 diabetes mellitus.<h4>Methods</h4>Both a static prediction model and a dynamic landmark model were used to provide predictions of a 2-year horizon time for diabetes-free su ...[more]

PMID: 31412790

Similar Datasets

Project description:BackgroundIntraoperative data may improve models predicting postoperative events. We evaluated the effect of incorporating intraoperative variables to the existing preoperative model on the predictive performance of the model for coronary artery bypass graft.MethodsWe analyzed 378 572 isolated coronary artery bypass graft cases performed across 1083 centers, using the national Society of Thoracic Surgeons Adult Cardiac Surgery Database between 2014 and 2016. Outcomes were operative mortality, 5 postoperative complications, and composite representation of all events. We fitted models by logistic regression or extreme gradient boosting (XGBoost). For each modeling approach, we used preoperative only, intraoperative only, or pre+intraoperative variables. We developed 84 models with unique combinations of the 3 variable sets, 2 variable selection methods, 2 modeling approaches, and 7 outcomes. Each model was tested in 20 iterations of 70:30 stratified random splitting into development/testing samples. Model performances were evaluated on the testing dataset using the C statistic, area under the precision-recall curve, and calibration metrics, including the Brier score.ResultsThe mean patient age was 65.3 years, and 24.7% were women. Operative mortality, excluding intraoperative death, occurred in 1.9%. In all outcomes, models that considered pre+intraoperative variables demonstrated significantly improved Brier score and area under the precision-recall curve compared with models considering pre or intraoperative variables alone. XGBoost without external variable selection had the best C statistics, Brier score, and area under the precision-recall curve values in 4 of the 7 outcomes (mortality, renal failure, prolonged ventilation, and composite) compared with logistic regression models with or without variable selection. Based on the calibration plots, risk restratification for mortality showed that the logistic regression model underestimated the risk in 11 114 patients (9.8%) and overestimated in 12 005 patients (10.6%). In contrast, the XGBoost model underestimated the risk in 7218 patients (6.4%) and overestimated in 0 patients (0%).ConclusionsIn isolated coronary artery bypass graft, adding intraoperative variables to preoperative variables resulted in improved predictions of all 7 outcomes. Risk models based on XGBoost may provide a better prediction of adverse events to guide clinical care.

Project description:BackgroundPrevalence of prediabetes and type 2 diabetes mellitus (T2DM) is increasing worldwide. The objective of this study was to determine the proportion of people in Northern Iceland with prediabetes, at risk of developing T2DM or with manifest undiagnosed T2DM, as this information is lacking in Iceland.MethodsA cross-sectional study. Clients of the three largest primary health care centres in the Health Care Institution of North Iceland (HSN) were invited to participate if fulfilling the following inclusion criteria: a) aged between 18 and 75 years, b) not diagnosed with diabetes, c) speaking and understanding Icelandic or English fluently and d) living in the included service area. Data collection took place via face-to-face interviews between 1 March 2020 and 15 May 2021. Participation included answering the Finnish Diabetes Risk Score (FINDRISC), measuring the HbA1c levels and background information.ResultsOf the 220 participants, 65.9% were women. The mean age was 52.1 years (SD ± 14.1) and FINDRISC scores were as follows: 47.3% scored ≤8 points, 37.2% scored between 9 and 14 points, and 15.5% scored between 15 and 26 points. The mean HbA1c levels in mmol/mol, were 35.5 (SD ± 3.9) for men and 34.4 (SD ± 3.4) for women, ranging from 24 to 47. Body mass index ≥30 kg/m2 was found in 32% of men and 35.9% of women. Prevalence of prediabetes in this cohort was 13.2%. None of the participants had undiagnosed T2DM. Best sensitivity and specificity for finding prediabetes was by using cut-off points of ≥11 on FINDRISC, which gave a ROC curve of 0.814.ConclusionsThe FINDRISC is a non-invasive and easily applied screening instrument for prediabetes. Used in advance of other more expensive and invasive testing, it can enable earlier intervention by assisting decision making, health promotion actions and prevention of the disease burden within primary health care.Trial registrationThis study is a pre-phase of the registered study "Effectiveness of Nurse-coordinated Follow up Program in Primary Care for People at risk of T2DM" at www.Clinicaltrialsgov (NCT01688359). Registered 30 December 2020.

Dataset Information

Dynamic risk prediction for diabetes using biomarker change measurements.

Background

Methods

Results

Conclusions

Publications

Dynamic risk prediction for diabetes using biomarker change measurements.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets