Prediction of type 2 diabetes mellitus onset using logistic regression-based scorecards.
Ontology highlight
ABSTRACT:
SUBMITTER: Edlitz Y
PROVIDER: S-EPMC9255967 | biostudies-literature | 2022 Jun
REPOSITORIES: biostudies-literature
Publications
Prediction of type 2 diabetes mellitus onset using logistic regression-based scorecards.
eLife 20220622
<h4>Background</h4>Type 2 diabetes (T2D) accounts for ~90% of all cases of diabetes, resulting in an estimated 6.7 million deaths in 2021, according to the International Diabetes Federation. Early detection of patients with high risk of developing T2D can reduce the incidence of the disease through a change in lifestyle, diet, or medication. Since populations of lower socio-demographic status are more susceptible to T2D and might have limited resources or access to sophisticated computational re ...[more]
Similar Datasets
Project description:ObjectivesGlycaemic control in children and adolescents with type 1 diabetes mellitus can be challenging, complex and influenced by many factors. This study aimed to identify patient characteristics that were predictive of satisfactory glycaemic control in the paediatric population using a logistic regression mixed-effects (population) modelling approach.MethodsThe data were obtained from 288 patients aged between 1 and 22 years old recorded retrospectively over 3 years (1852 HbA1c observations). HbA1c status was categorised as 'satisfactory' or 'unsatisfactory' glycaemic control, using an a priori cut-off value of HbA1c ≥ 9% (75 mmol/mol), as used routinely by the hospital's endocrine paediatricians. Patients' characteristics were tested as covariates in the model as potential predictors of glycaemic control.ResultsThere were three patient characteristics identified as having a significant influence on glycaemic control: HbA1c measurement at the beginning of the observation period (Odds Ratio (OR) = 0.30 per 1% HbA1c increase, 95% confidence interval (CI) = 0.20-0.41); Age (OR = 0.88 per year increase, 95% CI = 0.80-0.94), and fractional disease duration (disease duration/age, OR = 0.80 per 0.10 increase, 95% CI = 0.66-0.93) were collectively identified as factors contributing significantly to lower the probability of satisfactory glycaemic control.ConclusionsThe study outcomes may prove useful for identifying paediatric patients at risk of having unsatisfactory glycaemic control, and who could require more extensive monitoring, support, or targeted interventions.
| S-EPMC5540397 | biostudies-literature
Project description:BackgroundLysine acetylation is a crucial type of protein post-translational modification, which is involved in many important cellular processes and serious diseases. However, identification of protein acetylated sites through traditional experiment methods is time-consuming and laborious. Those methods are not suitable to identify a large number of acetylated sites quickly. Therefore, computational methods are still very valuable to accelerate lysine acetylated site finding.ResultIn this study, many biological characteristics of acetylated sites have been investigated, such as the amino acid sequence around the acetylated sites, the physicochemical property of the amino acids and the transition probability of adjacent amino acids. A logistic regression method was then utilized to integrate these information for generating a novel lysine acetylation prediction system named LAceP. When compared with existing methods, LAceP overwhelms most of state-of-the-art methods. Especially, LAceP has a more balanced prediction capability for positive and negative datasets.ConclusionLAceP can integrate different biological features to predict lysine acetylation with high accuracy. An online web server is freely available at http://www.scbit.org/iPTM/.
| S-EPMC3930742 | biostudies-literature
Project description:BACKGROUND:HPV-16-positive HNSCC and HPV-16-negative HNSCC have different clinical factors, representing distinct forms of cancers. The study aimed to identify patient-specific factors for HPV-16-positive HNSCC based on baseline clinical data. METHOD:Factors associated with HPV-16-positive HNSCC were identified using the data from 210 patients diagnosed with HNSCC at University College of London Hospital between January 1, 2003, and April 30, 2015, inclusive. A series of models were developed using logistic regression methods, and the overall model fit was compared using Akaike Information Criterion. Survival analysis was carried with Cox proportional hazards model for survival-time outcomes. The survival time for individual patients was defined as the time from diagnosis of HNSCC to the date of death from any cause. For patients who did not die, they were censored at the end of study on April 30, 2015. RESULTS:Of the 210 patients, 151 (72%) were found to have HPV-16-positive HNSCC. The logistic regression model showed that the prevalence of developing HPV-16-positive HNSCC was 3.79 times higher in patients with Type 2 Diabetes Mellitus (T2DM) (odd ratio [OR], 3.79; 95% CI, 1.70-8.44) than in those without T2DM, and 8.84 times higher in patients with history of primary HNSCC (OR, 8.84; 95% CI, 2.30-33.88) than in those without a history of primary HNSCC. HPV-16-positive HNSCC was also observed more in tonsils (OR, 4.02; 95% CL, 1.56-10.36) and less in non-alcohol drinker's oral cavity (OR, 0.14; 95% CI, 0.03-0.56). Furthermore, individual patients were followed-up for 1 to 13 years (median of 1 year). Patients with HPV-positive HNSCC had a median survival of 5 years (95% CI, 2.6-7.3 years). Among HPV-16-positive HNSCC cohort, T2DM was a risk for poorer prognosis (hazard ratio, 2.57; 95% Cl, 1.09-6.07), and had lower median survival of 3 years (95% CI, 1.8-4.1 years), as compared to 6 years (95% CI, 2.8-9.1 years) in non-T2DM. CONCLUSIONS:Patient-specific factors for HPV-positive HNSCC are T2DM, history of primary HNSCC and tonsillar site. T2DM is associated with poorer prognosis. These findings suggest that it might be beneficial if routine HPV-16 screening is carried out in T2DM patients which can provide better therapeutic and management strategies.
| S-EPMC6522118 | biostudies-literature
Project description:Most screening tests for T2DM in use today were developed using multivariate regression methods that are often further simplified to allow transformation into a scoring formula. The increasing volume of electronically collected data opened the opportunity to develop more complex, accurate prediction models that can be continuously updated using machine learning approaches. This study compares machine learning-based prediction models (i.e. Glmnet, RF, XGBoost, LightGBM) to commonly used regression models for prediction of undiagnosed T2DM. The performance in prediction of fasting plasma glucose level was measured using 100 bootstrap iterations in different subsets of data simulating new incoming data in 6-month batches. With 6 months of data available, simple regression model performed with the lowest average RMSE of 0.838, followed by RF (0.842), LightGBM (0.846), Glmnet (0.859) and XGBoost (0.881). When more data were added, Glmnet improved with the highest rate (+ 3.4%). The highest level of variable selection stability over time was observed with LightGBM models. Our results show no clinically relevant improvement when more sophisticated prediction models were used. Since higher stability of selected variables over time contributes to simpler interpretation of the models, interpretability and model calibration should also be considered in development of clinical prediction models.
| S-EPMC7371679 | biostudies-literature
Project description:BackgroundType 2 diabetes mellitus (T2DM) is a complex disease with high incidence and serious harm associated with polygenic determination. This study aimed to develop a predictive model so as to assess the risk of T2DM and apply it to health care and disease prevention in northern China.ObjectiveBased on genotyping results, a risk warning model for type 2 diabetes was established.MethodsBlood samples of 1042 patients with T2DM in northern China were collected. Multiplex polymerase chain reaction and high-throughput sequencing (NGS) techniques were used to design the amplification-based targeted sequencing panel to sequence the 21 T2DM susceptibility genes.ResultThe related key gene KQT-like subfamily member 1 played an important role in the T2DM risk model, and single-nucleotide polymorphism rs2237892 was highly significant, with a P value of 1.2 × 10-5.ConclusionsSusceptibility genes in different populations were examined, and a model was developed to assess the risk-based genetic analysis. The performance of the model reached 92.8%.
| S-EPMC8158054 | biostudies-literature
Project description:In this research, the photoplethysmogram (PPG) waveform analysis is utilized to develop a logistic regression-based predictive model for the classification of diabetes. The classifier has three predictors age, b/a, and SP indices in which they achieved an overall accuracy of 92.3% in the prediction of diabetes. In this study, a total of 587 subjects were enrolled. A total of 459 subjects were used for model training and development, while the rest of the 128 subjects were used for model testing and validation. The classifier was able to diagnose 63 patients correctly as diabetes while 27 subjects were wrongly classified as nondiabetes with an accuracy of 70%. Again, the model classified 479 subjects as nondiabetes correctly while it incorrectly classified 18 subjects as diabetes with an accuracy of 96.4%. Finally, the proposed model revealed an overall predictive accuracy of 92.3% which makes it a reliable surrogate measure for diabetes classification and prediction in clinical settings.
| S-EPMC7439205 | biostudies-literature
Project description:Numerous predictive models for the risk of type 2 diabetes mellitus (T2DM) exist, but a minority of them has implemented nutrition data so far, even though the significant effect of nutrition on the pathogenesis, prevention and management of T2DM has been established. Thus, in the present study, we aimed to build a predictive model for the risk of T2DM that incorporates nutrition data and calculates its predictive performance. We analysed cross-sectional data from 1591 individuals from the population-based Cooperative Health Research in the Region of Augsburg (KORA) FF4 study (2013-14) and used a bootstrap enhanced elastic net penalised multivariate regression method in order to build our predictive model and select among 193 food intake variables. After selecting the significant predictor variables, we built a logistic regression model with these variables as predictors and T2DM status as the outcome. The values of area under the receiver operating characteristic (ROC) curve, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy of our predictive model were calculated. Eleven out of the 193 food intake variables were selected for inclusion in our model, which yielded a value of area under the ROC curve of 0⋅79 and a maximum PPV, NPV and accuracy of 0⋅37, 0⋅98 and 0⋅91, respectively. The present results suggest that nutrition data should be implemented in predictive models to predict the risk of T2DM, since they improve their performance and they are easy to assess.
| S-EPMC8223171 | biostudies-literature
Project description:In the status forecasting problem, classification models such as logistic regression with input variables such as physiological, diagnostic, and treatment variables are typical ways of modeling. However, the parameter value and model performance differ among individuals with different baseline information. To cope with these difficulties, a subgroup analysis is conducted, in which models' ANOVA and rpart are proposed to explore the influence of baseline information on the parameters and model performance. The results show that the logistic regression model achieves satisfactory performance, which is generally higher than 0.95 in AUC and around 0.9 in F1 and balanced accuracy. The subgroup analysis presents the prior parameter values for monitoring variables including SpO2, milrinone, non-opioid analgesics and dobutamine. The proposed method can be used to explore variables that are and are not medically related to the baseline variables.
| S-EPMC9601351 | biostudies-literature
Project description:ObjectiveTo predict preterm birth in nulliparous women using logistic regression and machine learning.DesignPopulation-based retrospective cohort.ParticipantsNulliparous women (N = 112,963) with a singleton gestation who gave birth between 20-42 weeks gestation in Ontario hospitals from April 1, 2012 to March 31, 2014.MethodsWe used data during the first and second trimesters to build logistic regression and machine learning models in a "training" sample to predict overall and spontaneous preterm birth. We assessed model performance using various measures of accuracy including sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC) in an independent "validation" sample.ResultsDuring the first trimester, logistic regression identified 13 variables associated with preterm birth, of which the strongest predictors were diabetes (Type I: adjusted odds ratio (AOR): 4.21; 95% confidence interval (CI): 3.23-5.42; Type II: AOR: 2.68; 95% CI: 2.05-3.46) and abnormal pregnancy-associated plasma protein A concentration (AOR: 2.04; 95% CI: 1.80-2.30). During the first trimester, the maximum AUC was 60% (95% CI: 58-62%) with artificial neural networks in the validation sample. During the second trimester, 17 variables were significantly associated with preterm birth, among which complications during pregnancy had the highest AOR (13.03; 95% CI: 12.21-13.90). During the second trimester, the AUC increased to 65% (95% CI: 63-66%) with artificial neural networks in the validation sample. Including complications during the pregnancy yielded an AUC of 80% (95% CI: 79-81%) with artificial neural networks. All models yielded 94-97% negative predictive values for spontaneous PTB during the first and second trimesters.ConclusionAlthough artificial neural networks provided slightly higher AUC than logistic regression, prediction of preterm birth in the first trimester remained elusive. However, including data from the second trimester improved prediction to a moderate level by both logistic regression and machine learning approaches.
| S-EPMC8244906 | biostudies-literature
Project description:Type 1 diabetes mellitus (T1DM) patients are a significant threat to chronic kidney disease (CKD) development during their life. However, there is always a high chance of delay in CKD detection because CKD can be asymptomatic, and T1DM patients bypass traditional CKD tests during their routine checkups. This study aims to develop and validate a prediction model and nomogram of CKD in T1DM patients using readily available routine checkup data for early CKD detection. This research utilized 1375 T1DM patients' sixteen years of longitudinal data from multi-center Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials conducted at 28 sites in the USA and Canada and considered 17 routinely available features. Three feature ranking algorithms, extreme gradient boosting (XGB), random forest (RF), and extremely randomized trees classifier (ERT), were applied to create three feature ranking lists, and logistic regression analyses were performed to develop CKD prediction models using these ranked feature lists to identify the best performing top-ranked features combination. Finally, the most significant features were selected to develop a multivariate logistic regression-based CKD prediction model for T1DM patients. This model was evaluated using sensitivity, specificity, accuracy, precision, and F1 score on train and test data. A nomogram of the final model was further generated for easy application in clinical practices. Hypertension, duration of diabetes, drinking habit, triglycerides, ACE inhibitors, low-density lipoprotein (LDL) cholesterol, age, and smoking habit were the top-8 features ranked by the XGB model and identified as the most important features for predicting CKD in T1DM patients. These eight features were selected to develop the final prediction model using multivariate logistic regression, which showed 90.04% and 88.59% accuracy in internal and test data validation. The proposed model showed excellent performance and can be used for CKD identification in T1DM patients during routine checkups.
| S-EPMC9501949 | biostudies-literature