Development and validation of an insulin resistance model for a population without diabetes mellitus and its clinical implication: a prospective cohort study

Tsai, Shang‐Feng; Yang, Chao-Tung; Liu, Wei-Ju; Lee, Chia-Lin

doi:10.1016/j.eclinm.2023.101934

Cited by 20 publications

(11 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been used for many different types of data mining tasks such as classification, regression, and ranking (39). Recent studies indicate that GBDT-based models, such as XGBoost, outperform logistic regression (LR), K-Nearest Neighbor (KNN), decision tree (DT), support vector machines (SVM), artificial neural networks (ANN) and deep neural network (DNN), in predicting insulin resistance, supporting the superior predictive accuracy of GBDT-based models (40,41), which might be an important explanation of our findings that the LightGBM model is a better choice in developing models for insulin sensitivity in the community and primary care settings.…”

Section: Discussionmentioning

confidence: 99%

Development and validation of machine learning-augmented algorithm for insulin sensitivity assessment in the community and primary care settings: a population-based study in China

Zhang,

Zeng,

Zhang

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

ObjectiveInsulin plays a central role in the regulation of energy and glucose homeostasis, and insulin resistance (IR) is widely considered as the “common soil” of a cluster of cardiometabolic disorders. Assessment of insulin sensitivity is very important in preventing and treating IR-related disease. This study aims to develop and validate machine learning (ML)-augmented algorithms for insulin sensitivity assessment in the community and primary care settings.MethodsWe analyzed the data of 9358 participants over 40 years old who participated in the population-based cohort of the Hubei center of the REACTION study (Risk Evaluation of Cancers in Chinese Diabetic Individuals). Three non-ensemble algorithms and four ensemble algorithms were used to develop the models with 70 non-laboratory variables for the community and 87 (70 non-laboratory and 17 laboratory) variables for the primary care settings to screen the classifier of the state-of-the-art. The models with the best performance were further streamlined using top-ranked 5, 8, 10, 13, 15, and 20 features. Performances of these ML models were evaluated using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPR), and the Brier score. The Shapley additive explanation (SHAP) analysis was employed to evaluate the importance of features and interpret the models.ResultsThe LightGBM models developed for the community (AUROC 0.794, AUPR 0.575, Brier score 0.145) and primary care settings (AUROC 0.867, AUPR 0.705, Brier score 0.119) achieved higher performance than the models constructed by the other six algorithms. The streamlined LightGBM models for the community (AUROC 0.791, AUPR 0.563, Brier score 0.146) and primary care settings (AUROC 0.863, AUPR 0.692, Brier score 0.124) using the 20 top-ranked variables also showed excellent performance. SHAP analysis indicated that the top-ranked features included fasting plasma glucose (FPG), waist circumference (WC), body mass index (BMI), triglycerides (TG), gender, waist-to-height ratio (WHtR), the number of daughters born, resting pulse rate (RPR), etc.ConclusionThe ML models using the LightGBM algorithm are efficient to predict insulin sensitivity in the community and primary care settings accurately and might potentially become an efficient and practical tool for insulin sensitivity assessment in these settings.

show abstract

Section: Discussionmentioning

confidence: 99%

Development and validation of machine learning-augmented algorithm for insulin sensitivity assessment in the community and primary care settings: a population-based study in China

Zhang,

Zeng,

Zhang

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

show abstract

“…Harrell’s concordance index (C-index) was used to evaluate the performance of the prognostic models. Moreover, we calculated each feature’s contribution for the prognosis task by utilizing the SHapley Additive exPlanation (SHAP) values obtained from the “kernelshap” R package [ 38 , 39 ].…”

Section: Methodsmentioning

confidence: 99%

EfficientNet-Based System for Detecting EGFR-Mutant Status and Predicting Prognosis of Tyrosine Kinase Inhibitors in Patients with NSCLC

Xu,

Wang,

Dai

et al. 2024

J Digit Imaging. Inform. med.

View full text Add to dashboard Cite

We aimed to develop and validate a deep learning-based system using pre-therapy computed tomography (CT) images to detect epidermal growth factor receptor (EGFR)-mutant status in patients with non-small cell lung cancer (NSCLC) and predict the prognosis of advanced-stage patients with EGFR mutations treated with EGFR tyrosine kinase inhibitors (TKI). This retrospective, multicenter study included 485 patients with NSCLC from four hospitals. Of them, 339 patients from three centers were included in the training dataset to develop an EfficientNetV2-L-based model (EME) for predicting EGFR-mutant status, and the remaining patients were assigned to an independent test dataset. EME semantic features were extracted to construct an EME-prognostic model to stratify the prognosis of EGFR-mutant NSCLC patients receiving EGFR-TKI. A comparison of EME and radiomics was conducted. Additionally, we included patients from The Cancer Genome Atlas lung adenocarcinoma dataset with both CT images and RNA sequencing data to explore the biological associations between EME score and EGFR-related biological processes. EME obtained an area under the curve (AUC) of 0.907 (95% CI 0.840–0.926) on the test dataset, superior to the radiomics model (P = 0.007). The EME and radiomics fusion model showed better (AUC, 0.941) but not significantly increased performance (P = 0.895) compared with EME. In prognostic stratification, the EME-prognostic model achieved the best performance (C-index, 0.711). Moreover, the EME-prognostic score showed strong associations with biological pathways related to EGFR expression and EGFR-TKI efficacy. EME demonstrated a non-invasive and biologically interpretable approach to predict EGFR status, stratify survival prognosis, and correlate biological pathways in patients with NSCLC.

show abstract

“…Many potential factors may be associated with the development of IR, such as obesity, stress, age, medications, and genetics 2 . In addition, IR may also contribute to many clinical conditions, such as type 2 diabetes (T2D), metabolic syndrome, fatty liver disease, and cardiovascular disease 3 . IR may be an early predictor of T2D.…”

Section: Introductionmentioning

confidence: 99%

Using anthropometric parameters to predict insulin resistance among patients without diabetes mellitus

Liu

Jin²,

Feng

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Anthropometric parameters are widely used in the clinical assessment of hypertension, type 2 diabetes, and cardiovascular disease. However, few studies have compared the association between different anthropometric parameters and insulin resistance (IR). This study was aimed at investigating the relationship between 6 indicators, including body mass index (BMI), calf circumference (CC), arm circumference (AC), thigh circumference (TC), waist circumference (WC), waist-height ratio (WHtR), and IR. Methods: Homeostasis Model Assessment of Insulin Resistance (HOMA-IR) was used to measure IR. Weighted linear regression was used to assess the relationship between different parameters and IR. The receiver operating characteristic curve (ROC) was employed to compare the strength of the relationship between different anthropometric parameters and IR. Results: A total of 8,069 participants were enrolled in our study, including 4,873 without IR and 3,196 with IR. The weighted linear regression results showed that BMI, CC, AC, TC and WC were significantly correlated with IR, except WHtR. After adjusting for multiple confounding factors, we found that BMI, AC and WC were significantly positively correlated with IR, while TC was significantly negatively correlated with IR. Logistic regression results showed that a larger TC was associated with a decreased risk of IR. In addition, BMI and WC had similar areas under the curve (AUC: 0.780, 95% CI: 0.770-0.790; AUC: 0.774, 95% CI: 0.763-0.784, respectively), which were higher than TC and AC (AUC: 0.698, 95% CI: 0.687-0.710, AUC: 0.746, 95% CI: 0.735-0.757, respectively). Conclusions: To our knowledge, this is the first study to report a negative correlation between TC and IR among patients without diabetes mellitus. Therefore, TC may be a new tool to guide public health and a clinical predictor of IR in non-diabetic patients.

show abstract

Development and validation of an insulin resistance model for a population without diabetes mellitus and its clinical implication: a prospective cohort study

Cited by 20 publications

References 48 publications

Development and validation of machine learning-augmented algorithm for insulin sensitivity assessment in the community and primary care settings: a population-based study in China

Development and validation of machine learning-augmented algorithm for insulin sensitivity assessment in the community and primary care settings: a population-based study in China

EfficientNet-Based System for Detecting EGFR-Mutant Status and Predicting Prognosis of Tyrosine Kinase Inhibitors in Patients with NSCLC

Using anthropometric parameters to predict insulin resistance among patients without diabetes mellitus

Contact Info

Product

Resources

About