Increased insulin resistance is associated with vascular cognitive impairment in Chinese patients with cerebral small vessel disease

Impact Exploration of Spatiotemporal Feature Derivation and Selection on Machine Learning-Based Predictive Models for Post-Embolization Cerebral Aneurysm Recanalization

PURPOSE

To enhance the performance of machine learning (ML) models for the post-embolization recanalization of cerebral aneurysms, we evaluated the impact of hemodynamic feature derivation and selection method on six ML algorithms.

METHODS

We utilized computational fluid dynamics (CFD) to simulate hemodynamics in 66 cerebral aneurysms from 65 patients, including 57 stable and nine recanalized aneurysms. We derived a total of 107 features for each aneurysm, encompassing four clinical features, 12 morphological features, and 91 hemodynamic features. To investigate the influence of feature derivation and selection methods on the ML models, we employed two derivation methods, simplified and fully derived, in combination with four selection methods: all features, statistically significant analysis, stepwise multivariate logistic regression analysis (stepwise-LR), and recursive feature elimination (RFE). Model performance was assessed using the area under the receiver operating characteristic curve (AUROC) and precision-recall curve (AUPRC) on both the training and testing datasets.

RESULTS

The AUROC values on the testing dataset exhibited a wide-ranging spectrum, spanning from 0.373 to 0.863. Fully derived features and the RFE selection method demonstrated superior performance in intra-model comparisons. The multi-layer perceptron (MLP) model, trained with RFE-selected fully derived features, achieved the best performance on the testing dataset, with an AUROC value of 0.863 (95% CI: 0.684- 1.000).

CONCLUSION

Our study demonstrated the importance of feature derivation and selection in determining the performance of ML models. This enabled the development of accurate decision-making models without the need to invade the patient.

Fluid dynamic analysis in predicting the recanalization of intracranial aneurysms after coil embolization - A study of spatiotemporal characteristics

Purpose

Hemodynamics play a key role in the management of cerebral aneurysm recanalization after coil embolization; however, the most reliable hemodynamic parameter remains unknown. Previous studies have explored the use of both spatiotemporally averaged and maximal definitions for hemodynamic parameters, based on computational fluid dynamics (CFD) analysis, to build predictive models for aneurysmal recanalization. In this study, we aimed to assess the influence of different spatiotemporal characteristics of hemodynamic parameters on predictive performance.

Methods

Hemodynamics were simulated using CFD for 66 cerebral aneurysms from 65 patients. We evaluated 14 types of spatiotemporal definitions for two hemodynamic parameters in the pre-coiling model and five in virtual post-coiling model (VM) created by cutting the aneurysm from the pre-coiling model. A total of 91 spatiotemporal hemodynamic features were derived and utilized to develop univariate predictor (UP) and multivariate logistic regression (LR) models. The model's performance was assessed using two metrics: the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC).

Results

Different spatiotemporal hemodynamic features exhibited a wide range of AUROC values ranging from 0.224 to 0.747, with 22 feature pairs showing a significant difference in AUROC value (P-value <0.05), despite being derived from the same hemodynamic parameter. PDave,q1 was identified as the strongest UP with AUROC/AUPRC values of 0.747/0.385, yielding sensitivity and specificity value of 0.889 and 0.614 at the optimal cut-off value, respectively. The LR model further improved the prediction performance, having AUROC/AUPRC values of 0.890/0.903. At the optimal cut-off value, the LR model achieved a specificity of 0.877, sensitivity of 0.719, outperforming the UP model.

Conclusion

Our research indicated that the characteristics of hemodynamic parameters in terms of space and time had a significant impact on the development of predictive model. Our findings suggest that LR model based on spatiotemporal hemodynamic features could be clinically useful in predicting recanalization after coil embolization in patients, without the need for invasive procedures.

A machine learning-based diagnosis modelling of type 2 diabetes mellitus with environmental metal exposure

BACKGROUND AND OBJECTIVE

Increasing and compelling evidence has been proved that urinary and dietary metal exposure are underappreciated but potentially modifiable biomarkers for type 2 diabetes mellitus (T2DM). The aims of this study were (1) to identify the key potential biomarkers which contributed to T2DM with effective and parsimonious features and (2) to assess the utility of baseline variables and metal exposure in the diagnosis of T2DM.

METHODS

Based on the National Health and Nutrition Examination Survey (NHANES), we selected 9822 screening records with 82 significant variables covering demographics, lifestyle, anthropometric measures, diet and metal exposure for this study. Combining extreme gradient boosting (XGBoost), random forest and light gradient boosting machine (lightGBM), a soft voting ensemble model was proposed to measure the importance of 82 features. With this soft voting ensemble model and variance inflation factor (VIF), strong multicollinear features with low importance scores were further removed from candidate biomarkers. Then, a soft voting ensemble classifier was adopted to demonstrate the efficiency of the proposed feature selection method.

RESULTS

With the novel feature selection method, 12 baseline variables and 3 metal variables were selected to detect patients at risk for T2DM in our study. For metal variables, the dietary copper (Cu), urinary cadmium (Cd) and urinary mercury (Hg) metals were selected as the most remarkable metal exposure and the corresponding P-values were all less than 0.05. In a classification model of T2DM with 12 baseline biomarkers, the addition of 3 metal exposure improved the classification accuracy of T2DM from a traditional area under the curve (AUC) 0.792 of the receiver operating characteristic (ROC) to an AUC 0.847.

CONCLUSIONS

This was the first demonstration of T2DM classification with machine learning under urinary and dietary metal exposure. Improved prediction precision illustrated the effectiveness of the proposed machine learning-based diagnosis model facilitated lifestyle/dietary intervention for T2DM prevention.

Correlation between insulin resistance and cerebral microbleeds among Chinese patients with cerebral small vessel disease

BACKGROUND AND OBJECTIVES

Insulin resistance (IR) plays an important role in the pathogenesis of cerebral small vessel disease (CSVD); however, little is known about the relationship between IR and the incidence of cerebral microbleeds (CMBs) in Asian populations. The aim of this study is to investigate the relationship between CMBs and IR in Chinese patients with CSVD.

METHODS

This retrospective study included 240 patients with CSVD. Patients were categorized by the homeostatic model assessment of insulin resistance (HOMA-IR): Quartile 1 (≤1.26), Quartile 2 (1.27-1.92), Quartile 3 (1.93-2.89), and Quartile 4 (>2.89). The medical record of each patient was reviewed, and demographic, clinical and laboratory information was abstracted. All patients completed an MRI scan, and CMBs were defined as round or ovoid hypointense lesions on SWI sequence.

RESULTS

CMBs were present in 82 (34.17%) of the 240 patients that were included in the study (mean age, 71 years; male, 54.89%). After adjustment for potential confounding variables, insulin resistance was associated with the presence of CMBs (adjusted odds ratio 2.298, 95% confidence interval 1.017-5.194 for Q4:Q1; P = 0.046). According to receiver operating characteristic analysis, the best discriminating factor for CMBs was a HOMA-IR level ≥2.215 (area under the curve 0.595; sensitivity 51.2%; specificity 65.2%).

CONCLUSIONS

IR is significantly associated with the presence of CMBs, suggesting the potential role of IR as a predictive marker for CMBs in patients with CSVD.

The triglyceride glucose index is associated with the cerebral small vessel disease in a memory clinic population

BACKGROUND AND OBJECTIVES

Insulin resistance (IR) has been associated with the cerebral small vessel disease (cSVD). However, as the surrogate marker of IR, there is little known about the relationship between the triglyceride glucose (TyG) index and cSVD. In this cross-sectional study, we aimed to evaluate the relationship between the TyG index and cSVD in a memory clinic population and explore the value of TyG index to improve the risk stratification of cSVD.

METHODS

We included participants who attended our memory clinic from January 2016 to December 2020. TyG index was determined as ln [fasting triglyceride (mg/dL) × fasting plasma glucose (mg/dL)/2]. We assessed lacunes, microbleeds, white matter hyperintensity (WMH) and enlarged perivascular spaces (EPVS) on MRI and calculated the total cSVD burden.

RESULTS

A total of 297 subjects were included (median age: 65 years, male sex: 64.98%). In the adjusted model, when dividing TyG index into quartiles, subjects with TyG index in the top quartile, compared with those in the bottom quartile, were more likely to have lacunes (P = 0.035), moderate-severe WMH (P = 0.001), a higher grade of deep WMH (P = 0.004), a higher grade of PVWMH (P = 0.032), a higher grade of EPVS (P = 0.002), and a higher cSVD score (P < 0.001). When introducing TyG index into traditional risk factors to predict moderate to severe cSVD, both area under the curve (0.745 vs 0.802, P = 0.003) and integrated discrimination index (0.080, 95% CI 0.050-0.110, P < 0.001) displayed an improvement from TyG index.

CONCLUSIONS

The TyG index is correlated with cSVD and may have the potential to be a surrogate marker of insulin resistance and optimize the risk stratification.