Background: Insulin resistance is a common etiology of metabolic syndrome, but receiver operating characteristic (ROC) curve analysis shows a weak association in Koreans. Using a machine learning (ML) approach, we aimed to generate the best model for predicting insulin resistance in Korean adults aged > 40 of the Ansan/Ansung cohort using a machine learning (ML) approach. Methods: The demographic, anthropometric, biochemical, genetic, nutrient, and lifestyle variables of 8842 participants were included. The polygenetic risk scores (PRS) generated by a genome-wide association study were added to represent the genetic impact of insulin resistance. They were divided randomly into the training (n = 7037) and test (n = 1769) sets. Potentially important features were selected in the highest area under the curve (AUC) of the ROC curve from 99 features using seven different ML algorithms. The AUC target was ≥0.85 for the best prediction of insulin resistance with the lowest number of features. Results: The cutoff of insulin resistance defined with HOMA-IR was 2.31 using logistic regression before conducting ML. XGBoost and logistic regression algorithms generated the highest AUC (0.86) of the prediction models using 99 features, while the random forest algorithm generated a model with 0.82 AUC. These models showed high accuracy and k-fold values (>0.85). The prediction model containing 15 features had the highest AUC of the ROC curve in XGBoost and random forest algorithms. PRS was one of 15 features. The final prediction models for insulin resistance were generated with the same nine features in the XGBoost (AUC = 0.86), random forest (AUC = 0.84), and artificial neural network (AUC = 0.86) algorithms. The model included the fasting serum glucose, ALT, total bilirubin, HDL concentrations, waist circumference, body fat, pulse, season to enroll in the study, and gender. Conclusion: The liver function, regular pulse checking, and seasonal variation in addition to metabolic syndrome components should be considered to predict insulin resistance in Koreans aged over 40 years.

We present a simple synthetic approach for the preparation of monodisperse thermosensitive gelatin microspheres in a microfluidic system. Based on the mechanism of shear force-driven break-off, aqueous droplets of a gelatin solution were continuously produced in an immiscible continuous fluid. Under cooling conditions, the gelatin droplets solidified into hydrogel microspheres, which resulted from the aggregation or crystallization of collagen folds. The produced gelatin microspheres possess a high monodispersity and fast response to environmental temperature. In addition, the size of the prepared microspheres can be manipulated by altering the flow rate of the continuous phase or aqueous phase, and the physical strength of the gelatin microspheres can be controlled by simply changing the gelatin concentration. Furthermore, this approach enables the preparation of monodisperse microspheres with the ability to exhibit different thermosensitivities and encapsulate colloidal particles under mild conditions, which demonstrate sequential release of the desired encapsulants according to the responsive temperature.

BACKGROUND: Generation of monodisperse hydrogel microspheres is needed to make exquisite microenvironments, provide effective delivery system, and obtain reliable results. In this work, we present a simple microfluidic approach for the preparation of monodisperse pectin hydrogel microspheres because of efficient collection and shape of hydrogel.RESULTS: Based on the mechanism of in situ gelation and efficient collection, aqueous droplets of pectin polysaccharides are continuously generated in an immiscible continuous phase dissolving divalent metal ions, such as calcium. Under in situ gelation conditions, calcium ions are diffused into the interface between the continuous phase and the aqueous droplets, which triggers gelation of the pectin polysaccharides. The settling collection method, which involves dropping consecutive hydrogels from the outlet hole, is able to maintain the shape of the soft pectin hydrogels. Thus, pectin microspheres produced show high monodispersity (a coefficient of variation of 3.5%). In addition, the stiffness of the pectin hydrogels produced can be manipulated by a simple change of the concentration of pectin in the aqueous phase. The control of the mechanical properties can also be confirmed by measurement of the deformation of the pectin hydrogels using the micropipette aspiration method. Furthermore, the versatility of this approach enables the preparation of monodisperse pectin hydrogels with the capability to encapsulate or release nanoparticles on demand under mild conditions. The pectin microspheres are freely manipulated by the control of magnetic fields. CONCLUSION:We believe that the in situ microfluidic synthesis method combined with settling collection provides an efficient approach for the preparation of soft, monodisperse hydrogel microspheres.

Red blood cell membrane (RBCM) was coated onto the enzymatic glucose sensor. The permeability of RBCM was optimized by controlling the thickness. Intriguingly, the sensor was highly accurate, despite the existence of various interfering molecules.