Diabetic foot ulcer (DFU) is one of the most serious and alarming diabetic complications, which often leads to high amputation rates in diabetic patients.Machine learning is a part of the field of artificial intelligence, which can automatically learn models from data and better inform clinical decision-making. We aimed to develop an accurate and explainable prediction model to estimate the risk of in-hospital amputation in patients with DFU. A total of 618 hospitalised patients with DFU were included in this study. The patients were divided into non-amputation, minor amputation or major amputation group.Light Gradient Boosting Machine (LightGBM) and 5-fold cross-validation tools were used to construct a multi-class classification model to predict the three outcomes of interest. In addition, we used the SHapley Additive exPlanations (SHAP) algorithm to interpret the predictions of the model. Our area under the receiver-operating-characteristic curve (AUC) demonstrated a 0.90, 0.85 and 0.86 predictive ability for non-amputation, minor amputation and major amputation outcomes, respectively. Taken together, our data demonstrated that the developed explainable machine learning model provided accurate estimates of the amputation rate in patients with DFU during hospitalisation. Besides, the model could inform individualised analyses of the patients' risk factors.Puguang Xie and Yuyao Li contributed equally to this work.
AimThis study was designed to examine the potential mechanism underlying these roles of platelet-rich plasma in treating diabetic foot ulcers (DFUs).MethodsStaphylococcus aureus and HaCaT were co-cultured under high glucose conditions to serve as an in vitro model for infected cells in DFUs. Platelet-rich gel (PRG) or extract liquid of platelet-rich gel (EPG) were used to interfere with the model to observe the growth of HaCaT cells and S. aureus, and the effect of miR-21 changes in HaCaT cells on PDCD4, NF-κB activity and related inflammatory factors.ResultsIncubation of HaCaT cells with S. aureus promoted the decline of cell proliferation. Under this condition, the level of PDCD4 and the activity of NF-κB were increased in HaCaT cells with concomitant increased of IL-6, TNF-α and decreased IL-10, TGF-β1 in cultured supernatant. Both of PRG and EPG exhibited specific anti-S. aureus activity where they protect HaCaT cells from bacterial damage and promote cell proliferation. Meanwhile, EPG was observed to increase intracellular miRNA-21 while reduce PDCD4 expression and inhibit NF-κB activity to suppress the inflammation in HaCaT cells.ConclusionThis in vitro model provides a valuable tool for study of wound healing in the treatment of DFUs. Our results suggest that miRNA-21 may regulate the expression of NF-κB through PDCD4 where it plays an anti-inflammatory role and promote proliferation in infected DFUs treated by PRP. These findings could provide novel therapeutic targets for refractory wounds.
Serum cystatin C (CysC) has been identified as a possible potential biomarker in a variety of diabetic complications, including diabetic peripheral neuropathy and peripheral artery disease. We aimed to examine the association between CysC and diabetic foot ulceration (DFU) in patients with type 2 diabetes (T2D). 411 patients with T2D were enrolled in this cross-sectional study at a university hospital. Clinical manifestations and biochemical parameters were compared between DFU group and non-DFU group. The association between serum CysC and DFU was explored by binary logistic regression analysis. The cut point of CysC for DFU was also evaluated by receiver operating characteristic (ROC) curve. The prevalence of coronary artery disease, diabetic nephropathy (DN), and DFU dramatically increased with CysC (P < 0.01) in CysC quartiles. Multivariate logistic regression analysis indicated that the significant risk factors for DFU were serum CysC, coronary artery disease, hypertension, insulin use, the differences between supine and sitting TcPO2, and hypertension. ROC curve analysis revealed that the cut point of CysC for DFU was 0.735 mg/L. Serum CysC levels correlated with DFU and severity of tissue loss. Our study results indicated that serum CysC was associated with a high prevalence of DFU in Chinese T2D subjects.
The authors have received no financial support for the material presented in this study outside of the scope of standard patient care reimbursement. This work was supported by the National Natural Science Foundation of China (NO. 81500596) awarded to Dr Wuquan Deng.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.