Explore the vast range of titles available.

Machine learning (ML) has shown great potential in recognizing complex disease patterns and supporting clinical decision-making. Diabetic foot ulcers (DFUs) represent a significant multifactorial medical problem with high incidence and severe outcomes, providing an ideal example for a comprehensive framework that encompasses all essential steps for implementing ML in a clinically relevant fashion. This paper aims to provide a framework for the proper use of ML algorithms to predict clinical outcomes of multifactorial diseases and their treatments. The comparison of ML models was performed on a DFU dataset. The selection of patient characteristics associated with wound healing was based on outcomes of statistical tests, that is, ANOVA and chi-square test, and validated on expert recommendations. Imputation and balancing of patient records were performed with MIDAS (Multiple Imputation with Denoising Autoencoders) Touch and adaptive synthetic sampling, respectively. Logistic regression, support vector machine (SVM), k-nearest neighbors, random forest (RF), extreme gradient boosting (XGBoost), Bayesian additive regression trees, and artificial neural network were trained, cross-validated, and optimized using random sampling on the patient dataset. To evaluate model calibration and clinical utility, calibration curves, Brier scores, and decision curve analysis (DCA) were performed. The exploratory dataset consisted of 700 patient records with 199 variables. After dataset cleaning, the variables used for model training included age, smoking status, toe systolic pressure, blood pressure, oxygen saturation, hemoglobin, hemoglobin A , estimated glomerular filtration rate, wound location, diabetes type, Texas wound classification, neuropathy, and wound area measurement. The SVM obtained a stable accuracy of 0.853 (95% CI 0.810-0.896) with an area under the receiver operating characteristic curve of 0.922 (95% CI 0.889-0.955). The RF and XGBoost acquired an accuracy of 0.838 (95% CI 0.793-0.883) and 0.815 (95% CI 0.768-0.862), respectively, with areas under the receiver operating characteristic curve of 0.917 (95% CI 0.883-0.951) for RF and 0.889 (95% CI 0.849-0.929) for XGBoost. SVM, RF, and XGBoost were well-calibrated, with average Brier scores around 0.127 (SD 0.013). DCA showed that the SVM provided the highest net clinical benefit across relevant risk thresholds. Handling missing values, feature selection, and addressing class imbalance are critical components of the key steps in developing ML applications for clinical research. Seven models were selected for comparing their predictive power regarding complete wound healing, and each model representing a different branch in ML. In this initial DFU dataset used as an example, the SVM achieved the best performance in predicting clinical outcomes, followed by RF and XGBoost. The model's calibration and clinical utility were determined through calibration curves, Brier scores, and DCA, demonstrating its potential relevance in clinical decision-making.

Objective The aim of this online clinical vignette-based survey study was to compare risk assessments by vascular surgeons, anaesthesiologists and interventional radiologists involved in treating patients with aortic aneurysms in the Netherlands with the NSQIP risk calculator outcomes. Methods Participants, recruited using purposive sampling, provided their estimation of the likelihood of postoperative complications and events following aortic surgery in five fictional cases. These cases were subsequently scored using the NSQIP calculator. The risk assessments were statistically analysed using the ANOVA and student t-test. Results All participating specialists i.e. twelve vascular surgeons, ten interventional radiologists and ten anaesthesiologists completed the survey. In the vast majority of outcomes and vignettes, no significant differences were found between various specialists, whereas significant differences were found between the NSQIP risk calculator outcomes and the combined risk assessments of the specialists. Overall, specialist risk assessments differ from the NSQIP, but neither particularly higher nor lower compared to the risk calculator. Conclusions Risk assessment by vascular surgeons, anaesthesiologists and interventional radiologists differs significantly with NSQIP risk calculator outcomes, within the framework of both endovascular and open aortic aneurysm repair. Based on these results, implementing the NSQIP risk calculator in preoperative workup could be of added value in both patient planning as well as adequately informing patients for obtaining consent.

Objectives Radiocephalic arteriovenous fistulas (RCAVF) are the preferred vascular access (VA) for hemodialysis (HD). Cohort studies from North America revealed that nonmaturation is a significant disadvantage of RCAVFs compared to other VAs. DESIGN: This present retrospective study describes the incidence of nonmaturation of AVFs and functional failure of arteriovenous grafts (AVG) in a multicentre cohort in the Netherlands and attempts to create a prediction model for nonmaturation of RCAVFs. Furthermore, the efficacy of interventions to promote maturation as well as the variability between hemodialysis centers was evaluated. Materials Medical records from 8 hospitals from 1997 to 2016 were retrospectively evaluated for VA type, maturation/primary success and demographics and comorbidities. Methods A prediction model was created for RCAVF nonmaturation using multivariate logistic regression analysis, selecting significant predictors using backward selection. Discrimination and calibration of the model were assessed. Results 1383 AVFs and 273 AVGs were included in 1221 patients. Overall nonmaturation was 24% for RCAVFs, and 11% for upper arm AVFs. The functional failure rate for AVGs was 6%. The nonmaturation rate of contralateral RCAVFs after failure of an RCAVF was 22%. Procedures to improve RCAVF maturation were successful in 98/142 cases (69%). Predictors for nonmaturation were female gender, peripheral vascular disease, cerebrovascular disease and a cephalic vein diameter <2.5 mm, but the prediction model lacked sensitivity and specificity predicting individual RCAVF nonmaturation (C-statistic 0.629). Conclusion Nonmaturation rates are highest for RCAVFs, but nonmaturation could not be predicted with demographic parameters.

Endovascular aneurysm repair (EVAR) is first-choice treatment for many patients with abdominal aortic aneurysms. Complications unique to endovascular treatment include endoleak and endotension, which can eventually lead to rupture. We present two cases of late aortic rupture after EVAR, where both patients had recent preceding catheter-directed thrombolysis with urokinase for acute limb ischemia. These cases suggest a relation between thrombolytic therapy and aortic rupture after EVAR, and we should therefore be aware of this possible complication.

Purpose: Perioperative risk assessments for complex aneurysms are based on the anatomical extent of the aneurysm and do not take the length of the aortic exclusion into account, as it was developed for open repair. Nevertheless, in the endovascular repair (ER) of complex aortic aneurysms, additional segments of healthy aorta are excluded compared with open repair (OR). The aim of this study was to assess differences in aortic exclusion between the ER and OR of complex aortic aneurysms, to subsequently assess the current classification for complex aneurysm repair. Methods: This retrospective observational study included patients that underwent complex endovascular aortic aneurysm repair by means of fenestrated endovascular aneurysm repair (FEVAR), fenestrated and branched EVAR (FBEVAR), or branched EVAR (BEVAR). The length of aortic exclusion and the number of patent segmental arteries were determined and compared per case in ER and hypothetical OR, using a Wilcoxon signed-rank test. Results: A total of 71 patients were included, who were treated with FEVAR (n = 44), FBEVAR (n = 8), or BEVAR (n = 19) for Crawford types I (n = 5), II (n = 7), III (n = 6), IV (n = 7), and V (n = 2) thoracoabdominal or juxtarenal (n = 44) aneurysms. There was a significant increase in the median exclusion of types I, II, III, IV, and juxtarenal aneurysms (p < 0.05) in ER, compared with hypothetical OR. The number of patent segmental arteries in the ER of type I–IV and juxtarenal aneurysms was significantly lower than in hypothetical OR (p < 0.05). Conclusion: There are significant differences in the length of aortic exclusion between ER and hypothetical OR, with the increased exclusion in ER resulting in a lower number of patent segmental arteries. The ER and OR of complex aortic aneurysms should be regarded as distinct modalities, and as each approach deserves a particular risk assessment, future efforts should focus on reporting on the extent of exclusion per treatment modality, to allow for appropriate comparison.

Background: Drug-eluting stents (DES) have been introduced successfully in clinical practice to prevent post-angioplasty restenosis. Nevertheless, concerns about the safety of DES still exist. Objective: To investigate the vascular pathology and transcriptional responses to sirolimus and paclitaxel in a murine model for restenosis on underlying diseased atherosclerotic arteries. Methods: Atherosclerotic lesions were induced by placement of a perivascular cuff around the femoral artery of hypercholesterolaemic ApoE*3-Leiden transgenic mice. Two weeks later these cuffs were replaced either by sirolimus- or paclitaxel-eluting cuffs. The vascular pathological effects were evaluated after two additional weeks. Results: Both anti-restenotic compounds significantly inhibited restenotic lesion progression on the atherosclerotic plaques. Vascular histopathological analyses showed that local delivery of sirolimus has no significant adverse effects on vascular disease. Conversely, high dosages of paclitaxel significantly increased apoptosis, internal elastic lamina disruption, and decreased medial and intimal smooth muscle cells and collagen content. Moreover, transcriptional analysis by real-time RT-PCR showed an increased level of pro-apoptotic mRNA transcripts (FAS, BAX, caspase 3) in paclitaxel-treated arteries. Conclusions: Sirolimus and paclitaxel are effective in preventing restenosis. Sirolimus has no significant effect on arterial disease. In contrast, paclitaxel at high concentration demonstrated adverse vascular pathology and transcriptional responses, suggesting a narrower therapeutic range of this potent drug. Since the use of overlapping stents is becoming more common in DES technology, this factor is important, given that higher dosages of paclitaxel may lead to increased apoptosis in the vessel wall and, consequently, to a more unstable phenotype of the pre-existing atherosclerotic lesion.

Vascular diseases such as atherosclerosis, restenosis and vein graft stenosis affect millions of Americans each year. The pathophysiologies of these diseases all consist of unregulated smooth muscle cell proliferation that results in intimal hyperplasia and ultimately vascular occlusion. Gene therapy is a promising treatment option for smooth muscle proliferative diseases with several genes identified as potential therapies. However, the efficient delivery of these genes to the target cells remains a major limiting factor. Our lab recently developed a non-viral delivery method for gene transfer to the vasculature using electroporation. We have demonstrated that plasmid delivery by electroporation results in high level gene expression in rat mesenteric arteries with expression peaking between 1 and 3 days post transfer. Based on our results in the mesenteric arteries, we reasoned that electroporation could be used to deliver genes to other vascular beds. Using a square wave electroporator (200 V/cm, 8 pulses of 10msec duration) we delivered GFP and luciferase reporter plasmids to femoral arteries of mice. Delivery of a GFP-expressing plasmid results in expression not unlike that we have previously observed in the mesenteric arteries, and histological analysis was used to determine the localization of gene expression. To quantify the levels of gene expression, we delivered a CMV driven luciferase-expressing plasmid. In animals receiving DNA plus electroporation, we obtained an average of 200 pg/mouse with up to nanogram levels at 2 days post-transfer. In contrast, luciferase expression was undetected in arteries receiving DNA but no electroporation. These levels are similar to those achieved in the mesenteric vessels, thus providing evidence that our previously described gene delivery method for the vasculature can be successfully applied to multiple vascular beds. To extend these findings to a vascular disease model, we have focused on a mouse model of restenosis where a polyethylene cuff placed around the femoral artery results in significant intimal hyperplasia at 21 days post-injury. Based on results from other labs demonstrating that early expression of the cell cycle inhibitor p27 can inhibit intimal hyperplasia following vascular injury, we hypothesized that delivering a p27 expressing plasmid to the mouse femoral artery by electroporation immediately before cuff placement would decrease the degree of intimal thickening after injury, providing protection from intimal hyperplasia and vessel occlusion. To test this hypothesis we delivered a CMV driven p27 expressing plasmid by electroporation, placed the cuff, and assayed the degree of intimal hyperplasia by morphometric analysis on hematoxylin and eosin stained thin sections at 21 days post-injury. As expected, injury was less severe in the treated animals. Taken together with our previous results using a rat carotid angioplasty model, these results suggest that electroporation-mediated gene transfer of cytostatic genes can protect from restenosis.

There is a lack of comprehensive and uniform data on primary upper extremity deep venous thrombosis (pUEDVT). pUEDVT includes venous thoracic outlet syndrome related upper extremity deep venous thrombosis (UEDVT) and idiopathic UEDVT. Research on these conditions has been hampered by their rarity, lack of uniform diagnostic criteria, and heterogeneity in therapeutic strategies. To improve current research data collection using input of all various pUEDVT treating medical specialists, we initiated the ThoRacic OuTlet Syndrome (TROTS) registry. The aim of the TROTS registry is to a) collect extensive data on all pUEDVT patients through a predefined protocol, b) give insight in the long term outcome using patient reported outcome measures, c) create guidance in the diagnostic and clinical management of these conditions, and thereby d) help provide content for future research. The TROTS registry was designed as an international prospective longitudinal observational registry for data collection on pUEDVT patients. All pUEDVT patients, regardless of treatment received, can be included in the registry after informed consent is obtained. All relevant data regarding the initial presentation, diagnostics, treatment, and follow-up will be collected prospectively in an electronic case report form. In addition, a survey containing general questions, a Health-related Quality of Life questionnaire (EQ-5D-5L), and Functional Disability questionnaire (Quick-DASH) will be sent periodically (at the time of inclusion, one and two years after inclusion, and every five years after inclusion) to the participant. The registry protocol was approved by the Medical Ethical Review Board and registered in the Netherlands Trial Register under Trial-ID NL9680. The data generated by the registry will be used for future research on pUEDVT and published in peer reviewed journals. TROTS registry data will be used to further establish the optimal management of pUEDVT and lay the foundation for future research and guidelines.