ObjectiveThere is a paucity of research on patients presenting with uninfected diabetic foot ulcers (DFU) that go on to develop infection. We aimed to investigate the incidence and risk factors for developing infection in a large regional cohort of patients presenting with uninfected DFUs.MethodsWe performed a secondary analysis of data collected from a validated prospective state-wide clinical diabetic foot database in Queensland (Australia). Patients presenting for their first visit with an uninfected DFU to a Diabetic Foot Service in one of thirteen Queensland regions between January 2012 and December 2013 were included. Socio-demographic, medical history, foot disease history, DFU characteristics and treatment variables were captured at the first visit. Patients were followed until their DFU healed, or if their DFU did not heal for 12-months, to determine if they developed a foot infection in that period.ResultsOverall, 853 patients were included; mean(standard deviation) age 62.9(12.8) years, 68.0% male, 90.9% type 2 diabetes, 13.6% indigenous Australians. Foot infection developed in 342 patients for an overall incidence of 40.1%; 32.4% incidence in DFUs healed <3 months, 55.9% in DFUs healed between 3–12 months (p<0.05). Independent risk factors (Odds Ratio (95% confidence interval)) for developing infection were: DFUs healed between 3–12 months (2.3 (1.6–3.3)), deep DFUs (2.2 (1.2–3.9)), peripheral neuropathy (1.8 (1.1–2.9)), previous DFU history (1.7 (1.2–2.4)), foot deformity (1.4 (1.0–2.0)), female gender (1.5 (1.1–2.1)) and years of age (0.98 (0.97–0.99)) (all p<0.05).ConclusionsA considerable proportion of patients presenting with an uninfected DFU will develop an infection prior to healing. To prevent infection clinicians treating patients with uninfected DFUs should be particularly vigilant with those presenting with deep DFUs, previous DFU history, peripheral neuropathy, foot deformity, younger age, female gender and DFUs that have not healed by 3 months after presentation.

No abstract

The health condition of a wheelset bearing, the key component of a railway bogie, has a considerable impact on the safety of a train. Traditional bearing fault diagnosis techniques generally extract signals manually and then diagnose the bearing health conditions through the classifier. However, high-speed trains (HSTs) are usually faced with variable loads, variable speeds, and strong environmental noise, which pose a huge challenge to the application of the traditional bearing fault diagnosis methods in wheelset bearing fault diagnosis. Therefore, this paper proposes a 1D residual block, and based on the block, a novel deeper 1D convolutional neural network (Der-1DCNN) is proposed. The framework includes the idea of residual learning and can effectively learn high-level and abstract features while effectively alleviating the problem of training difficulty and the performance degradation of a deeper network. Additionally, for the first time, we fully use the wide convolution kernel and dropout technology to improve the model's ability to learn low-frequency signal features related to the fault components and to enhance the network's generalization performance. By constructing a deep residual learning network, Der-1DCNN can adaptively learn the deep fault features of the original vibration signal. This method not only achieves very high diagnostic accuracy for the fault diagnosis task of wheelset bearings in HSTs under strong noise environment, but also its performance is quite superior when the train's working load changes without any domain adaptation algorithm processing. The proposed Der-1DCNN is evaluated on the dataset of the multi-operating conditions of the wheelset bearings of HSTs. Experiments show that this method shows a better diagnostic performance compared with the state-of-the-art deep learning methods of bearing fault diagnosis, which proves the method's effectiveness and superiority. INDEX TERMS High-speed trains, wheelset bearings fault diagnosis, deep learning, one-dimensional residual block, wide convolutional kernel.