In a world where automation is becoming increasingly common, easier collection of mass of data and powerful computer processing has meant a transformation in the field of artificial intelligence (AI). The diabetic foot is a multifactorial problem; its issues render it suitable for analysis, interrogation, and development of AI. The latter has the potential to deliver many solutions to issues of delayed diagnosis, compliance, and defining preventative treatments. We describe the use of AI and the development of artificial neural networks that may supplement the failed networks in the diabetic foot. The potential of this technology, current developing applications, and their limitations for diabetic foot care are suggested.

Background: Revision surgery in the presence of infection carries high risks. We describe our results using a new technique to treat these challenging problems. We treated infected nonunions with cavitary voids with adjuvant antibiotic loaded calcium sulfate–hydroxyapatite paste composite and autologous bone graft (ABG) layer technique coupled with stable fixation. Methods: Thirty consecutive patients who underwent revision foot and ankle surgery for an infected nonunion were prospectively studied. Following multidisciplinary team workup, surgical debridement and biopsies were undertaken. Bone voids were measured and classified according to containment and size. ABG was mixed and layered with an adjuvant antibiotic-loaded calcium sulfate–hydroxyapatite paste followed by surgical reconstruction including arthrodesis and fixation. Empirical and pathogen-specific antibiotics were instituted until intraoperative sample-specific antibiotics were identified and used. Patients were prospectively followed up for a minimum of 1 year. Results: The male-female ratio was 16:14, mean age was 51.3 years, and 23.3% smoked at definitive surgery. Void volume was <1 cm3 (n=9), 1-2 cm3 (n = 13), and >2 cm3 (n=8). No patients either were lost to follow-up or had a further infective episode at a mean of 38.3 months; 86.7% united with fusion on imaging. Four patients had radiographic evidence of nonunion; 3 were asymptomatic and 1 required revision surgery (void >2 cm3). Independent ambulation was achieved at an average of 12 weeks, at 1 year mean American Orthopaedic Foot & Ankle Society score was 77.7 (SD 9.59), and the Manchester-Oxford Foot Questionnaire reached an effect size >0.5 in all domains at 1 year following surgery. The union rate was independent of smoking status and vitamin D deficiency ( P = .94). Conclusion: Layered autologous bone grafting with adjuvant antibiotic-loaded calcium sulfate–hydroxyapatite paste has been shown to be effective and safe in revision arthrodesis, with low comorbidities in void gaps without infection recurrence.

IntroductionDiabetic foot ulceration (DFU) is a common and challenging complication of diabetes. Risk stratification can guide further management. We aim to evaluate the prognostic performance of bedside tests used for peripheral arterial disease (PAD) diagnosis to predict DFU healing.Research design and methodsTesting for Arterial Disease in Diabetes (TrEAD) was a prospective observational study comparing the diagnostic performance of commonly used tests for PAD diagnosis. We performed a secondary analysis assessing whether these could predict DFU healing. Follow-up was performed prospectively for 12 months. The primary outcome was sensitivity for predicting ulcer healing. Secondary endpoints were specificity, predictive values, and likelihood ratios for ulcer healing.Results123 of TrEAD participants with DFU were included. In 12 months, 52.8% of ulcers healed. The best negative diagnostic likelihood ratio (NDLR) was observed for the podiatry ankle duplex scan (PAD-scan) monophasic or biphasic with adverse features(NDLR 0.35, 95% CI 0.14–0.90). The highest positive likelihood ratios were observed for toe brachial pressure index of ≤0.2 (positive diagnostic likelihood ratio (PDLR) 7.67, 95% CI 0.91–64.84) and transcutaneous pressure of oxygen of ≤20 mm Hg (PDLR 2.68, 95% CI 0.54–13.25). Cox proportional hazards modeling demonstrated significantly greater probabilities of healing with triphasic waveforms (HR=2.54, 95% CI 1.23–5.3, p=0.012) and biphasic waveforms with non-adverse features (HR=13.67, 95% CI 4.78–39.1, p<0.001) on PAD-scan.ConclusionsNo single test performed well enough to be used in isolation as a prognostic marker for the prediction of DFU healing.Trial registration numberNCT04058626.

Ameloblastic carcinoma is a rare odontogenic tumour with histologic features of ameloblastoma but with malignant potential. The majority occur in the mandible, arising de novo, or develop from pre-existing a benign ameloblastoma or odontogenic cysts. They typically present as a rapidly progressing, painful swelling of the face. Maxillary ameloblastic carcinoma is exceedingly rare and when reported, can present in a similar manner to mandibular ameloblastic carcinoma. We present a case of maxillary ameloblastic carcinoma in a 78-year-old man presenting with a 12-month history of unilateral nasal obstruction and frontal headaches. A benign-looking nasal lesion was identified and the patient was diagnosed with nasal polyps and underwent biopsy. However, histopathological examination of the lesion together with radiological imaging pointed towards a diagnosis of ameloblastic carcinoma. The patient was referred to our tertiary skull base centre and underwent successful treatment with radical surgical resection via a midfacial degloving approach. Final pathological examination of the surgical specimen confirmed the diagnosis of maxillary ameloblastic carcinoma. This case demonstrates an unusual presentation of an exceptionally rare malignancy, contributing to the growing number of reported cases in the literature of maxillary ameloblastic carcinoma.