Machine learning methods applied to audit of surgical margins after curative surgery for facial (non-melanoma) skin cancer.

We aimed to build a model to predict positive margin status after curative excision of facial non-melanoma skin cancer based on known risk factors that contribute to the complexity of the case mix. A pathology output of consecutive histology reports was requested from three oral and maxillofacial units in the south east of England. The dependent variable was a deep margin with peripheral margin clearance at a 0.5 mm threshold. A total of 3354 cases were analysed. Positivity of either the peripheral or deep margin for both squamous cell carcinoma (SCC) and basal cell carcinoma (BCC) was 15.4% at Unit 1, 21.1% at Unit 2, and 15.4% at Unit 3. Predictive models accounting for patient and tumour factors were developed using automated machine learning methods. The champion models demonstrated good discrimination for predicting margin status after excision of BCCs (AUROC = 0.67) and SCCs (AUROC = 0.71). We demonstrate that rates of positive excision margins of facial non-melanoma skin cancer (fNMSC), when adjusted by the risk prediction model, can be used to compare unit performance fairly once variations in tumour factors and patient factors are accounted for.

Longstanding unilateral dislocation of the temporomandibular joint in a 6-year-old girl.

Unilateral longstanding dislocation of the temporomandibular joint (TMJ) is rare in children. These patients may demonstrate some function in opening and closing of the mouth due to the formation of a pseudo-joint in the dislocated position. In this report we describe a case of longstanding unilateral dislocation of the TMJ in a 6-year-old girl, highlighting the diagnostic difficulty and management of the condition.

Transplant-related experience in pharyngo-oesophageal reconstruction: use of organ preservation techniques to improve ischaemic tolerance in free jejunal flaps.

Reconstruction of pharyngo-oesophageal defects remains a surgical challenge. Free jejunal flaps, first described by Seidenberg in 1959, are used to reconstruct circumferential defects, but their main disadvantage is sensitivity to ischaemia. Others are secretions, an unpleasant smell, and problems at the donor site. To improve the tolerance of the jejunal segment to ischaemia and to give the surgeon more time, we cool it after harvest and flush it with organ preservation fluid. We describe the technique in a small case series of seven patients.

Biopsy of parotid masses: Review of current techniques.

Definitive diagnosis of parotid gland masses is required optimal management planning and for prognosis. There is controversy over whether fine needle aspiration cytology (FNAC) or ultrasound guided core biopsy (USCB) should be the standard for obtaining a biopsy. The aim of this review is to assess the current evidence available to assess the benefits of each technique and also to assess the use of intra-operative frozen section (IOFS). Literature searches were performed using pubmed and google scholar. The literature has been reviewed and the evidence is presented. FNAC is an accepted and widely used technique. It has been shown to have variable diagnostic capabilities depending on centres and experience of staff. USCB has a highly consistent diagnostic accuracy and can help with tumour grading and staging. However, the technique is more invasive and there is a question regarding potential for seeding. Furthermore, USCB is less likely to be offered as part of a one-stop clinic. IOFS has no role as a first line diagnostic technique but may be reserved as an adjunct or for lesions not amenable to percutaneous biopsy. On balance, USCB seems to be the method of choice. The current evidence suggests it has superior diagnostic potential and is safe. With time, USCB is likely to supplant FNAC as the biopsy technique of choice, replicating that which has occurred already in other areas of medicine such a breast practice.