Search

Background: Machine learning algorithms could potentially be used to classify patients referred on the two-week wait pathway for suspected head and neck cancer. Patients could be classified into 'predicted cancer' or 'predicted non-cancer' groups. Methods: A variety of machine learning algorithms were assessed using the clinical data of 5082 patients. These patients had previously been referred via the two-week wait pathway for suspected head and neck cancer to two separate tertiary referral centres in the UK. Outcomes from machine learning classification were analysed in comparison to known clinical diagnoses. Results: Variational logistic regression was the most clinically useful technique of those chosen to perform the analysis and patient classification; the proportion of patients correctly classified as having 'non-cancer' was 25.8 per cent, with a false negative rate of 1 out of 1000. Conclusion: Machine learning algorithms can accurately and effectively classify patients referred with suspected head and neck cancer symptoms. [ABSTRACT FROM AUTHOR]

Background: Malignant otitis externa is a potentially fatal infection of the skull base. With an ageing population and increasing prevalence of diabetes, the incidence of malignant otitis externa in the British population is rising. To date, there remain no accepted diagnostic criteria, few prognostic indicators and no consensus treatment pathways. Method: A prospective case series was conducted at a tertiary referral teaching hospital. Results: A cohort of susceptible individuals predominates (elderly, male, with immunosuppression and diabetes), with 25 per cent reporting a preceding incident. Otorrhoea, otalgia and canal granulation were the commonest presenting features, alongside positive pseudomonas cultures. No clear markers for predicating disease severity were isolated; however, a high initial haemoglobin A1c level demonstrated a significant moderately positive correlation with length of treatment. Conclusion: A treatment pathway designed to provide a standardised approach to investigation and treatment is proposed, which aims to increase earlier diagnosis, streamline care and facilitate the development of best practice. [ABSTRACT FROM AUTHOR]