Objective Machine learning has been effective in other areas of medicine, this study aims to investigate this with regards to HNC and identify which algorithm works best to classify malignant patients. Design An observational cohort study. Setting Queen Elizabeth University Hospital. Participants Patients who were referred via the USOC pathway between January 2019 and May 2021. Main outcome measures Predicting the diagnosis of patients from three categories, benign, potential malignant and malignant, using demographics and symptoms data. Results The logistic regression-based models with a penalty term worked best on the data, ridge achieving an AUC of 0.7081. The demographic features describing living alone and recreational drug use history were the most important variables alongside the red flag symptom of a neck lump. Conclusion Further studies should aim to collect larger samples of malignant and pre-malignant patients to improve the class imbalance and increase the performance of the machine learning models.

Objectives Tonsillectomy, grommet insertion and adenoidectomy are only permissible in the UK when specific criteria are met. , Children from deprived backgrounds are more likely to require tonsillectomy. Our aim was to assess correlation between tonsillectomy and deprivation plus tonsillectomy and related infections. Design Retrospective observational study of data provided by Information Service Division between 1996/7 and 2016/17. Socio-economic background was determined by Scottish Index of Multiple Deprivation (SIMD) score. Setting and Participants Complete national data for all patients under 16 years old admitted to Scottish NHS hospitals. Main outcome measures Admission to hospital for ENT procedures and ENT-related infections. Results 60,456 tonsillectomies were performed during the study period, significantly fewer following the introduction of SIGN guidelines. Children from the most deprived areas were 72.0% more likely to receive tonsillectomy than the least deprived. Significantly increased rates of tonsillitis were observed following the introduction of SIGN guidelines. The most deprived children were 59% more likely to be admitted with quinsy than the least deprived. Conclusion Tonsillectomy rates are highest in the most deprived. Complications of throat infection appear to be increasing following the introduction of SIGN and NICE guidelines.

Key PointsThe mean TOI-14 was 48.22 (SD 10.10).The mean HALT was 45.80 (SD 22.22).There was a significant correlation between the TOI-14 and HALT,r = 0.605, p<0.001.This is the first evidence that patients with poor quality of life due to sore throat also have poor quality of life due to halitosis.It is currently unknown if the HALT score is modified by tonsillectomy.