Assessing the Performance of Machine Learning Methods Trained on Public Health Observational Data: A Case Study From COVID-19.

From early in the coronavirus disease 2019 (COVID-19) pandemic, there was interest in using machine learning methods to predict COVID-19 infection status based on vocal audio signals, for example, cough recordings. However, early studies had limitations in terms of data collection and of how the performances of the proposed predictive models were assessed. This article describes how these limitations have been overcome in a study carried out by the Turing-RSS Health Data Laboratory and the UK Health Security Agency.

A large-scale and PCR-referenced vocal audio dataset for COVID-19.

The UK COVID-19 Vocal Audio Dataset is designed for the training and evaluation of machine learning models that classify SARS-CoV-2 infection status or associated respiratory symptoms using vocal audio. The UK Health Security Agency recruited voluntary participants through the national Test and Trace programme and the REACT-1 survey in England from March 2021 to March 2022, during dominant transmission of the Alpha and Delta SARS-CoV-2 variants and some Omicron variant sublineages. Audio recordings of volitional coughs, exhalations, and speech were collected in the 'Speak up and help beat coronavirus' digital survey alongside demographic, symptom and self-reported respiratory condition data.

Significant changes in dietary intake and supplement use after breast cancer diagnosis in a UK multicentre study.

The diagnosis of cancer can motivate survivors to alter their lifestyle habits. Healthcare providers need to be aware of what changes patients are likely to make in order to derive more pertinent recommendations; however, few studies have reported pre- and post-diagnostic lifestyle behaviours. Semi-quantitative food frequency questionnaires (FFQs) completed approximately 1 year after diagnosis were used to evaluate dietary intake and supplement use before and after diagnosis in a cohort of 1,560 breast cancer patients participating in the UK, prospective DietCompLyf study.

IGF status is altered by tamoxifen in patients with breast cancer.

Aims: An increased concentration of insulin-like growth factor 1 (IGF-1) is an independent risk factor for premenopausal breast cancer. Tamoxifen is thought initially to reduce concentrations of IGF-1 and increase concentrations of the IGF binding proteins. The aim of this study was to compare concentrations of IGF-1, IGF binding protein 1 (IGF-BP1), and IGF-BP3 in patients with breast cancer (n = 14) with those seen in control subjects (n = 23) and to assess the effect of tamoxifen on IGF status in these patients.

Helix pomatia agglutinin lectin-binding oligosaccharides of aggressive breast cancer.

Predicting long-term outcome after breast-cancer diagnosis remains problematic, particularly for patients with clinically small, axillary lymph node- negative tumours. Evidence suggests that the lectin Helix pomatia agglutinin (HPA) identifies oligosaccharides associated with poor-prognosis cancer. Our aim was to identify oligosaccharides that bind HPA in aggressive breast cancers.