Using Machine Learning to Overcome Interfering Oxygen Effects in a Graphene Volatile Organic Compound Sensor.

Discriminating between volatile organic compounds (VOCs) for applications including disease diagnosis and environmental monitoring, is often complicated by the presence of interfering compounds such as oxygen. Graphene sensors are effective at detecting VOCs; however, they are also known to be highly sensitive to oxygen. Therefore, the combined effects of each of these gases on graphene sensors must be understood. In this work, we use graphene variable capacitor (varactor) sensors to examine the cross-selectivity of oxygen at 3 concentrations and 3 VOCs (ethanol, methanol, and methyl ethyl ketone) at 5 concentrations each. The sensor responses exhibit distinct shapes dependent on the relative concentrations in mixtures of oxygen and VOCs. Because the entire response shape is therefore informative for distinguishing between each gas mixture, a classification algorithm that utilizes entire sequences of data is needed. Accordingly, a long short-term memory (LSTM) network is used to classify the mixtures and VOC concentrations. The model achieves 100% accurate classification of the VOC type, even in the presence of varying levels of oxygen. When the VOC type and VOC concentration are classified, we show that the sensors can provide VOC concentration resolution within approximately 200 ppm. Throughout this work, we also demonstrate that an effective gas mixture classification can be achieved, even while the sensors exhibit varied drift patterns typical of graphene sensors. This is made possible due to the data analysis and machine learning methods employed.

Dual bronchodilators in Bronchiectasis study (DIBS): protocol for a pragmatic, multicentre, placebo-controlled, three-arm, double-blinded, randomised controlled trial studying bronchodilators in preventing exacerbations of bronchiectasis.

INTRODUCTION: Bronchiectasis is a long-term lung condition, with dilated bronchi, chronic inflammation, chronic infection and acute exacerbations. Recurrent exacerbations are associated with poorer clinical outcomes such as increased severity of lung disease, further exacerbations, hospitalisations, reduced quality of life and increased risk of death. Despite an increasing prevalence of bronchiectasis, there is a critical lack of high-quality studies into the disease and no treatments specifically approved for its treatment. This trial aims to establish whether inhaled dual bronchodilators (long acting beta agonist (LABA) and long acting muscarinic antagonist (LAMA)) taken as either a stand-alone therapy or in combination with inhaled corticosteroid (ICS) reduce the number of exacerbations of bronchiectasis requiring treatment with antibiotics during a 12 month treatment period. METHODS: This is a multicentre, pragmatic, double-blind, randomised controlled trial, incorporating an internal pilot and embedded economic evaluation. 600 adult patients (≥18 years) with CT confirmed bronchiectasis will be recruited and randomised to either inhaled dual therapy (LABA+LAMA), triple therapy (LABA+LAMA+ICS) or matched placebo, in a 2:2:1 ratio (respectively). The primary outcome is the number of protocol defined exacerbations requiring treatment with antibiotics during the 12 month treatment period. ETHICS AND DISSEMINATION: Favourable ethical opinion was received from the North East-Newcastle and North Tyneside 2 Research Ethics Committee (reference: 21/NE/0020). Results will be disseminated in peer-reviewed publications, at national and international conferences, in the NIHR Health Technology Assessments journal and to participants and the public (using lay language). TRIAL REGISTRATION NUMBER: ISRCTN15988757.

MET-PREVENT: metformin to improve physical performance in older people with sarcopenia and physical prefrailty/frailty - protocol for a double-blind, randomised controlled proof-of-concept trial.

INTRODUCTION: Skeletal muscle dysfunction is central to both sarcopenia and physical frailty, which are associated with a wide range of adverse outcomes including falls and fractures, longer hospital stays, dependency and the need for care. Resistance training may prevent and treat sarcopenia and physical frailty, but not everyone can or wants to exercise. Finding alternatives is critical to alleviate the burden of adverse outcomes associated with sarcopenia and physical frailty. This trial will provide proof-of-concept evidence as to whether metformin can improve physical performance in older people with sarcopenia and physical prefrailty or frailty. METHODS AND ANALYSIS: MET-PREVENT is a parallel group, double-blind, placebo-controlled proof-of-concept trial. Trial participants can participate from their own homes, including completing informed consent and screening assessments. Eligible participants with low grip strength or prolonged sit-to-stand time together with slow walk speed will be randomised to either oral metformin hydrochloride 500 mg tablets or matched placebo, taken three times a day for 4 months. The recruitment target is 80 participants from two secondary care hospitals in Newcastle and Gateshead, UK. Local primary care practices will act as participant identification centres. Randomisation will be performed using a web-based minimisation system with a random element, balancing on sex and baseline walk speed. Participants will be followed up for 4 months post-randomisation, with outcomes collected at baseline and 4 months. The primary outcome measure is the four metre walk speed at the 4-month follow-up visit. ETHICS AND DISSEMINATION: The trial has been approved by the Liverpool NHS Research Ethics Committee (20/NW/0470), the Medicines and Healthcare Regulatory Authority (EudraCT 2020-004023-16) and the UK Health Research Authority (IRAS 275219). Results will be made available to participants, their families, patients with sarcopenia, the public, regional and national clinical teams, and the international scientific community. TRIAL REGISTRATION NUMBER: ISRCTN29932357.