Search

In this report, we present our solution to the challenge provided by the SFI Centre for Machine Learning (ML-Labs) in which the distance between two phones needs to be estimated. It is a modified version of the NIST Too Close For Too Long (TC4TL) Challenge, as the time aspect is excluded. We propose a feature-based approach based on Bluetooth RSSI and IMU sensory data, that outperforms the previous state of the art by a significant margin, reducing the error down to 0.071. We perform an ablation study of our model that reveals interesting insights about the relationship between the distance and the Bluetooth RSSI readings.

Background: Symptomatic gastro-oesophageal reflux disease (GORD) has been associated with increased exacerbations and reduced quality of life in bronchiectasis (BR). We aimed to evaluate the prevalence of a BR-GORD phenotype, utilising the multi-domain Bronchiectasis Severity Index (BSI), to determine associations with disease severity and mortality. Methods: A retrospective cohort study in 212 consecutive BR patients attending our institution over a 2-year period was performed. A diagnosis of GORD was based on standardised definitions following full review of electronic records, review of prescriptions and investigator definitions. Results: 72 (19.8%) BR patients were confirmed to have co-existent GORD treated with proton pump inhibitors. These patients were predominantly male, older and with higher BMIs than their counterparts (p= Conclusion: BR-GORD patients have an increased disease severity and mortality risk compared with BR patients without GORD. Increased recognition of this BR-GORD phenotype and its potential for targeted therapy is needed.