arXiv subjects

Emma Karoune

Publications and source records attributed to Emma Karoune.

3 recordsLinked to original sources

arXiv2024

Professionalising Community Management Roles in Interdisciplinary Research Projects

In this article we discuss community management in interdisciplinary research teams, focusing on recognising and professionalising roles referred to here as the Research Community Managers (RCM). Drawing insights and examples from research and data science projects, we discuss how RCM roles address some of the researchâ€™s most pressing challenges, from promoting best practices for open research and reproducibility to engaging diverse stakeholders in community-led research and ensuring fair recognition for their contributions. We offer a Community Maturation Indicator and share examples of projects from The Alan Turing Institute, the UK's national institute for data science and Artificial Intelligence (AI), where institutionally supported RCM roles were established. With the aim to integrate RCM expertise in teams involved in data science and AI research, we provide an RCM Skills and Competencies Framework. We also propose a roadmap for professionalising RCM roles by improving recognition and rewards, potential career paths and organisational support structures. To systematically sustain and progress these roles, we recommend institutional investment in establishing RCM teams that are empowered to prioritise collaboration, transparency and community-based approaches in interdisciplinary projects, such as in data science and AI. As a team, RCMs are well placed to connect disparate teams, initiatives and resources across the organisation, building more resilient research communities that can achieve greater innovation, improved project outcomes and a strongly connected ecosystem, with impacts extending beyond their narrow contexts.

physics.soc-ph↗

arXiv2023

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 to help beat coronavirus' digital survey alongside demographic, self-reported symptom and respiratory condition data, and linked to SARS-CoV-2 test results. The UK COVID-19 Vocal Audio Dataset represents the largest collection of SARS-CoV-2 PCR-referenced audio recordings to date. PCR results were linked to 70,794 of 72,999 participants and 24,155 of 25,776 positive cases. Respiratory symptoms were reported by 45.62% of participants. This dataset has additional potential uses for bioacoustics research, with 11.30% participants reporting asthma, and 27.20% with linked influenza PCR test results.

cs.SD↗

arXiv2023

Audio-based AI classifiers show no evidence of improved COVID-19 screening over simple symptoms checkers

Recent work has reported that AI classifiers trained on audio recordings can accurately predict severe acute respiratory syndrome coronavirus 2 (SARSCoV2) infection status. Here, we undertake a large scale study of audio-based deep learning classifiers, as part of the UK governments pandemic response. We collect and analyse a dataset of audio recordings from 67,842 individuals with linked metadata, including reverse transcription polymerase chain reaction (PCR) test outcomes, of whom 23,514 tested positive for SARS CoV 2. Subjects were recruited via the UK governments National Health Service Test-and-Trace programme and the REal-time Assessment of Community Transmission (REACT) randomised surveillance survey. In an unadjusted analysis of our dataset AI classifiers predict SARS-CoV-2 infection status with high accuracy (Receiver Operating Characteristic Area Under the Curve (ROCAUC) 0.846 [0.838, 0.854]) consistent with the findings of previous studies. However, after matching on measured confounders, such as age, gender, and self reported symptoms, our classifiers performance is much weaker (ROC-AUC 0.619 [0.594, 0.644]). Upon quantifying the utility of audio based classifiers in practical settings, we find them to be outperformed by simple predictive scores based on user reported symptoms.

cs.SD↗