nature machine intelligence

Published: 07 February 2024(link is external)

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

Recent work has reported that respiratory audio-trained AI classifiers can accurately predict SARS-CoV-2 infection status. However, it has not yet been determined whether such model performance is driven by latent audio biomarkers with true causal links to SARS-CoV-2 infection or by confounding effects, such as recruitment bias, present in observational studies. Here we undertake a large-scale study of audio-based AI classifiers as part of the UK government’s pandemic response.


Science Direct

Published: 10 November 2023(link is external)

Zero-shot personalization of speech foundation models for depressed mood monitoring

Depression, as one of the most prevalent mental health diseases, negatively impacts millions of lives. Diagnoses are achieved by the assessment of symptoms with standardized tests. However, recent studies indicate that continuously monitoring symptoms (e.g., with ecological momentary assessments [EMAs]) may provide relevant additional information for both diagnosis and treatment decisions.


nature mental health

Published: 07 August 2023(link is external)

How to e-mental health: a guideline for researchers and practitioners using digital technology in the context of mental health

Despite an exponentially growing number of digital or e-mental health services, methodological guidelines for research and practical implementation are scarce. Here we aim to promote the methodological quality, evidence and long-term implementation of technical innovations in the healthcare system. This expert consensus is based on an iterative Delphi adapted process and provides an overview of the current state-of-the-art guidelines and practical recommendations on the most relevant topics in e-mental health assessment and intervention.


The Lancet

Published: 21 July 2021(link is external)

COVID-19 detection from audio: seven grains of salt

Digital mass testing for COVID-19 via a mobile phone application could be made possible through machine learning and its ability to identify patterns in data. COVID-19 appears to confer unique features in the audio produced by infected individuals and machine learning COVID-19 detection from breath, cough, and speech audio recordings has yielded promising results