Hyfe AI and ActiGraph Partner to Revolutionize Clinical Trials with AI-Powered Cough Detection

Hyfe Research and Publications

CLICK HERE

To learn more and use Hyfe in your research trial

Latest Publications

Towards a Neural Cough Classifier for Edge Devices

Hyfe has developed a Software Development Kit (SDK) that allows third parties to integrate cough detection into their own devices: Windows, Linux, Mac OS, Android, iOS and embedded targets.

All
Peer-reviewed publications
Abstracts
Research memos
Pre-print

Towards a Neural Cough Classifier for Edge Devices

Hyfe has developed a Software Development Kit (SDK) that allows third parties to integrate cough detection into their own devices: Windows, Linux, Mac OS, Android, iOS and embedded targets.

ACC 2023: Validation of the Hyfe Cough Monitoring System

Our validation assesses the accuracy and reliability of the Hyfe CoughMonitor, with expected high correlation for both cough and cough-seconds. The AI-powered capabilities provide continuous and non-intrusive monitoring, and have the potential to improve patient care, cough research and support drug development.

Predicting Tuberculosis from Real-World Cough Audio Recordings and Metadata

Our results suggest mobile phone-based applications that integrate clinical symptoms and cough sound analysis could help community health workers and, most importantly, health service programs to improve TB case-finding efforts while reducing costs, which could substantially improve public health.

Continuous cough monitoring: a novel digital biomarker for TB diagnosis and treatment response monitoring

Continuous cough monitoring in a multi-country cohort of people being evaluated for Tuberculosis showed that people with TB cough a lot more often than those with other respiratory conditions. The distinct cough patterns in TB patients could be used for improved diagnosis and treatment response monitoring.

Digital Cough Monitoring - A Potential Predictive Acoustic Biomarker Of Clinical Outcomes in Hospitalized COVID-19 Patients

According to this multi-center study results, patients hospitalized with COVID-19 who coughed 3.4 times per hour or less based on digital cough monitoring faced a greater risk for intubation or death.

ASTMH 2022: Revisiting a neglected symptom: clinical experience using the Hyfe Cough Tracker in malaria patients

Malaria patients had an almost two-fold probability to experience more than 10 episodes of cough in 30min than patients with other respiratory diseases. These results stress the importance of respiratory symptoms in malaria patients.

ERS 2022: Continuous cough monitoring with AI. Cases: treatment response, smoking cessation and COVID-19

This e-poster was presented as an oral presentation at ERS 2022 Congress in Barcelona. Based on our experience and case examples presented - objective cough frequency data has great potential to be a part of remote patient monitoring, smoking cessation and medication adherence, and complement PROs.

The Statistics of Counting Coughs: Easy as 1, 2, 3?

Cough is one of the most common reasons that individuals seek health care, and yet it is largely unmeasured in clinical medicine and practice.

12th LICS: Usability, feasibility, and effectiveness of continuous cough frequency monitoring with Hyfe Cough Tracker in patients with chronic cough

This study with 65 chronic cough patients monitored for more than a week suggests that continuous cough frequency monitoring with Hyfe Cough Tracker is potentially useful and applicable to real-world clinical practice.

Feasibility and analysis considerations of continuous community-based cough monitoring in low- and middle-income settings

Continuous cough monitoring using a smartphone application is feasible in low- and middle-income country settings, as shown in this study with 568 participants with presumptive Tuberculosis that were monitored for cough frequency dynamics for at least 10 days.

Making cough count in tuberculosis care

Cough assessment is central to the clinical management of respiratory diseases, including tuberculosis (TB), but strategies to objectively and unobtrusively measure cough are lacking. Validated cough assessment could support public health programs at various stages of the TB care cascade.

Performance evaluation of the smartphone-based AI cough monitoring app - Hyfe Cough Tracker against solicited respiratory sounds

Hyfe Cough Tracker app showed a very high correlation between the cough rate measured by Hyfe and that of human annotators (Pearson correlation of 0.968).

CHEST 2022: Cough monitoring using artificial intelligence to complement smoke cessation interventions

We have observed how objective cough frequency dynamics motivate smokers to quit smoking. A case of a 71 year-old female with a history of smoking 20-40 cigarettes/day between ages 18 to 36, and from age 67 to present is described.

Acoustic surveillance of cough for detecting respiratory disease using artificial intelligence

This study followed-up 616 participants and collected >62 000 coughs showed that artificial intelligence systems can detect changes in cough frequency that temporarily correlate with the onset of clinical disease at the individual level.

ATS 2022 Respiratory Innovation Summit: Hyfe Cough Monitoring System: Making Cough Count

This poster overviews Hyfe's values: insights for patient care, clinical cohort management and a powerful research tool.

Longitudinal Passive Cough Monitoring and Its Implications for Detecting...

Detecting changes in cough rates is complicated by significant stochastic variability. This study monitored cough continuously in a large cohort, allowing for comparison of cough estimates from different observation periods. Intermittent sampling as 24-hour monitoring can often be misleading.

High-throughput digital cough recording on a university campus

4302 coughs were recorded from 960 participants over 11 weeks, requiring approximately 30s to check-in a participant and collect their cough. This study shows that acoustic screening at scale is possible, easy and quick to implement.

Long-COVID severe refractory cough: discussion of a case with 6-week longitudinal cough characterization

This publication suggests that continuous cough monitoring can be used in remote patient monitoring, with a case of a patient with Long-COVID presented.

Reimagining the status quo: How close are we to rapid sputum-free tuberculosis diagnostics for all?

This review summarises key technologies in Tuberculosis triage and confirmation. Technologies such as artificial intelligence-based methods are particularly promising, with Hyfe featured as a potential rapidly scalable, and rapid screening tool for cough sound specimens.

Digital acoustic surveillance for early detection of respiratory disease outbreaks in Spain: a protocol for an observational study

Digital acoustic surveillance for early detection of respiratory disease outbreaks in Spain. Real-time tracking of the COVID-19 pandemic and detection of the emergence of novel variants or other respiratory pathogens represent challenges for public health authorities globally..

Cough detection & classification: preliminary validation of Hyfe cough detection & classification

We use multiple approaches to evaluate the accuracy of Hyfe’s cough detection algorithms and the performance of its apps in various real-world scenarios. In a clinical context, Hyfe has optimized its apps for high performance in quiet indoor settings, such as a bedroom or hospital room, for any user, and for all...

Effects of distance on Hyfe performance

Hyfe is designed for individual users. High performance means detecting all coughs from a nearby user and no ambient coughs from others in the distance. To achieve this, Hyfe uses various metrics to sort out the soundscape it is analyzing, filtering to loud noise...

AI-powered cough counting: an objective and scalable endpoint

Cough is a ubiquitous health indicator whose impact is extreme and underappreciated. As an information-rich symptom that is associated with a myriad of diseases, cough is also the ideal clinical endpoint. Yet, cough continues to be assessed mainly through limited subjective methods.

Risk scores in real-time: the untapped potential of mobile health

Cough is an information-rich and readily monitored syndrome that will pioneer ’smart risk profiling’ systems, prove their value in alleviating the global burden of respiratory disease, and usher in a new era of proactive mobile health.

Hyfe Vision Paper: Acoustic AI as a scalable tool for diagnostics & monitoring

Hyfe's vision for a healthier world, in which smartphones and acoustic epidemiology identify illness and track health, transforming healthcare systems for good.

White Paper: Smart cough monitoring - an innovation milestone for global respiratory health

Until recently technology has lagged behind the need for effective cough monitoring solutions. Now, with the parallel rise of smartphone use and machine learning analytics, half the world's population is already carrying a device that can fundamentally change our approach to the global crisis in respiratory health.

Continuous cough monitoring: a novel digital biomarker for TB diagnosis and treatment response monitoring

Continuous cough monitoring in a multi-country cohort of people being evaluated for Tuberculosis showed that people with TB cough a lot more often than those with other respiratory conditions. The distinct cough patterns in TB patients could be used for improved diagnosis and treatment response monitoring.

Digital Cough Monitoring - A Potential Predictive Acoustic Biomarker Of Clinical Outcomes in Hospitalized COVID-19 Patients

According to this multi-center study results, patients hospitalized with COVID-19 who coughed 3.4 times per hour or less based on digital cough monitoring faced a greater risk for intubation or death.

The Statistics of Counting Coughs: Easy as 1, 2, 3?

Cough is one of the most common reasons that individuals seek health care, and yet it is largely unmeasured in clinical medicine and practice.

Making cough count in tuberculosis care

Cough assessment is central to the clinical management of respiratory diseases, including tuberculosis (TB), but strategies to objectively and unobtrusively measure cough are lacking. Validated cough assessment could support public health programs at various stages of the TB care cascade.

Performance evaluation of the smartphone-based AI cough monitoring app - Hyfe Cough Tracker against solicited respiratory sounds

Hyfe Cough Tracker app showed a very high correlation between the cough rate measured by Hyfe and that of human annotators (Pearson correlation of 0.968).

Acoustic surveillance of cough for detecting respiratory disease using artificial intelligence

This study followed-up 616 participants and collected >62 000 coughs showed that artificial intelligence systems can detect changes in cough frequency that temporarily correlate with the onset of clinical disease at the individual level.

Longitudinal Passive Cough Monitoring and Its Implications for Detecting...

Detecting changes in cough rates is complicated by significant stochastic variability. This study monitored cough continuously in a large cohort, allowing for comparison of cough estimates from different observation periods. Intermittent sampling as 24-hour monitoring can often be misleading.

High-throughput digital cough recording on a university campus

4302 coughs were recorded from 960 participants over 11 weeks, requiring approximately 30s to check-in a participant and collect their cough. This study shows that acoustic screening at scale is possible, easy and quick to implement.

Long-COVID severe refractory cough: discussion of a case with 6-week longitudinal cough characterization

This publication suggests that continuous cough monitoring can be used in remote patient monitoring, with a case of a patient with Long-COVID presented.

Reimagining the status quo: How close are we to rapid sputum-free tuberculosis diagnostics for all?

This review summarises key technologies in Tuberculosis triage and confirmation. Technologies such as artificial intelligence-based methods are particularly promising, with Hyfe featured as a potential rapidly scalable, and rapid screening tool for cough sound specimens.

Digital acoustic surveillance for early detection of respiratory disease outbreaks in Spain: a protocol for an observational study

Digital acoustic surveillance for early detection of respiratory disease outbreaks in Spain. Real-time tracking of the COVID-19 pandemic and detection of the emergence of novel variants or other respiratory pathogens represent challenges for public health authorities globally..

ACC 2023: Validation of the Hyfe Cough Monitoring System

Our validation assesses the accuracy and reliability of the Hyfe CoughMonitor, with expected high correlation for both cough and cough-seconds. The AI-powered capabilities provide continuous and non-intrusive monitoring, and have the potential to improve patient care, cough research and support drug development.

ASTMH 2022: Revisiting a neglected symptom: clinical experience using the Hyfe Cough Tracker in malaria patients

Malaria patients had an almost two-fold probability to experience more than 10 episodes of cough in 30min than patients with other respiratory diseases. These results stress the importance of respiratory symptoms in malaria patients.

ERS 2022: Continuous cough monitoring with AI. Cases: treatment response, smoking cessation and COVID-19

This e-poster was presented as an oral presentation at ERS 2022 Congress in Barcelona. Based on our experience and case examples presented - objective cough frequency data has great potential to be a part of remote patient monitoring, smoking cessation and medication adherence, and complement PROs.

12th LICS: Usability, feasibility, and effectiveness of continuous cough frequency monitoring with Hyfe Cough Tracker in patients with chronic cough

This study with 65 chronic cough patients monitored for more than a week suggests that continuous cough frequency monitoring with Hyfe Cough Tracker is potentially useful and applicable to real-world clinical practice.

CHEST 2022: Cough monitoring using artificial intelligence to complement smoke cessation interventions

We have observed how objective cough frequency dynamics motivate smokers to quit smoking. A case of a 71 year-old female with a history of smoking 20-40 cigarettes/day between ages 18 to 36, and from age 67 to present is described.

ATS 2022 Respiratory Innovation Summit: Hyfe Cough Monitoring System: Making Cough Count

This poster overviews Hyfe's values: insights for patient care, clinical cohort management and a powerful research tool.

Towards a Neural Cough Classifier for Edge Devices

Hyfe has developed a Software Development Kit (SDK) that allows third parties to integrate cough detection into their own devices: Windows, Linux, Mac OS, Android, iOS and embedded targets.

Cough detection & classification: preliminary validation of Hyfe cough detection & classification

We use multiple approaches to evaluate the accuracy of Hyfe’s cough detection algorithms and the performance of its apps in various real-world scenarios. In a clinical context, Hyfe has optimized its apps for high performance in quiet indoor settings, such as a bedroom or hospital room, for any user, and for all...

Effects of distance on Hyfe performance

Hyfe is designed for individual users. High performance means detecting all coughs from a nearby user and no ambient coughs from others in the distance. To achieve this, Hyfe uses various metrics to sort out the soundscape it is analyzing, filtering to loud noise...

AI-powered cough counting: an objective and scalable endpoint

Cough is a ubiquitous health indicator whose impact is extreme and underappreciated. As an information-rich symptom that is associated with a myriad of diseases, cough is also the ideal clinical endpoint. Yet, cough continues to be assessed mainly through limited subjective methods.

Risk scores in real-time: the untapped potential of mobile health

Cough is an information-rich and readily monitored syndrome that will pioneer ’smart risk profiling’ systems, prove their value in alleviating the global burden of respiratory disease, and usher in a new era of proactive mobile health.

Hyfe Vision Paper: Acoustic AI as a scalable tool for diagnostics & monitoring

Hyfe's vision for a healthier world, in which smartphones and acoustic epidemiology identify illness and track health, transforming healthcare systems for good.

White Paper: Smart cough monitoring - an innovation milestone for global respiratory health

Until recently technology has lagged behind the need for effective cough monitoring solutions. Now, with the parallel rise of smartphone use and machine learning analytics, half the world's population is already carrying a device that can fundamentally change our approach to the global crisis in respiratory health.

Predicting Tuberculosis from Real-World Cough Audio Recordings and Metadata

Our results suggest mobile phone-based applications that integrate clinical symptoms and cough sound analysis could help community health workers and, most importantly, health service programs to improve TB case-finding efforts while reducing costs, which could substantially improve public health.

Feasibility and analysis considerations of continuous community-based cough monitoring in low- and middle-income settings

Continuous cough monitoring using a smartphone application is feasible in low- and middle-income country settings, as shown in this study with 568 participants with presumptive Tuberculosis that were monitored for cough frequency dynamics for at least 10 days.

Resources for Hyfe Research Partners

Want to partner with Hyfe in a research project?
Use these materials to get started with using Hyfe in your research, or check the status of your ongoing project. We work with researchers all over the world to pioneer the field of acoustic epidemiology.

Talk to a cough expert
Map image where Hyfe is working and has partners. Hyfe - Acoustic epidemiology is the next frontier in healthcare

Not Sure?

fqa

Frequently Asked Questions

Boilerplate IRB and consent language

Boilerplate IRB and consent language

download guide

Users Guide to the Hyfe Research App

Ready to get started?

talk to our clinical expert