Data from 585 patients was analysed. The age of study participants ranged from 29 days to 12
years, 41% were female and 28% were less than two years old.
For all predefined study endpoints, ResApp’s algorithms performed very well, achieving a
positive percent agreement (PPA) between 79% and 97% and a negative percent agreement
(NPA) between 80% and 91% when compared to a clinical diagnosis. The results for
asthma/reactive airway disease (RAD) were exceptional, with a PPA of 97% and an NPA of 91%.
Asthma/RAD diagnosis is typically performed in the clinic using an inhaled bronchodilator test,
which is time consuming and costly. For pneumonia, a disease that is responsible for the death
of more children under five than any other disease, ResApp’s algorithms delivered a PPA of 87%
and an NPA of 85%. For lower respiratory tract disease, a key diagnosis for telehealth
consultations in particular, ResApp’s algorithms yielded a PPA of 83% and an NPA of 82%. While
a shortage of patients under two without bronchiolitis limited the statistical robustness of the
study’s bronchiolitis results, the algorithm’s performance was again excellent with PPA and NPA
both above 80%.
According to Dr Paul Porter, MBBS, FRACP, the study principal investigator at Joondalup Health
Campus and Princess Margaret Hospital, “Even with all the information available to us in a
modern, well-equipped hospital we still face difficulties in diagnosing childhood respiratory
diseases. These excellent prospective results, obtained without the need to examine the patient
ResApp Health Limited ABN 51 094 468 318
Headquarters: Level 8, 127 Creek St, Brisbane QLD 4000 Australia
Registered Office: Level 24, 44 St Georges Tce, Perth WA 6000 Australia
T +61 8 6211 5099 E [email protected] W www.resapphealth.com.au
or perform investigations, will give clinicians significantly more confidence in their diagnosis of
respiratory disease, especially in telehealth and emergency department settings. I am grateful
to all the patients who participated in the study, as well as the clinical research teams at
Joondalup Health Campus and Princess Margaret Hospital who showed great expertise and
dedication in performing the study.”
A summary of the number of patients with each disease, PPA and NPA for the study endpoints
is presented in the table below.
Patients3 Positive Percent
Agreement
Negative Percent
Y N Agreement
Lower respiratory tract disease1 419 154
83%
(95% CI, 79-86%)
82%
(95% CI, 75-88%)
Asthma/reactive airway disease1 149 381
97%
(95% CI, 92-99%)
91%
(95% CI, 88-94%)
Croup2 68 500
88%
(95% CI, 78-95%)
86%
(95% CI, 82-89%)
Pneumonia1 60 509
87%
(95% CI, 75-94%)
85%
(95% CI, 82-88%)
Primary upper respiratory tract
disease1
89 482
79%
(95% CI, 69-87%)
80%
(95% CI, 76-83%)
Bronchiolitis1
(patients aged < 2 years old)
131 26
84%
(95% CI, 77-90%)
81%
(95% CI, 61-93%)
1. ResApp algorithm includes cough audio and patient reported symptoms as input.
2. ResApp algorithm includes cough audio as input only.
3. Number of patients clinically diagnosed as having disease (Y) or not having disease (N).
“The outstanding results delivered by the Breathe Easy prospective study are consistent with
our expectations, and for diseases such as pneumonia and asthma have even exceeded our
expectations. This formal confirmation of ResApp’s algorithms’ robust performance will allow us
to provide key diagnostic products in an array of clinical settings, especially in telehealth - one of
the fastest growing segments in healthcare - where up to 50% of consultations are respiratory
related”, said Tony Keating, CEO and Managing Director of ResApp. “We now have a solid
dataset to underpin our forthcoming CE mark and TGA submissions which will propel the
commercialisation of our products in Europe, Australia and the rest of the world outside the US.
The successful completion of Breathe Easy also gives us additional data, experience and
(20min delay)