MonitAir: a smart self-test to reduce the impact of lung attacks

Erik Bischoff
GP specialising in Asthma and COPD
Senior researcher at the Department of Primary Medicine, Radboud University Medical Center
Medical Consultant to MonitAir

Introduction:

In recent years, a lot more attention has been given to the prevention and prompt treatment of COPD lung attacks (previously called exacerbations). There are good reasons behind this; around 600,000 people suffer from COPD in the Netherlands alone. About 25% of these visit their GP at least once a year because of worsening respiratory symptoms. Every year, about one in five ends up in hospital due to a lung attack [1]. More than 50% of all COPD-related healthcare costs are the result of hospitalisation following lung attacks. A lung attack has an enormous impact on the burden of disease and disease progression.

Scientific studies show that early identification and prompt action reduce the severity and duration of lung attacks, improve patients’ quality of life, prevent complications, and reduce healthcare costs [2]. The COPD Standard of Care of the Netherlands Lung Alliance (‘Long Alliantie Nederland’) [3] and the COPD Standard of the Dutch Association of GPs (NHG) [4] therefore recommend using a printed lung attack action plan when worsening symptoms are identified and when taking action. However, research shows that patients do not use their action plans properly; instructions are followed either incorrectly or not at all [5]. Patients feel that the printed document provides insufficient support, and moreover they often don’t have it at hand. Patients prefer simple digital support that takes better account of their personal situation.

How MonitAir came into being:

We developed MonitAir so that COPD patients would receive maximum support during a lung attack. MonitAir is a smart self-test that can be easily used in the form of an app on a phone or tablet. MonitAir has two unique, innovative features: 1. The app identifies a lung attack at a very early stage by analysing answers to questions about respiratory and other symptoms in combination with biofeedback (lung functioning, oxygen saturation and body temperature), and by learning from previous lung attacks; 2. The app then immediately provides personal treatment advice to the patient, without the intervention of a healthcare provider. The self-testing software learns from previous lung attacks, so the estimated risk and treatment advice are adapted to the user’s circumstances. Since the first developments in 2010, we’ve been working as researchers together with patients from the Netherlands Lung Fund (‘Longfonds’), doctors from Radboud University Medical Center, mathematicians from Radboud University, and the business community. Patients were involved from the outset in the conception, validation and testing, which has ensured that the self-test meets the needs of end users; digital, simple and personal.

Scientific basis:

MonitAir was developed in several stages. First of all, patients and doctors determined the factors which identify a lung attack. We then used AI to develop a mathematical model that can analyse these factors to predict the risk of a lung attack. We optimised the reliability of this prediction with previously collected data from scientific studies conducted inside and outside Netherlands, and by collecting new data on lung attacks together with patients [6]. We then linked the mathematical prediction model to treatment recommendations devised by GPs, pulmonologists, nurses and psychologists. The advice may include recommendations on increasing airway medication, contacting the healthcare provider, saving energy, breathing exercises, and starting a course of prednisolone or antibiotics, if applicable. Healthcare providers can tailor these recommendations to the patient’s personal situation. Our next step was to validate MonitAir. The predictions and advice turned out to be very reliable, with 97% sensitivity, 66% specificity, a positive predictive value of 13% and a negative predictive value of 99% [7]. This means that the probability of MonitAir missing a lung attack is extremely small, and that MonitAir virtually always provides correct advice at the time of a lung attack.

We recently completed a randomised controlled trial, in which we compared the use of MonitAir for 1 year with an action plan printed on paper for a small group of people with COPD. Patients found MonitAir very useful, and preferred it over the printed action plan.

MonitAir was developed thanks to grants from Radboud University Medical Center, the technology foundation STW, the European Regional Development Fund, and a donation from Boehringer Ingelheim. In 2017, MonitAir won a cash prize from ZonMw following voting for the Medical Inspirator public award.

Certification:

MonitAir is CE certified as a Medical Device Class 1 product

Scientific publications:

[1] Netherlands Lung Alliance (Long Alliantie Nederland’) Lung Diseases Report. Facts and figures 2013. (Rapport Longziekten. Feiten en cijfers 2013.)
[2] Lenferink A, Brusse-Keizer M, van der Valk PD, Frith PA, Zwerink M, Monninkhof EM, van der Palen J, Effing TW. Self-management interventions including action plans for exacerbations versus usual care in patients with chronic obstructive pulmonary disease. Cochrane Database System Rev. 2017 Aug 4;8:CD011682.
[3] Netherlands Lung Alliance (Long Alliantie Nederland’) COPD Standard of Care (Zorgstandaard COPD). Amersfoort, June 2013
[4] Snoeck-Stroband JB, Schermer TRJ, Van Schayck CP, Muris JW, Van der Molen T, In ’t Veen JCCM, Chavannes NH, Broekhuizen BDL, Barnhoorn MJM, Smeele I, Geijer RMM, Tuut MK. COPD Standard of the Dutch Association of GPs (NHG Standaard COPD). General Practitioner Act 2015 (‘Huisarts Wet’) 2015;58(4):198-211.
[5] Bischoff EW, Hamd DH, Sedeno M, Benedetti A, Schermer TR, Bernard S, Maltais F, Bourbeau J. Effects of written action plan adherence on COPD exacerbation recovery. Thorax. 2011 Jan; 66(1):26-31.
[6] van der Heijden M, Lucas PJ, Lijnse B, Heijdra YF, Schermer TR. An autonomous mobile system for the management of COPD. J Biomed Inform. 2013 Jun;46(3):458-69
[7] Boer LM, van der Heijden M, van Kuijk NM, Lucas PJ, Vercoulen JH, Assendelft WJ, Bischoff EW, Schermer TR. Validation of ACCESS: an automated tool to support self-management of COPD exacerbations. Int J Chron Obstruct Pulmon Dis. 2018 Oct 10;13:3255-3267.