Application of Machine Learning Algorithms for Asthma Management with mHealth: A Clinical Review.
artificial intelligence
chronic disease
remote monitoring; asthma
self-management
smart devices
Journal
Journal of asthma and allergy
ISSN: 1178-6965
Titre abrégé: J Asthma Allergy
Pays: New Zealand
ID NLM: 101543450
Informations de publication
Date de publication:
2022
2022
Historique:
received:
27
10
2021
accepted:
16
06
2022
entrez:
6
7
2022
pubmed:
7
7
2022
medline:
7
7
2022
Statut:
epublish
Résumé
Asthma is a variable long-term condition. Currently, there is no cure for asthma and the focus is, therefore, on long-term management. Mobile health (mHealth) is promising for chronic disease management but to be able to realize its potential, it needs to go beyond simply monitoring. mHealth therefore needs to leverage machine learning to provide tailored feedback with personalized algorithms. There is a need to understand the extent of machine learning that has been leveraged in the context of mHealth for asthma management. This review aims to fill this gap. We searched PubMed for peer-reviewed studies that applied machine learning to data derived from mHealth for asthma management in the last five years. We selected studies that included some human data other than routinely collected in primary care and used at least one machine learning algorithm. Out of 90 studies, we identified 22 relevant studies that were then further reviewed. Broadly, existing research efforts can be categorized into three types: 1) technology development, 2) attack prediction, 3) patient clustering. Using data from a variety of devices (smartphones, smartwatches, peak flow meters, electronic noses, smart inhalers, and pulse oximeters), most applications used supervised learning algorithms (logistic regression, decision trees, and related algorithms) while a few used unsupervised learning algorithms. The vast majority used traditional machine learning techniques, but a few studies investigated the use of deep learning algorithms. In the past five years, many studies have successfully applied machine learning to asthma mHealth data. However, most have been developed on small datasets with internal validation at best. Small sample sizes and lack of external validation limit the generalizability of these studies. Future research should collect data that are more representative of the wider asthma population and focus on validating the derived algorithms and technologies in a real-world setting.
Sections du résumé
Background
UNASSIGNED
Asthma is a variable long-term condition. Currently, there is no cure for asthma and the focus is, therefore, on long-term management. Mobile health (mHealth) is promising for chronic disease management but to be able to realize its potential, it needs to go beyond simply monitoring. mHealth therefore needs to leverage machine learning to provide tailored feedback with personalized algorithms. There is a need to understand the extent of machine learning that has been leveraged in the context of mHealth for asthma management. This review aims to fill this gap.
Methods
UNASSIGNED
We searched PubMed for peer-reviewed studies that applied machine learning to data derived from mHealth for asthma management in the last five years. We selected studies that included some human data other than routinely collected in primary care and used at least one machine learning algorithm.
Results
UNASSIGNED
Out of 90 studies, we identified 22 relevant studies that were then further reviewed. Broadly, existing research efforts can be categorized into three types: 1) technology development, 2) attack prediction, 3) patient clustering. Using data from a variety of devices (smartphones, smartwatches, peak flow meters, electronic noses, smart inhalers, and pulse oximeters), most applications used supervised learning algorithms (logistic regression, decision trees, and related algorithms) while a few used unsupervised learning algorithms. The vast majority used traditional machine learning techniques, but a few studies investigated the use of deep learning algorithms.
Discussion
UNASSIGNED
In the past five years, many studies have successfully applied machine learning to asthma mHealth data. However, most have been developed on small datasets with internal validation at best. Small sample sizes and lack of external validation limit the generalizability of these studies. Future research should collect data that are more representative of the wider asthma population and focus on validating the derived algorithms and technologies in a real-world setting.
Identifiants
pubmed: 35791395
doi: 10.2147/JAA.S285742
pii: 285742
pmc: PMC9250768
doi:
Types de publication
Journal Article
Review
Langues
eng
Pagination
855-873Informations de copyright
© 2022 Tsang et al.
Déclaration de conflit d'intérêts
The authors report no conflicts of interest in this work.
Références
JAMIA Open. 2020 May 07;3(2):190-200
pubmed: 32734159
Transl Vis Sci Technol. 2020 Dec 03;9(13):5
pubmed: 33344049
Sci Rep. 2020 Sep 14;10(1):14999
pubmed: 32929109
Biosens Bioelectron. 2020 Nov 6;173:112799
pubmed: 33190052
BMC Med. 2017 Mar 17;15(1):64
pubmed: 28302126
J Asthma Allergy. 2010 Jul 26;3:43-56
pubmed: 21437039
NPJ Digit Med. 2020 Oct 30;3:145
pubmed: 33145441
Nat Med. 2020 Jun;26(6):964-973
pubmed: 32528151
J Med Eng Technol. 2017 Apr;41(3):208-215
pubmed: 27919170
BMJ Open. 2017 Jan 24;7(1):e013935
pubmed: 28119390
JMIR Mhealth Uhealth. 2019 Mar 11;7(3):e10828
pubmed: 30855232
Eur Respir J. 2013 Jan;41(1):53-9
pubmed: 22653768
J Allergy Clin Immunol. 2004 Jan;113(1):59-65
pubmed: 14713908
PLoS One. 2016 Sep 01;11(9):e0162128
pubmed: 27583523
PLoS One. 2012;7(1):e30412
pubmed: 22276193
PLoS One. 2019 Nov 1;14(11):e0224582
pubmed: 31675367
J Asthma Allergy. 2017 Mar 07;10:47-56
pubmed: 28331347
Eur Respir Rev. 2015 Mar;24(135):92-101
pubmed: 25726560
JMIR Mhealth Uhealth. 2020 Jul 31;8(7):e13737
pubmed: 32735229
J Physiol Anthropol Appl Human Sci. 2005 Jul;24(4):259-65
pubmed: 16079565
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:5689-5695
pubmed: 33019267
Am J Respir Crit Care Med. 2018 Aug 1;198(3):320-328
pubmed: 29688023
Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:1413-1416
pubmed: 29060142
Eur Respir J. 1999 Oct;14(4):902-7
pubmed: 10573240
PLoS One. 2018 Jan 18;13(1):e0191330
pubmed: 29346430
Br J Dis Chest. 1977 Apr;71(2):87-92
pubmed: 861159
Respir Med. 2015 Sep;109(9):1089-104
pubmed: 26073963
AMIA Jt Summits Transl Sci Proc. 2020 May 30;2020:191-200
pubmed: 32477638
BMJ. 2009 Jun 29;338:b2393
pubmed: 19564179
Pac Symp Biocomput. 2016;22:300-311
pubmed: 27896984
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:7153-7156
pubmed: 31947484
Respirology. 2013 Feb;18(2):354-63
pubmed: 23126237
Nature. 2020 Jan;577(7792):706-710
pubmed: 31942072
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:5673-5677
pubmed: 33019264
BMC Pulm Med. 2018 Oct 11;18(1):159
pubmed: 30305051
Sleep. 2001 Feb 1;24(1):90-5
pubmed: 11204057
J Breath Res. 2017 Mar 01;11(1):016016
pubmed: 28102830
J Asthma Allergy. 2021 Sep 16;14:1117-1127
pubmed: 34557000
Nat Methods. 2018 Sep;15(9):707-714
pubmed: 30171232
Front Neurol. 2020 Aug 14;11:825
pubmed: 32849251
Sci Rep. 2019 Apr 12;9(1):6012
pubmed: 30979917
J Med Internet Res. 2017 Mar 07;19(3):e69
pubmed: 28270380
J Breath Res. 2020 Jul 21;14(4):046003
pubmed: 32512553
Ann N Y Acad Sci. 2017 Jan;1387(1):153-165
pubmed: 27627195
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:445-448
pubmed: 30440430
Lancet. 2018 Jan 27;391(10118):350-400
pubmed: 28911920
Nat Med. 2020 Jul;26(7):1037-1040
pubmed: 32393804
Am J Respir Crit Care Med. 2009 Jul 1;180(1):59-99
pubmed: 19535666
J Asthma. 2021 Nov;58(11):1518-1527
pubmed: 32718193
BMC Pulm Med. 2019 Apr 8;19(1):74
pubmed: 30961573
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:217-220
pubmed: 31945881
J Asthma Allergy. 2020 Dec 14;13:669-678
pubmed: 33363391
JMIR Mhealth Uhealth. 2019 Feb 07;7(2):e11201
pubmed: 30730297
Heart Lung. 2020 Sep - Oct;49(5):548-555
pubmed: 32089295
BMC Bioinformatics. 2013 Mar 22;14:106
pubmed: 23522326
Comput Methods Programs Biomed. 2019 Sep;178:163-173
pubmed: 31416545
J Med Syst. 2019 Apr 26;43(6):158
pubmed: 31028489
J Health Serv Res Policy. 2016 Apr;21(2):73-82
pubmed: 26377727
Lancet Respir Med. 2015 Mar;3(3):210-9
pubmed: 25617215
Sensors (Basel). 2021 May 03;21(9):
pubmed: 34063576
JMIR Med Inform. 2020 May 28;8(5):e16452
pubmed: 32463370
Nat Biotechnol. 2017 Apr;35(4):354-362
pubmed: 28288104