Machine Learning Algorithms to Detect Subclinical Keratoconus: Systematic Review.
artificial intelligence
cornea
corneal disease
corneal imaging
corneal tomography
decision support systems
keratoconus
keratometry
machine learning
subclinical
Journal
JMIR medical informatics
ISSN: 2291-9694
Titre abrégé: JMIR Med Inform
Pays: Canada
ID NLM: 101645109
Informations de publication
Date de publication:
13 Dec 2021
13 Dec 2021
Historique:
received:
25
01
2021
accepted:
14
10
2021
revised:
10
05
2021
entrez:
13
12
2021
pubmed:
14
12
2021
medline:
14
12
2021
Statut:
epublish
Résumé
Keratoconus is a disorder characterized by progressive thinning and distortion of the cornea. If detected at an early stage, corneal collagen cross-linking can prevent disease progression and further visual loss. Although advanced forms are easily detected, reliable identification of subclinical disease can be problematic. Several different machine learning algorithms have been used to improve the detection of subclinical keratoconus based on the analysis of multiple types of clinical measures, such as corneal imaging, aberrometry, or biomechanical measurements. The aim of this study is to survey and critically evaluate the literature on the algorithmic detection of subclinical keratoconus and equivalent definitions. For this systematic review, we performed a structured search of the following databases: MEDLINE, Embase, and Web of Science and Cochrane Library from January 1, 2010, to October 31, 2020. We included all full-text studies that have used algorithms for the detection of subclinical keratoconus and excluded studies that did not perform validation. This systematic review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) recommendations. We compared the measured parameters and the design of the machine learning algorithms reported in 26 papers that met the inclusion criteria. All salient information required for detailed comparison, including diagnostic criteria, demographic data, sample size, acquisition system, validation details, parameter inputs, machine learning algorithm, and key results are reported in this study. Machine learning has the potential to improve the detection of subclinical keratoconus or early keratoconus in routine ophthalmic practice. Currently, there is no consensus regarding the corneal parameters that should be included for assessment and the optimal design for the machine learning algorithm. We have identified avenues for further research to improve early detection and stratification of patients for early treatment to prevent disease progression.
Sections du résumé
BACKGROUND
BACKGROUND
Keratoconus is a disorder characterized by progressive thinning and distortion of the cornea. If detected at an early stage, corneal collagen cross-linking can prevent disease progression and further visual loss. Although advanced forms are easily detected, reliable identification of subclinical disease can be problematic. Several different machine learning algorithms have been used to improve the detection of subclinical keratoconus based on the analysis of multiple types of clinical measures, such as corneal imaging, aberrometry, or biomechanical measurements.
OBJECTIVE
OBJECTIVE
The aim of this study is to survey and critically evaluate the literature on the algorithmic detection of subclinical keratoconus and equivalent definitions.
METHODS
METHODS
For this systematic review, we performed a structured search of the following databases: MEDLINE, Embase, and Web of Science and Cochrane Library from January 1, 2010, to October 31, 2020. We included all full-text studies that have used algorithms for the detection of subclinical keratoconus and excluded studies that did not perform validation. This systematic review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) recommendations.
RESULTS
RESULTS
We compared the measured parameters and the design of the machine learning algorithms reported in 26 papers that met the inclusion criteria. All salient information required for detailed comparison, including diagnostic criteria, demographic data, sample size, acquisition system, validation details, parameter inputs, machine learning algorithm, and key results are reported in this study.
CONCLUSIONS
CONCLUSIONS
Machine learning has the potential to improve the detection of subclinical keratoconus or early keratoconus in routine ophthalmic practice. Currently, there is no consensus regarding the corneal parameters that should be included for assessment and the optimal design for the machine learning algorithm. We have identified avenues for further research to improve early detection and stratification of patients for early treatment to prevent disease progression.
Identifiants
pubmed: 34898463
pii: v9i12e27363
doi: 10.2196/27363
pmc: PMC8713097
doi:
Types de publication
Journal Article
Review
Langues
eng
Pagination
e27363Subventions
Organisme : Medical Research Council
ID : MR/S031820/1
Pays : United Kingdom
Informations de copyright
©Howard Maile, Ji-Peng Olivia Li, Daniel Gore, Marcello Leucci, Padraig Mulholland, Scott Hau, Anita Szabo, Ismail Moghul, Konstantinos Balaskas, Kaoru Fujinami, Pirro Hysi, Alice Davidson, Petra Liskova, Alison Hardcastle, Stephen Tuft, Nikolas Pontikos. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 13.12.2021.
Références
Indian J Ophthalmol. 2008 Jan-Feb;56(1):45-50
pubmed: 18158403
Am J Ophthalmol. 2018 Nov;195:223-232
pubmed: 30098348
BMJ Open. 2019 Sep 12;9(9):e028761
pubmed: 31515418
Ophthalmology. 2021 Apr;128(4):515-521
pubmed: 32860813
Eye (Lond). 2015 Nov;29(11):1504-11
pubmed: 26315704
Eye Vis (Lond). 2016 Mar 11;3:6
pubmed: 26973847
Transl Vis Sci Technol. 2020 Sep 25;9(2):53
pubmed: 33062398
Ophthalmology. 1991 May;98(5 Suppl):786-806
pubmed: 2062513
Ophthalmology. 2012 Nov;119(11):2231-8
pubmed: 22892148
Arch Ophthalmol. 2011 Jun;129(6):691-7
pubmed: 21320951
Am J Ophthalmol. 2017 Mar;175:122-128
pubmed: 27993593
Acta Ophthalmol. 2014 May;92(3):e244-5
pubmed: 23910953
PLoS Med. 2009 Jul 21;6(7):e1000097
pubmed: 19621072
Ophthalmology. 2014 Apr;121(4):812-21
pubmed: 24393351
Clin Exp Optom. 2015 Jul;98(4):299-311
pubmed: 26104589
J Med Imaging (Bellingham). 2014 Oct;1(3):034504
pubmed: 26158069
Comput Biol Med. 2019 Jun;109:33-42
pubmed: 31035069
J Cataract Refract Surg. 2015 May;41(5):1065-72
pubmed: 26049838
Eye Vis (Lond). 2020 Sep 10;7:48
pubmed: 32974414
Ophthalmology. 1994 Mar;101(3):439-47
pubmed: 8127564
Br J Ophthalmol. 2011 Nov;95(11):1519-24
pubmed: 21349938
J Biomed Inform. 2020 Feb;102:103364
pubmed: 31891765
Cornea. 2016 Jun;35(6):827-32
pubmed: 27055215
Am J Ophthalmol. 2013 Aug;156(2):237-246.e1
pubmed: 23746611
Klin Monbl Augenheilkd. 2016 Jun;233(6):701-7
pubmed: 26789119
Ann Intern Med. 2011 Oct 18;155(8):529-36
pubmed: 22007046
J Refract Surg. 2017 Jul 1;33(7):434-443
pubmed: 28681902
J Curr Ophthalmol. 2016 Mar 29;28(1):21-6
pubmed: 27239598
J Cataract Refract Surg. 2016 Feb;42(2):275-83
pubmed: 27026453
PLoS One. 2019 Oct 11;14(10):e0223832
pubmed: 31603953
J Med Econ. 2021 Jan-Dec;24(1):410-420
pubmed: 33210975
Cornea. 2019 Nov;38(11):1382-1389
pubmed: 31335534
Am J Ophthalmol. 2017 Mar;175:169-172
pubmed: 28039037
Am J Ophthalmol. 2021 Jan;221:9-16
pubmed: 32818448
Eye (Lond). 2014 Feb;28(2):189-95
pubmed: 24357835
J Refract Surg. 2020 Apr 1;36(4):270-279
pubmed: 32267959
Eye (Lond). 2015 Apr;29(4):469-74
pubmed: 25592120
J Cataract Refract Surg. 2009 Aug;35(8):1358-62
pubmed: 19631120
Am J Ophthalmol. 2010 Apr;149(4):585-93
pubmed: 20138607
Ophthalmic Physiol Opt. 2017 Jul;37(4):460-466
pubmed: 28656673
J Ophthalmol. 2015;2015:496382
pubmed: 26075085
Sci Rep. 2017 Nov 28;7(1):16486
pubmed: 29184086
PLoS One. 2018 Nov 6;13(11):e0205998
pubmed: 30399144
J Refract Surg. 2016 Mar;32(3):187-92
pubmed: 27027626
Eye (Lond). 2000 Aug;14 ( Pt 4):625-8
pubmed: 11040911
Transl Vis Sci Technol. 2020 Apr 24;9(2):24
pubmed: 32818085
Transl Vis Sci Technol. 2020 Feb 10;9(2):5
pubmed: 32704411
Cont Lens Anterior Eye. 2017 Apr;40(2):104-108
pubmed: 27956045
Ophthalmic Physiol Opt. 2017 May;37(3):358-365
pubmed: 28303580
Invest Ophthalmol Vis Sci. 2010 Nov;51(11):5546-55
pubmed: 20554609
J Cataract Refract Surg. 2017 Dec;43(12):1582-1590
pubmed: 29335104
J Biophotonics. 2019 Oct;12(10):e201900126
pubmed: 31152630
Sci Rep. 2019 Oct 25;9(1):15379
pubmed: 31653884
Semin Ophthalmol. 2019;34(4):317-326
pubmed: 31304857
Commun Biol. 2021 Mar 1;4(1):266
pubmed: 33649486
J Cataract Refract Surg. 2017 Oct;43(10):1271-1280
pubmed: 29120713
Ophthalmologica. 1946 Feb-Mar;111(2-3):96-101
pubmed: 20275788
Invest Ophthalmol Vis Sci. 2010 Jul;51(7):3424-32
pubmed: 20164452
Eye Vis (Lond). 2020 Apr 16;7:22
pubmed: 32322599
Am J Ophthalmol. 2018 Sep;193:71-79
pubmed: 29920226
Br J Ophthalmol. 2016 Sep;100(9):1183-7
pubmed: 26659714
Nat Biomed Eng. 2018 Mar;2(3):158-164
pubmed: 31015713
IEEE Trans Neural Netw Learn Syst. 2021 Jun 10;PP:
pubmed: 34111009
Cornea. 2021 Jan;40(1):61-72
pubmed: 32769675
Ophthalmology. 2021 Nov;128(11):1516-1526
pubmed: 33892046
Acta Ophthalmol. 2021 Mar;99(2):e196-e201
pubmed: 32914586
JAMA Ophthalmol. 2020 May 1;138(5):519-526
pubmed: 32215587
Eye (Lond). 2013 Mar;27(3):329-39
pubmed: 23258309
Clin Ophthalmol. 2013;7:1539-48
pubmed: 23935360
J Cataract Refract Surg. 1998 Apr;24(4):456-63
pubmed: 9584238
Korean J Ophthalmol. 2013 Jun;27(3):162-6
pubmed: 23730107
Surv Ophthalmol. 2017 Nov - Dec;62(6):770-783
pubmed: 28688894
Cornea. 2017 Jun;36(6):689-695
pubmed: 28368992
Ophthalmology. 2017 Oct;124(10):1485-1495
pubmed: 28532974
Ophthalmology. 2019 Jul;126(7):935-945
pubmed: 30858022
Cornea. 2015 Sep;34(9):996-1004
pubmed: 26165793
Cornea. 2015 Apr;34(4):359-69
pubmed: 25738235
Optom Vis Sci. 2013 Apr;90(4):335-43
pubmed: 23376898
Acta Ophthalmol. 2020 Dec;98(8):e933-e942
pubmed: 32410342
J Refract Surg. 2018 Dec 1;34(12):840-847
pubmed: 30540367
Nat Med. 2020 Jun;26(6):892-899
pubmed: 32424211
J Refract Surg. 2016 Aug 1;32(8):510-6
pubmed: 27505311
Comput Biol Med. 2020 Jul;122:103809
pubmed: 32658727
Clin Exp Ophthalmol. 2005 Apr;33(2):199-209
pubmed: 15807834
J Cataract Refract Surg. 2014 Feb;40(2):259-68
pubmed: 24360499
Cont Lens Anterior Eye. 2021 Jun;44(3):101333
pubmed: 32448765
Ophthalmology. 2017 Dec;124(12):1726-1728
pubmed: 29157423
Invest Ophthalmol Vis Sci. 2011 Jun 08;52(7):4054-62
pubmed: 21372010
Br J Ophthalmol. 2019 Feb;103(2):167-175
pubmed: 30361278