• Something wrong with this record ?

Machine Learning Algorithms to Detect Subclinical Keratoconus: Systematic Review

H. Maile, JO. Li, D. Gore, M. Leucci, P. Mulholland, S. Hau, A. Szabo, I. Moghul, K. Balaskas, K. Fujinami, P. Hysi, A. Davidson, P. Liskova, A. Hardcastle, S. Tuft, N. Pontikos

. 2021 ; 9 (12) : e27363. [pub] 20211213

Language English Country Canada

Document type Journal Article, Review

Persistent link   https://www.medvik.cz/link/bmc22001055

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: The aim of this study is to survey and critically evaluate the literature on the algorithmic detection of subclinical keratoconus and equivalent definitions. 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: 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: 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.

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc22001055
003      
CZ-PrNML
005      
20220112153452.0
007      
ta
008      
220107s2021 xxc f 000 0|eng||
009      
AR
024    7_
$a 10.2196/27363 $2 doi
035    __
$a (PubMed)34898463
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxc
100    1_
$a Maile, Howard $u UCL Institute of Ophthalmology, University College London, London, United Kingdom
245    10
$a Machine Learning Algorithms to Detect Subclinical Keratoconus: Systematic Review / $c H. Maile, JO. Li, D. Gore, M. Leucci, P. Mulholland, S. Hau, A. Szabo, I. Moghul, K. Balaskas, K. Fujinami, P. Hysi, A. Davidson, P. Liskova, A. Hardcastle, S. Tuft, N. Pontikos
520    9_
$a 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: The aim of this study is to survey and critically evaluate the literature on the algorithmic detection of subclinical keratoconus and equivalent definitions. 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: 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: 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.
655    _2
$a časopisecké články $7 D016428
655    _2
$a přehledy $7 D016454
700    1_
$a Li, Ji-Peng Olivia $u Moorfields Eye Hospital, London, United Kingdom
700    1_
$a Gore, Daniel $u Moorfields Eye Hospital, London, United Kingdom
700    1_
$a Leucci, Marcello $u Moorfields Eye Hospital, London, United Kingdom
700    1_
$a Mulholland, Padraig $u UCL Institute of Ophthalmology, University College London, London, United Kingdom $u Moorfields Eye Hospital, London, United Kingdom $u Centre for Optometry & Vision Science, Biomedical Sciences Research Institute, Ulster University, Coleraine, United Kingdom
700    1_
$a Hau, Scott $u Moorfields Eye Hospital, London, United Kingdom
700    1_
$a Szabo, Anita $u UCL Institute of Ophthalmology, University College London, London, United Kingdom
700    1_
$a Moghul, Ismail $u Moorfields Eye Hospital, London, United Kingdom
700    1_
$a Balaskas, Konstantinos $u Moorfields Eye Hospital, London, United Kingdom
700    1_
$a Fujinami, Kaoru $u UCL Institute of Ophthalmology, University College London, London, United Kingdom $u Moorfields Eye Hospital, London, United Kingdom $u Laboratory of Visual Physiology, Division of Vision Research, National Institute of Sensory Organs, National Hospital Organization Tokyo Medical Center, Tokyo, Japan $u Department of Ophthalmology, Keio University School of Medicine, Tokyo, Japan
700    1_
$a Hysi, Pirro $u Section of Ophthalmology, School of Life Course Sciences, King's College London, London, United Kingdom $u Department of Twin Research and Genetic Epidemiology, King's College London, London, United Kingdom
700    1_
$a Davidson, Alice $u UCL Institute of Ophthalmology, University College London, London, United Kingdom
700    1_
$a Liskova, Petra $u Department of Paediatrics and Inherited Metabolic Disorders, First Faculty of Medicine, Charles University and General University Hospital, Prague, Czech Republic $u Department of Ophthalmology, First Faculty of Medicine, Charles University and General University Hospital, Prague, Czech Republic
700    1_
$a Hardcastle, Alison $u UCL Institute of Ophthalmology, University College London, London, United Kingdom
700    1_
$a Tuft, Stephen $u UCL Institute of Ophthalmology, University College London, London, United Kingdom $u Moorfields Eye Hospital, London, United Kingdom
700    1_
$a Pontikos, Nikolas $u UCL Institute of Ophthalmology, University College London, London, United Kingdom $u Moorfields Eye Hospital, London, United Kingdom
773    0_
$w MED00207620 $t JMIR medical informatics $x 2291-9694 $g Roč. 9, č. 12 (2021), s. e27363
856    41
$u https://pubmed.ncbi.nlm.nih.gov/34898463 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20220107 $b ABA008
991    __
$a 20220112153448 $b ABA008
999    __
$a ind $b bmc $g 1745344 $s 1152202
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2021 $b 9 $c 12 $d e27363 $e 20211213 $i 2291-9694 $m JMIR medical informatics $n JMIR Med Inform $x MED00207620
LZP    __
$a Pubmed-20220107

Find record

Citation metrics

Archiving options