Development and validation to predict visual acuity and keratometry two years after corneal crosslinking with progressive keratoconus by machine learning
To explore and validate the utility of machine learning (ML) methods using a limited sample size to predict changes in visual acuity and keratometry 2 years following corneal crosslinking (CXL) for progressive keratoconus. The study included all consecutive patients with progressive keratoconus who...
Gespeichert in:
| Veröffentlicht in: | Frontiers in medicine Jg. 10; S. 1146529 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Switzerland
Frontiers Media SA
03.07.2023
Frontiers Media S.A |
| Schlagworte: | |
| ISSN: | 2296-858X, 2296-858X |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | To explore and validate the utility of machine learning (ML) methods using a limited sample size to predict changes in visual acuity and keratometry 2 years following corneal crosslinking (CXL) for progressive keratoconus.
The study included all consecutive patients with progressive keratoconus who underwent CXL from July 2014 to December 2020, with a 2 year follow-up period before July 2022 to develop the model. Variables collected included patient demographics, visual acuity, spherical equivalence, and Pentacam parameters. Available case data were divided into training and testing data sets. Three ML models were evaluated based on their performance in predicting case corrected distance visual acuity (CDVA) and maximum keratometry (K
) changes compared to actual values, as indicated by average root mean squared error (RMSE) and R-squared (
) values. Patients followed from July 2022 to December 2022 were included in the validation set.
A total of 277 eyes from 195 patients were included in training and testing sets and 43 eyes from 35 patients were included in the validation set. The baseline CDVA (26.7%) and the ratio of steep keratometry to flat keratometry (K
/K
; 13.8%) were closely associated with case CDVA changes. The baseline ratio of K
to mean keratometry (K
/K
; 20.9%) was closely associated with case K
changes. Using these metrics, the best-performing ML model was XGBoost, which produced predicted values closest to the actual values for both CDVA and K
changes in testing set (
= 0.9993 and 0.9888) and validation set (
= 0.8956 and 0.8382).
Application of a ML approach using XGBoost, and incorporation of identifiable parameters, considerably improved variation prediction accuracy of both CDVA and K
2 years after CXL for treatment of progressive keratoconus. |
|---|---|
| AbstractList | To explore and validate the utility of machine learning (ML) methods using a limited sample size to predict changes in visual acuity and keratometry 2 years following corneal crosslinking (CXL) for progressive keratoconus.
The study included all consecutive patients with progressive keratoconus who underwent CXL from July 2014 to December 2020, with a 2 year follow-up period before July 2022 to develop the model. Variables collected included patient demographics, visual acuity, spherical equivalence, and Pentacam parameters. Available case data were divided into training and testing data sets. Three ML models were evaluated based on their performance in predicting case corrected distance visual acuity (CDVA) and maximum keratometry (K
) changes compared to actual values, as indicated by average root mean squared error (RMSE) and R-squared (
) values. Patients followed from July 2022 to December 2022 were included in the validation set.
A total of 277 eyes from 195 patients were included in training and testing sets and 43 eyes from 35 patients were included in the validation set. The baseline CDVA (26.7%) and the ratio of steep keratometry to flat keratometry (K
/K
; 13.8%) were closely associated with case CDVA changes. The baseline ratio of K
to mean keratometry (K
/K
; 20.9%) was closely associated with case K
changes. Using these metrics, the best-performing ML model was XGBoost, which produced predicted values closest to the actual values for both CDVA and K
changes in testing set (
= 0.9993 and 0.9888) and validation set (
= 0.8956 and 0.8382).
Application of a ML approach using XGBoost, and incorporation of identifiable parameters, considerably improved variation prediction accuracy of both CDVA and K
2 years after CXL for treatment of progressive keratoconus. PurposeTo explore and validate the utility of machine learning (ML) methods using a limited sample size to predict changes in visual acuity and keratometry 2 years following corneal crosslinking (CXL) for progressive keratoconus.MethodsThe study included all consecutive patients with progressive keratoconus who underwent CXL from July 2014 to December 2020, with a 2 year follow-up period before July 2022 to develop the model. Variables collected included patient demographics, visual acuity, spherical equivalence, and Pentacam parameters. Available case data were divided into training and testing data sets. Three ML models were evaluated based on their performance in predicting case corrected distance visual acuity (CDVA) and maximum keratometry (Kmax) changes compared to actual values, as indicated by average root mean squared error (RMSE) and R-squared ( R 2) values. Patients followed from July 2022 to December 2022 were included in the validation set.ResultsA total of 277 eyes from 195 patients were included in training and testing sets and 43 eyes from 35 patients were included in the validation set. The baseline CDVA (26.7%) and the ratio of steep keratometry to flat keratometry (K2/K1; 13.8%) were closely associated with case CDVA changes. The baseline ratio of Kmax to mean keratometry (Kmax/Kmean; 20.9%) was closely associated with case Kmax changes. Using these metrics, the best-performing ML model was XGBoost, which produced predicted values closest to the actual values for both CDVA and Kmax changes in testing set ( R 2 = 0.9993 and 0.9888) and validation set ( R 2 = 0.8956 and 0.8382).ConclusionApplication of a ML approach using XGBoost, and incorporation of identifiable parameters, considerably improved variation prediction accuracy of both CDVA and Kmax 2 years after CXL for treatment of progressive keratoconus. To explore and validate the utility of machine learning (ML) methods using a limited sample size to predict changes in visual acuity and keratometry 2 years following corneal crosslinking (CXL) for progressive keratoconus.PurposeTo explore and validate the utility of machine learning (ML) methods using a limited sample size to predict changes in visual acuity and keratometry 2 years following corneal crosslinking (CXL) for progressive keratoconus.The study included all consecutive patients with progressive keratoconus who underwent CXL from July 2014 to December 2020, with a 2 year follow-up period before July 2022 to develop the model. Variables collected included patient demographics, visual acuity, spherical equivalence, and Pentacam parameters. Available case data were divided into training and testing data sets. Three ML models were evaluated based on their performance in predicting case corrected distance visual acuity (CDVA) and maximum keratometry (Kmax) changes compared to actual values, as indicated by average root mean squared error (RMSE) and R-squared (R2) values. Patients followed from July 2022 to December 2022 were included in the validation set.MethodsThe study included all consecutive patients with progressive keratoconus who underwent CXL from July 2014 to December 2020, with a 2 year follow-up period before July 2022 to develop the model. Variables collected included patient demographics, visual acuity, spherical equivalence, and Pentacam parameters. Available case data were divided into training and testing data sets. Three ML models were evaluated based on their performance in predicting case corrected distance visual acuity (CDVA) and maximum keratometry (Kmax) changes compared to actual values, as indicated by average root mean squared error (RMSE) and R-squared (R2) values. Patients followed from July 2022 to December 2022 were included in the validation set.A total of 277 eyes from 195 patients were included in training and testing sets and 43 eyes from 35 patients were included in the validation set. The baseline CDVA (26.7%) and the ratio of steep keratometry to flat keratometry (K2/K1; 13.8%) were closely associated with case CDVA changes. The baseline ratio of Kmax to mean keratometry (Kmax/Kmean; 20.9%) was closely associated with case Kmax changes. Using these metrics, the best-performing ML model was XGBoost, which produced predicted values closest to the actual values for both CDVA and Kmax changes in testing set (R2 = 0.9993 and 0.9888) and validation set (R2 = 0.8956 and 0.8382).ResultsA total of 277 eyes from 195 patients were included in training and testing sets and 43 eyes from 35 patients were included in the validation set. The baseline CDVA (26.7%) and the ratio of steep keratometry to flat keratometry (K2/K1; 13.8%) were closely associated with case CDVA changes. The baseline ratio of Kmax to mean keratometry (Kmax/Kmean; 20.9%) was closely associated with case Kmax changes. Using these metrics, the best-performing ML model was XGBoost, which produced predicted values closest to the actual values for both CDVA and Kmax changes in testing set (R2 = 0.9993 and 0.9888) and validation set (R2 = 0.8956 and 0.8382).Application of a ML approach using XGBoost, and incorporation of identifiable parameters, considerably improved variation prediction accuracy of both CDVA and Kmax 2 years after CXL for treatment of progressive keratoconus.ConclusionApplication of a ML approach using XGBoost, and incorporation of identifiable parameters, considerably improved variation prediction accuracy of both CDVA and Kmax 2 years after CXL for treatment of progressive keratoconus. PurposeTo explore and validate the utility of machine learning (ML) methods using a limited sample size to predict changes in visual acuity and keratometry 2 years following corneal crosslinking (CXL) for progressive keratoconus.MethodsThe study included all consecutive patients with progressive keratoconus who underwent CXL from July 2014 to December 2020, with a 2 year follow-up period before July 2022 to develop the model. Variables collected included patient demographics, visual acuity, spherical equivalence, and Pentacam parameters. Available case data were divided into training and testing data sets. Three ML models were evaluated based on their performance in predicting case corrected distance visual acuity (CDVA) and maximum keratometry (Kmax) changes compared to actual values, as indicated by average root mean squared error (RMSE) and R-squared (R2) values. Patients followed from July 2022 to December 2022 were included in the validation set.ResultsA total of 277 eyes from 195 patients were included in training and testing sets and 43 eyes from 35 patients were included in the validation set. The baseline CDVA (26.7%) and the ratio of steep keratometry to flat keratometry (K2/K1; 13.8%) were closely associated with case CDVA changes. The baseline ratio of Kmax to mean keratometry (Kmax/Kmean; 20.9%) was closely associated with case Kmax changes. Using these metrics, the best-performing ML model was XGBoost, which produced predicted values closest to the actual values for both CDVA and Kmax changes in testing set (R2 = 0.9993 and 0.9888) and validation set (R2 = 0.8956 and 0.8382).ConclusionApplication of a ML approach using XGBoost, and incorporation of identifiable parameters, considerably improved variation prediction accuracy of both CDVA and Kmax 2 years after CXL for treatment of progressive keratoconus. |
| Author | Wang, Hao-yu Liu, Yu Qi, Meng-ying Zeng, Qing-yan Shen, Dan |
| AuthorAffiliation | 2 Aier Eye Hospital of Wuhan University , Wuhan , China 3 Aier Cornea Institute , Beijing , China 1 Aier School of Ophthalmology, Central South University , Changsha , China 4 Aier School of Ophthalmology and Optometry, Hubei University of Science and Technology , Xianning , China |
| AuthorAffiliation_xml | – name: 3 Aier Cornea Institute , Beijing , China – name: 2 Aier Eye Hospital of Wuhan University , Wuhan , China – name: 4 Aier School of Ophthalmology and Optometry, Hubei University of Science and Technology , Xianning , China – name: 1 Aier School of Ophthalmology, Central South University , Changsha , China |
| Author_xml | – sequence: 1 givenname: Yu surname: Liu fullname: Liu, Yu – sequence: 2 givenname: Dan surname: Shen fullname: Shen, Dan – sequence: 3 givenname: Hao-yu surname: Wang fullname: Wang, Hao-yu – sequence: 4 givenname: Meng-ying surname: Qi fullname: Qi, Meng-ying – sequence: 5 givenname: Qing-yan surname: Zeng fullname: Zeng, Qing-yan |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37534322$$D View this record in MEDLINE/PubMed |
| BookMark | eNp1ks1u1DAUhSNUREvpA7BBltiwmSGxncReIVQoVKrEBiR21rVzM-NpYg-2M9U8Cm9bz09RW4mVLfucT0f3ntfFifMOi-JtVc4ZE_JjP2I3pyVl86riTU3li-KMUtnMRC1-nzy6nxYXMa7KsqwYrXnFXhWnrK0ZZ5SeFX-_4AYHvx7RJQKuIxsYbAfJekeSJ-uAnTWJbGycYCBgJpu2e90tBkh-xBS2JN15skUIkUCfMBDjg8MsN8HHOFh3a92C3Nm0zDy_CBij3eCRYLybItFbMoJZWodkyCCXDW-Klz0MES-O53nx6-rrz8vvs5sf364vP9_MDJc8zWqsGWvLXgJvW22qxtC21LyjXGgwVJRUNxxYybSWXcNEzbtG59FU2IFmINl5cX3gdh5Wah3sCGGrPFi1f_BhoSAkawZUWhhaNSUKFJJrCoC640xzDbKpe9ll1qcDaz3pvB6ThxpgeAJ9-uPsUi38RlUlk3k7VSZ8OBKC_zNhTGq00eAwgEM_RUUFr5u6Zi3N0vfPpCs_BZdnpRhtaSOElG1WvXsc6V-WhwpkQXsQ7LcVsFfGpn0BckI75Ghq1ze165va9U0d-5ad1TPnA_z_nnudO92L |
| CitedBy_id | crossref_primary_10_1016_j_heliyon_2025_e43050 crossref_primary_10_3389_fmed_2025_1462653 crossref_primary_10_1155_joph_3678453 |
| Cites_doi | 10.1186/s12886-021-02235-4 10.3389/fnut.2020.577923 10.1145/3386252 10.1016/S0002-9394(02)02220-1 10.1016/j.jcrs.2010.10.052 10.1097/ICO.0000000000000434 10.1097/01.ico.0000226359.26678.d1 10.1111/aos.13032 10.1016/j.jcrs.2007.12.039 10.1007/s10792-021-01908-9 10.1155/2021/9979560 10.1023/A:1024068626366 10.1016/j.ajo.2012.03.020 10.2147/OPTH.S183347 10.1016/j.clae.2021.101559 10.1038/eye.2014.163 10.1007/s10792-016-0262-z 10.1097/01.icl.0000189038.74139.4a 10.1016/j.jfo.2014.11.017 10.1016/j.exer.2018.08.009 10.1007/s00417-021-05173-5 10.1007/978-3-540-24775-3_3 10.1167/iovs.06-0557 10.1016/j.jfo.2020.08.040 10.1080/02713683.2019.1594945 10.3928/1081597X-20120518-02 10.3928/1081597X-20210830-01 10.2196/27363 10.1093/bib/bbz096 10.1016/j.ajo.2013.11.001 10.1167/iovs.12-10639 10.3928/1081597X-20141120-01 10.3390/jcm10040844 10.1155/2017/4109208 10.3389/fmolb.2022.843150 10.1007/978-1-4842-7150-6_15 10.1167/iovs.02-0973 10.1016/j.survophthal.2017.12.008 10.1016/j.jcrs.2019.01.026 10.1016/j.joco.2016.10.004 10.1111/aos.14275 10.3928/1081597X-20201229-02 10.1097/j.jcrs.0000000000000952 10.1016/j.ophtha.2013.10.028 10.14744/bej.2021.15046 10.1097/ICO.0000000000001051 |
| ContentType | Journal Article |
| Copyright | Copyright © 2023 Liu, Shen, Wang, Qi and Zeng. 2023. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. Copyright © 2023 Liu, Shen, Wang, Qi and Zeng. 2023 Liu, Shen, Wang, Qi and Zeng |
| Copyright_xml | – notice: Copyright © 2023 Liu, Shen, Wang, Qi and Zeng. – notice: 2023. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: Copyright © 2023 Liu, Shen, Wang, Qi and Zeng. 2023 Liu, Shen, Wang, Qi and Zeng |
| DBID | AAYXX CITATION NPM 3V. 7X7 7XB 88E 8C1 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA GHDGH K9. M0S M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA |
| DOI | 10.3389/fmed.2023.1146529 |
| DatabaseName | CrossRef PubMed ProQuest Central (Corporate) Health Medical collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Public Health Database Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One Community College ProQuest Central Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) Health & Medical Collection (Alumni Edition) PML(ProQuest Medical Library) ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Central China ProQuest Central ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Health & Medical Research Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest Public Health ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | PubMed Publicly Available Content Database MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 2296-858X |
| ExternalDocumentID | oai_doaj_org_article_b8c2160e8e894b2aaebd43b4ba965f9d PMC10393251 37534322 10_3389_fmed_2023_1146529 |
| Genre | Journal Article |
| GeographicLocations | United States--US China |
| GeographicLocations_xml | – name: China – name: United States--US |
| GrantInformation_xml | – fundername: Research Fund of the Clinical Research Institute of Aier Eye Hospital Group grantid: AR2110D22 – fundername: Health Commission of Wuhan grantid: WX20Q19 |
| GroupedDBID | 53G 5VS 9T4 AAFWJ AAYXX ACGFS ADBBV ADRAZ AFPKN ALMA_UNASSIGNED_HOLDINGS AOIJS BAWUL BCNDV CITATION DIK GROUPED_DOAJ HYE KQ8 M48 M~E OK1 PGMZT RPM ACXDI IPNFZ NPM RIG 3V. 7X7 7XB 88E 8C1 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA K9. M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM |
| ID | FETCH-LOGICAL-c494t-5e53370f9a477bc16c270b4d248bac2802b64a303bb9d63854d6b2961edab3a93 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 9 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001029169400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2296-858X |
| IngestDate | Fri Oct 03 12:52:47 EDT 2025 Thu Aug 21 18:42:11 EDT 2025 Thu Oct 02 07:40:19 EDT 2025 Thu Nov 20 00:37:16 EST 2025 Thu Apr 03 06:57:19 EDT 2025 Sat Nov 29 01:47:46 EST 2025 Tue Nov 18 21:38:42 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | XGBoost (extreme gradient boosting) keratoconus prediction model machine learning crosslinking (CXL) corneal collagen |
| Language | English |
| License | Copyright © 2023 Liu, Shen, Wang, Qi and Zeng. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c494t-5e53370f9a477bc16c270b4d248bac2802b64a303bb9d63854d6b2961edab3a93 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Edited by: Cristina Nicula, University of Medicine and Pharmacy Iuliu Hatieganu, Romania Reviewed by: Mehran Zarei-Ghanavati, Tehran University of Medical Sciences, Iran; Ahmed Abdelkareem Elmassry, Alexandria University, Egypt |
| OpenAccessLink | https://doaj.org/article/b8c2160e8e894b2aaebd43b4ba965f9d |
| PMID | 37534322 |
| PQID | 3272688997 |
| PQPubID | 7426803 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_b8c2160e8e894b2aaebd43b4ba965f9d pubmedcentral_primary_oai_pubmedcentral_nih_gov_10393251 proquest_miscellaneous_2845655372 proquest_journals_3272688997 pubmed_primary_37534322 crossref_citationtrail_10_3389_fmed_2023_1146529 crossref_primary_10_3389_fmed_2023_1146529 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-07-03 |
| PublicationDateYYYYMMDD | 2023-07-03 |
| PublicationDate_xml | – month: 07 year: 2023 text: 2023-07-03 day: 03 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland – name: Lausanne |
| PublicationTitle | Frontiers in medicine |
| PublicationTitleAlternate | Front Med (Lausanne) |
| PublicationYear | 2023 |
| Publisher | Frontiers Media SA Frontiers Media S.A |
| Publisher_xml | – name: Frontiers Media SA – name: Frontiers Media S.A |
| References | Bikbova (ref5) 2016; 94 Sarac (ref12) 2016; 35 Gilevska (ref14) 2021; 259 Greenstein (ref40) 2011; 37 Korstanje (ref20) 2021 Peña-García (ref33) 2012; 53 Santodomingo-Rubido (ref7) 2022; 45 Sot (ref11) 2021; 44 Sağlık (ref10) 2021; 41 Rebala (ref18) 2019 Tayfur (ref32) 2021; 6 Bradford (ref43) 2018; 177 Greenstein (ref39) 2012; 28 Kato (ref23) 2021; 10 Lombardo (ref4) 2019; 45 De Angelis (ref38) 2015; 38 Iqbal (ref3) 2020; 98 Lenk (ref9) 2021; 37 Badawi (ref17) 2017; 2017 Zhao (ref30) 2020; 21 Wittig-Silva (ref2) 2014; 121 Sedaghat (ref34) 2019; 44 Jester (ref49) 2003; 44 Uçakhan (ref42) 2006; 32 Cronin (ref25) 2022; 48 Maile (ref21) 2021; 9 Ozgurhan (ref45) 2014; 30 Kotecha (ref48) 2006; 47 Viswanathan (ref36) 2015; 34 Wang (ref19) 2020; 53 Xia (ref31) 2022; 9 Mazzotta (ref26) 2014; 28 Wollensak (ref1) 2003; 135 Wisse (ref13) 2014; 157 Aatila (ref22) 2021; 2021 Raiskup-Wolf (ref8) 2008; 34 Kan (ref29) 2020; 7 Godefrooij (ref16) 2017; 37 Mimouni (ref44) 2021; 37 Zhong (ref6) 2018; 63 Vinciguerra (ref46) 2012; 154 Amanzadeh (ref37) 2017; 29 McMahon (ref24) 2006; 25 Olivo-Payne (ref47) 2019; 13 Bouckaert (ref28) 2004; 3056 Nadeau (ref27) 2003; 52 Takahashi (ref41) 1990; 94 Tian (ref15) 2022; 22 Motlagh (ref35) 2019; 8 |
| References_xml | – volume: 22 start-page: 7 year: 2022 ident: ref15 article-title: Predictive factors of the accelerated transepithelial corneal cross-linking outcomes in keratoconus publication-title: BMC Ophthalmol doi: 10.1186/s12886-021-02235-4 – volume: 7 start-page: 577923 year: 2020 ident: ref29 article-title: A machine learning based dose prediction of lutein supplements for individuals with eye fatigue publication-title: Front Nutr doi: 10.3389/fnut.2020.577923 – volume: 53 start-page: 1 year: 2020 ident: ref19 article-title: Generalizing from a few examples: A survey on few-shot learning[J] publication-title: ACM Comput Surv doi: 10.1145/3386252 – volume: 135 start-page: 620 year: 2003 ident: ref1 article-title: Riboflavin/ultraviolet-A–induced collagen crosslinking for the treatment of keratoconus publication-title: Am J Ophthalmol doi: 10.1016/S0002-9394(02)02220-1 – volume: 37 start-page: 691 year: 2011 ident: ref40 article-title: Corneal thickness changes after corneal collagen crosslinking for keratoconus and corneal ectasia: one-year results publication-title: J Cataract Refract Surg doi: 10.1016/j.jcrs.2010.10.052 – volume: 34 start-page: 791 year: 2015 ident: ref36 article-title: Relationship of structural characteristics to biomechanical profile in Normal, Keratoconic, and crosslinked eyes publication-title: Cornea doi: 10.1097/ICO.0000000000000434 – volume: 25 start-page: 794 year: 2006 ident: ref24 article-title: A new method for grading the severity of keratoconus: the keratoconus severity score (KSS) publication-title: Cornea doi: 10.1097/01.ico.0000226359.26678.d1 – volume: 94 start-page: 1068 year: 1990 ident: ref41 article-title: Quantitative analysis of collagen fiber in keratoconus publication-title: Nippon Ganka Gakkai Zasshi – volume: 94 start-page: e600 year: 2016 ident: ref5 article-title: Standard corneal collagen crosslinking versus transepithelial iontophoresis-assisted corneal crosslinking, 24 months follow-up: randomized control trial publication-title: Acta Ophthalmol doi: 10.1111/aos.13032 – volume: 34 start-page: 796 year: 2008 ident: ref8 article-title: Collagen crosslinking with riboflavin and ultraviolet-A light in keratoconus: long-term results publication-title: J Cataract Refract Surg doi: 10.1016/j.jcrs.2007.12.039 – volume: 41 start-page: 3443 year: 2021 ident: ref10 article-title: Risk factors for progression following corneal collagen crosslinking in keratoconus publication-title: Int Ophthalmol doi: 10.1007/s10792-021-01908-9 – volume: 2021 start-page: 9979560 year: 2021 ident: ref22 article-title: Keratoconus severity classification using features selection and machine learning algorithms publication-title: Comput Math Methods Med doi: 10.1155/2021/9979560 – volume: 52 start-page: 239 year: 2003 ident: ref27 article-title: Inference for the generalization error publication-title: Mach Learn doi: 10.1023/A:1024068626366 – volume: 154 start-page: 520 year: 2012 ident: ref46 article-title: Two-year corneal cross-linking results in patients younger than 18 years with documented progressive keratoconus publication-title: Am J Ophthalmol doi: 10.1016/j.ajo.2012.03.020 – volume: 13 start-page: 1183 year: 2019 ident: ref47 article-title: Optimal management of pediatric keratoconus: challenges and solutions publication-title: Clin Ophthalmol doi: 10.2147/OPTH.S183347 – volume: 8 start-page: 177 year: 2019 ident: ref35 article-title: Pentacam® corneal tomography for screening of refractive surgery candidates: A review of the literature, part I publication-title: Med Hypothesis Discov Innov Ophthalmol – volume: 45 start-page: 101559 year: 2022 ident: ref7 article-title: Keratoconus: an updated review publication-title: Cont Lens Anterior Eye doi: 10.1016/j.clae.2021.101559 – volume: 28 start-page: 1179 year: 2014 ident: ref26 article-title: Pulsed vs continuous light accelerated corneal collagen crosslinking: in vivo qualitative investigation by confocal microscopy and corneal OCT publication-title: Eye (Lond) doi: 10.1038/eye.2014.163 – volume: 37 start-page: 341 year: 2017 ident: ref16 article-title: Predictors for treatment outcomes after corneal crosslinking for keratoconus: a validation study publication-title: Int Ophthalmol doi: 10.1007/s10792-016-0262-z – volume: 32 start-page: 183 year: 2006 ident: ref42 article-title: In vivo confocal microscopy findings in keratoconus publication-title: Eye Contact Lens doi: 10.1097/01.icl.0000189038.74139.4a – volume: 38 start-page: 595 year: 2015 ident: ref38 article-title: Facteurs prédictifs de bonne réponse au crosslinking d'un kératocône évolutif: résultats réfractifs et topographiques à un an postopératoire [Predictive factors for visual outcome after corneal collagen crosslinking treatment in progressive keratoconus: One-year refractive and topographic results] publication-title: J Fr Ophtalmol doi: 10.1016/j.jfo.2014.11.017 – volume: 177 start-page: 173 year: 2018 ident: ref43 article-title: Collagen fiber crimping following in vivo UVA-induced corneal crosslinking publication-title: Exp Eye Res doi: 10.1016/j.exer.2018.08.009 – volume: 259 start-page: 2259 year: 2021 ident: ref14 article-title: Are changes in visual acuity and astigmatism after corneal cross-linking (CXL) in keratoconus predictable? publication-title: Graefes Arch Clin Exp Ophthalmol doi: 10.1007/s00417-021-05173-5 – volume: 3056 start-page: 3 year: 2004 ident: ref28 article-title: Evaluating the replicability of significance tests for comparing learning algorithms publication-title: Lecture Notes Comput Sci doi: 10.1007/978-3-540-24775-3_3 – volume: 47 start-page: 5337 year: 2006 ident: ref48 article-title: Corneal thickness- and age-related biomechanical properties of the cornea measured with the ocular response analyzer publication-title: Invest Ophthalmol Vis Sci doi: 10.1167/iovs.06-0557 – volume: 44 start-page: 863 year: 2021 ident: ref11 article-title: Risk factors for keratoconus progression after treatment by accelerated cross-linking (A-CXL): a prospective 24-month study publication-title: J Fr Ophtalmol doi: 10.1016/j.jfo.2020.08.040 – volume: 44 start-page: 707 year: 2019 ident: ref34 article-title: Predictors of successful outcome following intrastromal corneal ring segments implantation publication-title: Curr Eye Res doi: 10.1080/02713683.2019.1594945 – volume: 28 start-page: 397 year: 2012 ident: ref39 article-title: Effect of topographic cone location on outcomes of corneal collagen cross-linking for keratoconus and corneal ectasia publication-title: J Refract Surg doi: 10.3928/1081597X-20120518-02 – volume: 37 start-page: 816 year: 2021 ident: ref9 article-title: Risk factors for progression of keratoconus and failure rate after corneal cross-linking publication-title: J Refract Surg doi: 10.3928/1081597X-20210830-01 – volume: 9 start-page: e27363 year: 2021 ident: ref21 article-title: Machine learning algorithms to detect subclinical keratoconus: systematic review publication-title: JMIR Med Inform doi: 10.2196/27363 – volume: 21 start-page: 1581 year: 2020 ident: ref30 article-title: Evaluation of single-cell classifiers for single-cell RNA sequencing data sets publication-title: Brief Bioinform doi: 10.1093/bib/bbz096 – volume: 157 start-page: 519 year: 2014 ident: ref13 article-title: A multivariate analysis and statistical model for predicting visual acuity and keratometry one year after cross-linking for keratoconus publication-title: Am J Ophthalmol doi: 10.1016/j.ajo.2013.11.001 – volume: 53 start-page: 8447 year: 2012 ident: ref33 article-title: Intracorneal ring segment in keratoconus: a model to predict visual changes induced by the surgery publication-title: Invest Ophthalmol Vis Sci doi: 10.1167/iovs.12-10639 – volume: 30 start-page: 843 year: 2014 ident: ref45 article-title: Accelerated corneal cross-linking in pediatric patients with keratoconus: 24-month outcomes publication-title: J Refract Surg doi: 10.3928/1081597X-20141120-01 – volume: 10 start-page: 844 year: 2021 ident: ref23 article-title: Predicting keratoconus progression and need for corneal crosslinking using deep learning publication-title: J Clin Med doi: 10.3390/jcm10040844 – volume: 2017 start-page: 4109208 year: 2017 ident: ref17 article-title: Predictive factors of the standard cross-linking outcomes in adult keratoconus: one-year follow-up publication-title: J Ophthalmol doi: 10.1155/2017/4109208 – volume: 9 start-page: 843150 year: 2022 ident: ref31 article-title: Inferring retinal degeneration-related genes based on Xgboost publication-title: Front Mol Biosci doi: 10.3389/fmolb.2022.843150 – volume-title: Advanced Forecasting With Python year: 2021 ident: ref20 article-title: Gradient boosting with XGBoost and LightGBM doi: 10.1007/978-1-4842-7150-6_15 – volume: 44 start-page: 1850 year: 2003 ident: ref49 article-title: Myofibroblast differentiation of normal human keratocytes and hTERT, extended-life human corneal fibroblasts publication-title: Invest Ophthalmol Vis Sci doi: 10.1167/iovs.02-0973 – start-page: 1 volume-title: An Introduction to Machine Learning year: 2019 ident: ref18 article-title: Machine learning definition and basics – volume: 63 start-page: 453 year: 2018 ident: ref6 article-title: Angiogenesis and lymphangiogenesis in corneal transplantation—a review publication-title: Surv Ophthalmol doi: 10.1016/j.survophthal.2017.12.008 – volume: 45 start-page: 992 year: 2019 ident: ref4 article-title: Two-year outcomes of a randomized controlled trial of transepithelial corneal crosslinking with iontophoresis for keratoconus publication-title: J Cataract Refract Surg doi: 10.1016/j.jcrs.2019.01.026 – volume: 29 start-page: 189 year: 2017 ident: ref37 article-title: Effects of single-segment Intacs implantation on visual acuity and corneal topographic indices of keratoconus publication-title: J Curr Ophthalmol doi: 10.1016/j.joco.2016.10.004 – volume: 98 start-page: e352 year: 2020 ident: ref3 article-title: Standard cross-linking protocol versus accelerated and transepithelial cross-linking protocols for treatment of paediatric keratoconus: a 2-year comparative study publication-title: Acta Ophthalmol doi: 10.1111/aos.14275 – volume: 37 start-page: 186 year: 2021 ident: ref44 article-title: Fellow eye as a predictor for keratoconus progression following accelerated corneal cross-linking publication-title: J Refract Surg doi: 10.3928/1081597X-20201229-02 – volume: 48 start-page: 1175 year: 2022 ident: ref25 article-title: Oxygen-supplemented transepithelial-accelerated corneal crosslinking with pulsed irradiation for progressive keratoconus: 1 year outcomes publication-title: J Cataract Refract Surg doi: 10.1097/j.jcrs.0000000000000952 – volume: 121 start-page: 812 year: 2014 ident: ref2 article-title: A randomized, controlled trial of corneal collagen cross-linking in progressive keratoconus: three-year results publication-title: Ophthalmology doi: 10.1016/j.ophtha.2013.10.028 – volume: 6 start-page: 267 year: 2021 ident: ref32 article-title: Factors affecting visual gain after accelerated crosslinking in pediatric Keratoconic cases publication-title: Beyoglu Eye J doi: 10.14744/bej.2021.15046 – volume: 35 start-page: 1503 year: 2016 ident: ref12 article-title: Factors influencing progression of keratoconus 2 years after corneal collagen cross-linking in pediatric patients publication-title: Cornea doi: 10.1097/ICO.0000000000001051 |
| SSID | ssj0001325413 |
| Score | 2.29554 |
| Snippet | To explore and validate the utility of machine learning (ML) methods using a limited sample size to predict changes in visual acuity and keratometry 2 years... PurposeTo explore and validate the utility of machine learning (ML) methods using a limited sample size to predict changes in visual acuity and keratometry 2... |
| SourceID | doaj pubmedcentral proquest pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 1146529 |
| SubjectTerms | Algorithms Cornea crosslinking (CXL) corneal collagen Datasets keratoconus Machine learning Medicine prediction model Surgery Visual acuity Vitamin B XGBoost (extreme gradient boosting) |
| SummonAdditionalLinks | – databaseName: Health Medical collection dbid: 7X7 link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Jj9MwFLZgQIgL-xIYkJE4IUUktuPlhAAx4sKIA0i9Rd4yVDBJyVLUn8K_5dlx2ylCc-HauNFT3uLv2Z_eh9DLQK0wyrhc6QYaFNjTIKWczWkD4Ljh3BnpotiEOD2Vi4X6nA7chkSr3NbEWKhdZ8MZ-WtKBOESugPxZvUzD6pR4XY1SWhcRdeCbHaIc7EQ-zMWCu1PSefLTOjFFDjLh_GghMYZuVUElvvtKE7t_xfU_JsxeWELOrn9v8bfQbcS-MRv52i5i6749h668Sldr99Hvy9QiLBuHYYwXM6iS3js8KoPK0e8Xg4TvEbbCSB8XPc9jGbuzv3Yb_D4q8MbyJ8BR_1xDO1tC2gUxw-QpBpwOP7FkRsWaLhrn94Azfk0YLPB55Hj6XEStTh7gL6efPjy_mOetBtyyxQb88oDjhRFozQTwtiSWyIKwxxh0mhLZEEMZxr2T2OUgxpQMccNUbz0ThuqFX2Ijtqu9Y8R9qphleOeEm8APhLpG8WMU5YUUnNpM1RsXVjbNNg86Gv8qKHBCV6vg9fr4PU6eT1Dr3Z_Wc1TPS5b_C7ExW5hGMgdf-j6szrld22kJSUvvPQSjCNae-MYNcxoxatGuQwdbyOjTlViqPdhkaEXu8eQ3-HSRre-m4Ya4ANg7ooKkqFHcxDuLKHQazKoyBmSB-F5YOrhk3b5Lc4QDwwAyI7yyeV2PUU3w6eI_GR6jI7GfvLP0HW7HpdD_zxm2x-DBzlx priority: 102 providerName: ProQuest |
| Title | Development and validation to predict visual acuity and keratometry two years after corneal crosslinking with progressive keratoconus by machine learning |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/37534322 https://www.proquest.com/docview/3272688997 https://www.proquest.com/docview/2845655372 https://pubmed.ncbi.nlm.nih.gov/PMC10393251 https://doaj.org/article/b8c2160e8e894b2aaebd43b4ba965f9d |
| Volume | 10 |
| WOSCitedRecordID | wos001029169400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: DOA dateStart: 20140101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: M~E dateStart: 20140101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: 7X7 dateStart: 20190101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: BENPR dateStart: 20190101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Public Health Database customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: 8C1 dateStart: 20190101 isFulltext: true titleUrlDefault: https://search.proquest.com/publichealth providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: PIMPY dateStart: 20190101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Li9RAEG50FfEivo2uQwuehMGku9OPo7vsoocdBlEYT6Ff0UE3WSbJyPyU_bdb3ekdZ0T04iWQpBM6qarU96WLrxB6HUorjDJuqnQNBAVyGoSUs1NaAziuOXdGuthsQsxmcrFQ851WX6EmbJQHHl_cWyMtKXjupZeKGaK1N45Rw4xWvKyVC1_fXKgdMhX_rlAgPgUdlzGBhSkwkw_CoIRGddwyQspfiSjq9f8JZP5eK7mTfE7vo3sJNeJ342wfoBu-eYjunKV18Ufocqf2B-vGYfCf5dgtCfctvliFkT1eL7sBbqPtANg7jvseNJXbc9-vNrj_2eINOH6HY-NwDLy0ARiJ4_xTjwUc_tviWNQV6mfXPt0BWPXQYbPB57E40-PUjeLrY_T59OTT8ftparowtUyxflp6AIAir5VmQhhbcEtEbpgjTBpticyJ4UxD4jNGOQjekjluiOKFd9pQregTdNC0jX-GsFc1Kx33lHgDuI9IX4MJnbIkl5pLm6H82gKVTYrkoTHGjwqYSTBaFYxWBaNVyWgZerO95GKU4_jb4KNg1u3AoKQdD4B_Vcm_qn_5V4YOr52iSuHdVZQIwiVQVZGhV9vTEJhhtUU3vh26CvI-gOWSCpKhp6MPbWdCgSQy-JRmSO55195U9880y29R_Dss3YNzF8__x8O9QHfDC4vlx_QQHfSrwb9Et-26X3arCbopFiJuJWzlcTFBt45OZvOPkxhssDf_cDb_cgVloTJh |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bb9MwFLamDQEv3C-BAUaCF6SI1HYS-wEhbtOqrVUfhjSegm8ZFSwpTdqpP4U_wW_k2HHbFaG97YHXxo1c9zvH53O-nA-hF05aoYQysZAlEBTY0yCkjI5pCcVxmWVGcePNJvLhkB8fi9EW-r18F8bJKpc50SdqU2t3Rv6akpxkHNhB_nbyM3auUe7p6tJCo4PFgV2cAWVr3vQ_wv_7kpC9T0cf9uPgKhBrJlgbpxYqnDwphWR5rnQv0yRPFDOEcSU14QlRGZOQ2ZUSBtCZMpMpIrKeNVJR6ZovQcrfYQ7s22hn1B-MvqxPdSgQrh7tHp8C-xMAD-sakhLqu_KmvpRdb4DeJ-Bfxe3fGs1zm97ezf9tuW6hG6G8xu-6eLiNtmx1B10dBAHBXfTrnEgKy8pgCLRxZyuF2xpPpm5ki-fjZga3kXoGJMWP--6aT9entp0ucHtW4wX8tgZ7h3UMBL6Cehv7BQ9mFNgdcGOvfnNC47kNd9B1NWuwWuBTr2K1ONh2nNxDny9lYe6j7aqu7EOErShZajJLiVVQIBNuS8GUEZokXGZcRyhZQqbQoXW7cxD5UQCFcygrHMoKh7IioCxCr1ZfmXR9Sy4a_N7hcDXQtRz3H9TTkyJksEJxTXpZYrnlMDkipVWGUcWUFFlaChOh3SUSi5AHm2INwwg9X12GDOYeS8nK1rOmgAIJWEVKcxKhBx3oVzOhwKYZ7DkR4hvhsDHVzSvV-Jvvku40DhCNvUcXz-sZurZ_NDgsDvvDg8foulsWr8amu2i7nc7sE3RFz9txM30aYh2jr5cdL38A_PeW8Q |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Development+and+validation+to+predict+visual+acuity+and+keratometry+two+years+after+corneal+crosslinking+with+progressive+keratoconus+by+machine+learning&rft.jtitle=Frontiers+in+medicine&rft.au=Liu%2C+Yu&rft.au=Shen%2C+Dan&rft.au=Wang%2C+Hao-yu&rft.au=Qi%2C+Meng-ying&rft.date=2023-07-03&rft.pub=Frontiers+Media+S.A&rft.eissn=2296-858X&rft.volume=10&rft_id=info:doi/10.3389%2Ffmed.2023.1146529&rft.externalDocID=PMC10393251 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2296-858X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2296-858X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2296-858X&client=summon |