Patient selection for corneal topographic evaluation of keratoconus: A screening approach using artificial intelligence
BackgroundCorneal topography is a clinically validated examination method for keratoconus. However, there is no clear guideline regarding patient selection for corneal topography. We developed and validated a novel artificial intelligence (AI) model to identify patients who would benefit from cornea...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2022.934865/full |
| _version_ | 1811221323424202752 |
|---|---|
| author | Hyunmin Ahn Na Eun Kim Jae Lim Chung Young Jun Kim Ikhyun Jun Tae-im Kim Kyoung Yul Seo |
| author_facet | Hyunmin Ahn Na Eun Kim Jae Lim Chung Young Jun Kim Ikhyun Jun Tae-im Kim Kyoung Yul Seo |
| author_sort | Hyunmin Ahn |
| collection | DOAJ |
| description | BackgroundCorneal topography is a clinically validated examination method for keratoconus. However, there is no clear guideline regarding patient selection for corneal topography. We developed and validated a novel artificial intelligence (AI) model to identify patients who would benefit from corneal topography based on basic ophthalmologic examinations, including a survey of visual impairment, best-corrected visual acuity (BCVA) measurement, intraocular pressure (IOP) measurement, and autokeratometry.MethodsA total of five AI models (three individual models with fully connected neural network including the XGBoost, and the TabNet models, and two ensemble models with hard and soft voting methods) were trained and validated. We used three datasets collected from the records of 2,613 patients' basic ophthalmologic examinations from two institutions to train and validate the AI models. We trained the AI models using a dataset from a third medical institution to determine whether corneal topography was needed to detect keratoconus. Finally, prospective intra-validation dataset (internal test dataset) and extra-validation dataset from a different medical institution (external test dataset) were used to assess the performance of the AI models.ResultsThe ensemble model with soft voting method outperformed all other AI models in sensitivity when predicting which patients needed corneal topography (90.5% in internal test dataset and 96.4% in external test dataset). In the error analysis, most of the predicting error occurred within the range of the subclinical keratoconus and the suspicious D-score in the Belin-Ambrósio enhanced ectasia display. In the feature importance analysis, out of 18 features, IOP was the highest ranked feature when comparing the average value of the relative attributions of three individual AI models, followed by the difference in the value of mean corneal power.ConclusionAn AI model using the results of basic ophthalmologic examination has the potential to recommend corneal topography for keratoconus. In this AI algorithm, IOP and the difference between the two eyes, which may be undervalued clinical information, were important factors in the success of the AI model, and may be worth further reviewing in research and clinical practice for keratoconus screening. |
| first_indexed | 2024-04-12T07:57:25Z |
| format | Article |
| id | doaj.art-4450918a87b0463281ad6de3ed4fa407 |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-04-12T07:57:25Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-4450918a87b0463281ad6de3ed4fa4072022-12-22T03:41:26ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2022-08-01910.3389/fmed.2022.934865934865Patient selection for corneal topographic evaluation of keratoconus: A screening approach using artificial intelligenceHyunmin Ahn0Na Eun Kim1Jae Lim Chung2Young Jun Kim3Ikhyun Jun4Tae-im Kim5Kyoung Yul Seo6Department of Ophthalmology, The Institute of Vision Research, Yonsei University College of Medicine, Seoul, South KoreaDepartment of Ophthalmology, The Institute of Vision Research, Yonsei University College of Medicine, Seoul, South KoreaEyejun Ophthalmic Clinic, Seoul, South KoreaEyejun Ophthalmic Clinic, Seoul, South KoreaDepartment of Ophthalmology, The Institute of Vision Research, Yonsei University College of Medicine, Seoul, South KoreaDepartment of Ophthalmology, The Institute of Vision Research, Yonsei University College of Medicine, Seoul, South KoreaDepartment of Ophthalmology, The Institute of Vision Research, Yonsei University College of Medicine, Seoul, South KoreaBackgroundCorneal topography is a clinically validated examination method for keratoconus. However, there is no clear guideline regarding patient selection for corneal topography. We developed and validated a novel artificial intelligence (AI) model to identify patients who would benefit from corneal topography based on basic ophthalmologic examinations, including a survey of visual impairment, best-corrected visual acuity (BCVA) measurement, intraocular pressure (IOP) measurement, and autokeratometry.MethodsA total of five AI models (three individual models with fully connected neural network including the XGBoost, and the TabNet models, and two ensemble models with hard and soft voting methods) were trained and validated. We used three datasets collected from the records of 2,613 patients' basic ophthalmologic examinations from two institutions to train and validate the AI models. We trained the AI models using a dataset from a third medical institution to determine whether corneal topography was needed to detect keratoconus. Finally, prospective intra-validation dataset (internal test dataset) and extra-validation dataset from a different medical institution (external test dataset) were used to assess the performance of the AI models.ResultsThe ensemble model with soft voting method outperformed all other AI models in sensitivity when predicting which patients needed corneal topography (90.5% in internal test dataset and 96.4% in external test dataset). In the error analysis, most of the predicting error occurred within the range of the subclinical keratoconus and the suspicious D-score in the Belin-Ambrósio enhanced ectasia display. In the feature importance analysis, out of 18 features, IOP was the highest ranked feature when comparing the average value of the relative attributions of three individual AI models, followed by the difference in the value of mean corneal power.ConclusionAn AI model using the results of basic ophthalmologic examination has the potential to recommend corneal topography for keratoconus. In this AI algorithm, IOP and the difference between the two eyes, which may be undervalued clinical information, were important factors in the success of the AI model, and may be worth further reviewing in research and clinical practice for keratoconus screening.https://www.frontiersin.org/articles/10.3389/fmed.2022.934865/fullartificial intelligencecorneal topographykeratoconusmachine learningPentacamscreening test |
| spellingShingle | Hyunmin Ahn Na Eun Kim Jae Lim Chung Young Jun Kim Ikhyun Jun Tae-im Kim Kyoung Yul Seo Patient selection for corneal topographic evaluation of keratoconus: A screening approach using artificial intelligence Frontiers in Medicine artificial intelligence corneal topography keratoconus machine learning Pentacam screening test |
| title | Patient selection for corneal topographic evaluation of keratoconus: A screening approach using artificial intelligence |
| title_full | Patient selection for corneal topographic evaluation of keratoconus: A screening approach using artificial intelligence |
| title_fullStr | Patient selection for corneal topographic evaluation of keratoconus: A screening approach using artificial intelligence |
| title_full_unstemmed | Patient selection for corneal topographic evaluation of keratoconus: A screening approach using artificial intelligence |
| title_short | Patient selection for corneal topographic evaluation of keratoconus: A screening approach using artificial intelligence |
| title_sort | patient selection for corneal topographic evaluation of keratoconus a screening approach using artificial intelligence |
| topic | artificial intelligence corneal topography keratoconus machine learning Pentacam screening test |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2022.934865/full |
| work_keys_str_mv | AT hyunminahn patientselectionforcornealtopographicevaluationofkeratoconusascreeningapproachusingartificialintelligence AT naeunkim patientselectionforcornealtopographicevaluationofkeratoconusascreeningapproachusingartificialintelligence AT jaelimchung patientselectionforcornealtopographicevaluationofkeratoconusascreeningapproachusingartificialintelligence AT youngjunkim patientselectionforcornealtopographicevaluationofkeratoconusascreeningapproachusingartificialintelligence AT ikhyunjun patientselectionforcornealtopographicevaluationofkeratoconusascreeningapproachusingartificialintelligence AT taeimkim patientselectionforcornealtopographicevaluationofkeratoconusascreeningapproachusingartificialintelligence AT kyoungyulseo patientselectionforcornealtopographicevaluationofkeratoconusascreeningapproachusingartificialintelligence |