Establishment of a prediction tool for ocular trauma patients with machine learning algorithm

AIM: To predict final visual acuity and analyze significant factors influencing open globe injury prognosis. METHODS: Prediction models were built using a supervised classification algorithm from Microsoft Azure Machine Learning Studio. The best algorithm was selected to analyze the predicted final...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Seungkwon Choi, Jungyul Park, Sungwho Park, Iksoo Byon, Hee-Young Choi
Formato:	article
Lenguaje:	EN
Publicado:	Press of International Journal of Ophthalmology (IJO PRESS) 2021
Materias:	machine learning ocular trauma open globe injury predictive model vision preservation Ophthalmology RE1-994
Acceso en línea:	https://doaj.org/article/0f78c503aef04a928849d330af73ccf8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0f78c503aef04a928849d330af73ccf8
record_format	dspace
spelling	oai:doaj.org-article:0f78c503aef04a928849d330af73ccf82021-11-26T04:02:12ZEstablishment of a prediction tool for ocular trauma patients with machine learning algorithm2222-39592227-489810.18240/ijo.2021.12.20https://doaj.org/article/0f78c503aef04a928849d330af73ccf82021-12-01T00:00:00Zhttp://ies.ijo.cn/en_publish/2021/12/20211220.pdfhttps://doaj.org/toc/2222-3959https://doaj.org/toc/2227-4898AIM: To predict final visual acuity and analyze significant factors influencing open globe injury prognosis. METHODS: Prediction models were built using a supervised classification algorithm from Microsoft Azure Machine Learning Studio. The best algorithm was selected to analyze the predicted final visual acuity. We retrospectively reviewed the data of 171 patients with open globe injury who visited the Pusan National University Hospital between January 2010 and July 2020. We then applied cross-validation, the permutation feature importance method, and the synthetic minority over-sampling technique to enhance tool performance. RESULTS: The two-class boosted decision tree model showed the best predictive performance. The accuracy, precision, recall, F1 score, and area under the receiver operating characteristic curve were 0.925, 0.962, 0.833, 0.893, and 0.971, respectively. To increase the efficiency and efficacy of the prognostic tool, the top 14 features were finally selected using the permutation feature importance method: (listed in the order of importance) retinal detachment, location of laceration, initial visual acuity, iris damage, surgeon, past history, size of the scleral laceration, vitreous hemorrhage, trauma characteristics, age, corneal injury, primary diagnosis, wound location, and lid laceration. CONCLUSION: Here we devise a highly accurate model to predict the final visual acuity of patients with open globe injury. This tool is useful and easily accessible to doctors and patients, reducing the socioeconomic burden. With further multicenter verification using larger datasets and external validation, we expect this model to become useful worldwide.Seungkwon ChoiJungyul ParkSungwho ParkIksoo ByonHee-Young ChoiPress of International Journal of Ophthalmology (IJO PRESS)articlemachine learningocular traumaopen globe injurypredictive modelvision preservationOphthalmologyRE1-994ENInternational Journal of Ophthalmology, Vol 14, Iss 12, Pp 1941-1949 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	machine learning ocular trauma open globe injury predictive model vision preservation Ophthalmology RE1-994
spellingShingle	machine learning ocular trauma open globe injury predictive model vision preservation Ophthalmology RE1-994 Seungkwon Choi Jungyul Park Sungwho Park Iksoo Byon Hee-Young Choi Establishment of a prediction tool for ocular trauma patients with machine learning algorithm
description	AIM: To predict final visual acuity and analyze significant factors influencing open globe injury prognosis. METHODS: Prediction models were built using a supervised classification algorithm from Microsoft Azure Machine Learning Studio. The best algorithm was selected to analyze the predicted final visual acuity. We retrospectively reviewed the data of 171 patients with open globe injury who visited the Pusan National University Hospital between January 2010 and July 2020. We then applied cross-validation, the permutation feature importance method, and the synthetic minority over-sampling technique to enhance tool performance. RESULTS: The two-class boosted decision tree model showed the best predictive performance. The accuracy, precision, recall, F1 score, and area under the receiver operating characteristic curve were 0.925, 0.962, 0.833, 0.893, and 0.971, respectively. To increase the efficiency and efficacy of the prognostic tool, the top 14 features were finally selected using the permutation feature importance method: (listed in the order of importance) retinal detachment, location of laceration, initial visual acuity, iris damage, surgeon, past history, size of the scleral laceration, vitreous hemorrhage, trauma characteristics, age, corneal injury, primary diagnosis, wound location, and lid laceration. CONCLUSION: Here we devise a highly accurate model to predict the final visual acuity of patients with open globe injury. This tool is useful and easily accessible to doctors and patients, reducing the socioeconomic burden. With further multicenter verification using larger datasets and external validation, we expect this model to become useful worldwide.
format	article
author	Seungkwon Choi Jungyul Park Sungwho Park Iksoo Byon Hee-Young Choi
author_facet	Seungkwon Choi Jungyul Park Sungwho Park Iksoo Byon Hee-Young Choi
author_sort	Seungkwon Choi
title	Establishment of a prediction tool for ocular trauma patients with machine learning algorithm
title_short	Establishment of a prediction tool for ocular trauma patients with machine learning algorithm
title_full	Establishment of a prediction tool for ocular trauma patients with machine learning algorithm
title_fullStr	Establishment of a prediction tool for ocular trauma patients with machine learning algorithm
title_full_unstemmed	Establishment of a prediction tool for ocular trauma patients with machine learning algorithm
title_sort	establishment of a prediction tool for ocular trauma patients with machine learning algorithm
publisher	Press of International Journal of Ophthalmology (IJO PRESS)
publishDate	2021
url	https://doaj.org/article/0f78c503aef04a928849d330af73ccf8
work_keys_str_mv	AT seungkwonchoi establishmentofapredictiontoolforoculartraumapatientswithmachinelearningalgorithm AT jungyulpark establishmentofapredictiontoolforoculartraumapatientswithmachinelearningalgorithm AT sungwhopark establishmentofapredictiontoolforoculartraumapatientswithmachinelearningalgorithm AT iksoobyon establishmentofapredictiontoolforoculartraumapatientswithmachinelearningalgorithm AT heeyoungchoi establishmentofapredictiontoolforoculartraumapatientswithmachinelearningalgorithm
_version_	1718409883609464832

Establishment of a prediction tool for ocular trauma patients with machine learning algorithm

Ejemplares similares