An improved machine learning model for calculation of intraocular lens power during cataract surgery in Republic of Korea: development
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Background: To assess an improved machine learning model for calculation of intraocular lens (IOL) power during cataract surgery.Methods: We reviewed 346 medical records of cataract surgery patients from the Dankook University Hospital and developed a machine regression model to calculate IOL power. Well-known machine learning algorithms such as random forest, gradient boosting machine, support vector machine (SVM), and eXtreme Gradient Boosting were tested to develop the best prediction model. The model accuracy was judged by comparing the difference between the predicted refractory powers and the actual postoperative refractory ones based on ±0.25, ±0.5, ±0.75, and ±1 D. The prediction error was also evaluated by statistical measures. The proposed model was compared with existing formulas, such as SRK/T, Barrett Universal II, Hill-RBF, and Kane.Results: The proposed SVM model produced an accuracy of 43.3%, 77.2%, 87.0%, and 95.4% for refraction powers based on ±0.25, ±0.5, ±0.75, and ±1 D, respectively. In contrast, the Barrett Universal II formula produced an accuracy of 34.3%, 60.8%, 83.2%, and 93.0% for refraction powers.Conclusion: The proposed machine learning prediction model showed better performance than the current formulas. This improved machine learning model using machine learning calculations could thus be used in IOL power calculations.
Abstract
Background: To assess an improved machine learning model for calculation of intraocular lens (IOL) power during cataract surgery.Methods: We reviewed 346 medical records of cataract surgery patients from the Dankook University Hospital and developed a machine regression model to calculate IOL power. Well-known machine learning algorithms such as random forest, gradient boosting machine, support vector machine (SVM), and eXtreme Gradient Boosting were tested to develop the best prediction model. The model accuracy was judged by comparing the difference between the predicted refractory powers and the actual postoperative refractory ones based on ±0.25, ±0.5, ±0.75, and ±1 D. The prediction error was also evaluated by statistical measures. The proposed model was compared with existing formulas, such as SRK/T, Barrett Universal II, Hill-RBF, and Kane.Results: The proposed SVM model produced an accuracy of 43.3%, 77.2%, 87.0%, and 95.4% for refraction powers based on ±0.25, ±0.5, ±0.75, and ±1 D, respectively. In contrast, the Barrett Universal II formula produced an accuracy of 34.3%, 60.8%, 83.2%, and 93.0% for refraction powers.Conclusion: The proposed machine learning prediction model showed better performance than the current formulas. This improved machine learning model using machine learning calculations could thus be used in IOL power calculations.
참고문헌 (21)
- Fernández-Álvarez JC, "Using a multilayer perceptron in intraocular lens power calculation", J Cataract Refract Surg, 45, pp.1753~1761 (2019)
- Sramka M, "Improving clinical refractive results of cataract surgery by machine learning", PeerJ, 7, pp.e7202~ (2019)
- Carmona González D, "Accuracy of a new intraocular lens power calculation method based on artificial intelligence", Eye(Lond), 35, pp.517~522 (2021)
- Retzlaff JA, "Development of the SRK", T intraocular lens implant power calculation formula, 1990, pp.16, 333~340
- Barrett GD, "Intraocular lens calculation formulas for new intraocular lens implants", J Cataract Refract Surg, 13, pp.389~396 (1987)
- "Haag-Streit White Paper. Hill-RBF method" (2017)[URL]
- Connell BJ, "Comparison of the Kane formula with existing formulas for intraocular lens power selection", BMJ Open Ophthalmol, 4, pp.e000251~ (2019)
- Cortes C, "Support-vector networks", Mach Learn, 20, pp.273~297 (1995)
- Vapnik V, "Support vector method for function approximation, regression estimation and signal processing", NIPS’96: Proceedings of the 9th International Conference on Neural Information Processing Systems, pp.281~287 (1996), MIT Press
- Breiman L, "Classification and regression trees" (1984), Wadsworth International Group
- Freund Y, "Experiments with a new boosting algorithm", ICML’96: Proceedings of the Thirteenth International Conference on International Conference on Machine Learning, pp.148~156 (1996), Morgan Kaufmann Publishers Inc
- Friedman JH, "Greedy function approximation : a gradient boosting machine", Ann Stat, 29, pp.1189~1232 (2001)
- "xgboost: eXtreme Gradient Boosting" (2014)[URL]
- 정진호, "Hoffer Q와 SRK", T 인공수정체 도수 계산 공식의 이론적 임상적 비교, 2014, pp.55(1), 85~92[DOI]
- Olsen T, "Calculation of intraocular lens power : a review", Acta Ophthalmol Scand, 85, pp.472~485 (2007)
- Olson M, "Modern neural networks generalize on small data sets", NIPS’18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp.3623~3632 (2018), Curran Associates Inc
- "Package ‘corTest’" (2020)[URL]
- Refaeilzadeh P, "Encyclopedia of Database Systems", pp.532~538 (2009), Springer
- Sigireddi RR, "How much astigmatism to treat in cataract surgery", Curr Opin Ophthalmol, 31, pp.10~14 (2020)
- Kim M, "Comparative evaluation of refractive outcomes after implantation of two types of intraocular lenses with different diopter intervals(0. 25 diopter versus 0. 50 diopter)", BMC Ophthalmol, 18, pp.176~ (2018)
- Kane JX, "Accuracy of intraocular lens power formulas modified for patients with keratoconus", Ophthalmology, 127, pp.1037~1042 (2020)