A Myopia Degree Prediction Model for Children and Adolescents Based on Follow-up Data with Different Time Intervals

Pengyuan Ma; Shukui Ma; Guowei Zhang; Fei Ma; Guangping Zhuo

doi:10.62051/ijcsit.v5n1.14

Authors

Pengyuan Ma
Shukui Ma
Guowei Zhang
Fei Ma
Guangping Zhuo

DOI:

https://doi.org/10.62051/ijcsit.v5n1.14

Keywords:

Prediction of Myopia in Children and Adolescents, Spherical Equivalent (SE), IST-xLSTM, Hierarchical Temporal Attention Mechanism

Abstract

Myopia has become a global public health issue, and existing research primarily focuses on predicting the future spherical equivalent (SE) of children and adolescents based on ocular optical data. However, electronic medical record (EMR) data often exhibit characteristics such as multi-dimensionality, irregular time series, missing values, and non-uniform time intervals, which present significant challenges for prediction. To address these issues, this paper proposes a prediction model named IST-xLSTM, which utilizes a temporal dense prediction module to handle missing data and overcome long-range dependencies and irregular time intervals. Additionally, a hierarchical temporal attention mechanism is introduced to extract both local and global features along the irregular time dimension, enhancing prediction accuracy. Experimental results show that the mean absolute error on the validation set is 0.216 ± 0.176 (D), which is significantly lower than the clinically acceptable prediction threshold of 0.50 (D).

Downloads

Download data is not yet available.

References

[1] World Health Organization. Vision impairment and blindness. https://www.who.int/news-room/fact-sheets/detail/blindness-and-visual-impairment (2023).

[2] W. H. Organization, World report on vision (2019).

[3] Pärssinen O, Lyyra AL. Myopia and myopic progression among schoolchildren: a three-year follow-up study. Investigative ophthalmology & visual science. 1993 Aug 1; 34(9):2794-802.

[4] Jonas, Jost B., et al. Myopia in China: a population-based cross-sectional, histological, and experimental study. The Lancet 388 (2016): S20.

[5] Sankaridurg, Padmaja, et al. Imi impact of myopia, Investigative Ophthalmology & Visual Science 62 (2021) 2. doi:10.1167/iovs.62.5.2.

[6] Liao, J., Tang, Z., & Liu, X. (2020). Discussion on building hospital information operation and maintenance platform using big data and artificial intelligence technologies. Information and Computer, 32(24), 124-126..

[7] Jong, M., Resnikoff, S., & Tan, K. O. (2022). Asia Myopia Management Consensus. Chinese Journal of Optometry and Visual Science, 24(3), 161-169.

[8] World Health Organization. Child and adolescent health in humanitarian settings: operational guide: a holistic approach for programme managers [J]. 2021.

[9] French AN, Morgan IG, Mitchell P, Rose KA. Risk factors for incident myopia in Australian schoolchildren: the Sydney adolescent vascular and eye study. Ophthalmology. 2013 Oct 1; 120(10):2100-8.

[10] Fan Q, Guo X, Tideman JW, et al. Childhood gene-environment interactions and age-dependent effects of genetic variants associated with refractive error and myopia: The CREAM Consortium. Scientific reports. 2016 May 13;6(1):25853.

[11] Tedja MS, Haarman AE, Meester-Smoor MA, et al. IMI–myopia genetics report. Investigative ophthalmology & visual science. 2019 Feb 28; 60(3):M89-105.

[12] Jones LA, Sinnott LT, Mutti DO, et al. Parental history of myopia, sports and outdoor activities, and future myopia. Investigative ophthalmology & visual science. 2007 Aug 1; 48(8):3524-32.

[13] Chua SY, Sabanayagam C, Cheung YB, et al. Age of onset of myopia predicts risk of high myopia in later childhood in myopic Singapore children. Ophthalmic and Physiological Optics. 2016 Jul; 36(4):388-94.

[14] Jones LA, Sinnott LT, Mutti DO, et al. Parental history of myopia, sports and outdoor activities, and future myopia. Investigative ophthalmology & visual science. 2007 Aug 1; 48(8):3524-32.

[15] Lin H, Long E, Ding X, et al. Prediction of myopia development among Chinese school-aged children using refraction data from electronic medical records: a retrospective, multicentre machine learning study. PLoS medicine. 2018 Nov 6; 15(11): e1002674.

[16] Ma Y, Zou H, Lin S, et al. Cohort study with 4‐year follow‐up of myopia and refractive parameters in primary schoolchildren in Baoshan district, Shanghai. Clinical & Experimental Ophthalmology. 2018 Nov; 46(8): 861-72.

[17] Chen Y, Han X, Guo X, et al. Contribution of genome-wide significant single nucleotide polymorphisms in myopia prediction: findings from a 10-year cohort of Chinese twin children. Ophthalmology. 2019 Dec 1; 126(12):1607-14.

[18] Yang X, Chen G, Qian Y, et al. Prediction of myopia in adolescents through machine learning methods. International Journal of Environmental Research and Public Health. 2020 Jan; 17(2):463.

[19] Huang J, Zhang Q, Zhao N, et al. Myopia contributing factors and myopia prediction based on vision examination data. J. Univ. Electron. Sci. Technol. China. 2021; 50:256-60.

[20] Sarker IH. Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions. SN computer science. 2021 Nov; 2(6):420.

[21] Adam G, Rampášek L, Safikhani Z, et al. Machine learning approaches to drug response prediction: challenges and recent progress. NPJ precision oncology. 2020 Jun 15; 4(1):19.

[22] Jalali A, Lonsdale H, Do N, et al. Deep learning for improved risk prediction in surgical outcomes. Scientific reports. 2020 Jun 9; 10(1):9289.

[23] Sun C, Hong S, Song M, et al. Predicting COVID-19 disease progression and patient outcomes based on temporal deep learning. BMC Medical Informatics and Decision Making. 2021 Dec; 21:1-6.

[24] Spadon G, Hong S, Brandoli B, et al. Pay attention to evolution: Time series forecasting with deep graph-evolution learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2021 Apr 27; 44(9):5368-84.

[25] Beck M, Pöppel K, Spanring M, et al. xLSTM: Extended Long Short-Term Memory. arxiv preprint arxiv: 2405.04517. 2024 May 7.

[26] Kia SM, Rad NM, van Opstal D, et al. PROMISSING: Pruning Missing Values in Neural Networks. arxiv preprint arxiv: 2206.01640. 2022 Jun 3.