03 December 2024 : Clinical Research
Machine Learning Models for Predicting 24-Hour Intraocular Pressure Changes: A Comparative Study
Chen Ranran ACDEG 1,2, Lei Jinming ACD 3, Liao Yujie BC 1,2, Jin Yiping BC 1,2, Wang Xue CD 4, Li Hong BD 1, Bi Yanlong ACF 5*, Zhu Haohao ABFG 1,2DOI: 10.12659/MSM.945483
Med Sci Monit 2024; 30:e945483
Figure 4 Heatmap of correlations between various features and 24-hour IOP fluctuations. IOP – intraocular pressure; MSO – metabolic status and obesity; C/D ratio – cup-to-disc ratio; RE – refractive error; CCT – central corneal thickness; SBP10am – systolic blood pressure at 10: 00 AM; DBP10am – diastolic blood pressure at 10: 00 AM; BMI – body mass index; IOP10am – intraocular pressure at 10: 00 AM; IOP12pm – intraocular pressure at 12: 00 PM; IOP2pm – intraocular pressure at 2: 00 PM; IOP4pm – intraocular pressure at 4: 00 PM; MAP10am – mean arterial pressure at 10: 00AM; SOPP10am – systolic ocular perfusion pressure at 10: 00 AM; DOPP10am – diastolic ocular perfusion pressure at 10: 00 AM; MOPP10am – mean ocular perfusion pressure at 10: 00 AM; S10am – the slope of the diurnal curve at 10: 00 AM; S12pm – the slope of the diurnal curve at 12: 00 PM; S2pm – the slope of the diurnal curve at 2: 00 PM.