Fig 1.
Classification of the study population.
Training and test groups study groups, patients with normal intracranial pressure ICPn (ICP≤25cm water) and high intracranial pressure ICPh (ICP>25cm water).
Fig 2.
Data points from training and test study groups.
The data points are sub-classified into arterial and venous points, in patients with normal intracranial pressure ICPn (ICP≤25cm water) and high intracranial pressure ICPh (ICP>25cm water).
Table 1.
Bayesian optimised Extreme Gradient Boost hyperparameters.
Fig 3.
Flow chart of image processing, analysis, and XGB model application.
1) Alignment and segmentation of image frames from a video sequence spanning three consecutive cardiac cycles captured from 21 subjects using Modified Photoplethysmography. 2) Image analysis was performed by fitting a harmonic regression model to each pixel cluster. The periodic component was represented by the first two harmonics of a Fourier series. 3) The Fourier coefficients, harmonic regression amplitude, together with the distance along the vessel, induced intraocular pressure (IOPi), ocular laterality (right/left), and hemiretinal locus of the blood vessel (superior/inferior) constituted the model features. 4) Separate retinal arterial (XGBA) and venous (XGBV) Extreme gradient Boost models were constructed, where an 80/20% split was chosen for the training/test set for each vascular model. 5) Seven hold-out test cases were used for external model validation and intracranial pressure (ICP) prediction.
Fig 4.
Violin plots of the harmonic regression waveform amplitude (HRWa).
The central marker in the violin plots indicate the median and interquartile range. Noted are the reduction of the difference in maximum and median retinal vascular pulsation amplitudes within the ICP groups as a consequence of a reduction of the venous and increase in the arterial pulsation amplitudes within the ICPh group. Between group differences indicate a ICPh and ICPn groups.
Table 2.
Summary descriptive statistics for the high intracranial pressure (ICPh) and normal intracranial pressure (ICPn) groups.
Fig 5.
The arterial model consisted of a total of 137 nodes, 136 edges, and 7,951 leaves. The model had an R2 of 0.89, and other accuracy parameters were: MSE = 10.99, MAE = 2.03, RSME = 3.32.
Fig 6.
The venous model was composed of a total of 451 nodes, 450 edges, and 35,589 leaves. The model had a higher R2 of 0.91, other accuracy parameters were: MSE = 11.85, MAE = 2.11, RSME = 3.44.
Fig 7.
Importance plot retinal arterial model.
IOPi, an1 and HRWa were the most important features in this model. IOPi = Induced intraocular pressure, HRWa=Harmonic regression wave amplitude, an1,2 = the cosine coefficient of the first and second harmonics, bn1,2 = the sine coefficient of the first and second harmonics, laterality = left / right eye, Distance = distance along the retinal vessel measured in mm, hemiretina = superior / inferior retina.
Fig 8.
Importance plot retinal venous model.
IOPi, HRWa, and an1 were the most important features in this model. IOPi = Induced intraocular pressure, HRWa=Harmonic regression wave amplitude, an1,2 = the cosine coefficient of the first and second harmonics, bn1,2 = the sine coefficient of the first and second harmonics, laterality = left / right eye, Distance = distance along the retinal vessel measured in mm, hemiretina = superior / inferior retina.
Table 3.
Feature importance of the machine learning models.
Fig 9.
SHAP summary plot retinal arterial model demonstrating the feature contribution of the XGB model predicting ICP from the arterial model.
Induced intraocular pressure (IOPi) was the most important feature in the model (mean SHAP = 5.3884), approximately four times the value of the cosine coefficient of the first harmonic (an1 mean = 1.4689). Laterality = Right/Left eye, Distance = Retinal vascular pulsation amplitude as a function of distance from the center of the optic disc in mm, HRWa=Harmonic regression wave amplitude, an1,2, bn1,2=cosine and sine coefficients of the first and second harmonics, hemiretina = Superior/Inferior retina.
Fig 10.
SHAP summary plot retinal venous model demonstrating the feature contribution of the XGB model predicting ICP from the venous model.
Induced intraocular pressure (IOPi) was the most important feature in the model (mean SHAP = 5.723), approximately four times the value of the harmonic regression wave amplitude (HRWa mean = 1.425). HRWa=Harmonic regression wave amplitude, an1,2, bn1,2=cosine and sine coefficients of the first and second harmonics, laterality = Right/Left eye, Distance = Retinal vascular pulsation amplitude as a function of distance from the center of the optic disc in mm, hemiretina = Superior/Inferior retina.
Table 4.
Mean SHAP values for the arterial and venous models.
Fig 11.
Bland-Altman plot predicted median predicted intracranial pressure of the arterial Extreme Gradient Boost model.
The intervals of two standard deviations are considered as the concordance limits between the two measurements, accounting for 95% of the observed differences. The Bland-Altman bias was 0.139±1.6545 cm water (p<0.94), the arterial model provided a potential avenue for internal validation of the prediction.
Fig 12.
Bland-Altman plot predicted median predicted intracranial pressure of the venous Extreme Gradient Boost model.
The intervals of two standard deviations are considered as the concordance limits between the two measurements, accounting for 95% of the observed differences. The Bland-Altman bias from the venous model (0.034±1.8013 cm water (p<0.99)) was lower compared to that of the arterial model.
Table 5.
Hold-out test set comparing measured and predicted ICP (cm water) using the XGB models for both the arteries and veins.
Table 6.
Bland-Altman analysis and t-test, comparing between the measured and predicted ICP using XGB.