Dataset Information

Accuracy of Kalman Filtering in Forecasting Visual Field and Intraocular Pressure Trajectory in Patients With Ocular Hypertension.

ABSTRACT: Importance:Techniques that properly identify patients in whom ocular hypertension (OHTN) is likely to progress to open-angle glaucoma can assist clinicians with deciding on the frequency of monitoring and the potential benefit of early treatment. Objective:To test whether Kalman filtering (KF), a machine learning technique, can accurately forecast mean deviation (MD), pattern standard deviation, and intraocular pressure values 5 years into the future for patients with OHTN. Design, Setting, and Participants:This cohort study was a secondary analysis of data from patients with OHTN from the Ocular Hypertension Treatment Study, performed between February 1994 and March 2009. Patients underwent tonometry and perimetry every 6 months for up to 15 years. A KF (KF-OHTN) model was trained, validated, and tested to assess how well it could forecast MD, pattern standard deviation, and intraocular pressure at up to 5 years, and the forecasts were compared with results from the actual trial. Kalman filtering for OHTN was compared with a previously developed KF for patients with high-tension glaucoma (KF-HTG) and 3 traditional forecasting algorithms. Statistical analysis for the present study was performed between May 2018 and May 2019. Main Outcomes and Measures:Prediction error and root-mean-square error at 12, 24, 36, 48, and 60 months for MD, pattern standard deviation, and intraocular pressure. Results:Among 1407 eligible patients (2806 eyes), 809 (57.5%) were female and the mean (SD) age at baseline was 57.5?(9.6) years. For 2124 eyes with sufficient measurements, KF-OHTN forecast MD values 60 months into the future within 0.5 dB of the actual value for 696 eyes (32.8%), 1.0 dB for 1295 eyes (61.0%), and 2.5 dB for 1980 eyes (93.2%). Among the 5 forecasting algorithms tested, KF-OHTN achieved the lowest root-mean-square error (1.72 vs 1.85-4.28) for MD values 60 months into the future. For the subset of eyes that progressed to open-angle glaucoma, KF-OHTN and KF-HTG forecast MD values 60 months into the future within 1 dB of the actual value for 30 eyes (68.2%; 95% CI, 54.4%-82.0%) and achieved the lowest root-mean-square error among all models. Conclusions and Relevance:These findings suggest that machine learning algorithms such as KF can accurately forecast MD, pattern standard deviation, and intraocular pressure 5 years into the future for many patients with OHTN. These algorithms may aid clinicians in managing OHTN in their patients.

SUBMITTER: Garcia GP

PROVIDER: S-EPMC6865321 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Accuracy of Kalman Filtering in Forecasting Visual Field and Intraocular Pressure Trajectory in Patients With Ocular Hypertension.

Garcia Gian-Gabriel P GP Lavieri Mariel S MS Andrews Chris C Liu Xiang X Van Oyen Mark P MP Kass Michael A MA Gordon Mae O MO Stein Joshua D JD

JAMA ophthalmology 20191201 12

<h4>Importance</h4>Techniques that properly identify patients in whom ocular hypertension (OHTN) is likely to progress to open-angle glaucoma can assist clinicians with deciding on the frequency of monitoring and the potential benefit of early treatment.<h4>Objective</h4>To test whether Kalman filtering (KF), a machine learning technique, can accurately forecast mean deviation (MD), pattern standard deviation, and intraocular pressure values 5 years into the future for patients with OHTN.<h4>Des ...[more]

PMID: 31725846

Similar Datasets

Project description:PurposeLongitudinal testing plays a key role in glaucoma management. Variability between visits hampers the ability to monitor progression. It has previously been shown that average intraocular pressure (IOP) exhibits seasonal fluctuations. This study examines whether visual field sensitivity also exhibits seasonal fluctuations and seeks to determine whether such fluctuations are correlated to seasonal IOP effects.DesignComparative case series.ParticipantsA total of 33 873 visits by 1636 participants enrolled in the Ocular Hypertension Treatment Study. Participants were split into 6 geographic zones according to the prevailing climate in their location.TestingAt each visit, standard automated perimetry was conducted on each eye, and IOP was measured.Main outcome measuresMixed effects regression models were formed to look for sinusoidal periodic effects on the change in perimetric mean deviation since the last visit (?MD) and on IOP, both overall and within each zone.ResultsWhen all the data were included, a significant seasonal effect on ?MD was found with magnitude 0.06 dB, peaking in February (P < 0.001). Five of the 6 geographic zones exhibited significant seasonal effects on ?MD, peaking between January and April, with magnitudes ranging from 0.04 dB (P = 0.049) to 0.21 dB (P < 0.001). Zones with greater climactic variation showed larger seasonal effects on ?MD. All 6 zones exhibited a seasonal effect on IOP, peaking in January or February, with magnitudes ranging from 0.14 to 0.39 mmHg (P ? 0.02 in all cases). However, there was no evidence of a significant association between the magnitudes or dates of peaks of the 2 seasonal effects.ConclusionsThe mean deviation was significantly higher in winter than in summer. There is no evidence of an association with seasonal IOP fluctuations. The cause of the seasonal effect on visual field sensitivity is unknown. These findings may help shed light on the glaucomatous disease process and aid efforts to reduce test-retest variability.

Project description:Purpose: To investigate the relationship between retinal microvasculature changes and intraocular pressure (IOP) for ocular hypertension (OHT) patients and further assess the factors associated with retinal microcirculation changes. Methods: This was a single-center prospective study designed for OHT patients, which consisted of two visits. After collecting baseline data of those who met the eligibility criteria, these patients were treated with latanoprost 0.005% ophthalmic solution for 4 weeks. Peripapillary vessel density (VD) of radial peripapillary capillaries (RPC) layer, macular VD in both superficial and deep layers, and foveal avascular zone (FAZ) area were measured by optical coherence tomography angiography (OCTA) before and after the treatment. We compared the changes in IOP and VD among the two visits by paired-sample t-test. Bonferroni correction was applied. Factors associated with VD changes were analyzed by linear regression analysis. Results: Thirty-four eyes of thirty-four patients were included. The mean IOP decreased by 6.5 ± 2.2 mmHg (p < 0.001). The peripapillary RPC VD increased significantly from 51.8 ± 2.5 to 53.0 ± 3.1% (Adjusted-p = 0.012). We found no significant difference in detailed sectors of the peripapillary region after correction. In the macular area, both the superficial and deep layers in foveal (superficial: 0.2 ± 1.9%, p = 0.523; deep: 0.0 ± 2.3%, p = 0.969) and parafoveal (superficial: 0.3 ± 3.0%, p = 0.565; deep: 0.5 ± 3.1%, p = 0.423) VD remained unchanged. The decrease of the mean FAZ area was insignificant (p = 0.295). The percentage of IOP reduction (β = 0.330, p = 0.031) and the baseline RNFL thickness (β = 0.450, p = 0.004) significantly correlated with the percentage of peripapillary RPC VD improvement in the multivariate linear regression analysis. Conclusion: The peripapillary VD in OHT patients increased after the reduction of IOP. The mild change of IOP did not alter the microcirculation in the macula. In addition, the percentage of IOP change and the baseline RNFL thickness were independent factors for the peripapillary RPC VD improvement.

Project description:Ocular trauma is one of the leading causes of visual impairment worldwide. Because of the popularity of cataract surgeries, aged individuals with ocular trauma commonly have a surgical wound in their eyes. The purpose of this study was to evaluate the visual outcome of cases that were coincident with intraocular lens (IOL) ejection in the eyes with ruptured open-globe ocular injuries. Consecutive patients with open-globe ocular injuries were first reviewed. Patients' characteristics, corrected distance visual acuities (CDVAs) over 3 years after the trauma, causes of injuries, traumatic wound patterns, and coexistence of retinal detachment were examined. The relationships between poor CDVA and the other factors, including the complications of crystalline lens and IOL ejection, were examined. A total of 105 eyes/patients [43 eyes with rupture, 33 with penetrating, 28 with intraocular foreign body (IOFB), and 1 with perforating injuries] were included. Rupture injuries were common in aged patients and were mostly caused by falls, whereas penetrating and IOFB injuries were common in young male patients. CDVAs of the eyes with rupture injuries were significantly worse than those of the eyes with penetrating or IOFB injuries. CDVA from more than 50% of the ruptured eyes resulted in no light perception or light perception to 20/500. CDVA of the ruptured eyes complicated by crystalline lens ejection was significantly worse than that of those complicated by IOL ejection. The wounds of the ruptured eyes complicated by IOL ejection were mainly located at the superior corneoscleral limbus, whereas those of the eyes complicated by crystalline lens ejection were located at the posterior sclera. There were significant correlations between poor CDVA and retinal detachment and crystalline lens ejection. These results proposed a new trend in the ocular injuries that commonly occur in aged patients; history of cataract surgery might affect the final visual outcome after open-globe ocular injuries.

Dataset Information

Accuracy of Kalman Filtering in Forecasting Visual Field and Intraocular Pressure Trajectory in Patients With Ocular Hypertension.

Publications

Accuracy of Kalman Filtering in Forecasting Visual Field and Intraocular Pressure Trajectory in Patients With Ocular Hypertension.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets