Dataset Information

Using Kalman Filtering to Forecast Disease Trajectory for Patients With Normal Tension Glaucoma.

ABSTRACT: PURPOSE:To determine whether a machine learning technique called Kalman filtering (KF) can accurately forecast future values of mean deviation (MD), pattern standard deviation, and intraocular pressure for patients with normal tension glaucoma (NTG). DESIGN:Development and testing of a forecasting model for glaucoma progression. METHODS:We parameterized and validated a KF (KF-NTG) to forecast MD, pattern standard deviation, and intraocular pressure at 24 months into the future using 263 eyes of 263 Japanese patients with NTG. We determined the proportion of patients with MD forecasts within 0.5, 1.0, and 2.5 dBs of the actual values and calculated the root mean squared error (RMSE) for each forecast. We compared KF-NTG with a previously published KF model calibrated using patients with high-tension open-angle glaucoma (KF-HTG) and to 3 conventional forecasting algorithms. RESULTS:The 263 patients with NTG had mean ± standard deviation age of 63.4 ± 10.5 years. KF-NTG forecasted MD values 24 months ahead within 0.5, 1.0, and 2.5 dBs of the actual value for 78 eyes (32.2%), 122 eyes (50.4%), and 211 eyes (87.2%), respectively. The proportion of eyes with MD values forecasted within 2.5 dB of the actual value for the KF-NTG (87.2%) were similar to KF-HTG (86.0%) and the null model (86.4%), and much better than the 2 linear regression-based models (72.7-74.0%; P < .001). When forecasting MD, KF-NTG (RMSE = 2.71) and KF-HTG (RMSE = 2.68) achieved lower RMSE than the other 3 forecasting models (RMSE = 2.81-3.90), indicating better performance. CONCLUSION:As observed previously for patients with HTG, KF can also effectively forecast disease trajectory for many patients with NTG.

SUBMITTER: Garcia GP

PROVIDER: S-EPMC6662653 | biostudies-literature | 2019 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using Kalman Filtering to Forecast Disease Trajectory for Patients With Normal Tension Glaucoma.

Garcia Gian-Gabriel P GP Nitta Koji K Lavieri Mariel S MS Andrews Chris C Liu Xiang X Lobaza Elizabeth E Van Oyen Mark P MP Sugiyama Kazuhisa K Stein Joshua D JD

American journal of ophthalmology 20181016

<h4>Purpose</h4>To determine whether a machine learning technique called Kalman filtering (KF) can accurately forecast future values of mean deviation (MD), pattern standard deviation, and intraocular pressure for patients with normal tension glaucoma (NTG).<h4>Design</h4>Development and testing of a forecasting model for glaucoma progression.<h4>Methods</h4>We parameterized and validated a KF (KF-NTG) to forecast MD, pattern standard deviation, and intraocular pressure at 24 months into the fut ...[more]

PMID: 30336130

Similar Datasets

Project description:Importance:Mutations in the myocilin (MYOC) gene are the most common molecularly defined cause of primary open-angle glaucoma that typically occurs in patients with high intraocular pressures (IOP). One MYOC mutation, p.Gln368Ter, has been associated with as many as 1.6% of primary open-angle glaucoma cases that had a mean maximum recorded IOP of 30 mm Hg. However, to our knowledge, the role of the p.Gln368Ter mutation in patients with normal-tension glaucoma (NTG) with an IOP of 21 mm Hg or lower has not been investigated. Objective:To evaluate the role of the p.Gln368Ter MYOC mutation in patients with NTG. Design, Setting, and Participants:In this case-control study of the prevalence of the p.Gln368Ter mutation in patients with NTG, cohort 1 was composed of 772 patients with NTG and 2152 controls from the United States (Iowa, Minnesota, and New York) and England and cohort 2 was composed of 561 patients with NTG and 2606 controls from the Massachusetts Eye and Ear Infirmary and the NEIGHBORHOOD consortium. Genotyping was conducted using real-time polymerase chain reaction that was confirmed with Sanger sequencing, the imputation of genome-wide association study data, or an analysis of whole-exome sequence data. Data analysis occurred between April 2007 and April 2018. Main Outcomes and Measures:Comparison of the frequency of the p.Gln368Ter MYOC mutation between NTG cases and controls with the Fisher exact test. Results:Of 6091 total participants, 3346 (54.9%) were women and 5799 (95.2%) were white. We detected the p.Gln368Ter mutation in 7 of 772 patients with NTG (0.91%) and 7 of 2152 controls (0.33%) in cohort 1 (P = .03). In cohort 2, we detected the p.Gln368Ter mutation in 4 of 561 patients with NTG (0.71%) and 10 of 2606 controls (0.38%; P = .15). When the cohorts were analyzed as a group, the p.Gln368Ter mutation was associated with NTG (odds ratio, 2.3; 95% CI, 0.98-5.3; P = .04). Conclusions and Relevance:In cohorts 1 and 2, the p.Gln368Ter mutation in MYOC was found in patients with IOPs that were 21 mm Hg or lower (NTG), although at a frequency that is lower than previously detected in patients with higher IOP. These data suggest that the p.Gln368Ter mutation may be associated with glaucoma in patients with normal IOPs as well as in patients with IOPs that are greater than 21 mm Hg.

Project description:ImportanceTechniques 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.ObjectiveTo 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 participantsThis 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 measuresPrediction error and root-mean-square error at 12, 24, 36, 48, and 60 months for MD, pattern standard deviation, and intraocular pressure.ResultsAmong 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 relevanceThese 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.

Project description:AIM:Polymorphisms in OPA1, the gene responsible for autosomal dominant optic atrophy, were recently found to be strongly associated with normal tension glaucoma (NTG). The aim of this study was to determine whether OPA1 polymorphisms affect the phenotype of NTG patients. METHODS:A retrospective analysis was performed of 108 well characterised NTG patients who had been genotyped for OPA1 variations, and who had previously undergone automated perimetry and Heidelberg retina tomography (HRT). 25 NTG patients had the at-risk OPA1 genotype (IVS 8 +4 C/T; +32 T/C) and 83 NTG patients did not. Differences between groups were sought in a wide range of structural, psychophysical, and demographic factors. These included sex, age at diagnosis, family history of glaucoma, history of ischaemic risk factors and vasospasm, laterality of glaucoma, presenting and highest diurnal intraocular pressure (IOP), initial cup-disc (CD) ratio, baseline visual field global indices, and optic disc parameters as measured by HRT. For a subgroup of patients with at least 5 years of follow up and 10 visual field tests, pointwise linear regression analysis (PROGRESSOR for Windows software) was applied to the visual field series. RESULTS:There was no significant difference in the two groups with respect to sex, age at diagnosis, family history of glaucoma, history of ischaemic risk factors and vasospasm, or laterality of glaucoma. The comparison of IOP, CD ratio and visual field global indices, MD and CPSD in the two groups showed no significant difference. There were no differences in the mean values for any of the HRT parameters analysed. For the subgroup of patients with at least 5 years of follow up, there was also no significant difference in the number of patients with progressing locations, the mean number of progressing locations per subject, the mean slope of the progressing locations or the mean slope for whole visual field. CONCLUSIONS:The absence of phenotypic differences in normal tension glaucoma patients with and without the OPA1 polymorphisms IVS 8 +4 C/T; +32 T/C suggest that these OPA1 polymorphisms do not underlie any major phenotypic diversity in these patients.

Dataset Information

Using Kalman Filtering to Forecast Disease Trajectory for Patients With Normal Tension Glaucoma.

Publications

Using Kalman Filtering to Forecast Disease Trajectory for Patients With Normal Tension Glaucoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets