scholarly journals Prediction of Function in ABCA4-Related Retinopathy Using Ensemble Machine Learning

2020 ◽  
Vol 9 (8) ◽  
pp. 2428 ◽  
Author(s):  
Philipp L. Müller ◽  
Tim Treis ◽  
Alexandru Odainic ◽  
Maximilian Pfau ◽  
Philipp Herrmann ◽  
...  
Keyword(s):  
Machine Learning ◽  
Visual Impairment ◽  
Age Of Onset ◽  
Outer Nuclear Layer ◽  
Stargardt Disease ◽  
Full Field ◽  
Corrected Visual Acuity ◽  
Ensemble Machine Learning ◽  
Prediction Of Function ◽  
Patient Burden

Full-field electroretinogram (ERG) and best corrected visual acuity (BCVA) measures have been shown to have prognostic value for recessive Stargardt disease (also called “ABCA4-related retinopathy”). These functional tests may serve as a performance-outcome-measure (PerfO) in emerging interventional clinical trials, but utility is limited by variability and patient burden. To address these limitations, an ensemble machine-learning-based approach was evaluated to differentiate patients from controls, and predict disease categories depending on ERG (‘inferred ERG’) and visual impairment (‘inferred visual impairment’) as well as BCVA values (‘inferred BCVA’) based on microstructural imaging (utilizing spectral-domain optical coherence tomography) and patient data. The accuracy for ‘inferred ERG’ and ‘inferred visual impairment’ was up to 99.53 ± 1.02%. Prediction of BCVA values (‘inferred BCVA’) achieved a precision of ±0.3LogMAR in up to 85.31% of eyes. Analysis of the permutation importance revealed that foveal status was the most important feature for BCVA prediction, while the thickness of outer nuclear layer and photoreceptor inner and outer segments as well as age of onset highly ranked for all predictions. ‘Inferred ERG’, ‘inferred visual impairment’, and ‘inferred BCVA’, herein, represent accurate estimates of differential functional effects of retinal microstructure, and offer quasi-functional parameters with the potential for a refined patient assessment, and investigation of potential future treatment effects or disease progression.

scholarly journals Retinal Degeneration Associated With RPGRIP1: A Review of Natural History, Mutation Spectrum, and Genotype–Phenotype Correlation in 228 Patients

2021 ◽  
Vol 9 ◽  
Author(s):  
Avigail Beryozkin ◽  
Hamzah Aweidah ◽  
Roque Daniel Carrero Valenzuela ◽  
Myriam Berman ◽  
Oscar Iguzquiza ◽  
...  
Keyword(s):  
Visual Acuity ◽  
Retinal Degeneration ◽  
Clinical Data ◽  
Age Of Onset ◽  
Outer Nuclear Layer ◽  
Visual Fields ◽  
Severe Form ◽  
Posterior Pole ◽  
Missense Mutations ◽  
Full Field

Purpose:RPGRIP1 encodes a ciliary protein expressed in the photoreceptor connecting cilium. Mutations in this gene cause ∼5% of Leber congenital amaurosis (LCA) worldwide, but are also associated with cone–rod dystrophy (CRD) and retinitis pigmentosa (RP) phenotypes. Our purpose was to clinically characterize RPGRIP1 patients from our cohort, collect clinical data of additional RPGRIP1 patients reported previously in the literature, identify common clinical features, and seek genotype–phenotype correlations.Methods: Clinical data were collected from 16 patients of our cohort and 212 previously reported RPGRIP1 patients and included (when available) family history, best corrected visual acuity (BCVA), refraction, comprehensive ocular examination, optical coherence tomography (OCT) imaging, visual fields (VF), and full-field electroretinography (ffERG).Results: Out of 228 patients, the majority (197, 86%) were diagnosed with LCA, 18 (7%) with RP, and 13 (5%) with CRD. Age of onset was during early childhood (n = 133, average of 1.7 years). All patients but 6 had moderate hyperopia (n = 59, mean of 4.8D), and average BCVA was 0.06 Snellen (n = 124; only 10 patients had visual acuity [VA] > 0.10 Snellen). On funduscopy, narrowing of blood vessels was noted early in life. Most patients had mild bone spicule-like pigmentation starting in the midperiphery and later encroaching upon the posterior pole. OCT showed thinning of the outer nuclear layer (ONL), while cystoid changes and edema were relatively rare. VF were usually very constricted from early on. ffERG responses were non-detectable in the vast majority of cases. Most of the mutations are predicted to be null (363 alleles), and 93 alleles harbored missense mutations. Missense mutations were identified only in two regions: the RPGR-interacting domain and the C2 domains. Biallelic null mutations are mostly associated with a severe form of the disease, whereas biallelic missense mutations usually cause a milder disease (mostly CRD).Conclusion: Our results indicate that RPGRIP1 biallelic mutations usually cause severe retinal degeneration at an early age with a cone–rod pattern. However, most of the patients exhibit preservation of some (usually low) BCVA for a long period and can potentially benefit from gene therapy. Missense changes appear only in the conserved domains and are associated with a milder phenotype.

scholarly journals Postsurgery Classification of Best-Corrected Visual Acuity Changes Based on Pterygium Characteristics Using the Machine Learning Technique

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Fatin Nabihah Jais ◽  
Mohd Zulfaezal Che Azemin ◽  
Mohd Radzi Hilmi ◽  
Mohd Izzuddin Mohd Tamrin ◽  
Khairidzan Mohd Kamal
Keyword(s):  
Machine Learning ◽  
Visual Acuity ◽  
Visual Impairment ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Machine Learning Technique ◽  
Corrected Visual Acuity ◽  
Learning Technique ◽  
Best Corrected Visual Acuity

Introduction. Early detection of visual symptoms in pterygium patients is crucial as the progression of the disease can cause visual disruption and contribute to visual impairment. Best-corrected visual acuity (BCVA) and corneal astigmatism influence the degree of visual impairment due to direct invasion of fibrovascular tissue into the cornea. However, there were different characteristics of pterygium used to evaluate the severity of visual impairment, including fleshiness, size, length, and redness. The innovation of machine learning technology in visual science may contribute to developing a highly accurate predictive analytics model of BCVA outcomes in postsurgery pterygium patients. Aim. To produce an accurate model of BCVA changes of postpterygium surgery according to its morphological characteristics by using the machine learning technique. Methodology. A retrospective of the secondary dataset of 93 samples of pterygium patients with different pterygium attributes was used and imported into four different machine learning algorithms in RapidMiner software to predict the improvement of BCVA after pterygium surgery. Results. The performance of four machine learning techniques were evaluated, and it showed the support vector machine (SVM) model had the highest average accuracy (94.44% ± 5.86%), specificity (100%), and sensitivity (92.14% ± 8.33%). Conclusion. Machine learning algorithms can produce a highly accurate postsurgery classification model of BCVA changes using pterygium characteristics.

scholarly journals Phenotypic Progression of Stargardt Disease in a Large Consanguineous Tunisian Family Harboring New ABCA4 Mutations

2018 ◽  
Vol 2018 ◽  
pp. 1-7 ◽  
Author(s):  
Yousra Falfoul ◽  
Imen Habibi ◽  
Ahmed Turki ◽  
Ahmed Chebil ◽  
Asma Hassairi ◽  
...  
Keyword(s):  
Age Of Onset ◽  
Stargardt Disease ◽  
Full Field ◽  
Stage Disease ◽  
Bull’S Eye Maculopathy ◽  
Diffuse Atrophy ◽  
Rpe Atrophy ◽  
End Stage ◽  
Bull's Eye ◽  
Tunisian Family

To assess the progression of Stargardt (STGD) disease over nine years in two branches of a large consanguineous Tunisian family. Initially, different phenotypes were observed with clinical intra- and interfamilial variations. At presentation, four different retinal phenotypes were observed. In phenotype 1, bull’s eye maculopathy and slight alteration of photopic responses in full-field electroretinography were observed in the youngest child. In phenotype 2, macular atrophy and yellow white were observed in two brothers. In phenotype 3, diffuse macular, peripapillary, and peripheral RPE atrophy and hyperfluorescent dots were observed in two sisters. In phenotype 4, Stargardt disease-fundus flavimaculatus phenotype was observed in two cousins with later age of onset. After a progression of 9 years, all seven patients displayed the same phenotype 3 with advanced stage STGD and diffuse atrophy. WES and MLPA identified two ABCA4 mutations M1: c.[(?_4635)_(5714+?)dup; (?_6148)_(6479_+?) del] and M2: c.[2041C>T], p.[R681∗]. In one branch, the three affected patients had M1/M1 causal mutations and in the other branch the two affected patients had M1/M2 causal mutations. After 9-year follow-up, all patients showed the same phenotypic evolution, confirming the progressive nature of the disease. Genetic variations in the two branches made no difference to similar end-stage disease.

scholarly journals Expanding the Mutation Spectrum in ABCA4: Sixty Novel Disease Causing Variants and Their Associated Phenotype in a Large French Stargardt Cohort

2018 ◽  
Vol 19 (8) ◽  
pp. 2196 ◽  
Author(s):  
Marco Nassisi ◽  
Saddek Mohand-Saïd ◽  
Claire-Marie Dhaenens ◽  
Fiona Boyard ◽  
Vanessa Démontant ◽  
...  
Keyword(s):  
Near Infrared ◽  
Age Of Onset ◽  
Fundus Autofluorescence ◽  
Mutation Spectrum ◽  
Fundus Photography ◽  
Heterozygous Mutation ◽  
Autofluorescence Imaging ◽  
Stargardt Disease ◽  
Full Field ◽  
Uncertain Significance

Here we report novel mutations in ABCA4 with the underlying phenotype in a large French cohort with autosomal recessive Stargardt disease. The DNA samples of 397 index subjects were analyzed in exons and flanking intronic regions of ABCA4 (NM_000350.2) by microarray analysis and direct Sanger sequencing. At the end of the screening, at least two likely pathogenic mutations were found in 302 patients (76.1%) while 95 remained unsolved: 40 (10.1%) with no variants identified, 52 (13.1%) with one heterozygous mutation, and 3 (0.7%) with at least one variant of uncertain significance (VUS). Sixty-three novel variants were identified in the cohort. Three of them were variants of uncertain significance. The other 60 mutations were classified as likely pathogenic or pathogenic, and were identified in 61 patients (15.4%). The majority of those were missense (55%) followed by frameshift and nonsense (30%), intronic (11.7%) variants, and in-frame deletions (3.3%). Only patients with variants never reported in literature were further analyzed herein. Recruited subjects underwent complete ophthalmic examination including best corrected visual acuity, kinetic and static perimetry, color vision test, full-field and multifocal electroretinography, color fundus photography, short-wavelength and near-infrared fundus autofluorescence imaging, and spectral domain optical coherence tomography. Clinical evaluation of each subject confirms the tendency that truncating mutations lead to a more severe phenotype with electroretinogram (ERG) impairment (p = 0.002) and an earlier age of onset (p = 0.037). Our study further expands the mutation spectrum in the exonic and flanking regions of ABCA4 underlying Stargardt disease.

scholarly journals Ensemble Machine Learning Assisted Reservoir Characterization Using Field Production Data–An Offshore Field Case Study

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 1052
Author(s):  
Baozhong Wang ◽  
Jyotsna Sharma ◽  
Jianhua Chen ◽  
Patricia Persaud
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Reservoir Characterization ◽  
Time Lapse ◽  
Production Data ◽  
Oil Saturation ◽  
Ensemble Machine Learning ◽  
Input Parameters ◽  
Saturation Profiles ◽  
Field Production

Estimation of fluid saturation is an important step in dynamic reservoir characterization. Machine learning techniques have been increasingly used in recent years for reservoir saturation prediction workflows. However, most of these studies require input parameters derived from cores, petrophysical logs, or seismic data, which may not always be readily available. Additionally, very few studies incorporate the production data, which is an important reflection of the dynamic reservoir properties and also typically the most frequently and reliably measured quantity throughout the life of a field. In this research, the random forest ensemble machine learning algorithm is implemented that uses the field-wide production and injection data (both measured at the surface) as the only input parameters to predict the time-lapse oil saturation profiles at well locations. The algorithm is optimized using feature selection based on feature importance score and Pearson correlation coefficient, in combination with geophysical domain-knowledge. The workflow is demonstrated using the actual field data from a structurally complex, heterogeneous, and heavily faulted offshore reservoir. The random forest model captures the trends from three and a half years of historical field production, injection, and simulated saturation data to predict future time-lapse oil saturation profiles at four deviated well locations with over 90% R-square, less than 6% Root Mean Square Error, and less than 7% Mean Absolute Percentage Error, in each case.

Sign in / Sign up

Export Citation Format

Share Document