Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 4 de 4
Filtrar
Más filtros











Base de datos
Intervalo de año de publicación
1.
Ophthalmol Sci ; 3(1): 100222, 2023 Mar.
Artículo en Inglés | MEDLINE | ID: mdl-36325476

RESUMEN

Purpose: Two novel deep learning methods using a convolutional neural network (CNN) and a recurrent neural network (RNN) have recently been developed to forecast future visual fields (VFs). Although the original evaluations of these models focused on overall accuracy, it was not assessed whether they can accurately identify patients with progressive glaucomatous vision loss to aid clinicians in preventing further decline. We evaluated these 2 prediction models for potential biases in overestimating or underestimating VF changes over time. Design: Retrospective observational cohort study. Participants: All available and reliable Swedish Interactive Thresholding Algorithm Standard 24-2 VFs from Massachusetts Eye and Ear Glaucoma Service collected between 1999 and 2020 were extracted. Because of the methods' respective needs, the CNN data set included 54 373 samples from 7472 patients, and the RNN data set included 24 430 samples from 1809 patients. Methods: The CNN and RNN methods were reimplemented. A fivefold cross-validation procedure was performed on each model, and pointwise mean absolute error (PMAE) was used to measure prediction accuracy. Test data were stratified into categories based on the severity of VF progression to investigate the models' performances on predicting worsening cases. The models were additionally compared with a no-change model that uses the baseline VF (for the CNN) and the last-observed VF (for the RNN) for its prediction. Main Outcome Measures: PMAE in predictions. Results: The overall PMAE 95% confidence intervals were 2.21 to 2.24 decibels (dB) for the CNN and 2.56 to 2.61 dB for the RNN, which were close to the original studies' reported values. However, both models exhibited large errors in identifying patients with worsening VFs and often failed to outperform the no-change model. Pointwise mean absolute error values were higher in patients with greater changes in mean sensitivity (for the CNN) and mean total deviation (for the RNN) between baseline and follow-up VFs. Conclusions: Although our evaluation confirms the low overall PMAEs reported in the original studies, our findings also reveal that both models severely underpredict worsening of VF loss. Because the accurate detection and projection of glaucomatous VF decline is crucial in ophthalmic clinical practice, we recommend that this consideration is explicitly taken into account when developing and evaluating future deep learning models.

2.
Mol Genet Metab Rep ; 31: 100841, 2022 Jun.
Artículo en Inglés | MEDLINE | ID: mdl-35242579

RESUMEN

Background: Fabry disease (FD) is a lysosomal storage disorder resulting in systemic accumulation of globotriaosylceramide (Gb3) causing multi-organ dysfunction. The audiologic involvement in FD has been neglected in previous studies; while not a lethal aspect of the disease, hearing loss can have a significantly negative impact on quality of life. Objective: To investigate hearing loss from baseline through 16 years follow-up of the Danish FD cohort and to compare audiometric data to other clinical variables. Methods: Data was collected prospectively and assessed retrospectively during a period of 16 years from 83 patients (age: 9-72 years; sex: 29 males and 54 females). 55 patients underwent treatment. Air conduction thresholds was assessed at six frequencies between 0.25 and 8 kHz bilaterally. Data was analyzed using multilinear models. Results: Mean follow-up period for patients undergoing a FD specific treatment was 7.8 years (0-12.8 years, SD 3.8 years, n = 55). Hearing thresholds for FD patients deviated from healthy individuals at all frequencies for both sexes (p < 0.001). Males had more profound hearing loss than females at high frequencies (4,8 kHz) (p = 0.025). There was no improvement in hearing with treatment (p = 0.343♂, p = 0.256♀). No associations between hearing loss and measured glomerular filtration rate, left ventricular wall thickness or cerebral white matter lesions were found. Lower plasma Gb3 concentration correlated with better hearing (p = 0.046) in males. Conclusion: Our findings demonstrated significant hearing loss in FD patients compared to audiologically healthy individuals at all frequencies, and no change in hearing during treatment. Lower plasma Gb3 concentrations correlated with better hearing in males.

3.
Hear Res ; 421: 108379, 2022 08.
Artículo en Inglés | MEDLINE | ID: mdl-34756677

RESUMEN

High-frequency hearing above 5000 Hz improves the detection and discrimination of high frequency phonemes. Improved access to high-frequency hearing may be particularly advantageous in unilaterally deafened listeners who experience reduced access to high frequency speech cues on their impaired side and decreased speech perception abilities in competing noise. This study aimed to investigate the effects of extended high-frequency bandwidth on speech perception in unilaterally deafened osseointegrated bone conduction hearing device recipients. To study the effect of extended high-frequency bandwidth, participants underwent aided testing in narrow bandwidth and extended high-frquency bandwidth BCD listening conditions. Aided word and phoneme recognition in quiet was assessed at soft and conversational speech levels with the better ear plugged. Aided thresholds and Ling 6 phoneme sounds were also assessed in quiet with the better ear plugged. Speech perception in noise was assessed at ± 90° and co-located at 0° using the adaptive Hearing in Noise Test. Findings demonstrate a significant improvement in speech perception outcomes when listening with extended high-frequency bandwidth. Extended high-frequency bandwidth significantly improved word and phoneme recognition for soft and average conversational speech. The largest effects were observed for voiceless phonemes. Results suggest use of bone conduction devices with extended high-frequency bandwidth result in improved hearing outcomes when compared with narrow bandwidth bone conduction devices.


Asunto(s)
Audífonos , Percepción del Habla , Conducción Ósea , Pruebas Auditivas , Humanos , Ruido/efectos adversos
4.
Ophthalmol Sci ; 1(3): 100039, 2021 Sep.
Artículo en Inglés | MEDLINE | ID: mdl-36247822

RESUMEN

Purpose: To evaluate macular pigment response to carotenoid supplementation in glaucomatous eyes. Design: Double-masked, randomized, placebo-controlled clinical trial, the European Nutrition in Glaucoma Management Study (ClinicalTrials.gov identifier, NCT04460365). Participants: Sixty-two participants (38 men, 24 women) with a diagnosis of open-angle glaucoma were enrolled. Forty-two were randomized to receive the active supplement, 20 participants were allocated to placebo. Methods: Macular pigment optical density (MPOD) was measured by autofluorescence using the Heidelberg Spectralis scanning laser ophthalmoscope. Macular pigment optical density volume within the central 6° of retinal eccentricity as well as MPOD at 0.23°, 0.51°, 0.74°, and 1.02° were recorded at baseline and at 6-month intervals over 18 months. Visual function was assessed using visual acuity, mesopic and photopic contrast sensitivity under glare conditions, photo stress recovery time, microperimetry, and Glaucoma Activities Limitation 9 questionnaire. Advanced glaucoma module scans of retinal nerve fiber layer thickness and ganglion cell complex thickness over the central 6° of retinal eccentricity also were completed at each study visit. Main Outcome Measures: Change in MPOD after supplementation with 10 mg lutein, 2 mg zeaxanthin, and 10 mg meso-zeaxanthin or placebo over 18 months. Results: A mixed-model repeated measures analysis of variance revealed a statistically significant increase in MPOD volume (significant time effect: F(3,111) = 89.31, mean square error (MSE) = 1656.9; P < 0.01). Post hoc t tests revealed a significant difference in MPOD volume at each study visit for the treatment group (P < 0.01 for all), but no change in the placebo group (P > 0.05 for all). A statistically significant increase in mesopic contrast sensitivity under glare conditions was noted at 18 months in the treatment group, but not placebo. No other structural or functional changes were observed. No serious adverse events were noted during the trial. Conclusions: Macular pigment can be augmented in glaucomatous eyes by supplementation with a formulation containing the carotenoids lutein, zeaxanthin, and meso-zeaxanthin. The greatest relative benefit was observed in those with the lowest baseline levels, but increases were noted across all participants and each retinal eccentricity. The potential benefits of MP augmentation for macular health in glaucoma merit further long-term evaluation.

SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA