Artificial intelligence capabilities have, recently, greatly improved. In the past few years, one of the deep learning algorithms, the recurrent neural network (RNN), has shown an outstanding ability in sequence labeling and prediction tasks for sequential data. We built a reliable visual field prediction algorithm using RNN and evaluated its performance in comparison with the conventional pointwise ordinary linear regression (OLR) method. A total of 1,408 eyes were used as a training dataset and another dataset, comprising 281 eyes, was used as a test dataset. Five consecutive visual field tests were provided to the constructed RNN as input and a 6 th visual field test was compared with the output of the RNN. The performance of the RNN was compared with that of OLR by predicting the 6 th visual field in the test dataset. The overall prediction performance of RNN was significantly better than OLR. The pointwise prediction error of the RNN was significantly smaller than that of the OLR in most areas known to be vulnerable to glaucomatous damage. The RNN was also more robust and reliable regarding worsening in the visual field examination. In clinical practice, the RNN model can therefore assist in decision-making for further treatment of glaucoma.
Background/aimsThis study aimed to investigate treatment patterns and medication adherence of glaucoma. It also identified key factors associated with non-adherence.MethodsIt was a cross-sectional, observational study. Patients who use eye-drops for ≤2 years were recruited at 15 eye clinics from March to November 2013. Data were collected through self-administered questionnaires and medical chart review. Medication adherence was evaluated using patients’ self-report on pill count and defined as patients’ administering drug for ≥80% of prescribed days. Medication adherence rate was calculated by dividing actual number of administration from total prescribed number of administration for 7 days. Patients whose self-reported prescription was different from total daily doses of physicians' prescription were considered as non-adherent.ResultsA total of 1050 patients included, and medication adherence rate was evaluated in 1046 patients whose verification of adherence was available. Of the total, 27.4% were non-adherent, and the medication adherence rates of the total, the adherent, and the non-adherent were 90.6±17.8%, 96.8±5.5% and 56.6±24.7%, respectively. The most commonly used medication was prostaglandin (PGA) alone and the second was combination of two-class (β-blocker and carbonic anhydrase inhibitor (CAI)) and three-class combination of PGA, β-blocker and CAI followed. In multivariate analysis, the risk of non-adherence was 1.466 times greater in males than in females (95% CI 1.106 to 1.943) and 1.328-fold greater as the daily number of administration was increased (95% CI 1.186 to 1.487).ConclusionApproximately, one-third of the patients were non-adherent, and males and increased daily number of administration were associated with non-adherence. It highlights that more systematic treatment strategies should be considered for better medication adherence, leading to effective glaucoma management.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.