To develop an artificial intelligence (AI) model that predicts anti-vascular endothelial growth factor (VEGF) agent-specific anatomical treatment outcomes in neovascular age-related macular degeneration (AMD), thereby assisting clinicians in selecting the most suitable anti-VEGF agent for each patient. This retrospective study included patients diagnosed with neovascular AMD who received three loading injections of either ranibizumab or aflibercept. Training was performed using optical coherence tomography (OCT) images with an attention generative adversarial network (GAN) model. To test the performance of the AI model, the sensitivity and specificity to predict the presence of retinal fluid after treatment were calculated for the AI model, an experienced (Examiner 1), and a less experienced (Examiner 2) human examiners. A total of 1684 OCT images from 842 patients (419 treated with ranibizumab and 423 treated with aflibercept) were used as the training set. Testing was performed using images from 98 patients. In patients treated with ranibizumab, the sensitivity and specificity, respectively, were 0.615 and 0.667 for the AI model, 0.385 and 0.861 for Examiner 1, and 0.231 and 0.806 for Examiner 2. In patients treated with aflibercept, the sensitivity and specificity, respectively, were 0.857 and 0.881 for the AI model, 0.429 and 0.976 for Examiner 1, and 0.429 and 0.857 for Examiner 2. In 18.5% of cases, the fluid status of synthetic posttreatment images differed between ranibizumab and aflibercept. The AI model using GAN might predict anti-VEGF agent-specific short-term treatment outcomes with relatively higher sensitivity than human examiners. Additionally, there was a difference in the efficacy in fluid resolution between the anti-VEGF agents. These results suggest the potential of AI in personalized medicine for patients with neovascular AMD.
Background and purpose: Alzheimer disease (AD) is the most common type of dementia. Amyloidβ (Aβ) positivity is the main diagnostic marker for AD. Aβ positron emission tomography and cerebrospinal fluid are widely used in the clinical diagnosis of AD.However, these methods only assess the concentrations of Aβ, and the accessibility of these methods is thus relatively limited compared with structural magnetic resonance imaging (sMRI). Methods: We investigated whether regions of interest (ROIs) in sMRIs can be used to predict Aβ positivity for samples with normal cognition (NC), mild cognitive impairment (MCI), and dementia. We obtained 846 Aβ negative (Aβ−) and 865 Aβ positive (Aβ+) samples from the Alzheimer's Disease Neuroimaging Initiative database. To predict which samples are Aβ+, we built five machine learning models using ROIs and apolipoprotein E (APOE) genotypes as features. To test the performance of the machine learning models, we constructed a new cohort containing 97 Aβ− and 81 Aβ+ samples. Results:The best performing machine learning model combining ROIs and APOE had an accuracy of 0.798, indicating that it can help predict Aβ+. Furthermore, we searched ROIs that could aid our prediction and discovered that an average left entorhinal cortical region (L-ERC) thickness is an important feature. We also noted significant differences in L-ERC thickness between the Aβ− and Aβ+ samples even in the same diagnosis of NC, MCI, and dementia. Conclusions:Our findings indicate that ROIs from sMRIs along with APOE can be used as an initial screening tool in the early diagnosis of AD.
Integration of multiple biological datasets is crucial to understand comprehensive biological mechanisms with the aid of a rapid development of biomedical technology. However, the predictive modeling for such an integrated dataset faces two major challenges, namely, heterogeneity and imbalance in the acquired data. Thus, in this study, we present a method for the integration of multiple biological datasets called multimodal multitask matrix factorization (MMMF) to address these issues. The MMMF uses matrix factorization (MF) to integrate data from multiple heterogeneous biological datasets, and oversampling is applied to resolve the imbalanced data during the training step. Moreover, gradient surgery is used for multitask (MF and classification) learning to increase the quantity of classification information by projecting the gradients of the MF that conflict with the classification gradient onto the normal plane of a classification gradient. We demonstrate that MMMF outperforms other state-of-the-art biomedical classification models in binary and multi-class classification problems using five biological datasets. We also show that MMMF can be used as a feature selection approach for finding biomarkers that help in classification. The source code of the MMMF is available at https://github.com/DMCB-GIST/MMMF.
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.