Ophthalmology

Fuzzing the brain: Automated stress testing for the safety of ML-driven neurostimulation.

OBJECTIVE: Machine learning (ML) models are increasingly used to generate electrical stimulation patterns in neuroprosthetic devices such as visual prostheses. While these models promise precise and personalized control, they also introduce new safety risks when model outputs are delivered directly to neural tissue. We propose a systematic, quantitative approach to detect and characterize unsafe s...

InfoCAM: An information-weighted class activation mapping for explaining visual neural networks.

With the rapid advancement of deep learning technologies, visual neural networks have made significant progress across various benchmarks. However, these networks heavily rely on nonlinear functions and hyperparameter tuning techniques, which leads to black-box behavior during forward inference. To enhance the transparency of decision-making, the information flow in visual neural networks is revis...

Accuracy and completeness of large language models in Epidemic keratoconjunctivitis Queries: A Comparative study.

BACKGROUND: Large language models (LLMs) are increasingly applied in clinical contexts, yet their reliability in disease-specific ophthalmic domains r...

Clinically interpretable machine-learning model for predicting heart mean dose using simple BEV-based metrics.

Radiation-induced cardiac toxicity remains a major concern in left-sided breast cancer radiotherapy, with mean heart dose (MHD) serving as a key predi...

Geographic atrophy in age-related macular degeneration: phenotypic characterisation for clinical trial consideration.

Geographic atrophy (GA) is an advanced form of age-related macular degeneration (AMD) and a leading cause of central vision loss. Advances in multimod...

Antioxidant vitamin index and risk of age-related macular degeneration: multicenter validation and clinical translation.

Age-related macular degeneration (AMD) is a leading cause of blindness in older adults, with oxidative stress as a central driver. We proposed the Ant...

Machine learning-based prediction of persistent diabetic macular edema using OCT-derived structural biomarkers and clinical features.

BACKGROUND: Persistent diabetic macular edema (DME) remains a leading cause of vision loss in diabetic retinopathy, even with anti-VEGF therapy. About...

Accurate Prediction of Humphrey 10-2 Visual Fields in Glaucoma from a Single Rapid IMOvifa 24plus(1-2).

PURPOSE: Predicting the Humphrey Field Analyzer (HFA) 10-2 visual field (VF) using machine learning (ML) based on IMOvifa 24plus(1-2) VF data. DESIGN:...

Artificial intelligence and medicine: an epistemological inquiry.

Artificial intelligence (AI) in medicine inspires both enthusiasm and concern. It introduces an unprecedented development in the history of knowledge:...

Narrative as technology: the role of the medical humanities in responding to emerging biomedical technologies.

Often, the medical humanities are framed as a corrective to various instrumental inclinations within biomedicine. The humanities, according to this fo...

Hallucination filtering in radiology vision-language models using discrete semantic entropy.

OBJECTIVE: To determine whether using discrete semantic entropy (DSE) to reject questions likely to generate hallucinations can improve the accuracy o...

Achieving more human brain-like vision via human EEG representational alignment.

Despite advancements in artificial intelligence, object recognition models still lag behind in emulating visual information processing in human brains...

Outer Retinal Erosion and Outer Retinal Pinching at the Origin of Subretinal Fluid in Central Serous Chorioretinopathy.

PURPOSE: To characterize early outer retinal changes at the site of origin of subretinal fluid (SRF) in central serous chorioretinopathy (CSCR). To in...

Interpretable spatiotemporal machine learning reveals hydrogeological and climatic controls on groundwater heavy metal transport in acid mine drainage.

Acid mine drainage (AMD) generated by sulfide-bearing waste rock dumps poses persistent risks to groundwater through acidic leachate and heavy-metal m...

Generative AI in preanesthetic consultations: Effects on efficiency, documentation workload, quality, and physician-patient interaction: A simulation trial.

BACKGROUND: Clinicians spend over 30% of their workday on electronic health records, reducing patient interaction and contributing to burnout. Preanes...

Assessment of Predictive Factors That Shorten Duration of Treatment in Patients With Multiple Myeloma Using AI: Real-World Longitudinal Study Using Data From Medical Data Vision Claims Database.

BACKGROUND: With the availability of newer therapies, the duration of therapy (DoT) shortens with each increasing line of treatment in Japanese patien...

Loading dose and 12-month outcomes in treatment-naïve patients with neovascular age-related macular degeneration treated with faricimab, with AI-based analysis of fluid dynamics.

PURPOSE: To evaluate the effects of loading dose and 12 months of faricimab treatment on visual function, retinal anatomy, and fluid dynamics in a rea...

Automated Report Generation in Ophthalmology: Integrating Artificial Intelligence, Multimodal Imaging, and Clinical Data.

Artificial intelligence (AI) has emerged as a transformative force in ophthalmology, enabling automated, accurate, and efficient clinical reporting. T...

Robust and interpretable unit level causal inference in neural networks for pediatric myopia.

Understanding causal mechanisms in deep learning is essential for clinical adoption, where interpretability and reliability are critical. Most existin...

Predicting Visual Outcomes in Congenital Posterior Lens Opacities: A Deep Learning Model Using Ultra-Widefield Fundus Images.

PURPOSE: To develop and validate a deep learning (DL) model for the automatic segmentation of lens opacity projected shadow (LOPS) on ultra-widefield ...