Nolan Huck

Retinal hemorrhages in pediatric patients can be a diagnostic challenge for ophthalmologists. These hemorrhages can occur due to various underlying etiologies, including abusive head trauma, accidental trauma, and medical conditions. Accurate identification of the etiology is crucial for appropriate management and legal considerations. In recent years, deep learning techniques have shown promise in assisting healthcare professionals in making more accurate and timely diagnosis of a variety of disorders. We explore the potential of deep learning approaches for differentiating etiologies of pediatric retinal hemorrhages. Our study, which spanned multiple centers, analyzed 898 images, resulting in a final dataset of 597 retinal hemorrhage fundus photos categorized into medical (49.9%) and trauma (50.1%) etiologies. Deep learning models, specifically those based on ResNet and transformer architectures, were applied; FastViT-SA12, a hybrid transformer model, achieved the highest accuracy (90.55%) and area under the receiver operating characteristic curve (AUC) of 90.55%, while ResNet18 secured the highest sensitivity value (96.77%) on an independent test dataset. The study highlighted areas for optimization in artificial intelligence (AI) models specifically for pediatric retinal hemorrhages. While AI proves valuable in diagnosing these hemorrhages, the expertise of medical professionals remains irreplaceable. Collaborative efforts between AI specialists and pediatric ophthalmologists are crucial to fully harness AI’s potential in diagnosing etiologies of pediatric retinal hemorrhages.

Objective Our laboratory has recently shown that there is a decrease in neuronal complexity in head pain processing regions in mouse models of chronic migraine‐associated pain and aura. Importantly, restoration of this neuronal complexity corresponds with anti‐migraine effects of known and experimental pharmacotherapies. The objective of the current study was to expand this work and examine other brain regions involved with pain or emotional processing. We also investigated the generalizability of our findings by analyzing neuronal cytoarchitectural changes in a model of complex regional pain syndrome (CRPS), a peripheral pain disorder. Methods We used the nitroglycerin (NTG) model of chronic migraine‐associated pain in which mice receive 10 mg/kg NTG every other day for 9 days. Cortical spreading depression (CSD), a physiological corelate of migraine aura, was evoked in anesthetized mice using KCl. CRPS was induced by tibial fracture followed by casting. Neuronal cytoarchitecture was visualized with Golgi stain and analyzed with Simple Neurite Tracer. Results In the NTG model, we previously showed decreased neuronal complexity in the trigeminal nucleus caudalis (TNC) and periaqueductal gray (PAG). In contrast, we found increased neuronal complexity in the thalamus and no change in the amygdala or caudate putamen in this study. Following CSD, we observed decreased neuronal complexity in the PAG, in line with decreases in the somatosensory cortex and TNC reported with this model previously. In the CRPS model there was decreased neuronal complexity in the hippocampus, as reported by others; increased complexity in the PAG; and no change within the somatosensory cortex. Conclusions Collectively these results demonstrate that alterations in neuronal complexity are a feature of both chronic migraine and chronic CRPS. However, each type of pain presents a unique cytoarchitectural signature, which may provide insight on how these pain states differentially transition from acute to chronic conditions.