Prediction of neovascular age-related macular degeneration recurrence using optical coherence tomography images with a deep neural network.

Neovascular age-related macular degeneration (nAMD) can result in blindness if left untreated, and patients often require repeated anti-vascular endothelial growth factor injections. Although, the treat-and-extend method is becoming popular to reduce vision loss attributed to recurrence, it may pose a risk of overtreatment. This study aimed to develop a deep learning model based on DenseNet201 to predict nAMD recurrence within 3 months after confirming dry-up 1 month following three loading injections in treatment-naïve patients. A dataset of 1076 spectral domain optical coherence tomography (OCT) images from 269 patients diagnosed with nAMD was used. The performance of the model was compared with that of 6 ophthalmologists, using 100 randomly selected samples. The DenseNet201-based model achieved 53.0% accuracy in predicting nAMD recurrence using a single pre-injection image and 60.2% accuracy after viewing all the images immediately after the 1st, 2nd, and 3rd injections. The model outperformed experienced ophthalmologists, with an average accuracy of 52.17% using a single pre-injection image and 53.3% after examining four images before and after three loading injections. In conclusion, the artificial intelligence model demonstrated a promising ability to predict nAMD recurrence using OCT images and outperformed experienced ophthalmologists. These findings suggest that deep learning models can assist in nAMD recurrence prediction, thus improving patient outcomes and optimizing treatment strategies.

A quality improvement initiative to reduce antibiotic use in transient tachypnea of the newborn.

OBJECTIVE: Evidence suggests that antibiotics are unnecessary in infants with transient tachypnea of the newborn (TTN) that are low-risk for early-onset sepsis. The aim was to reduce ampicillin and gentamicin days of therapy (DOT) in infants with suspected TTN by 10% within 12 months. STUDY DESIGN: We used the Model for Improvement to test interventions from August 2019 to September 2021 to decrease antibiotic utilization in low-risk infants with TTN. Interventions included the creation of an evidence-based clinical pathway, admission huddles, and prescriber audit and feedback. RESULTS: We reduced ampicillin and gentamicin use by 26% and 23%, respectively. In 123 infants with suspected TTN, we sequentially decreased starting antibiotics in this group from 71% to 41%, 13% and 0%. There were no cases of missed bacteremia. CONCLUSION: Creation of a multidisciplinary antimicrobial stewardship QI team and subsequent interventions were successful in safely reducing antibiotic use in infants with TTN.

Developing and Evaluating an AI-Based Computer-Aided Diagnosis System for Retinal Disease: Diagnostic Study for Central Serous Chorioretinopathy.

BACKGROUND: Although previous research has made substantial progress in developing high-performance artificial intelligence (AI)-based computer-aided diagnosis (AI-CAD) systems in various medical domains, little attention has been paid to developing and evaluating AI-CAD system in ophthalmology, particularly for diagnosing retinal diseases using optical coherence tomography (OCT) images. OBJECTIVE: This diagnostic study aimed to determine the usefulness of a proposed AI-CAD system in assisting ophthalmologists with the diagnosis of central serous chorioretinopathy (CSC), which is known to be difficult to diagnose, using OCT images. METHODS: For the training and evaluation of the proposed deep learning model, 1693 OCT images were collected and annotated. The data set included 929 and 764 cases of acute and chronic CSC, respectively. In total, 66 ophthalmologists (2 groups: 36 retina and 30 nonretina specialists) participated in the observer performance test. To evaluate the deep learning algorithm used in the proposed AI-CAD system, the training, validation, and test sets were split in an 8:1:1 ratio. Further, 100 randomly sampled OCT images from the test set were used for the observer performance test, and the participants were instructed to select a CSC subtype for each of these images. Each image was provided under different conditions: (1) without AI assistance, (2) with AI assistance with a probability score, and (3) with AI assistance with a probability score and visual evidence heatmap. The sensitivity, specificity, and area under the receiver operating characteristic curve were used to measure the diagnostic performance of the model and ophthalmologists. RESULTS: The proposed system achieved a high detection performance (99% of the area under the curve) for CSC, outperforming the 66 ophthalmologists who participated in the observer performance test. In both groups, ophthalmologists with the support of AI assistance with a probability score and visual evidence heatmap achieved the highest mean diagnostic performance compared with that of those subjected to other conditions (without AI assistance or with AI assistance with a probability score). Nonretina specialists achieved expert-level diagnostic performance with the support of the proposed AI-CAD system. CONCLUSIONS: Our proposed AI-CAD system improved the diagnosis of CSC by ophthalmologists, which may support decision-making regarding retinal disease detection and alleviate the workload of ophthalmologists.

Prediction of Visual Acuity in Pathologic Myopia with Myopic Choroidal Neovascularization Treated with Anti-Vascular Endothelial Growth Factor Using a Deep Neural Network Based on Optical Coherence Tomography Images.

Myopic choroidal neovascularization (mCNV) is a common cause of vision loss in patients with pathological myopia. However, predicting the visual prognosis of patients with mCNV remains challenging. This study aimed to develop an artificial intelligence (AI) model to predict visual acuity (VA) in patients with mCNV. This study included 279 patients with mCNV at baseline; patient data were collected, including optical coherence tomography (OCT) images, VA, and demographic information. Two models were developed: one comprising horizontal/vertical OCT images (H/V cuts) and the second comprising 25 volume scan images. The coefficient of determination (R2) and root mean square error (RMSE) were computed to evaluate the performance of the trained network. The models achieved high performance in predicting VA after 1 (R2 = 0.911, RMSE = 0.151), 2 (R2 = 0.894, RMSE = 0.254), and 3 (R2 = 0.891, RMSE = 0.227) years. Using multiple-volume scanning, OCT images enhanced the performance of the models relative to using only H/V cuts. This study proposes AI models to predict VA in patients with mCNV. The models achieved high performance by incorporating the baseline VA, OCT images, and post-injection data. This model could assist in predicting the visual prognosis and evaluating treatment outcomes in patients with mCNV undergoing intravitreal anti-vascular endothelial growth factor therapy.

Stevia (Stevia rebaudiana) extract ameliorates insulin resistance by regulating mitochondrial function and oxidative stress in the skeletal muscle of db/db mice.

BACKGROUND: Type 2 diabetes mellitus (T2DM), a growing health problem worldwide, is a metabolic disorder characterized by hyperglycemia due to insulin resistance and defective insulin secretion by pancreatic ß-cells. The skeletal muscle is a central organ that consumes most of the insulin-stimulated glucose in the body, and insulin resistance can damage muscles in T2DM. Based on a strong correlation between diabetes and muscles, we investigated the effects of stevia extract (SE) and stevioside (SV) on the skeletal muscle of diabetic db/db mice. METHODS: The mice were administered saline, metformin  (200 mg/kg/day), SE (200 and 500 mg/kg/day), and SV (40 mg/kg/day) for 35 days. During administration, we checked the levels of fasting blood glucose twice a week and conducted the oral glucose tolerance test (OGTT) and insulin tolerance test (ITT). After administration, we analyzed serum biochemical parameters, triglyceride (TG), total cholesterol (TC), insulin and antioxidant enzymes, and the cross-sectional area of skeletal muscle fibers of db/db mice. Western blots were conducted using the skeletal muscle of mice to examine the effect of SE and SV on protein expression of insulin signaling, mitochondrial function, and oxidative stress. RESULTS: SE and SV administration lowered the levels of fasting blood glucose, OGTT, and ITT in db/db mice. The administration also decreased serum levels of TG, TC, and insulin while increasing those of superoxide dismutase (SOD) and glutathione peroxidase (GPx). Interestingly, muscle fiber size was significantly increased in db/db mice treated with SE500 and SV. In the skeletal muscle of db/db mice, SE and SV administration activated insulin signaling by increasing the protein expression of insulin receptor substrate, Akt, and glucose transporter type 4. Furthermore, SE500 administration markedly increased the protein expression of AMP-activated protein kinase-α, sirtuin-1, and peroxisome proliferator-activated receptor-γ coactivator-1α. SV administration significantly reduced oxidative stress by down-regulating the protein expression of 4-hydroxynonenal, heme oxygenase-1, SOD, and GPx. In addition, SE500 and SV administration suppressed the expression of apoptosis-related proteins in the skeletal muscle of db/db mice. CONCLUSION: SE and SV administration attenuated hyperglycemia in diabetic mice. Moreover, the administration ameliorated insulin resistance by regulating mitochondrial function and oxidative stress, increasing muscle fiber size. Overall, this study suggests that SE and SV administration may serve as a potential strategy for the treatment of diabetic muscles.

Dancing on the inside: A qualitative study on online dance learning with teacher-AI cooperation.

Recent technologies have extended opportunities for online dance learning by overcoming the limitations of space and time. However, dance teachers report that student-teacher interaction is more likely to be challenging in a distant and asynchronous learning environment than in a conventional dance class, such as a dance studio. To address this issue, we introduce DancingInside, an online dance learning system that encourages a beginner to learn dance by providing timely and sufficient feedback based on Teacher-AI cooperation. The proposed system incorporates an AI-based tutor agent (AI tutor, in short) that uses a 2D pose estimation approach to quantitatively estimate the similarity between a learner's and teacher's performance. We conducted a two-week user study with 11 students and 4 teachers. Our qualitative study results highlight that the AI tutor in DancingInside could support the reflection on a learner's practice and help the performance improvement with multimodal feedback resources. The interview results also reveal that the human teacher's role is essential in complementing the AI feedback. We discuss our design and suggest potential implications for future AI-supported cooperative dance learning systems.

Detecting Macular Disease Based on Optical Coherence Tomography Using a Deep Convolutional Network.

Neovascular age-related macular degeneration (nAMD) and central serous chorioretinopathy (CSC) are two of the most common macular diseases. This study proposes a convolutional neural network (CNN)-based deep learning model for classifying the subtypes of nAMD (polypoidal choroidal vasculopathy, retinal angiomatous proliferation, and typical nAMD) and CSC (chronic CSC and acute CSC) and healthy individuals using single spectral-domain optical coherence tomography (SD-OCT) images. The proposed model was trained and tested using 6063 SD-OCT images from 521 patients and 47 healthy participants. We used three well-known CNN architectures (VGG-16, VGG-19, and ResNet) and two customized classification layers. Additionally, transfer learning and mix-up-based data augmentation were applied to improve robustness and accuracy. Our model demonstrated high accuracies of 99.7% and 91.1% in the nAMD and CSC classification and retinopathy (nAMD and CSC) subtype classification, including normal participants, respectively. Furthermore, we performed an external test to compare the classification accuracy with that of eight ophthalmologists, and our model showed the highest accuracy. The region determined to be important for classification by the model was confirmed using gradient-weighted class activation mapping. The model's clinical criteria were similar to that of the ophthalmologists.

COVID-19 is Observed in Older Children During the Omicron Wave in New York City.

BACKGROUND: The Omicron variant of SARS-CoV-2 has a predilection for the upper airways, causing symptoms such as sore throat, hoarse voice, and stridor. OBJECTIVE: We describe a series of children with COVID-19-associated croup in an urban multicenter hospital system. METHODS: We conducted a cross-sectional study of children ≤18 years of age presenting to the emergency department during the COVID-19 pandemic. Data were extracted from an institutional data repository comprised of all patients who were tested for SARS-CoV-2. We included patients with a croup diagnosis by International Classification of Diseases, 10th revision code and a positive SARS-CoV-2 test within 3 days of presentation. We compared demographics, clinical characteristics, and outcomes for patients presenting during a pre-Omicron period (March 1, 2020-December 1, 2021) to the Omicron wave (December 2, 2021-February 15, 2022). RESULTS: We identified 67 children with croup, 10 (15%) pre-Omicron and 57 (85%) during the Omicron wave. The prevalence of croup among SARS-CoV-2-positive children increased by a factor of 5.8 (95% confidence interval 3.0-11.4) during the Omicron wave compared to prior. More patients were ≥6 years of age in the Omicron wave than prior (19% vs. 0%). The majority were not hospitalized (77%). More patients ≥6 years of age received epinephrine therapy for croup during the Omicron wave (73% vs. 35%). Most patients ≥6 years of age had no croup history (64%) and only 45% were vaccinated against SARS-CoV-2. CONCLUSION: Croup was prevalent during the Omicron wave, atypically affecting patients ≥6 years of age. COVID-19-associated croup should be added to the differential diagnosis of children with stridor, regardless of age. © 2022 Elsevier Inc.

Stevia and Stevioside Attenuate Liver Steatosis through PPARα-Mediated Lipophagy in db/db Mice Hepatocytes.

Lipophagy, a type of autophagy that breaks down lipid droplets, is essential in the regulation of intracellular lipid accumulation and intracellular free fatty acid levels in numerous organisms and metabolic conditions. We investigated the effects of Stevia rebaudiana Bertoni (S), a low-calorie sweetener, and stevioside (SS) on hepatic steatosis and autophagy in hepatocytes, as well as in db/db mice. S and SS reduced the body and liver weight and levels of serum triglyceride, total cholesterol, and hepatic lipogenic proteins. In addition, S and SS increased the levels of fatty acid oxidase, peroxisome proliferator-activated receptor alpha (PPARα), and microtubule-associated protein light chain 3 B but decreased that of sequestosome 1 (p62) in the liver of db/db mice. Additionally, Beclin 1, lysosomal associated membrane protein 1, and phosphorylated adenosine monophosphate-activated protein kinase protein expression was augmented following S and SS treatment of db/db mice. Furthermore, the knockdown of PPARα blocked lipophagy in response to SS treatment in HepG2 cells. These outcomes indicate that PPARα-dependent lipophagy is involved in hepatic steatosis in the db/db mouse model and that SS, a PPARα agonist, represents a new therapeutic option for managing associated diseases.

Experiencing Stress During COVID-19: A Computational Analysis of Stressors and Emotional Responses to Stress.

This study aims to unveil how COVID-19 affected the experience of stress by focusing on the stressors. Using computational analysis based on a newly developed stressor identification model, we compared the experience of stress expressed by Korean Twitter users before and during the pandemic in terms of (1) the stressors as the source of stress and (2) emotion as the manifestation of stress. Both tweet-level (N = 202,556) and user-level (N = 24,803) analyses revealed that social factors are prevalent sources of stress both before and during the pandemic. Moreover, social stressors increased the most during the pandemic. While stress from social stressors was manifested mainly as sadness before the pandemic, anger became the predominant emotional manifestation during the pandemic. Public health policies and educators should consider social stressors as the predominant source of stress during the pandemic and seek ways to prepare the public better for such threats.

Indications for Hospitalization in Children with SARS-CoV-2 Infection during the Omicron Wave in New York City.

The emergence of the Omicron variant was accompanied by an acute increase in COVID-19 cases and hospitalizations in New York City. An increased incidence of COVID-19-associated croup in children during the Omicron wave has been recognized, suggesting that there may be other changes in clinical symptoms and severity. To better understand clinical outcomes and health care utilization in children infected with SARS-CoV-2 during the Omicron wave, we performed a cross-sectional study in pediatric patients aged ≤18 years who were tested for SARS-CoV-2 in pediatric emergency departments within a large medical system in New York City from 2 December 2021 to 23 January 2022. We described the clinical characteristics and outcomes of pediatric patients who presented to the pediatric emergency department and were hospitalized with SARS-CoV-2 infection during the Omicron wave in New York City. There were 2515 children tested in the ED for SARS-CoV-2 of whom 794 (31.6%) tested positive. Fifty-eight children were hospitalized for a COVID-19-related indication, representing 7.3% of all COVID-19-positive children and 72% of hospitalized COVID-19-positive children. Most (64%) children hospitalized for a COVID-19-related indication were less than 5 years old. Indications for hospitalization included respiratory symptoms, clinical monitoring of patients with comorbid conditions, and exacerbations of underlying disease. Eleven (19%) hospitalized children were admitted to the ICU and six (10%) required mechanical ventilation. Children infected with COVID-19 during the Omicron wave, particularly those less than 5 years old, were at risk for hospitalization. A majority of hospitalizations were directly related to COVID-19 infection although clinical indications varied with less than a half being admitted for respiratory diseases including croup. Our findings underscore the need for an effective COVID-19 vaccine in those less than 5 years old, continued monitoring for changes in clinical outcomes and health care utilization in children as more SARS-CoV-2 variants emerge, and understanding that children are often admitted for non-respiratory diseases with COVID-19.

Social Sharing of Emotion During the COVID-19 Pandemic.

The long-term uncertainty and persistence of isolation caused by the COVID-19 pandemic created prolonged emotional distress individually and collectively. As the pandemic progressed, the dynamic ride of emotional experience was expressed live and shared online, particularly on social media. In this study, we collected posted messages on Twitter for a longitudinal investigation to determine how emotional experiences changed over time during the pandemic. In total, we analyzed 41,868,013 COVID-19-related tweets in English posted from January 21 to July 31, 2020. Using a stage model, the results demonstrated that there were three stages during the pandemic characterized by distinct emotional changes. The first stage features high anxiety and negative emotions compared with the other stages, possibly due to the lack of information about the disease. The second stage shows the dynamic ride of all emotions and an increase in negative emotions (particularly anger) as the COVID-19 pandemic proceeds. In the third stage, most emotions are stabilized, except for depression, despite the protracted pandemic.

Stevioside Enhances the Anti-Adipogenic Effect and ß-Oxidation by Activating AMPK in 3T3-L1 Cells and Epididymal Adipose Tissues of db/db Mice.

Stevioside, the primary sweetener in stevia, is a glycoside with numerous beneficial biological activities. However, its anti-adipogenic effects on tissue differentiation and adipose tissues remain to be thoroughly investigated. In this study, the anti-adipogenic effects of stevioside during the differentiation of 3T3-L1 cells and epididymal adipose tissues of db/db mice were investigated by measuring the lipid droplets stained with Oil Red O and an immunoblot assay. Immunoblot analysis revealed that stevioside downregulated the expression of peroxisome proliferator-activated receptor-gamma (PPARγ), sterol regulatory element-binding protein-1c (SREBP-1c), CCAAT/enhancer-binding protein alpha (C/EBPα), and fatty acid synthase (FAS). Additionally, the protein expression of carnitine palmitoyltransferase 1 (CPT1), silent mating type information regulation 2 homolog 1 (SIRT1), and peroxisome proliferator-activated receptor gamma coactivator 1 alpha (PGC-1α) increased following treatment with stevioside. Furthermore, stevioside increased the phosphorylation of adenosine monophosphate (AMP)-activated protein kinase (AMPK) and acetyl-CoA carboxylase (ACC), both in vitro and in vivo. The activity of AMPK in stevioside-treated 3T3-L1 cells was further confirmed using agonists and antagonists of AMPK signaling. Our data indicate that stevioside ameliorates anti-adipogenic effects and promotes ß-oxidation in adipocytes by activating AMPK-mediated signaling. The results of this study clearly demonstrated the inhibitory effect of stevioside on the differentiation of adipocytes and the reduction of lipid accumulation in the epididymal adipose tissues of db/db mice.

N-Doped Carbon Nanorods from Biomass as a Potential Antidiabetic Nanomedicine.

Insufficient glucose control remains a critical challenge for type 2 diabetes mellitus (T2DM) patients with currently used therapeutic drugs, which can also have detrimental side effects. The facile synthesis of nitrogen-doped carbon nanorods (N-CNRs) as therapeutic agents in a T2DM transgenic db/db mouse model is reported herein. N-CNRs are synthesized from silkworm powder without the assistance of any template and possess a hollow graphitic nature, rough surface, and good aqueous solubility, which make them ideal candidates for fabricating nanomedicines. N-CNRs are employed to reduce fasting blood glucose and ameliorate serum biomarker levels linked to oxidative stress and inflammation. Interestingly, through the downregulation of enhanced expression of glutathione peroxidase, superoxide dismutase, and catalase as well as inflammatory responses, N-CNRs reverse pancreatic dysfunction and normalize the secretory functions of pancreatic cells. Moreover, hepatic steatosis is attenuated by downregulating lipogenesis and increasing fatty acid oxidation. This finding may help in designing novel therapeutics for T2DM treatment.

The connection to the public's preferred sports analysis and physical education curriculum.

People have their favorite type of sport, but such preferences tend to be shared for nearly a lifetime. How this preference persists remains inconclusive; hence, this study attempts to determine why people have different viewpoints on sports. It is reasonable to infer that these differences arise from differences in culture, occupation, and race. Therefore, we collected the following data and conducted research in Korea, the United States, and Japan, countries with various differences. The types of sports that people play were collected through surveys and comparisons among sports networks. Namely, "Sport Classification," "The K-12 Physical Education System (textbooks)," "Survey (actual physical activity)," "Simple Notification Service (SNS) Activity" have been examined to deduce the reason why any particular sport is played. Firstly, Korea, the United States, and Japan conduct different physical education courses. Hence, the results affect people's preferences. Secondly, what people post on SNS and their actual physical activities are different. Thirdly, the degree of connection between sports-type varied as well. Lastly, sports that serve the purpose of being regarded as hubs among sports-type were common in Korea, the United States, and Japan.

Classifying neovascular age-related macular degeneration with a deep convolutional neural network based on optical coherence tomography images.

Neovascular age-related macular degeneration (nAMD) is among the main causes of visual impairment worldwide. We built a deep learning model to distinguish the subtypes of nAMD using spectral domain optical coherence tomography (SD-OCT) images. Data from SD-OCT images of nAMD (polypoidal choroidal vasculopathy, retinal angiomatous proliferation, and typical nAMD) and normal healthy patients were analyzed using a convolutional neural network (CNN). The model was trained and validated based on 4749 SD-OCT images from 347 patients and 50 healthy controls. To adopt an accurate and robust image classification architecture, we evaluated three well-known CNN structures (VGG-16, VGG-19, and ResNet) and two customized classification layers (fully connected layer with dropout vs. global average pooling). Following the test set performance, the model with the highest classification accuracy was used. Transfer learning and data augmentation were applied to improve the robustness and accuracy of the model. Our proposed model showed an accuracy of 87.4% on the test data (920 images), scoring higher than ten ophthalmologists, for the same data. Additionally, the part that our model judged to be important in classification was confirmed through Grad-CAM images, and consequently, it has a similar judgment criteria to that of ophthalmologists. Thus, we believe that our model can be used as an auxiliary tool in clinical practice.

Assessing central serous chorioretinopathy with deep learning and multiple optical coherence tomography images.

Central serous chorioretinopathy (CSC) is one of the most common macular diseases that can reduce the quality of life of patients. This study aimed to build a deep learning-based classification model using multiple spectral domain optical coherence tomography (SD-OCT) images together to diagnose CSC. Our proposed system contains two modules: single-image prediction (SIP) and a final decision (FD) classifier. A total of 7425 SD-OCT images from 297 participants (109 acute CSC, 106 chronic CSC, 82 normal) were included. In the fivefold cross validation test, our model showed an average accuracy of 94.2%. Compared to other end-to-end models, for example, a 3D convolutional neural network (CNN) model and a CNN-long short-term memory (CNN-LSTM) model, the proposed system showed more than 10% higher accuracy. In the experiments comparing the proposed model and ophthalmologists, our model showed higher accuracy than experts in distinguishing between acute, chronic, and normal cases. Our results show that an automated deep learning-based model could play a supplementary role alongside ophthalmologists in the diagnosis and management of CSC. In particular, the proposed model seems clinically applicable because it can classify CSCs using multiple OCT images simultaneously.

Classifying central serous chorioretinopathy subtypes with a deep neural network using optical coherence tomography images: a cross-sectional study.

Central serous chorioretinopathy (CSC) is the fourth most common retinopathy and can reduce quality of life. CSC is assessed using optical coherence tomography (OCT), but deep learning systems have not been used to classify CSC subtypes. This study aimed to build a deep learning system model to distinguish CSC subtypes using a convolutional neural network (CNN). We enrolled 435 patients with CSC from a single tertiary center between January 2015 and January 2020. Data from spectral domain OCT (SD-OCT) images of the patients were analyzed using a deep CNN. Five-fold cross-validation was employed to evaluate the model's ability to discriminate acute, non-resolving, inactive, and chronic atrophic CSC. We compared the performances of the proposed model, Resnet-50, Inception-V3, and eight ophthalmologists. Overall, 3209 SD-OCT images were included. The proposed model showed an average cross-validation accuracy of 70.0% (95% confidence interval [CI], 0.676-0.718) and the highest test accuracy was 73.5%. Additional evaluation in an independent set of 104 patients demonstrated the reliable performance of the proposed model (accuracy: 76.8%). Our model could classify CSC subtypes with high accuracy. Thus, automated deep learning systems could be useful in the classification and management of CSC.

Distinguishing retinal angiomatous proliferation from polypoidal choroidal vasculopathy with a deep neural network based on optical coherence tomography.

This cross-sectional study aimed to build a deep learning model for detecting neovascular age-related macular degeneration (AMD) and to distinguish retinal angiomatous proliferation (RAP) from polypoidal choroidal vasculopathy (PCV) using a convolutional neural network (CNN). Patients from a single tertiary center were enrolled from January 2014 to January 2020. Spectral-domain optical coherence tomography (SD-OCT) images of patients with RAP or PCV and a control group were analyzed with a deep CNN. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC) were used to evaluate the model's ability to distinguish RAP from PCV. The performances of the new model, the VGG-16, Resnet-50, Inception, and eight ophthalmologists were compared. A total of 3951 SD-OCT images from 314 participants (229 AMD, 85 normal controls) were analyzed. In distinguishing the PCV and RAP cases, the proposed model showed an accuracy, sensitivity, and specificity of 89.1%, 89.4%, and 88.8%, respectively, with an AUROC of 95.3% (95% CI 0.727-0.852). The proposed model showed better diagnostic performance than VGG-16, Resnet-50, and Inception-V3 and comparable performance with the eight ophthalmologists. The novel model performed well when distinguishing between PCV and RAP. Thus, automated deep learning systems may support ophthalmologists in distinguishing RAP from PCV.