Development of a deep learning model to distinguish the cause of optic disc atrophy using retinal fundus photography.

The differential diagnosis for optic atrophy can be challenging and requires expensive, time-consuming ancillary testing to determine the cause. While Leber's hereditary optic neuropathy (LHON) and optic neuritis (ON) are both clinically significant causes for optic atrophy, both relatively rare in the general population, contributing to limitations in obtaining large imaging datasets. This study therefore aims to develop a deep learning (DL) model based on small datasets that could distinguish the cause of optic disc atrophy using only fundus photography. We retrospectively reviewed fundus photographs of 120 normal eyes, 30 eyes (15 patients) with genetically-confirmed LHON, and 30 eyes (26 patients) with ON. Images were split into a training dataset and a test dataset and used for model training with ResNet-18. To visualize the critical regions in retinal photographs that are highly associated with disease prediction, Gradient-Weighted Class Activation Map (Grad-CAM) was used to generate image-level attention heat maps and to enhance the interpretability of the DL system. In the 3-class classification of normal, LHON, and ON, the area under the receiver operating characteristic curve (AUROC) was 1.0 for normal, 0.988 for LHON, and 0.990 for ON, clearly differentiating each class from the others with an overall total accuracy of 0.93. Specifically, when distinguishing between normal and disease cases, the precision, recall, and F1 scores were perfect at 1.0. Furthermore, in the differentiation of LHON from other conditions, ON from others, and between LHON and ON, we consistently observed precision, recall, and F1 scores of 0.8. The model performance was maintained until only 10% of the pixel values of the image, identified as important by Grad-CAM, were preserved and the rest were masked, followed by retraining and evaluation.

Development and validation of an artificial intelligence model for the early classification of the aetiology of meningitis and encephalitis: a retrospective observational study.

Background: Early diagnosis and appropriate treatment are essential in meningitis and encephalitis management. We aimed to implement and verify an artificial intelligence (AI) model for early aetiological determination of patients with encephalitis and meningitis, and identify important variables in the classification process. Methods: In this retrospective observational study, patients older than 18 years old with meningitis or encephalitis at two centres in South Korea were enrolled for development (n = 283) and external validation (n = 220) of AI models, respectively. Their clinical variables within 24 h after admission were used for the multi-classification of four aetiologies including autoimmunity, bacteria, virus, and tuberculosis. The aetiology was determined based on the laboratory test results of cerebrospinal fluid conducted during hospitalization. Model performance was assessed using classification metrics, including the area under the receiver operating characteristic curve (AUROC), recall, precision, accuracy, and F1 score. Comparisons were performed between the AI model and three clinicians with varying neurology experience. Several techniques (eg, Shapley values, F score, permutation feature importance, and local interpretable model-agnostic explanations weights) were used for the explainability of the AI model. Findings: Between January 1, 2006, and June 30, 2021, 283 patients were enrolled in the training/test dataset. An ensemble model with extreme gradient boosting and TabNet showed the best performance among the eight AI models with various settings in the external validation dataset (n = 220); accuracy, 0.8909; precision, 0.8987; recall, 0.8909; F1 score, 0.8948; AUROC, 0.9163. The AI model outperformed all clinicians who achieved a maximum F1 score of 0.7582, by demonstrating a performance of F1 score greater than 0.9264. Interpretation: This is the first multiclass classification study for the early determination of the aetiology of meningitis and encephalitis based on the initial 24-h data using an AI model, which showed high performance metrics. Future studies can improve upon this model by securing and inputting time-series variables and setting various features about patients, and including a survival analysis for prognosis prediction. Funding: MD-PhD/Medical Scientist Training Program through the Korea Health Industry Development Institute, funded by the Ministry of Health & Welfare, Republic of Korea.

A large-scale meta-analytic atlas of mental health problems prevalence during the COVID-19 early pandemic.

The COVID-19 pandemic and related restrictions can impact mental health. To quantify the mental health burden of COVID-19 pandemic, we conducted a systematic review and meta-analysis, searching World Health Organization COVID-19/PsycInfo/PubMed databases (09/29/2020), including observational studies reporting on mental health outcomes in any population affected by COVID-19. Primary outcomes were the prevalence of anxiety, depression, stress, sleep problems, posttraumatic symptoms. Sensitivity analyses were conducted on severe mental health problems, in high-quality studies, and in representative samples. Subgroup analyses were conducted stratified by age, sex, country income level, and COVID-19 infection status. One-hundred-seventy-three studies from February to July 2020 were included (n = 502,261, median sample = 948, age = 34.4 years, females = 63%). Ninety-one percent were cross-sectional studies, and 18.5%/57.2% were of high/moderate quality. The highest prevalence emerged for posttraumatic symptoms in COVID-19 infected people (94%), followed by behavioral problems in those with prior mental disorders (77%), fear in healthcare workers (71%), anxiety in caregivers/family members of people with COVID-19 (42%), general health/social contact/passive coping style in the general population (38%), depression in those with prior somatic disorders (37%), and fear in other-than-healthcare workers (29%). Females and people with COVID-19 infection had higher rates of almost all outcomes; college students/young adults of anxiety, depression, sleep problems, suicidal ideation; adults of fear and posttraumatic symptoms. Anxiety, depression, and posttraumatic symptoms were more prevalent in low-/middle-income countries, sleep problems in high-income countries. The COVID-19 pandemic adversely impacts mental health in a unique manner across population subgroups. Our results inform tailored preventive strategies and interventions to mitigate current, future, and transgenerational adverse mental health of the COVID-19 pandemic.

Multiview child motor development dataset for AI-driven assessment of child development.

BACKGROUND: Children's motor development is a crucial tool for assessing developmental levels, identifying developmental disorders early, and taking appropriate action. Although the Korean Developmental Screening Test for Infants and Children (K-DST) can accurately assess childhood development, its dependence on parental surveys rather than reliable, professional observation limits it. This study constructed a dataset based on a skeleton of recordings of K-DST behaviors in children aged between 20 and 71 months, with and without developmental disorders. The dataset was validated using a child behavior artificial intelligence (AI) learning model to highlight its possibilities. RESULTS: The 339 participating children were divided into 3 groups by age. We collected videos of 4 behaviors by age group from 3 different angles and extracted skeletons from them. The raw data were used to annotate labels for each image, denoting whether each child performed the behavior properly. Behaviors were selected from the K-DST's gross motor section. The number of images collected differed by age group. The original dataset underwent additional processing to improve its quality. Finally, we confirmed that our dataset can be used in the AI model with 93.94%, 87.50%, and 96.31% test accuracy for the 3 age groups in an action recognition model. Additionally, the models trained with data including multiple views showed the best performance. CONCLUSION: Ours is the first publicly available dataset that constitutes skeleton-based action recognition in young children according to the standardized criteria (K-DST). This dataset will enable the development of various models for developmental tests and screenings.