Automated interpretation of systolic and diastolic function on the echocardiogram: a multicohort study.

BACKGROUND: Echocardiography is the diagnostic modality for assessing cardiac systolic and diastolic function to diagnose and manage heart failure. However, manual interpretation of echocardiograms can be time consuming and subject to human error. Therefore, we developed a fully automated deep learning workflow to classify, segment, and annotate two-dimensional (2D) videos and Doppler modalities in echocardiograms. METHODS: We developed the workflow using a training dataset of 1145 echocardiograms and an internal test set of 406 echocardiograms from the prospective heart failure research platform (Asian Network for Translational Research and Cardiovascular Trials; ATTRaCT) in Asia, with previous manual tracings by expert sonographers. We validated the workflow against manual measurements in a curated dataset from Canada (Alberta Heart Failure Etiology and Analysis Research Team; HEART; n=1029 echocardiograms), a real-world dataset from Taiwan (n=31 241), the US-based EchoNet-Dynamic dataset (n=10 030), and in an independent prospective assessment of the Asian (ATTRaCT) and Canadian (Alberta HEART) datasets (n=142) with repeated independent measurements by two expert sonographers. FINDINGS: In the ATTRaCT test set, the automated workflow classified 2D videos and Doppler modalities with accuracies (number of correct predictions divided by the total number of predictions) ranging from 0·91 to 0·99. Segmentations of the left ventricle and left atrium were accurate, with a mean Dice similarity coefficient greater than 93% for all. In the external datasets (n=1029 to 10 030 echocardiograms used as input), automated measurements showed good agreement with locally measured values, with a mean absolute error range of 9-25 mL for left ventricular volumes, 6-10% for left ventricular ejection fraction (LVEF), and 1·8-2·2 for the ratio of the mitral inflow E wave to the tissue Doppler e' wave (E/e' ratio); and reliably classified systolic dysfunction (LVEF <40%, area under the receiver operating characteristic curve [AUC] range 0·90-0·92) and diastolic dysfunction (E/e' ratio ≥13, AUC range 0·91-0·91), with narrow 95% CIs for AUC values. Independent prospective evaluation confirmed less variance of automated compared with human expert measurements, with all individual equivalence coefficients being less than 0 for all measurements. INTERPRETATION: Deep learning algorithms can automatically annotate 2D videos and Doppler modalities with similar accuracy to manual measurements by expert sonographers. Use of an automated workflow might accelerate access, improve quality, and reduce costs in diagnosing and managing heart failure globally. FUNDING: A*STAR Biomedical Research Council and A*STAR Exploit Technologies.

Detecting visually significant cataract using retinal photograph-based deep learning.

Age-related cataracts are the leading cause of visual impairment among older adults. Many significant cases remain undiagnosed or neglected in communities, due to limited availability or accessibility to cataract screening. In the present study, we report the development and validation of a retinal photograph-based, deep-learning algorithm for automated detection of visually significant cataracts, using more than 25,000 images from population-based studies. In the internal test set, the area under the receiver operating characteristic curve (AUROC) was 96.6%. External testing performed across three studies showed AUROCs of 91.6-96.5%. In a separate test set of 186 eyes, we further compared the algorithm's performance with 4 ophthalmologists' evaluations. The algorithm performed comparably, if not being slightly more superior (sensitivity of 93.3% versus 51.7-96.6% by ophthalmologists and specificity of 99.0% versus 90.7-97.9% by ophthalmologists). Our findings show the potential of a retinal photograph-based screening tool for visually significant cataracts among older adults, providing more appropriate referrals to tertiary eye centers.

Variations in longitudinal sleep duration trajectories from infancy to early childhood.

OBJECTIVE: This study investigates variations in night, day, and total sleep trajectories across infancy and childhood in Asian children. PARTICIPANTS: Participants consisted of a subset of 901 children, within the Growing Up in Singapore Towards healthy Outcomes cohort, which recruited 1247 pregnant women between June 2009 and September 2010. DESIGN: We used a novel conditional probabilistic trajectory model: a probabilistic model for mixture distribution, allowing different trajectory curves and model variances among groups to cluster longitudinal observations. Longitudinal sleep duration data for the trajectory analyses were collected from caregiver-reported questionnaires at 3, 6, 9, 12, 18, 24, and 54 months. RESULTS: We found 3 patterns of night sleep trajectories (n = 356): long consistent (31%), moderate consistent (41%), and short variable (28%); and 4 patterns of day sleep trajectories (n = 347): long variable (21%), long consistent (20%), moderate consistent (34%), and short consistent (25%). We also identified 4 patterns of total sleep trajectories (n = 345): long variable (19%), long consistent (26%), moderate consistent (28%), and short variable (27%). Short, moderate, and long trajectories differed significantly in duration. Children with consistent trajectories also displayed sleep patterns that were significantly more representative of typical developmental sleep patterns than children with variable trajectories. CONCLUSIONS: This is the first study to describe multiple sleep trajectories in Singaporean children and identify between-individual variability within the trajectory groups. Compared to predominantly Caucasian samples, night/total sleep trajectories were generally shorter, while day sleep trajectories were longer. Future studies should investigate how these variations are linked to different developmental outcomes.