Age and sex affect deep learning prediction of cardiometabolic risk factors from retinal images.
ABSTRACT: Deep neural networks can extract clinical information, such as diabetic retinopathy status and individual characteristics (e.g. age and sex), from retinal images. Here, we report the first study to train deep learning models with retinal images from 3,000 Qatari citizens participating in the Qatar Biobank study. We investigated whether fundus images can predict cardiometabolic risk factors, such as age, sex, blood pressure, smoking status, glycaemic status, total lipid panel, sex steroid hormones and bioimpedance measurements. Additionally, the role of age and sex as mediating factors when predicting cardiometabolic risk factors from fundus images was studied. Predictions at person-level were made by combining information of an optic disc centred and a macula centred image of both eyes with deep learning models using the MobileNet-V2 architecture. An accurate prediction was obtained for age (mean absolute error (MAE): 2.78 years) and sex (area under the curve: 0.97), while an acceptable performance was achieved for systolic blood pressure (MAE: 8.96?mmHg), diastolic blood pressure (MAE: 6.84?mmHg), Haemoglobin A1c (MAE: 0.61%), relative fat mass (MAE: 5.68 units) and testosterone (MAE: 3.76 nmol/L). We discovered that age and sex were mediating factors when predicting cardiometabolic risk factors from fundus images. We have found that deep learning models indirectly predict sex when trained for testosterone. For blood pressure, Haemoglobin A1c and relative fat mass an influence of age and sex was observed. However, achieved performance cannot be fully explained by the influence of age and sex. In conclusion we confirm that age and sex can be predicted reliably from a fundus image and that unique information is stored in the retina that relates to blood pressure, Haemoglobin A1c and relative fat mass. Future research should focus on stratification when predicting person characteristics from a fundus image.
Project description:Associations between sleep disordered breathing (SDB) and cardiometabolic outcomes have not been examined in highlanders.We performed nocturnal polygraphy in Peruvian highlanders (3825?m). Multivariable linear regression models examined associations between SDB metrics and haemoglobin, glucose tolerance (haemoglobin A1c (HbA1c)), fasting glucose, homeostatic model-based assessments of insulin resistance and ?-cell function (HOMA-IR and HOMA-?, respectively), blood pressure, and lipids, while adjusting for age, sex, body mass index (BMI) and wake oxygenation.Participants (n=187; 91 men) were (median (interquartile range)) 52 (45-62) years old, and had a BMI of 27.0 (24.3-29.5) kg·m-2 and 87% (85-88%) oxyhaemoglobin (arterial oxygen) saturation during wakefulness. In fully adjusted models, worsening nocturnal hypoxaemia was associated with haemoglobin elevations in men (p=0.03), independent of wake oxygenation and apnoea-hypopnoea index (AHI), whereas worsening wake oxygenation was associated with haemoglobin elevations in older women (p=0.02). In contrast, AHI was independently associated with HbA1c elevations (p<0.05). In single-variable models, nocturnal hypoxaemia was associated with higher HbA1c, HOMA-IR and HOMA-? (p<0.001, p=0.02 and p=0.04, respectively), whereas AHI was associated with HOMA-IR, systolic blood pressure and triglyceride elevations (p=0.02, p=0.01 and p<0.01, respectively). These associations were not significant in fully adjusted models.In highlanders, nocturnal hypoxaemia and sleep apnoea were associated with distinct cardiometabolic outcomes, conferring differential risk for excessive erythrocytosis and glucose intolerance, respectively.
Project description:BACKGROUND:Retinal imaging has been applied for detecting eye diseases and cardiovascular risks using deep learning-based methods. Furthermore, retinal microvascular and structural changes were found in renal function impairments. However, a deep learning-based method using retinal images for detecting early renal function impairment has not yet been well studied. OBJECTIVE:This study aimed to develop and evaluate a deep learning model for detecting early renal function impairment using retinal fundus images. METHODS:This retrospective study enrolled patients who underwent renal function tests with color fundus images captured at any time between January 1, 2001, and August 31, 2019. A deep learning model was constructed to detect impaired renal function from the images. Early renal function impairment was defined as estimated glomerular filtration rate <90 mL/min/1.73 m2. Model performance was evaluated with respect to the receiver operating characteristic curve and area under the curve (AUC). RESULTS:In total, 25,706 retinal fundus images were obtained from 6212 patients for the study period. The images were divided at an 8:1:1 ratio. The training, validation, and testing data sets respectively contained 20,787, 2189, and 2730 images from 4970, 621, and 621 patients. There were 10,686 and 15,020 images determined to indicate normal and impaired renal function, respectively. The AUC of the model was 0.81 in the overall population. In subgroups stratified by serum hemoglobin A1c (HbA1c) level, the AUCs were 0.81, 0.84, 0.85, and 0.87 for the HbA1c levels of ?6.5%, >6.5%, >7.5%, and >10%, respectively. CONCLUSIONS:The deep learning model in this study enables the detection of early renal function impairment using retinal fundus images. The model was more accurate for patients with elevated serum HbA1c levels.
Project description:Studies examining the effects of consumption of diets low in advanced glycation end products (AGEs) on cardiometabolic parameters are conflicting. Hence, we performed a meta-analysis to determine the effect of low AGE diets in reducing cardiometabolic risk factors. Seventeen randomised controlled trials comprising 560 participants were included. Meta-analyses using random effects models were used to analyse the data. Low AGE diets decreased insulin resistance (mean difference [MD] -1.3, 95% CI -2.3, -0.2), total cholesterol (MD -8.5 mg/dl, 95% CI -9.5, -7.4) and low-density lipoprotein (MD -2.4 mg/dl, 95% CI -3.4, -1.3). There were no changes in weight, fasting glucose, 2-h glucose and insulin, haemoglobin A1c, high-density lipoprotein or blood pressure. In a subgroup of patients with type 2 diabetes, a decrease in fasting insulin (MD -7 µU/ml, 95% CI -11.5, -2.5) was observed. Tumour necrosis factor α, vascular cell adhesion molecule-1, 8-isoprostane, leptin, circulating AGEs and receptor for AGEs were reduced after consumption of low AGE diets with