Objective: To investigate the effect of Janus kinase (JAK) inhibition by baricitinib on erosion repair in rheumatoid arthritis (RA) patients with active disease using high-resolution peripheral quantitative computer tomography (HR-pQCT). Hypothesis: JAK inhibitor can lead to repair of existing erosion in RA patients with active disease. Design and Subjects: This is a 24-week, randomized, placebo-controlled, double-blind study. We plan to enroll 60 adult patients with active RA (disease activity score 28-C-reactive protein [DAS28-CRP] > 3.2) and at least one bone erosion on HR-pQCT. They will be randomized 1:1 to receive JAK inhibitor (baricitinib 4 mg once daily) or placebo for 24 weeks. Medications will be adjusted according to a standard protocol aiming to achieve low disease activity. Biologic or other targeted synthetic disease-modifying antirheumatic drugs are not permitted. Methodology: HR-pQCT of the 2-4 metacarpophalangeal joints will be done at baseline and 24 weeks. Inflammatory cytokine profile and bone–cartilage interface biomarkers will also be checked at baseline and 24 weeks. Clinical response will be monitored using DAS28-CRP. Main Outcome Measures and Analysis: The primary outcome is the proportion of patients with erosion volume regression on HR-pQCT, comparing the two groups by chi-square test. Secondary outcomes include dimensions of erosion, marginal osteosclerosis, and joint space width on HR-pQCT; RA disease activity; and serum biomarkers. The above-mentioned parameters will be compared before and after treatment by Wilcoxon signed-rank, with their changes compared between the two treatment arms using the Mann–Whitney [Formula: see text]test. Independent factors predicting response to JAK inhibitors will be analyzed by multivariate logistic regression.

Purpose: This study aims to develop a method for detecting referable (intermediate and advanced) age-related macular degeneration (AMD) and neovascular AMD, as well as providing an automatic segmentation of choroidal neovascularisation (CNV) on colour fundus retinal images. We also demonstrated that brain health risk scores estimated by AI-based Retinal Image Analysis (ARIA), such as white matter hyperintensities and depression, are significantly associated with AMD and neovascular AMD. Methods: A primary dataset of 1480 retinal images was collected from Zhongshan Hospital of Fudan University for training and 10-fold cross-validation. Additionally, two validation subdataset comprising 238 images (retinal images and wide-field images) were used. Using fluorescein angiography-based labels, we applied the InceptionResNetV2 deep network with the ARIA method to detect AMD, and a transfer ResNet50_Unet was used to segment CNV. The risks of cerebral white matter hyperintensities and depression were estimated using an AI-based Retinal Image Analysis approach. Results: In a 10-fold cross-validation, we achieved sensitivities of 97.4% and 98.1%, specificities of 96.8% and 96.1%, and accuracies of 97.0% and 96.4% in detecting referable AMD and neovascular AMD, respectively. In the external validation, we achieved accuracies of 92.9% and 93.7% and AUCs of 0.967 and 0.967, respectively. The performances on two validation sub-datasets show no statistically significant difference in detecting referable AMD (p = 0.704) and neovascular AMD (p = 0.213). In the segmentation of CNV, we achieved a global accuracy of 93.03%, a mean accuracy of 91.83%, a mean intersection over union (IoU) of 68.7%, a weighted IoU of 89.63%, and a mean boundary F1 (BF) of 67.77%. Conclusions: The proposed method shows promising results as a highly efficient and cost-effective screening tool for detecting neovascular and referable AMD on both retinal and wide-field images, and providing critical insights into CNV. Its implementation could be particularly valuable in resource-limited settings, enabling timely referrals, enhancing patient care, and supporting decision-making across AMD classifications. In addition, we demonstrated that AMD and neovascular AMD are significantly associated with increased risks of WMH and depression.

Background: Rheumatoid arthritis (RA) features joint inflammation and bone erosions that impair function. High-resolution peripheral quantitative computed tomography (HR-pQCT) detects very early erosions not visible using radiography, enabling detailed monitoring of structural change in early RA (ERA). The baseline total erosion score assessed by HR-pQCT at two MCP joints, is known to correlate with the Health Assessment Questionnaire (HAQ) score1. Whether erosive progression/regression detected on HR-pQCT impacts HAQ score at medium-term needs to be assessed. We aimed to determine whether HR-pQCT-detected changes in erosion predict medium-term changes in functional status in ERA patients. Methods: We recruited 101 patients with ERA (symptom duration < 2 years). HR-pQCT scans were obtained at baseline and after 2 years. Erosions were assessed at the second to fourth metacarpophalangeal joints (MCPJ 2-4) of the most affected hand or dominant hand when both hands are equally affected. Repair was defined as either a decrease in erosion counts by [Formula: see text] 1 or a reduction in total erosion volume exceeding least significant change (LSC). Progression was defined as either an increase in erosion counts by [Formula: see text] 1 or an increase in total erosion volume exceeding the LSC. Results: Of the 101 patients at baseline, 78 (77%) were women, with a mean age of 57.2 ± 12.3 years. Disease activity and functional status (assessed by HAQ) improved significantly after 2 years of protocolized treatment. The proportion receiving b/tsDMARDs increased from 0.9% at baseline to 23.8% at month 24 (p<0.001). Paired HR-pQCT analyses at baseline and month 24 were available for 98 patients. Thirty-seven (37.8%) patients had no erosion at both time points. Among the 61 patients who had erosions at either baseline or month 24, 16 (26.2%) achieved partial repair (repair group), while 38 (62.3%) showed progression. In the repair group, change in total erosion volume correlated positively with improvement in HAQ score ([Formula: see text]= 0.719, p = 0.003; Figure 1). This association remained significant after adjusting for change in disease activity (p = 0.009; 95% CI 0.178–1.047). Conclusion: Bone erosion repair detected by HR-pQCT may independently contribute to functional improvement in patients with early RA.

White matter in the brain has a highly anisotropic structure, leading to orientation-dependent MRI contrasts, such as those observed in quantitative magnetization transfer (MT). These orientation-dependent contrasts can complicate the quantification of tissue parameters, posing significant challenges for correction methods. A common physical mechanism underlying this orientation dependence is residual dipolar coupling (RDC), which plays a critical role in the anisotropy observed in MRI spin relaxation. A novel technique, macromolecular proton fraction mapping based on spin-lock (MPF-SL), was recently proposed to achieve orientation-independent MT measurements by minimizing RDC effects during data acquisition. This study aimed to validate the orientation independence of MPF-SL in vivo in brain white matter. Experiments were conducted on 20 healthy volunteers, with data collected at two different head orientations. MRI exams were repeated one week apart. MPF-SL measurements showed negligible differences (<2%) between head orientations, while conventional quantitative MT imaging exhibited statistically significant variation (p < 0.05). Both methods demonstrated good repeatability, with intraclass correlation coefficients (ICC) > 0.75, bias < 0.05%, and limits of agreement < 0.5%. These findings confirm that MPF-SL effectively addresses orientation-dependent limitations in MT measurements of white matter, offering a reliable approach for future clinical and research applications.

Introduction: Neurocognitive impairment from inadvertent brain irradiation is common following intensitymodulated radiotherapy (IMRT) for nasopharyngeal carcinoma (NPC). This study aimed to determine the prevalence, pattern, and radiation dose-toxicity relationship of this late complication. Materials and methods: We undertook a cross-sectional study of 190 post-IMRT NPC survivors. Neurocognitive function was screened using the Montreal Cognitive Assessment-Hong Kong (HK-MoCA). Detailed assessments of eight distinct neurocognitive domains were conducted: intellectual capacity (WAIS-IV), attention span (Digit Span and Visual Spatial Span), visual memory (Visual Reproduction Span), verbal memory (Auditory Verbal Learning Test), processing speed (Color Trail Test), executive function (Stroop Test), motor dexterity (Grooved Pegboard Test) and language ability (Verbal Fluency Test). The mean percentiles and Z-scores were compared with normative population data. Associations between radiation dose and brain substructures were explored using multivariable logistic regression. Results: The median post-IMRT interval was 7.0 years. The prevalence of impaired HK-MoCA was 25.3 % (48/ 190). Among the participants, 151 (79.4 %) exhibited impairments in at least one neurocognitive domain. The predominantly impaired domains included verbal memory (short-term: mean Z-score, -0.56, p < 0.001; longterm: mean Z-score, -0.70, p < 0.001), processing speed (basic: mean Z-score, -1.04, p < 0.001; advanced: mean Z-score, -0.38, p < 0.001), executive function (mean Z-score, -1.90, p < 0.001), and motor dexterity (dominant hand: mean Z-score, -0.97, p < 0.001). Radiation dose to the whole brain, hippocampus, and temporal lobe was associated with impairments in executive function, verbal memory, processing speed, and motor dexterity. Conclusions: Neurocognitive impairment is prevalent and profound in post-IMRT NPC survivors. Cognitive assessment and rehabilitation should be considered part of survivorship care.

Objectives Train an automatic retinal image analysis (ARIA) method to screen glaucomatous optic neuropathy (GON) on non-mydriatic retinal images labelled with the additional results of optical coherence tomography (OCT) and assess different models for the GON classification.Methods All the images were obtained from the hospital for training and 10-fold cross-validation. Two methods were used to improve the classification performance: (1) using images labelled with the additional results of OCT as the reference standard and (2) generating models using retinal features from the entire images, the region of interest (ROI) of the optic disc, and the ROI of the macula, and the combination of all the features.Results Overall, we collected 1338 images with paired OCT scans. In 10-fold validation, ARIA achieved sensitivities of 92.2 %, 92.7% and 85.7%, specificities of 88.8%, 86.7% and 80.2% and accuracies of 90.6%, 89.9% and 83.1% using the retinal features from the entire images, the ROI of the optic disc and the ROI of the macula, respectively. We found the model combining all the features has the best classification performance and obtained a sensitivity of 92.5%, a specificity of 92.1% and an accuracy of 92.4%, which is significantly different from other models (p<0.001).Conclusion We used two methods to improve the classification performance and found the best model to detect glaucoma on colour fundus retinal images. It can become a cost-effective and relatively more accurate glaucoma screening tool than conventional methods.

Background:Stroke is the second leading cause of death worldwide, causing a considerable disease burden. Ischemic stroke is more frequent, but haemorrhagic stroke is responsible for more deaths. The clinical management and treatment are different, and it is advantageous to classify their risk as early as possible for disease prevention. Furthermore, retinal characteristics have been associated with stroke and can be used for stroke risk estimation. This study investigated machine learning approaches to retinal images for risk estimation and classification of ischemic and haemorrhagic stroke.Study design:A case-control study was conducted in the Shenzhen Traditional Chinese Medicine Hospital. According to the computerized tomography scan (CT) or magnetic resonance imaging (MRI) results, stroke patients were classified as either ischemic or hemorrhage stroke. In addition, a control group was formed using non-stroke patients from the hospital and healthy individuals from the community. Baseline demographic and medical information was collected from participants' hospital medical records. Retinal images of both eyes of each participant were taken within 2 weeks of admission. Classification models using a machine-learning approach were developed. A 10-fold cross-validation method was used to validate the results.Results:711 patients were included, with 145 ischemic stroke patients, 86 haemorrhagic stroke patients, and 480 controls. Based on 10-fold cross-validation, the ischemic stroke risk estimation has a sensitivity and a specificity of 91.0% and 94.8%, respectively. The area under the ROC curve for ischemic stroke is 0.929 (95% CI 0.900 to 0.958). The haemorrhagic stroke risk estimation has a sensitivity and a specificity of 93.0% and 97.1%, respectively. The area under the ROC curve is 0.951 (95% CI 0.918 to 0.983).Conclusion:A fast and fully automatic method can be used for stroke subtype risk assessment and classification based on fundus photographs alone.

BackgroundPeople living with HIV (PLWH) have increased risks of non-communicable diseases, especially cardiovascular diseases. Current HIV clinical management guidelines recommend regular cardiovascular risk screening, but the risk equation models are not specific for PLWH. Better tools are needed to assess cardiovascular risk among PLWH accurately.MethodsWe performed a prospective study to determine the performance of automatic retinal image analysis in assessing coronary artery disease (CAD) in PLWH. We enrolled PLWH with ≥1 cardiovascular risk factor. All participants had computerized tomography (CT) coronary angiogram and digital fundus photographs. The primary outcome was coronary atherosclerosis; secondary outcomes included obstructive CAD. In addition, we compared the performances of three models (traditional cardiovascular risk factors alone; retinal characteristics alone; and both traditional and retinal characteristics) by comparing the area under the curve (AUC) of receiver operating characteristic curves.ResultsAmong the 115 participants included in the analyses, with a mean age of 54 years, 89% were male, 95% had undetectable HIV RNA, 45% had hypertension, 40% had diabetes, 45% had dyslipidemia, and 55% had obesity, 71 (61.7%) had coronary atherosclerosis, and 23 (20.0%) had obstructive CAD. The machine-learning models, including retinal characteristics with and without traditional cardiovascular risk factors, had AUC of 0.987 and 0.979, respectively and had significantly better performance than the model including traditional cardiovascular risk factors alone (AUC 0.746) in assessing coronary artery disease atherosclerosis. The sensitivity and specificity for risk of coronary atherosclerosis in the combined model were 93.0% and 93.2%, respectively. For the assessment of obstructive CAD, models using retinal characteristics alone (AUC 0.986) or in combination with traditional risk factors (AUC 0.991) performed significantly better than traditional risk factors alone (AUC 0.777). The sensitivity and specificity for risk of obstructive CAD in the combined model were 95.7% and 97.8%, respectively.ConclusionIn this cohort of Asian PLWH at risk of cardiovascular diseases, retinal characteristics, either alone or combined with traditional risk factors, had superior performance in assessing coronary atherosclerosis and obstructive CAD.SummaryPeople living with HIV in an Asian cohort with risk factors for cardiovascular disease had a high prevalence of coronary artery disease (CAD). A machine-learning-based retinal image analysis could increase the accuracy in assessing the risk of coronary atherosclerosis and obstructive CAD.

Background:Osteoarthritis (OA) is a global healthcare problem. The increasing population of OA patients demands a greater bandwidth of imaging and diagnostics. It is important to provide automatic and objective diagnostic techniques to address this challenge. This study demonstrates the utility of unsupervised domain adaptation (UDA) for automated OA phenotype classification.Methods:We collected 318 and 960 three-dimensional double-echo steady-state magnetic resonance images from the Osteoarthritis Initiative (OAI) dataset as the source dataset for phenotype cartilage/meniscus and subchondral bone, respectively. Fifty three-dimensional turbo spin echo (TSE)/fast spin echo (FSE) MR images from our institute were collected as the target datasets. For each patient, the degree of knee OA was initially graded according to the MRI Knee Osteoarthritis Knee Score before being converted to binary OA phenotype labels. The proposed four-step UDA pipeline included (I) pre-processing, which involved automatic segmentation and region-of-interest cropping; (II) source classifier training, which involved pre-training a convolutional neural network (CNN) encoder for phenotype classification using the source dataset; (III) target encoder adaptation, which involved unsupervised adjustment of the source encoder to the target encoder using both the source and target datasets; and (IV) target classifier validation, which involved statistical analysis of the classification performance evaluated by the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity and accuracy. We compared our model on the target data with the source pre-trained model and the model trained with the target data from scratch.Results:For phenotype cartilage/meniscus, our model has the best performance out of the three models, giving 0.90 [95% confidence interval (CI): 0.79-1.02] of the AUROC score, while the other two model show 0.52 (95% CI: 0.13-0.90) and 0.76 (95% CI: 0.53-0.98). For phenotype subchondral bone, our model gave 0.75 (95% CI: 0.56-0.94) at AUROC, which has a close performance of the source pre-trained model (0.76, 95% CI: 0.55-0.98), and better than the model trained from scratch on the target dataset only (0.53, 95% CI: 0.33-0.73).Conclusions:By utilising a large, high-quality source dataset for training, the proposed UDA approach enhances the performance of automated OA phenotype classification for small target datasets. As a result, our technique enables improved downstream analysis of locally collected datasets with a small sample size.

This study evaluates if there is an association between lifestyle changes and the risk of small vessel disease (SVD) as measured by cerebral white matter hyperintensities (WMH) estimated by the automatic retinal image analysis (ARIA) method. We recruited 274 individuals into a community cohort study. Subjects were assessed at baseline and annually with the Health-Promoting Lifestyle Profile II Questionnaire (HPLP-II) and underwent a simple physical assessment. Retinal images were taken using a non-mydriatic digital fundus camera to evaluate the level of WMH estimated by ARIA (ARIA-WMH) to measure the risk of small vessel disease. We calculated the changes from baseline to one year for the six domains of HPLP-II and analysed the relationship with the ARIA-WMH change. A total of 193 (70%) participants completed both the HPLP-II and ARIA-WMH assessments. The mean age was 59.1 ± 9.4 years, and 76.2% (147) were women. HPLP-II was moderate (Baseline, 138.96 ± 20.93; One-year, 141.97 ± 21.85). We observed a significant difference in ARIA-WMH change between diabetes and non-diabetes subjects (0.03 vs. −0.008, respectively, p = 0.03). A multivariate analysis model showed a significant interaction between the health responsibility (HR) domain and diabetes (p = 0.005). For non-diabetes subgroups, those with improvement in the HR domain had significantly decreased in ARIA-WMH than those without HR improvement (−0.04 vs. 0.02, respectively, p = 0.003). The physical activity domain was negatively related to the change in ARIA-WMH (p = 0.02). In conclusion, this study confirms that there is a significant association between lifestyle changes and ARIA-WMH. Furthermore, increasing health responsibility for non-diabetes subjects reduces the risk of having severe white matter hyperintensities.

Image quality assessment is essential for retinopathy detection on color fundus retinal image. However, most studies focused on the classification of good and poor quality without considering the different types of poor quality. This study developed an automatic retinal image analysis (ARIA) method, incorporating transfer net ResNet50 deep network with the automatic features generation approach to automatically assess image quality, and distinguish eye-abnormality-associated-poor-quality from artefact-associated-poor-quality on color fundus retinal images. A total of 2434 retinal images, including 1439 good quality and 995 poor quality (483 eye-abnormality-associated-poor-quality and 512 artefact-associated-poor-quality), were used for training, testing, and 10-ford cross-validation. We also analyzed the external validation with the clinical diagnosis of eye abnormality as the reference standard to evaluate the performance of the method. The sensitivity, specificity, and accuracy for testing good quality against poor quality were 98.0%, 99.1%, and 98.6%, and for differentiating between eye-abnormality-associated-poor-quality and artefact-associated-poor-quality were 92.2%, 93.8%, and 93.0%, respectively. In external validation, our method achieved an area under the ROC curve of 0.997 for the overall quality classification and 0.915 for the classification of two types of poor quality. The proposed approach, ARIA, showed good performance in testing, 10-fold cross validation and external validation. This study provides a novel angle for image quality screening based on the different poor quality types and corresponding dealing methods. It suggested that the ARIA can be used as a screening tool in the preliminary stage of retinopathy grading by telemedicine or artificial intelligence analysis.

Introduction Undiagnosed diabetes is a global health issue. Previous studies have estimated that about 24.1%–75.1% of all diabetes cases are undiagnosed, leading to more diabetic complications and inducing huge healthcare costs. Many current methods for diabetes diagnosis rely on metabolic indices and are subject to considerable variability. In contrast, a digital approach based on retinal image represents a stable marker of overall glycemic status.Research design and methods Our study involves 2221 subjects for developing a classification model, with 945 subjects with diabetes and 1276 controls. The training data included 70% and the testing data 30% of the subjects. All subjects had their retinal images taken using a non-mydriatic fundus camera. Two separate data sets were used for external validation. The Hong Kong testing data contain 734 controls without diabetes and 660 subjects with diabetes, and the UK testing data have 1682 subjects with diabetes.Results The 10-fold cross-validation using the support vector machine approach has a sensitivity of 92% and a specificity of 96.2%. The separate testing data from Hong Kong provided a sensitivity of 99.5% and a specificity of 91.1%. For the UK testing data, the sensitivity is 98.0%. The accuracy of the Caucasian retinal images is comparable with that of the Asian data. It implies that the digital method can be applied globally. Those with diabetes complications in both Hong Kong and UK data have a higher probability of risk of diabetes compared with diabetes subjects without complications.Conclusions A digital machine learning-based method to estimate the risk of diabetes based on retinal images has been developed and validated using both Asian and Caucasian data. Retinal image analysis is a fast, convenient, and non-invasive technique for community health applications. In addition, it is an ideal solution for undiagnosed diabetes prescreening.

Post-radiation neurocognitive decline is a debilitating late complication after (chemo-)radiotherapy for nasopharyngeal cancer (NPC). Radiation dose correlates poorly with neurocognitive outcomes. This study explored the association between retinal vessel characteristics with neurocognitive outcomes in NPC survivors using an artificial intelligence-based analytic platform. This cross-sectional study recruited 180 NPC survivors in a tertiary oncology center. Comprehensive neurocognitive assessments were performed on 8 principal domains. Results were presented as z-scores normalized to population references. Retinal images were captured by a non-mydriatic fundus camera. Vascular characteristics were analyzed by a machine learning approach using fractal analysis, high order spectra analysis, and statistical texture analysis. Results were outputted as a continuous risk score (ARIA-WMH Score) ranging from 0 to 1, with cutoffs of >0.4 and >0.6 refer to moderate and high risk of severe white matter hyperintensities from cerebral magnetic resonance imaging, respectively. The median time from radiotherapy was 7.0 years. Significant impairments were observed in verbal memory (mean z-score -0.43), executive function (mean z-score -1.71), processing speed (mean z-score -0.73), motor dexterity (mean z-score -0.88) and language fluency (mean z-score -0.28). Upon analysis of the retinal vessels characteristics by ARIA-WMH, 11.7% (21/180) and 48.9% (88/180) of the patients scored >0.6 and >0.4, respectively. Patients with ARIA-WMH Score >0.6 had more severe verbal memory impairment than patients who scored ≤0.6 (mean z-score, -1.04 vs -0.35, p=0.0035). Similar findings were observed if lower cutoff of 0.4 was used (mean z-score, -0.60 vs -0.26, p=0.029). The severity of ARIA-WMH was associated with the level of verbal memory impairment. Neurocognitive impairment is prevalent after radiotherapy for NPC. Retinal image analysis may offer a quick and non-invasive tool to identify patients with impairment in verbal memory for formal assessments or interventions. Further studies that incorporate radiation dosimetry information are warranted.

Purpose: Quantitative T-1 rho imaging is an emerging technique to assess the biochemical properties of tissues. In this paper, we report our observation that liver iron content (LIC) affects T-1 rho quantification of the liver at 3.0T field strength and develop a method to correct the effect of LIC. Theory and Methods: On-resonance R-1 rho (1/T-1 rho) is mainly affected by the intrinsic R-2 (1/T-2), which is influenced by LIC. As on-resonance R-1 rho is closely related to the Carr-Purcell-Meiboom-Gill (CPMG) R-2, and because the calibration between CPMG R-2 and LIC has been reported at 1.5T, a correction method was proposed to correct the R-2 contribution to the R-1 rho. The correction coefficient was obtained from the calibration results and related transformed factors. To compensate for the difference between CPMG R-2 and R-1 rho, a scaling factor was determined using the values of CPMG R-2 and R-1 rho, obtained simultaneously from a single breath-hold from volunteers. The livers of 110 subjects were scanned to validate the correction method. Results: LIC was significantly correlated with R-1 rho in the liver. However, when the proposed correction method was applied to R-1 rho, LIC and the iron-corrected R-1 rho were not significantly correlated. Conclusion: LIC can affect T(1 rho )in the liver. We developed an iron-correction method for the quantification of T-1 rho in the liver at 3.0T.

Retinal vessels are known to be associated with various cardiovascular and cerebrovascular disease outcomes. Recent research has shown significant correlations between retinal characteristics and the presence of cerebral small vessel disease as measured by white matter hyperintensities from cerebral magnetic resonance imaging. Early detection of age-related white matter changes using retinal images is potentially helpful for population screening and allow early behavioural and lifestyle intervention. This study investigates the ability of the machine-learning method for the localization of brain white matter hyperintensities. All subjects were age 65 or above without any history of stroke and dementia and recruited from local community centres and community networks. Subjects with known retinal disease or disease influencing vessel structure in colour retina images were excluded. All subjects received MRI on the brain, and age-related white matter changes grading was determined from MRI as the primary endpoint. The presence of age-related white matter changes on each of the six brain regions was also studied. Retinal images were captured using a fundus camera, and the analysis was done based on a machine-learning approach. A total of 240 subjects are included in the study. The analysis of various brain regions included the left and right sides of frontal lobes, parietal-occipital lobes and basal ganglia. Our results suggested that data from both eyes are essential for detecting age-related white matter changes in the brain regions, but the retinal parameters useful for estimation of the probability of age-related white matter changes in each of the brain regions may differ for different locations. Using a classification and regression tree approach, we also found that at least three significant heterogeneous subgroups of subjects were identified to be essential for the localization of age-related white matter changes. Namely those with age-related white matter changes in the right frontal lobe, those without age-related white matter changes in the right frontal lobe but with age-related white matter changes in the left parietal-occipital lobe, and the rest of the subjects. Outcomes such as risks of severe grading of age-related white matter changes and the proportion of hypertension were significantly related to these subgroups. Our study showed that automatic retinal image analysis is a convenient and non-invasive screening tool for detecting age-related white matter changes and cerebral small vessel disease with good overall performance. The localization analysis for various brain regions shows that the classification models on each of the six brain regions can be done, and it opens up potential future clinical application.

To estimate National Institutes of Health Stroke Scale (NIHSS) grading of stroke patients with retinal characteristics. A cross-sectional study was conducted in Shenzhen Traditional Chinese Medicine Hospital. Baseline information and retinal photos were collected within 2 weeks of admission. An NIHSS score was measured for each patient by trained doctors. Patients were classified into 0 to 4 score group and 5 to 42 score group for analysis. Three multivariate logistic models, with traditional clinical characteristics alone, with retinal characteristics alone, and with both, were built. For clinical characteristics, hypertension duration is statistically significantly associated with higher NIHSS score (P = .014). Elevated total homocysteine levels had an OR of 0.456 (P = .029). For retinal characteristics, the fractal dimension of the arteriolar network had an OR of 0.245 (P < .001) for the left eyes, and an OR of 0.417 (P = .009) for right eyes. The bifurcation coefficient of the arteriole of the left eyes had an OR of 2.931 (95% CI 1.573-5.46, P = .001), the nipping of the right eyes had an OR of 0.092 (P = .003) showed statistical significance in the model. The area under receiver-operating characteristic curve increased from 0.673, based on the model with clinical characteristics alone, to 0.896 for the model with retinal characteristics alone and increased to 0.931 for the model with both clinical and retinal characteristics combined. Retinal characteristics provided more information than clinical characteristics in estimating NIHSS grading and can provide us with an objective method for stroke severity estimation.

Purpose To establish a prediction model for stroke side identification.Methods A total of 168 patients (89 left-sided stroke patients and 79 right-sided stroke patients) were recruited from the Shenzhen Traditional Chinese Medicine Hospital in the study. Retinal characteristics were analyzed using an automated retinal image analysis (ARIA) system. Multivariable logistic regression was used to identify and develop predictive models. Results Each unit increase in the right eye bifurcation coefficient of arterioles increased the risk of right-side stroke by 7.523 times (95% CI, 1.823-31.044). Additionally, an elevated bifurcation coefficient of venules in the right eye also increased the risk of stroke in the right side of the brain, with an odds ratio (OR) of 7.377 (95% CI, 1.771-30.724). A complex retinal composite score was also associated with a higher risk of right-side stroke (OR, 4.955; 95% CI, 3.061-8.022). Conclusion This study demonstrated that retinal image analysis can provide useful information for stroke side identification and the specific retinal characteristics may help in predicting stroke occurrence.

Background Recent surveys revealed that the health status of many people from Hong Kong is far from ideal. Although non-communicable diseases are largely preventable, few relevant health promotion and disease prevention programs are available. Thus, we assessed the health indicators of Chinese adults in Hong Kong to investigate the relationship between obesity, common chronic diseases, and health-promoting lifestyle profiles to provide inspirations for decision makers in formulating targeted disease prevention and health management programs. Methods This is a secondary analysis of a data set of 270 community-dwelling Hong Kong adults who were within the eligible age range between 18 and 80 years without eye diseases that affect retinal photographs. The study exposure variable, health-promoting lifestyle profiles, was measured using the Health-Promoting Lifestyle Profile II (HPLP-II) questionnaire. The primary outcome variable, obesity, was defined using body mass index and waist-hip ratio. The secondary study outcome, estimated chronic diseases, including of anemia, chronic kidney disease, and cardiovascular disease, were estimated using automatic retinal image analysis from the retinal images. Data were analyzed using tests of proportion, the independent sample t-tests, Welch’s t-test, and binary logistic regression models. Results All HPLP-II subscales had positive responses (≥ 2.5). Significant differences were noted between men and women in the health responsibility and nutrition subscales (Health Responsibility: p = 0.059; Nutrition: p = 0.067). Regression models revealed that nutrition (adjusted odds ratio [AOR] = 0.41; p = 0.017), physical activity (AOR = 0.50; p = 0.015), interpersonal relations (AOR = 2.14; p = 0.016), and stress management (AOR = 2.07; p 0.038) were associated with obesity; while spiritual growth (AOR = 0.24; p = 0.077) and interpersonal relations (AOR = 5.06; p 0.069) were associated with estimated chronic kidney disease. Conclusions Improving health behaviors may control or alleviate the prevalence of obesity and chronic kidney disease. These findings could arouse concern about lifestyle behaviors and promote self-assessment of health-promoting lifestyles to the general public. The study also provided new insights into the relationship between the HPLP-II and other common chronic diseases that warrant further study.

To identify the clinical risk factors and investigate the efficacy of a classification model based on the identified factors for predicting 2-year recurrence after ischemic stroke. From June 2017 to January 2019, 358 patients with first-ever ischemic stroke were enrolled and followed up in Shenzhen Traditional Chinese Medicine Hospital. Demographic and clinical characteristics were recorded by trained medical staff. The outcome was defined as recurrence within 2 years. A multivariate logistic regression model with risk factors and their interaction effects was established and evaluated. The mean (standard deviation) age of the participants was 61.6 (12.1) years, and 101 (28.2%) of the 358 patients were female. The common comorbidities included hypertension (286 patients, 79.9%), diabetes (148 patients, 41.3%), and hyperlipidemia (149 patients, 41.6%). The 2-year recurrence rate was 30.7%. Of the 23 potential risk factors, 10 were significantly different between recurrent and non-recurrent subjects in the univariate analysis. A multivariate logistic regression model was developed based on 10 risk factors. The significant variables include diabetes mellitus, smoking status, peripheral artery disease, hypercoagulable state, depression, 24 h minimum systolic blood pressure, 24 h maximum diastolic blood pressure, age, family history of stroke, NIHSS score status. The area under the receiver operating characteristic curve (ROC) was 0.78 (95% confidence interval: 0.726-0.829) with a sensitivity of 0.61 and a specificity of 0.81, indicating a potential predictive ability. Ten risk factors were identified, and an effective classification model was built. This may aid clinicians in identifying high-risk patients who would benefit most from intensive follow-up and aggressive risk factor reduction.