Search

Abstract Diabetic retinopathy (DR) is the most prevalent cause of preventable vision loss worldwide, imposing a significant economic and medical burden on society today, of which early identification is the cornerstones of the management. The diagnosis and severity grading of DR rely on scales based on clinical visualized features, but lack detailed quantitative parameters. Retinal non-perfusion area (NPA) is a pathogenic characteristic of DR that symbolizes retinal hypoxia conditions, and was found to be intimately associated with disease progression, prognosis, and management. However, the practical value of NPA is constrained since it appears on fundus fluorescein angiography (FFA) as distributed, irregularly shaped, darker plaques that are challenging to measure manually. In this study, we propose a deep learning-based method, NPA-Net, for accurate and automatic segmentation of NPAs from FFA images acquired in clinical practice. NPA-Net uses the U-net structure as the basic backbone, which has an encoder-decoder model structure. To enhance the recognition performance of the model for NPA, we adaptively incorporate multi-scale features and contextual information in feature learning and design three modules: Adaptive Encoder Feature Fusion (AEFF) module, Multilayer Deep Supervised Loss, and Atrous Spatial Pyramid Pooling (ASPP) module, which enhance the recognition ability of the model for NPAs of different sizes from different perspectives. We conducted extensive experiments on a clinical dataset with 163 eyes with NPAs manually annotated by ophthalmologists, and NPA-Net achieved better segmentation performance compared to other existing methods with an area under the receiver operating characteristic curve (AUC) of 0.9752, accuracy of 0.9431, sensitivity of 0.8794, specificity of 0.9459, IOU of 0.3876 and Dice of 0.5686. This new automatic segmentation model is useful for identifying NPA in clinical practice, generating quantitative parameters that can be useful for further research as well as guiding DR detection, grading severity, treatment planning, and prognosis.

Abstract The question of whether artificial intelligence (AI) can surpass human capabilities is crucial in the application of AI in clinical medicine. To explore this, an interpretable deep learning (DL) model was developed to assess myopia status using retinal refraction maps obtained with a novel peripheral refractor. The DL model demonstrated promising performance, achieving an AUC of 0.9074 (95% CI 0.83–0.97), an accuracy of 0.8140 (95% CI 0.70–0.93), a sensitivity of 0.7500 (95% CI 0.51–0.90), and a specificity of 0.8519 (95% CI 0.68–0.94). Grad-CAM analysis provided interpretable visualization of the attention of DL model and revealed that the DL model utilized information from the central retina, similar to human readers. Additionally, the model considered information from vertical regions across the central retina, which human readers had overlooked. This finding suggests that AI can indeed surpass human capabilities, bolstering our confidence in the use of AI in clinical practice, especially in new scenarios where prior human knowledge is limited.

Abstract Background It is uncertain whether the weekend warrior pattern is associated with all-cause mortality among adults living with type 2 diabetes. This study explored how the ‘weekend warrior’ physical activity (PA) pattern was associated with all-cause mortality among adults living with type 2 diabetes. Methods This prospective cohort study investigated US adults living with type 2 diabetes in the National Health and Nutrition Examination Survey (NHANES). Mortality data was linked to the National Death Index. Based on self-reported leisure-time and occupational moderate-to-vigorous PA (MVPA), participants were categorized into 3 groups: physically inactive (

Abstract Background Sexually transmitted infections (STIs) pose a significant global public health challenge. Early diagnosis and treatment reduce STI transmission, but rely on recognising symptoms and care-seeking behaviour of the individual. Digital health software that distinguishes STI skin conditions could improve health-seeking behaviour. We developed and evaluated a deep learning model to differentiate STIs from non-STIs based on clinical images and symptoms. Methods We used 4913 clinical images of genital lesions and metadata from the Melbourne Sexual Health Centre collected during 2010–2023. We developed two binary classification models to distinguish STIs from non-STIs: (1) a convolutional neural network (CNN) using images only and (2) an integrated model combining both CNN and fully connected neural network (FCN) using images and metadata. We evaluated the model performance by the area under the ROC curve (AUC) and assessed metadata contributions to the Image-only model. Results Our study included 1583 STI and 3330 non-STI images. Common STI diagnoses were syphilis (34.6%), genital warts (24.5%) and herpes (19.4%), while most non-STIs (80.3%) were conditions such as dermatitis, lichen sclerosis and balanitis. In both STI and non-STI groups, the most frequently observed groups were 25–34 years (48.6% and 38.2%, respectively) and heterosexual males (60.3% and 45.9%, respectively). The Image-only model showed a reasonable performance with an AUC of 0.859 (SD 0.013). The Image + Metadata model achieved a significantly higher AUC of 0.893 (SD 0.018) compared to the Image-only model (p

Summary: Intraocular pressure (IOP) is closely correlated with blood pressure (BP), and while BP has been linked to brain volumes, the effect of IOP on brain volumes remains unclear. This study analyzed participants from the UK Biobank with MRI-measured brain volumes. Observational analyses included 8,634 participants for IOP and 36,069 for BP, followed by Mendelian randomization (MR) analyses of 37,410 participants. Observational analyses revealed that each 10-mmHg increase in diastolic BP was linked to a 0.13 mL larger white matter hyperintensity (WMH) after adjusting for covariates. Associations between IOP and brain volumes were more pronounced in younger individuals or those without hypertension. MR analyses confirmed significant relationships between diastolic BP and WMH, and each 5-mmHg increase in IOP reduced gray matter volumes by 3.24 mL. The study suggests that targeting IOP and BP could help prevent brain volume reduction.

BackgroundThe 2022 global outbreak of mpox has significantly impacted health facilities, and necessitated additional infection prevention and control measures and alterations to clinic processes. Early identification of suspected mpox cases will assist in mitigating these impacts. ObjectiveWe aimed to develop and evaluate an artificial intelligence (AI)–based tool to differentiate mpox lesion images from other skin lesions seen in a sexual health clinic. MethodsWe used a data set with 2200 images, that included mpox and non-mpox lesions images, collected from Melbourne Sexual Health Centre and web resources. We adopted deep learning approaches which involved 6 different deep learning architectures to train our AI models. We subsequently evaluated the performance of each model using a hold-out data set and an external validation data set to determine the optimal model for differentiating between mpox and non-mpox lesions. ResultsThe DenseNet-121 model outperformed other models with an overall area under the receiver operating characteristic curve (AUC) of 0.928, an accuracy of 0.848, a precision of 0.942, a recall of 0.742, and an F1-score of 0.834. Implementation of a region of interest approach significantly improved the performance of all models, with the AUC for the DenseNet-121 model increasing to 0.982. This approach resulted in an increase in the correct classification of mpox images from 79% (55/70) to 94% (66/70). The effectiveness of this approach was further validated by a visual analysis with gradient-weighted class activation mapping, demonstrating a reduction in false detection within the background of lesion images. On the external validation data set, ResNet-18 and DenseNet-121 achieved the highest performance. ResNet-18 achieved an AUC of 0.990 and an accuracy of 0.947, and DenseNet-121 achieved an AUC of 0.982 and an accuracy of 0.926. ConclusionsOur study demonstrated it was possible to use an AI-based image recognition algorithm to accurately differentiate between mpox and common skin lesions. Our findings provide a foundation for future investigations aimed at refining the algorithm and establishing the place of such technology in a sexual health clinic.

Abstract Background Little is known regarding the leading risk factors for dementia/Alzheimer’s disease (AD) in individuals with and without APOE4. The identification of key risk factors for dementia/Alzheimer’s disease (AD) in individuals with and without the APOE4 gene is of significant importance in global health. Methods Our analysis included 110,354 APOE4 carriers and 220,708 age- and sex-matched controls aged 40–73 years at baseline (between 2006–2010) from UK Biobank. Incident dementia was ascertained using hospital inpatient, or death records until January 2021. Individuals of non-European ancestry were excluded. Furthermore, individuals without medical record linkage were excluded from the analysis. Moderation analysis was tested for 134 individual factors. Results During a median follow-up of 11.9 years, 4,764 cases of incident all-cause dementia and 2065 incident AD cases were documented. Hazard ratios (95% CIs) for all-cause dementia and AD associated with APOE4 were 2.70(2.55–2.85) and 3.72(3.40–4.07), respectively. In APOE4 carriers, the leading risk factors for all-cause dementia included low self-rated overall health, low household income, high multimorbidity risk score, long-term illness, high neutrophil percentage, and high nitrogen dioxide air pollution. In non-APOE4 carriers, the leading risk factors included high multimorbidity risk score, low overall self-rated health, low household income, long-term illness, high microalbumin in urine, high neutrophil count, and low greenspace percentage. Population attributable risk for these individual risk factors combined was 65.1%, and 85.8% in APOE4 and non-APOE4 carriers, respectively. For 20 risk factors including multimorbidity risk score, unhealthy lifestyle habits, and particulate matter air pollutants, their associations with incident dementia were stronger in non-APOE4 carriers. For only 2 risk factors (mother’s history of dementia, low C-reactive protein), their associations with incident all-cause dementia were stronger in APOE4 carriers. Conclusions Our findings provide evidence for personalized preventative approaches to dementia/AD in APOE4 and non-APOE4 carriers. A mother’s history of dementia and low levels of C-reactive protein were more important risk factors of dementia in APOE4 carriers whereas leading risk factors including unhealthy lifestyle habits, multimorbidity risk score, inflammation and immune-related markers were more predictive of dementia in non-APOE4 carriers.

Visual recognition with deep learning has recently been shown to be effective in robotic vision. However, these algorithms tend to be build under fixed and structured environment, which is rarely the case in real life. When facing unknown objects, avoidance or human interactions are required, which may miss critical objects or be prohibitively costly to obtain on robots in the real world. We consider a practical problem setting that aims to allow robots to automatically discover novel classes with only labelled known class samples in hand, defined as open-set clustering (OSC). To address the OSC problem, we propose a framework combining three approaches: 1) using selfsupervised vision transformers to mitigate the discard of information needed for clustering unknown classes; 2) adaptive weighting for image patches to prioritize patches with richer textures; and 3) incorporating a temperature scaling strategy to generate more separable feature embeddings for clustering. We demonstrate the efficacy of our approach in six fine-grained image datasets.

Abstract It is unclear regarding associations of dietary patterns with a wide range of chronic diseases and which dietary score is more predictive of major chronic diseases. Using the UK Biobank, we examine associations of four individual healthy dietary scores with the risk of 48 individual chronic diseases. Higher Alternate Mediterranean Diet score is associated with a lower risk of 32 (all 8 cardiometabolic disorders, 3 out of 10 types of cancers, 7 out of 10 psychological/neurological disorders, 5 out of 6 digestive disorders, and 9 out of 14 other chronic diseases). Alternate Healthy Eating Index-2010 and Healthful Plant-based Diet Index are inversely associated with the risk of 29 and 23 individual chronic diseases, respectively. A higher Anti-Empirical Dietary Inflammatory Index is associated with a lower risk of 14 individual chronic diseases and a higher incidence of two diseases. Our findings support dietary guidelines for the prevention of most chronic diseases.

Abstract Background Screening for hyperthyroidism using gold-standard diagnostic criteria in the general population is not cost-effective, leading to a relatively high rate of undiagnosed and untreated patients. This study aimed to establish a deep learning-based system to detect hyperthyroidism based on retinal photographs. Methods The multicenter, observational study included retinal photographs taken from participants in two hospitals and 24 health care centers throughout China. We first trained two models to identify hyperthyroidism: in model #1, the non-hyperthyroidism individuals were randomly selected, while in model #2, the non-hyperthyroidism group was matched for age and gender with the hyperthyroidism group. After internal validation, we selected the better model for further evaluation using external validation datasets. Results The study included 22,940 retinal photographs of 11,409 participants for the model development, and 3862 retinal photographs (1870 participants) which were obtained from two hospitals and four medical centers as the external validation datasets. Model #1 achieved a higher area under the receiver operator curve (AUC) than model #2 (0.907, 95% CI: 0.894–0.918 versus 0.850, 95% CI: 0.832–0.866) in the internal validation so that model #1 was used for further evaluation. In external datasets, model #1 reached AUCs ranging from 0.816 (95% CI 0.789–0.846) to 0.849 (95% CI 0.824–0.874) and achieved accuracies between 0.735 (95% CI 0.700–0.773) and 0.796 (95% CI 0.765–0.824). Heatmaps showed a focus of the DL-algorism on large fundus vessels and the optic nerve head. Conclusions Retinal fundus photographs may serve for DL systems for a cost-effective and non-invasive method to detect hyperthyroidism.

BackgroundData regarding the association between antioxidant supplementation and incident dementia are limited.MethodsWe included 494,632 adults (54.5% females) aged 40–71 years at baseline from the United Kingdom Biobank in the final analysis. Incident dementia was ascertained using hospital inpatient and death records up to January 2021.ResultsOver a median follow-up of 11.9 years, 7,128 new cases of all-cause dementia, 2,772 cases of Alzheimer’s disease, and 1,397 cases of vascular dementia were recorded. The hazard ratio (95% CI) for incident dementia associated with zinc supplementation was 0.84 (0.74–0.96), and the association remained significant after adjusting for all confounders (0.84 (0.74–0.96)). In the full model, zinc supplementation was associated with a reduced risk of Alzheimer’s disease [HR (95% CI): 0.71 (0.57–0.88)]. There was no significant association between zinc supplementation and the risk of vascular dementia. No significant associations with incident dementia were observed for other antioxidant supplementation. The association between zinc supplementation and incident dementia was significant among individuals with [HR (95% CI): 0.34 (0.15–0.77)] and without cataract [0.87 (0.77–0.99)] but it was stronger among those with cataract (p value for interaction = 0.0271).ConclusionOur findings suggest that zinc supplementation may help reduce the risk of all-cause dementia and Alzheimer’s disease in middle-aged or older adults, especially among those with cataracts.

Summary: Retinopathy of prematurity (ROP) is currently one of the leading causes of infant blindness worldwide. Recently significant progress has been made in deep learning-based computer-aided diagnostic methods. However, deep learning often requires a large amount of annotated data for model optimization, but this requires long hours of effort by experienced doctors in clinical scenarios. In contrast, a large number of unlabeled images are relatively easy to obtain. In this paper, we propose a new semi-supervised learning framework to reduce annotation costs for automatic ROP staging. We design two consistency regularization strategies, prediction consistency loss and semantic structure consistency loss, which can help the model mine useful discriminative information from unlabeled data, thus improving the generalization performance of the classification model. Extensive experiments on a real clinical dataset show that the proposed method promises to greatly reduce the labeling requirements in clinical scenarios while achieving good classification performance.

Abstract Optical coherence tomography angiography (OCTA) has been a frequently used diagnostic method in neovascular age-related macular degeneration (nAMD) because it is non-invasive and provides a comprehensive view of the characteristic lesion, choroidal neovascularization (CNV). In order to study its characteristics, an automated method is needed to identify and quantify CNV. Here, we have developed a deep learning model that can automatically segment CNV regions from OCTA images. Specifically, we use the ResNeSt block as our basic backbone, which learns better feature representations through group convolution and split-attention mechanisms. In addition, considering the varying sizes of CNVs, we developed a spatial pyramid pooling module, which uses different receptive fields to enable the model to extract contextual information at different scales to better segment CNVs of different sizes, thus further improving the segmentation performance of the model. Experimental results on a clinical OCTA dataset containing 116 OCTA images show that the CNV segmentation model has an AUC of 0.9476 (95% CI 0.9473–0.9479), with specificity and sensitivity of 0.9950 (95% CI 0.9945–0.9955) and 0.7271 (95% CI 0.7265–0.7277), respectively. In summary, the model has satisfactory performance in extracting CNV regions from the background of OCTA images of nAMD patients.

Abstract Electroencephalogram (EEG) datasets from epilepsy patients have been used to develop seizure detection and prediction algorithms using machine learning (ML) techniques with the aim of implementing the learned model in a device. However, the format and structure of publicly available datasets are different from each other, and there is a lack of guidelines on the use of these datasets. This impacts the generatability, generalizability, and reproducibility of the results and findings produced by the studies. In this narrative review, we compiled and compared the different characteristics of the publicly available EEG datasets that are commonly used to develop seizure detection and prediction algorithms. We investigated the advantages and limitations of the characteristics of the EEG datasets. Based on our study, we identified 17 characteristics that make the EEG datasets unique from each other. We also briefly looked into how certain characteristics of the publicly available datasets affect the performance and outcome of a study, as well as the influences it has on the choice of ML techniques and preprocessing steps required to develop seizure detection and prediction algorithms. In conclusion, this study provides a guideline on the choice of publicly available EEG datasets to both clinicians and scientists working to develop a reproducible, generalizable, and effective seizure detection and prediction algorithm.

Introduction Despite significant advances in managing acute stroke and reducing stroke mortality, preventing complications like post-stroke epilepsy (PSE) has seen limited progress. PSE research has been scattered worldwide with varying methodologies and data reporting. To address this, we established the International Post-stroke Epilepsy Research Consortium (IPSERC) to integrate global PSE research efforts. This protocol outlines an individual patient data meta-analysis (IPD-MA) to determine outcomes in patients with post-stroke seizures (PSS) and develop/validate PSE prediction models, comparing them with existing models. This protocol informs about creating the International Post-stroke Epilepsy Research Repository (IPSERR) to support future collaborative research.Methods and analysis We utilised a comprehensive search strategy and searched MEDLINE, Embase, PsycInfo, Cochrane, and Web of Science databases until 30 January 2023. We extracted observational studies of stroke patients aged ≥18 years, presenting early or late PSS with data on patient outcome measures, and conducted the risk of bias assessment. We did not apply any restriction based on the date or language of publication. We will invite these study authors and the IPSERC collaborators to contribute IPD to IPSERR. We will review the IPD lodged within IPSERR to identify patients who developed epileptic seizures and those who did not. We will merge the IPD files of individual data and standardise the variables where possible for consistency. We will conduct an IPD-MA to estimate the prognostic value of clinical characteristics in predicting PSE.Ethics and dissemination Ethics approval is not required for this study. The results will be published in peer-reviewed journals. This study will contribute to IPSERR, which will be available to researchers for future PSE research projects. It will also serve as a platform to anchor future clinical trials.Trial registration number NCT06108102

Content-based medical image retrieval is an important diagnostic tool that improves the explainability of computer-aided diagnosis systems and provides decision-making support to healthcare professionals. A common approach to content-based image retrieval is learning a distance metric by transforming images into a feature space where the distance between samples is a similarity measure. Proxy metric learning methods are effective at learning this transformation due to the use of proxy feature vectors that enable efficient learning. Training with a distance-based classification loss enables a single proxy model to be suitable for both retrieval and classification. However, these methods are designed only for single-label data, making them unsuitable for multimorbidity medical images. Addressing this, we propose a novel multi-label proxy metric learning method for content-based image retrieval and classification. Unlike existing proxy-based methods, training samples assign to multiple proxies that span multiple class labels. This results in a feature space that encodes the complex relationships between diseases. We introduce negative proxies to better encode the relationships between samples without detected diseases. The efficacy of our approach is demonstrated experimentally on two multimorbidity radiology datasets. Results show that our method outperforms state-of-the-art image retrieval systems and baseline approaches. Our method is clinically significant as it improves on two key factors shown to affect medical professionals’ willingness to use computer-aided diagnosis systems: accuracy and interpretability.

Abstract Background Little is known regarding whether sex assigned at birth modifies the association between several predictive factors for dementia and the risk of dementia itself. Methods Our retrospective cohort study included 214,670 men and 214,670 women matched by age at baseline from the UK Biobank. Baseline data were collected between 2006 and 2010, and incident dementia was ascertained using hospital inpatient or death records until January 2021. Mediation analysis was tested for 133 individual factors. Results Over 5,117,381 person-years of follow-up, 5928 cases of incident all-cause dementia (452 cases of young-onset dementia, 5476 cases of late-onset dementia) were documented. Hazard ratios (95% CI) for all-cause, young-onset, and late-onset dementias associated with the male sex (female as reference) were 1.23 (1.17–1.29), 1.42 (1.18–1.71), and 1.21 (1.15–1.28), respectively. Out of 133 individual factors, the strongest mediators for the association between sex and incident dementia were multimorbidity risk score (percentage explained (95% CI): 62.1% (45.2–76.6%)), apolipoprotein A in the blood (25.5% (15.2–39.4%)), creatinine in urine (24.9% (16.1–36.5%)), low-density lipoprotein cholesterol in the blood (23.2% (16.2–32.1%)), and blood lymphocyte percentage (21.1% (14.5–29.5%)). Health-related conditions (percentage (95% CI) explained: 74.4% (51.3–88.9%)) and biomarkers (83.0% (37.5–97.5%)), but not lifestyle factors combined (30.1% (20.7–41.6%)), fully mediated sex differences in incident dementia. Health-related conditions combined were a stronger mediator for late-onset (75.4% (48.6–90.8%)) than for young-onset dementia (52.3% (25.8–77.6%)), whilst lifestyle factors combined were a stronger mediator for young-onset (42.3% (19.4–69.0%)) than for late-onset dementia (26.7% (17.1–39.2%)). Conclusions Our analysis matched by age has demonstrated that men had a higher risk of all-cause, young-onset, and late-onset dementias than women. This association was fully mediated by health-related conditions or blood/urinary biomarkers and largely mediated by lifestyle factors. Our findings are important for understanding potential mechanisms of sex in dementia risk.

Abstract Given the unprecedented phenomenon of population ageing, studies have increasing captured the heterogeneity within the ageing process. In this context, the concept of “biological age” has been introduced as an integrated measure reflecting the individualized ageing pace. Identifying reliable and robust biomarkers of age is critical for the accurate risk stratification of individuals and exploration into antiageing interventions. Numerous potential biomarkers of ageing have been proposed, spanning from molecular changes and imaging characteristics to clinical phenotypes. In this review, we will start off with a discussion of the development of ageing biomarkers, then we will provide a comprehensive summary of currently identified ageing biomarkers in humans, discuss the rationale behind each biomarker and highlight their accuracy and clinical value with a contemporary perspective. Additionally, we will discuss the challenges, potential applications, and future opportunities in this field. While research on ageing biomarkers has led to significant progress and applications, further investigations are still necessary. We anticipate that future breakthroughs in this field will involve exploring potential mechanisms, developing biomarkers by combining various data sources or employing new technologies, and validating the clinical value of existing and emerging biomarkers through comprehensive collaboration and longitudinal studies.

Abstract Background Little is known regarding life-course trajectories of important diseases. We aimed to identify diseases that were strongly associated with mortality and test temporal trajectories of these diseases before mortality. Methods Our analysis was based on UK Biobank. Diseases were identified using questionnaires, nurses’ interviews, or inpatient data. Mortality register data were used to identify mortality up to January 2021. The association between 60 individual diseases at baseline and in the life course and incident mortality was examined using Cox proportional regression models. Those diseases with great contribution to mortality were identified and disease trajectories in life course were then derived. Results During a median follow-up of 11.8 years, 31,373 individuals (median age at death (interquartile range): 70.7 (65.3–74.8) years, 59.4% male) died of all-cause mortality (with complete data on diagnosis date of disease), with 16,237 dying with cancer and 6702 with cardiovascular disease (CVD). We identified 37 diseases including cancers and heart diseases that were associated with an increased risk of mortality independent of other diseases (hazard ratio ranged from 1.09 to 7.77). Among those who died during follow-up, 2.2% did not have a diagnosis of any disease of interest and 90.1% were diagnosed with two or more diseases in their life course. Individuals who were diagnosed with more diseases in their life course were more likely to have longer longevity. Cancer was more likely to be diagnosed following hypertension, hypercholesterolemia, CVD, or digestive disorders and more likely to be diagnosed ahead of CVD, chronic kidney disease (CKD), or digestive disorders. CVD was more likely to be diagnosed following hypertension, hypercholesterolemia, or digestive disorders and more likely to be diagnosed ahead of cancer or CKD. Hypertension was more likely to precede other diseases, and CKD was more likely to be diagnosed as the last disease before more mortality. Conclusions There are significant interplays between cancer and CVD for mortality. Cancer and CVD were frequently clustered with hypertension, CKD, and digestive disorders with CKD highly being diagnosed as the last disease in the life course. Our findings underline the importance of health checks among middle-aged adults for the prevention of premature mortality.

BackgroundConvolutional neural networks (CNNs) are a type of artificial intelligence that shows promise as a diagnostic aid for skin cancer. However, the majority are trained using retrospective image data sets with varying image capture standardization. ObjectiveThe aim of our study was to use CNN models with the same architecture—trained on image sets acquired with either the same image capture device and technique (standardized) or with varied devices and capture techniques (nonstandardized)—and test variability in performance when classifying skin cancer images in different populations. MethodsIn all, 3 CNNs with the same architecture were trained. CNN nonstandardized (CNN-NS) was trained on 25,331 images taken from the International Skin Imaging Collaboration (ISIC) using different image capture devices. CNN standardized (CNN-S) was trained on 177,475 MoleMap images taken with the same capture device, and CNN standardized number 2 (CNN-S2) was trained on a subset of 25,331 standardized MoleMap images (matched for number and classes of training images to CNN-NS). These 3 models were then tested on 3 external test sets: 569 Danish images, the publicly available ISIC 2020 data set consisting of 33,126 images, and The University of Queensland (UQ) data set of 422 images. Primary outcome measures were sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). Teledermatology assessments available for the Danish data set were used to determine model performance compared to teledermatologists. ResultsWhen tested on the 569 Danish images, CNN-S achieved an AUROC of 0.861 (95% CI 0.830-0.889) and CNN-S2 achieved an AUROC of 0.831 (95% CI 0.798-0.861; standardized models), with both outperforming CNN-NS (nonstandardized model; P=.001 and P=.009, respectively), which achieved an AUROC of 0.759 (95% CI 0.722-0.794). When tested on 2 additional data sets (ISIC 2020 and UQ), CNN-S (P

BackgroundHIV and sexually transmitted infections (STIs) are major global public health concerns. Over 1 million curable STIs occur every day among people aged 15 years to 49 years worldwide. Insufficient testing or screening substantially impedes the elimination of HIV and STI transmission. ObjectiveThe aim of our study was to develop an HIV and STI risk prediction tool using machine learning algorithms. MethodsWe used clinic consultations that tested for HIV and STIs at the Melbourne Sexual Health Centre between March 2, 2015, and December 31, 2018, as the development data set (training and testing data set). We also used 2 external validation data sets, including data from 2019 as external “validation data 1” and data from January 2020 and January 2021 as external “validation data 2.” We developed 34 machine learning models to assess the risk of acquiring HIV, syphilis, gonorrhea, and chlamydia. We created an online tool to generate an individual’s risk of HIV or an STI. ResultsThe important predictors for HIV and STI risk were gender, age, men who reported having sex with men, number of casual sexual partners, and condom use. Our machine learning–based risk prediction tool, named MySTIRisk, performed at an acceptable or excellent level on testing data sets (area under the curve [AUC] for HIV=0.78; AUC for syphilis=0.84; AUC for gonorrhea=0.78; AUC for chlamydia=0.70) and had stable performance on both external validation data from 2019 (AUC for HIV=0.79; AUC for syphilis=0.85; AUC for gonorrhea=0.81; AUC for chlamydia=0.69) and data from 2020-2021 (AUC for HIV=0.71; AUC for syphilis=0.84; AUC for gonorrhea=0.79; AUC for chlamydia=0.69). ConclusionsOur web-based risk prediction tool could accurately predict the risk of HIV and STIs for clinic attendees using simple self-reported questions. MySTIRisk could serve as an HIV and STI screening tool on clinic websites or digital health platforms to encourage individuals at risk of HIV or an STI to be tested or start HIV pre-exposure prophylaxis. The public can use this tool to assess their risk and then decide if they would attend a clinic for testing. Clinicians or public health workers can use this tool to identify high-risk individuals for further interventions.

BackgroundThyroid-associated ophthalmopathy (TAO) is one of the most common orbital diseases that seriously threatens visual function and significantly affects patients’ appearances, rendering them unable to work. This study established an intelligent diagnostic system for TAO based on facial images.MethodsPatient images and data were obtained from medical records of patients with TAO who visited Shanghai Changzheng Hospital from 2013 to 2018. Eyelid retraction, ocular dyskinesia, conjunctival congestion, and other signs were noted on the images. Patients were classified according to the types, stages, and grades of TAO based on the diagnostic criteria. The diagnostic system consisted of multiple task-specific models.ResultsThe intelligent diagnostic system accurately diagnosed TAO in three stages. The built-in models pre-processed the facial images and diagnosed multiple TAO signs, with average areas under the receiver operating characteristic curves exceeding 0.85 (F1 score >0.80).ConclusionThe intelligent diagnostic system introduced in this study accurately identified several common signs of TAO.

Summary: Background: Little is known regarding associations of conventional and emerging diseases and their multimorbidity with brain volumes. Methods: This cross-sectional study included 36,647 European ancestry individuals aged 44–81 years with brain magnetic resonance imaging data from UK Biobank. Brain volumes were measured between 02 May 2014 and 31 October 2019. General linear regression models were used to associate 57 individual major diseases with brain volumes. Latent class analysis was used to identify multimorbidity patterns. A multimorbidity score for brain volumes was computed based on the estimates for individual groups of diseases. Findings: Out of 57 major diseases, 16 were associated with smaller volumes of total brain, 14 with smaller volumes of grey matter, and six with smaller hippocampus volumes, and four major diseases were associated with higher white matter hyperintensity (WMH) load after adjustment for all other diseases. The leading contributors to the variance of total brain volume were hypertension (R2=0·0229), dyslipidemia (0·0190), cataract (0·0176), coronary heart disease (0·0107), and diabetes (0·0077). We identified six major multimorbidity patterns and multimorbidity patterns of cardiometabolic disorders (CMD), and CMD-multiple disorders, and metabolic disorders were independently associated with smaller volumes of total brain (β (95% CI): -6·6 (-8·9, -4·3) ml, -7·3 (-10·4, -4·1) ml, and -10·4 (-13·5, -7·3) ml, respectively), grey matter (-7·1 (-8·5, -5·7) ml, -9·0 (-10·9, -7·1) ml, and -11·8 (-13·6, -9·9) ml, respectively), and higher WMH load (0·23 (0·19, 0·27), 0·25 (0·19, 0·30), and 0·33 (0·27, 0·39), respectively) after adjustment for geographic, socioeconomic, and lifestyle factors (all P-values

Recent studies have increasingly shown that the chemical modification of mRNA plays an important role in the regulation of gene expression. N7-methylguanosine (m7G) is a type of positively-charged mRNA modification that plays an essential role for efficient gene expression and cell viability. However, the research on m7G has received little attention to date. Bioinformatics tools can be applied as auxiliary methods to identify m7G sites in transcriptomes. In this study, we develop a novel interpretable machine learning-based approach termed XG-m7G for the differentiation of m7G sites using the XGBoost algorithm and six different types of sequence-encoding schemes. Both 10-fold and jackknife cross-validation tests indicate that XG-m7G outperforms iRNA-m7G. Moreover, using the powerful SHAP algorithm, this new framework also provides desirable interpretations of the model performance and highlights the most important features for identifying m7G sites. XG-m7G is anticipated to serve as a useful tool and guide for researchers in their future studies of mRNA modification sites.

Summary: Background: Identifying independent and interactive associations of a wide range of diseases and multimorbidity and apolipoprotein E4 (APOE4) with dementia may help promote cognitive health. The main aim of the present study was to investigate associations of such diseases and their multimorbidity with incident dementia. Methods: In this retrospective cohort study, we included 471,485 individuals of European ancestry from the UK Biobank, aged 38–73 years at baseline (2006–10). Dementia was identified using inpatient records and death registers. The follow-up period was between March 16, 2006, and Jan 31, 2021. Findings: During a median follow-up of 11·9 years, 6189 cases of incident all-cause dementia (503 young-onset cases, 5686 late-onset cases) were documented. In multivariable-adjusted analysis, 33 out of 63 major diseases were associated with an increased risk of dementia. The hazard ratio (HR [95% CI]) ranged from 1·12 (1·06–1·19) for obesity to 14·22 (12·33–16·18) for Parkinson's disease. In addition to conventional diseases, respiratory disorders, musculoskeletal disorders, digestive disorders, painful conditions, and chronic kidney disease were associated with increased dementia risk. A larger HR for dementia was observed for a larger number of diseases (3·97 [3·51–4·48] for ≥6 diseases versus no disease). These individual diseases and multimorbidity were more predictive of young-onset dementia than of late-onset dementia. Dementia risk score incorporating multimorbidity, age, and APOE4 status had strong prediction performance (area under the curve [95% CI]: 82·2% [81·7–82·7%]). APOE4 was more predictive of late-onset dementia (HR [95% CI]: 2·90 [2·75–3·06]) than of young-onset dementia (1·26 [1·03–1·54]). Associations of painful conditions, depression, obesity, diabetes, stroke, Parkinson's disease, high cholesterol, and their multimorbidity with incident dementia were stronger among non-APOE4 carriers. Interpretation: Besides conventional diseases, numerous diseases are associated with an increased risk of dementia. These individual diseases and multimorbidity are more predictive of young-onset dementia, whereas APOE4 is more predictive of late-onset dementia. Individual diseases and multimorbidity are stronger predictors of dementia in non-APOE4 carriers. Although multiple risk factors have been adjusted for in the analysis, potential confounding from unknown factors may have biased the associations. Funding: The Fundamental Research Funds of the State Key Laboratory of Ophthalmology, Project of Investigation on Health Status of Employees in Financial Industry in Guangzhou, China (Z012014075), Science and Technology Program of Guangzhou, China (202,002,020,049).

MotivationRetinal microvasculature is a unique window for predicting and monitoring major cardiovascular diseases, but high throughput tools based on deep learning for in-detail retinal vessel analysis are lacking. As such, we aim to develop and validate an artificial intelligence system (Retina-based Microvascular Health Assessment System, RMHAS) for fully automated vessel segmentation and quantification of the retinal microvasculature.ResultsRMHAS achieved good segmentation accuracy across datasets with diverse eye conditions and image resolutions, having AUCs of 0.91, 0.88, 0.95, 0.93, 0.97, 0.95, 0.94 for artery segmentation and 0.92, 0.90, 0.96, 0.95, 0.97, 0.95, 0.96 for vein segmentation on the AV-WIDE, AVRDB, HRF, IOSTAR, LES-AV, RITE, and our internal datasets. Agreement and repeatability analysis supported the robustness of the algorithm. For vessel analysis in quantity, less than 2 s were needed to complete all required analysis.

High-definition display technology for underwater images is of great significance for many applications, such as marine animal observation, seabed mining, and marine fishery production. The traditional underwater visual display systems have problems, such as low visibility, poor real-time performance, and low resolution, and cannot meet the needs of real-time high-definition displays in extreme environments. To solve these issues, we propose an underwater image enhancement method and a corresponding image super-resolution algorithm. To improve the quality of underwater images, we modify the Retinex algorithm and combine it with a neural network. The Retinex algorithm is used to defog the underwater image, and then, the image brightness is improved by applying gamma correction. Then, by combining with the dark channel prior and multilayer perceptron, the transmission map is further refined to improve the dynamic range of the image. In the super-resolution process, the current convolutional neural network reconstruction algorithm is only trained on the Y channel, which will lead to problems due to the insufficient acquisition of the color feature. Therefore, an image super-resolution reconstruction algorithm that is based on color features is proposed. The experimental results show that the proposed method improves the reconstruction effect of the image edges and texture details, increases the image clarity, and enhances the image color recovery.

This paper focuses on improving the performance of scientific instrumentation that uses glass spray chambers for sample introduction, such as spectrometers, which are widely used in analytical chemistry, by detecting incidents using deep convolutional models. The performance of these instruments can be affected by the quality of the introduction of the sample into the spray chamber. Among the indicators of poor quality sample introduction are two primary incidents: The formation of liquid beads on the surface of the spray chamber, and flooding at the bottom of the spray chamber. Detecting such events autonomously as they occur can assist with improving the overall operational accuracy and efficacy of the chemical analysis, and avoid severe incidents such as malfunction and instrument damage. In contrast to objects commonly seen in the real world, beading and flooding detection are more challenging since they are of significantly small size and transparent. Furthermore, the non-rigid property increases the difficulty of the detection of these incidents, as such that existing deep-learning-based object detection frameworks are prone to fail for this task. There is no former work that uses computer vision to detect these incidents in the chemistry industry. In this work, we propose two frameworks for the detection task of these two incidents, which not only leverage the modern deep learning architectures but also integrate with expert knowledge of the problems. Specifically, the proposed networks first localize the regions of interest where the incidents are most likely generated and then refine these incident outputs. The use of data augmentation and synthesis, and choice of negative sampling in training, allows for a large increase in accuracy while remaining a real-time system for inference. In the data collected from our laboratory, our method surpasses widely used object detection baselines and can correctly detect 95% of the beads and 98% of the flooding. At the same time, out method can process four frames per second and is able to be implemented in real time.

This paper presents a novel approach to fruit detection using deep convolutional neural networks. The aim is to build an accurate, fast and reliable fruit detection system, which is a vital element of an autonomous agricultural robotic platform; it is a key element for fruit yield estimation and automated harvesting. Recent work in deep neural networks has led to the development of a state-of-the-art object detector termed Faster Region-based CNN (Faster R-CNN). We adapt this model, through transfer learning, for the task of fruit detection using imagery obtained from two modalities: colour (RGB) and Near-Infrared (NIR). Early and late fusion methods are explored for combining the multi-modal (RGB and NIR) information. This leads to a novel multi-modal Faster R-CNN model, which achieves state-of-the-art results compared to prior work with the F1 score, which takes into account both precision and recall performances improving from 0 . 807 to 0 . 838 for the detection of sweet pepper. In addition to improved accuracy, this approach is also much quicker to deploy for new fruits, as it requires bounding box annotation rather than pixel-level annotation (annotating bounding boxes is approximately an order of magnitude quicker to perform). The model is retrained to perform the detection of seven fruits, with the entire process taking four hours to annotate and train the new model per fruit.