Researchers analyzed UK Biobank data and found that night-active individuals had higher risks of major depressive disorder and anxiety disorders compared to daytime-active individuals. An early-morning-active phenotype was associated with lower MDD risk, while higher physical activity at certain times was linked to adverse outcomes.
Researchers propose a new conceptual framework called Health Elements, which integrates technological factors alongside traditional domains as core drivers of health. The framework highlights the increasingly important role of digital infrastructures in shaping health behaviors and outcomes.
A groundbreaking international study analyzed objective sleep data from 88,461 adults and found significant associations between sleep traits and 172 diseases. Sleep regularity, such as bedtime consistency and circadian rhythm stability, was linked to an increased risk of various diseases.
Researchers found that ChatGPT-4 performed better across demographic groups, while LLaVA showed significant sex-related biases in diagnosing skin diseases from medical images. The study emphasizes the need to address these biases to ensure AI models are safe and effective for all patients.
A large international real-world data study found that antidepressant use does not significantly increase the risk of manic episodes in patients with bipolar depression. The study analyzed data from 122,843 outpatients and employed propensity score matching to control for confounding factors.
Researchers found that moderate levels of physical activity significantly reduced brain aging and improved cognitive function. The study's findings suggest a U-shaped relationship between physical activity intensity and brain age gap, with both insufficient and excessive exercise linked to accelerated brain aging.
A large-scale UK biobank study found that loneliness increases the risk of hearing loss, with a 24% higher risk for lonely individuals compared to non-lonely counterparts. The study also identified distinct pathways through which loneliness contributes to hearing loss, including inflammation and chronic diseases.
A new study reveals a concerning rise in type 2 diabetes among depression inpatients in Beijing from 2005 to 2018. Depression and type 2 diabetes co-occurrence is understudied, but the research found 9.13% of depression patients had T2DM, with significant age, sex, and socioeconomic factors linked to elevated risk.
A new study in Health Data Science identifies individuals with both cardiovascular and musculoskeletal conditions as a distinct high-risk group. These 'osteo-cardiovascular fallers' face a higher risk of severe falls and death compared to healthy participants.
A study of 24 countries found that digital exclusion significantly increases the risk of depressive symptoms among older adults. The association remains strong even after adjusting for demographic factors.
Researchers developed an innovative model, ECG-LM, that leverages large language models to interpret complex ECG signals. The model improves the accuracy and speed of heart-related diagnostics, particularly in resource-limited environments.
A study analyzing 400,000 participants found that loneliness increases NAFLD risk by 22% and social isolation by 13%, independent of traditional risk factors. Unhealthy lifestyle behaviors, depression, and inflammatory responses partially explained these associations.
Early-onset type 2 diabetes incidence and disability-adjusted life years increased sharply in China from 1990 to 2021, primarily driven by high body mass index and ambient pollution. Targeted interventions are needed for males and younger age groups.
Researchers developed ProtET, an AI model leveraging multi-modal learning to controllably edit proteins through text-based instructions. This approach enhances functional protein design across domains like enzyme activity, stability, and antibody binding, promising real-world applicability in biomedical research.
A groundbreaking AI model developed by researchers at Emory University accurately predicts the likelihood of blood transfusion in non-traumatic ICU patients, addressing longstanding challenges in predicting transfusion needs. The model achieved exceptional performance metrics, including an AUROC of 0.97 and an accuracy rate of 0.93.
A systematic review of 46 research papers found that machine learning techniques, particularly GAN-based methods and context-aware time-series imputation (CATSI), consistently outperform traditional statistical approaches in handling both longitudinal and cross-sectional datasets.
A recent study found that cancer patients who traveled to local or national healthcare centers had higher five-year survival rates compared to those who remained in their residential cities. The study highlights critical disparities in healthcare resource allocation and quality across regions.
A recent study found a positive association between smoking and CKD risk in observational studies, but Mendelian randomization analysis revealed no direct causal link. Researchers propose that diabetes and hypertension may mediate the relationship.
A comprehensive benchmark evaluates statistical and engineering approaches to federated learning for healthcare applications. Statistical FL methods excel in non-predictive tasks, while engineering-based FL algorithms demonstrate superior predictive performance.
China's carbon mitigation strategies aim to reduce deaths and diseases related to air pollution, such as PM2.5 and ozone, and mitigate climate-related health impacts.
A 30-year study reveals changes in incidence and mortality rates of 15 common neonatal infectious diseases across LMICs, identifying key trends and areas for targeted public health interventions. Higher socio-demographic index and universal health coverage are generally associated with reduced disease burden.
Researchers developed ERTool, an open-source Python package, to simplify the Evidential Reasoning (ER) approach for multi-source evidence fusion. The tool automates complex algorithms, enabling researchers and professionals to integrate multi-source data for evidence-based decision-making.
Researchers developed a novel noninvasive choroidal angiography method using deep learning, enabling layer-wise visualization and evaluation of choroidal vessels. The approach employs an advanced segmentation model to handle varying quality of OCT B-scans, offering a promising tool for clinical applications.
A novel collaborative framework integrates semi-supervised learning techniques to improve MRI segmentation accuracy, even with limited labeled data. The approach achieves high Dice scores and demonstrates its potential for practical clinical application.
A new study by Zhejiang University highlights the disproportionate health challenges faced by sexual and gender-diverse individuals during the COVID-19 pandemic. SGD individuals experienced higher rates of COVID-19 symptoms and mental health issues compared to non-SGD users, according to a large-scale social media analysis.
Researchers have found that integrating machine learning with statistical methods improves disease risk prediction model accuracy. The study highlights the potential of such integrated models in clinical diagnosis and screening practices, which could lead to better patient outcomes.
Recent advances in Brain Network Models (BNMs) have improved simulations of brain activities, understanding neuropathological mechanisms, and predicting disease progression. BNMs integrate structural and functional connectivity data to analyze abnormal network dynamics.
A new study reveals a significant association between COVID-19 and acute kidney disorders, including acute kidney injury, peaking during the second week after infection. Healthcare providers should closely monitor kidney function in COVID-19 patients with moderate to severe cases, particularly during the first few weeks after infection.
A recent study published in Health Data Science reveals a significant association between socioeconomic status (SES) inequality and the risk of developing age-related macular degeneration (AMD). Individuals with medium and low SES had a 10% and 22% increased risk of AMD, respectively, compared to high SES individuals.
A new study published in Health Data Science reveals that both spontaneous and induced abortions are associated with an increased risk of premature mortality. The research found that induced abortions were strongly linked to cardiovascular death, while spontaneous abortions also elevated the risk of all-cause premature mortality.
A new dataset integrates global Health AI research, providing a structured resource for researchers, policymakers, and practitioners. The dataset includes 96,332 Health AI documents, covering publications, open research datasets, patents, grants, and clinical trials.
A recent study found that high cumulative BMI is associated with smaller brain volume, larger white matter lesions, and abnormal microstructural integrity in adults. Maintaining a healthy BMI below 26.2 kg/m² is suggested for better brain health.
A new study in Health Data Science leverages keywords from Google Trends alongside research abstracts from the WHO COVID-19 database to dissect the pandemic's discourse dynamics. Academics respond faster and provide more detailed insights than GT, enriching policy formulation.
The KEDD framework integrates structured and unstructured knowledge to enhance predictive accuracy in AI-driven drug discovery. It outperforms existing models in critical tasks, including the 'missing modality problem', by leveraging sparse attention and modality masking techniques.
A pioneering study using mobile phone data analysis sheds light on socioeconomic disparities in unhealthy food reliance during COVID-19, particularly among racial minorities and low-income households. The study found that COVID-19 has exacerbated convenience store reliance, especially in Hispanic-majority counties and areas with older ...
Recent advances in wearable EEG-based BCIs enable continuous monitoring of intermittent neurological diseases like epilepsy and migraine. Wearable BCI technology also enhances assistive devices control and disease prediction, diagnosis, treatment.
A new study reveals that living near major roads is associated with a higher incidence of dementia and alterations in brain structure due to air pollution. The research, conducted in China and the UK, analyzed data from 460,901 participants over 12.8 years.
A new open-source Python toolbox called simpleNomo has been made available, enabling the creation of nomograms directly from logistic regression coefficients. This facilitates the translation of research findings into practical use, particularly in resource-poor settings or areas without internet access.
The study found a 1.14% incidence rate of moderate and severe OHSS among Chinese women of reproductive age between 2013 and 2017. Women under 35 years old receiving ART are at high risk, accounting for 80% of new cases during this period.
The use of AI is improving diagnostic accuracy for digestive cancers, but challenges in data sharing and standardization hinder its widespread application. Researchers surveyed recent applications of AI to these deadly cancers, finding that AI can automate complex processes and detect patterns not visible to humans.
A recent study found a significant decrease in influenza activity in China during the 2020-2022 COVID-19 pandemic, particularly in winter and spring. The observed reduction in influenza seasonality may be attributed to everyday COVID-19 public health interventions.
Vivli's generalist repository is the largest clinical trial repository in the world, providing managed access to over 6,600 trials. The platform has contributed to over 100 publications and features a COVID-19 portal with quick data addition capabilities.
A perspective paper explores the role of clinician-data-scientists in healthcare, emphasizing their need for interdisciplinary knowledge and training. The researchers highlight the importance of integrating data science into conventional medical education to prepare clinicians for the digital health era.
A team of scientists from China published a perspective paper on the use of AI in skin diseases, highlighting its potential to assist clinicians. They propose several recommendations to improve AI-assisted diagnosis systems, including establishing a robust database and adapting algorithms to existing real-world databases.
Researchers reviewed mobile sensing designs, outcomes, and limitations to better understand its capacity for remote detection, longitudinal tracking, and exposure tracing. Despite technical and societal challenges, advances in data analytics and machine learning may improve data quality and scalability.
A scoping review of knowledge graph applications in medical imaging analysis identifies increasing trend and potential future directions. The study highlights the effectiveness of prior knowledge in medical imaging tasks, but also reveals limitations, including limited annotated data and weak generalizability.
The article discusses how big data can improve non-communicable disease (NCD) surveillance by providing real-time information and reducing costs. This new approach uses electronic health records, national administrative data, and other datasets to track NCDs more effectively.
The review highlights advances in fundamental visualization methods for medical images in 3D, including scalar, vector, and tensor data. Medical professionals can quickly locate proper techniques using a taxonomy of medical problems and examples of health applications.
A recent study from Emory University found that people who self-report non-medical prescription drug use (NMPDU) express more negative emotions and less positive emotions on social media compared to those who do not, and that NMPDU tweets are highly polarized
Researchers analyzed over 4 million Twitter posts to find that fact-related users were negatively associated with vaccination rates, while fake-news users showed no significant impact. Exclusive fact-based users were more likely to be verified accounts with higher online influence.