Search

Sim, Tham et al. explore the combined predictive ability of clinical, retinal, and blood biomarkers for the prediction of cognitive decline in Southeast Asian memory clinic participants. Authors find that combining blood tests, eye markers, and clinical data may be a potential noninvasive tool for early risk detection for cognitive decline.

Diabetic retinopathy is a major cause of blindness, yet ways to predict who will be affected remain limited. Here, the authors show that patterns of blood proteins can reveal disease mechanisms and enable powerful early prediction across diverse populations.

Can clinical artificial intelligence borrow from the experience of developing safe autonomous vehicles to develop safe autonomous consultations for medicine?

Trained and validated on multimodal data from 14.5 million images from multicountry datasets, a foundation model is shown to increase diagnostic and referral accuracy of clinicians when used as an assistant in a trial involving 16 ophthalmologists and 668 patients.

Urinary albumin-to-creatinine ratio (UCAR) is associated with various clinical outcomes such as kidney disease and cardiovascular disease. Here, the authors report genome-wide meta-analysis in over 500,000 individuals and find 68 UACR loci, followed by statistical fine-mapping, gene prioritization and experimental validation in flies.

Large language models (LLMs) are emerging as powerful tools in healthcare, with a growing role in global health, particularly in low- and middle-income countries. This Perspective examines the current progress, challenges and prospects of LLMs in addressing health system disparities and supporting achievement of the Sustainable Development Goals.

A deep learning algorithm shows promising performance in predicting progression to diabetic retinopathy in patients, up to 5 years in advance, potentially providing support for medical treatment decisions and indications for personalized screening frequency in a real-world cohort.

A reinforcement learning-based virtual reality system, implementing a series of sport sessions with coaching, was as effective as standard physical activity in reducing fat mass in adolescents, with positive effects on cognition.

Previous ophthalmic foundation models have struggled to generalize effectively to diverse and rare fundus diseases, restricting their clinical applicability. Here, the authors introduce a vision-language foundation model that demonstrates superior performance in diagnosing both common and rare fundus conditions.

DeepRETStroke is a deep learning system using retinal photographs to detect silent brain infarction and predict future stroke events.

Inbreeding depression has been observed in many different species, but in humans a systematic analysis has been difficult so far. Here, analysing more than 1.3 million individuals, the authors show that a genomic inbreeding coefficient (FROH) is associated with disadvantageous outcomes in 32 out of 100 traits tested.

Deep-learning models for the automated measurement of retinal-vessel calibre in retinal photographs perform comparably to or better than expert graders in associations of measurements of retinal-vessel calibre with cardiovascular risk factors.

Structural variations (SV) contribute to inter-individual variability. Here, the authors describe a first-generation multi-ancestry Asian SV catalogue containing 73,035 SVs from 8392 Singaporeans to provide insights into Asian SV diversity.

Using synthetic data generated via conditioning with disease labels can enhance the pretraining efficiency and generalization of medical foundation models, as shown for the detection of eye diseases via fundus photographs.

A multi-ancestry genome-wide gene–smoking interaction study identifies 13 new loci associated with serum lipids.

Tailored to provide diabetes management recommendations from large training and validation datasets, an artificial intelligence system integrating language and computer vision capabilities is shown to improve self-management of patients in a prospective implementation study.

The advantage of living in cities compared with rural areas with respect to height and BMI in children and adolescents has generally become smaller globally from 1990 to 2020, except in sub-Saharan Africa.

Mao et al. systematically evaluates the integration of digital health technologies (DHT) in 262 clinical trials across ten rare diseases. Results reveal that DHTs enable remote monitoring, digital interventions and patient support, enhancing trial inclusivity, authors also propose a “4A” framework for DHT implementation.

X-chromosomal genetic variants are understudied but can yield valuable insights into sexually dimorphic human traits and diseases such as chronic kidney disease (CKD). Here, the authors perform a sex-stratified, cross-ancestry X-chromosome-wide association meta-analysis of seven kidney-related traits, with results including identification of four novel loci associated with the CKD-defining trait eGFR.

Age-related cataracts are characterized by clouding of the eye’s lens and cause vision impairment or loss. Here the authors develop a retinal photograph-based deep-leaning method to detect visually significant cataracts and report that it detects cataracts with similar accuracy to ophthalmologists.

A deep understanding of the genetic signatures of neovascular age-related macular degeneration subtypes in Asian patients remains a significant gap. Here the authors pinpoint contributing common and rare variants using GWAS and exome sequencing approaches.

Trans-ancestry meta-analysis of estimated glomerular filtration rate (eGFR) from 1,046,070 individuals identifies 264 associated loci, providing a resource of molecular targets for translational research of chronic kidney disease.

The genetics and clinical consequences of resting heart rate (RHR) remain incompletely understood. Here, the authors discover new genetic variants associated with RHR and find that higher genetically predicted RHR decreases risk of atrial fibrillation and ischemic stroke.

Ji et al. assess the responses of four major large language models in the context of cardiovascular disease prevention queries in both English and Chinese. The large language model chatbots exhibit significant disparities in performance across different models and languages, with ChatGPT-4 outperforming the others in English.

Transancestral GWAS meta-analysis in 160,420 individuals identifies 139 loci associated with refractive error, including myopia. Newly identified genes implicate pathways involved in eye growth and light signaling cascades.

A deep-learning algorithm trained with retinal images and subject metadata from the UK Biobank predicts blood-haemoglobin levels.

Clinically significant genetic variation in Asian populations is under-characterized. Here, the authors show the diversity in prevalence and spectrum of human disease and pharmacogenetic variants in a multi-ethnic Asian population.

Elsawy, Keenan, Chen et al. detect cataracts from color fundus photography using an explainable deep learning network called DeepOpacityNet. DeepOpacityNet detects cataracts more accurately than ophthalmologists and demonstrates that the absence of blood vessels is an indicator that cataracts are present.

Reduced central corneal thickness (CCT) is observed in common eye diseases as well as in rare Mendelian disorders. Here, in a cross-ancestry GWAS, the authors identify 19 novel genetic loci associated with CCT, a subset of which is involved in rare corneal or connective tissue disorders.

Here, the authors report a multi-ethnic genome wide association meta-analysis of 12 studies from the International Cataract Genetics Consortium. They find six new loci associated with age-related nuclear cataract, in addition to replicating the association at CRYAA, and suggest a strong genetic link between age-related nuclear and congenital cataracts.