Navigate peer-reviewed breakthroughs by pharmacological class, genetic target, circulating biomarker, or diagnostic modality. Select any clinical entity to inspect all linked studies.
Everyday Health & Science Hubs
Indexed Entities (24)
Modality / Tech47 Peer-Reviewed Briefings
Clinical AI & Deep Learning Models
Computer vision radiomics, multimodal clinical foundation models, and machine-learning diagnostics.
Active Specialties:AI in MedicineNeurologyOncologyCardiologyPsychiatryEndocrinologyNephrologyGastroenterologyPulmonology
Your Medical Records Could Reveal Your True 'Biological Age' — And Predict Your Health Future. A new AI tool, ClinicalAge, uses your existing health records to calculate your biological age, offering a powerful predictor of future health risks and lifespan.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
There is an ongoing need to evaluate screening algorithms using large systematic data sets, assess their cost-effectiveness, explore the... The optimal timing for initiation of disease-modifying therapies is uncertain, and this represents a key priority for future research.
4/5 Strong Trial
Evidence Meter · 4/5
Strong Clinical Evidence
Tested directly in patients through a prospective clinical trial or large multicenter human cohort.
Brazil's Hidden Dementia Crisis: A Glimmer of Hope for the Underserved. Undiagnosed dementia in Brazil significantly decreased over five years, especially among vulnerable populations, suggesting improved access to care.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Together, these strategies position interoperability as a strategic imperative for the future of neurologic care, quality measurement,... These examples highlight the potential of shared terminologies, structured neurologic observations, and API-enabled exchange, while underscoring persistent challenges, including limited availability of discrete neurologic data elements and the substantial effort required for mapping and governance.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Current evidence consistently demonstrates that rs-fMRI acquired during the acute phase of brain injury is associated with neurologic and functional outcomes in patients with DoC. In addition, rs-fMRI may help identify patients more likely to recover consciousness and achieve favorable functional outcomes by characterizing the integrity of large-scale brain networks.
5/5 Gold Standard
Evidence Meter · 5/5
Gold-Standard Human Evidence
Backed by randomized controlled human trials or a formal meta-analysis pooling multiple clinical studies.
Our analysis suggests that NCCP comprehensiveness varies substantially between countries with consistent weaknesses in financing, outcome measurement, and contextual analysis. A shared health systems framework and scalable AI appraisal tools, such as PRISM, could support more complete, comparable, and actionable plans to strengthen cancer control globally by providing the possibility for rapid analysis of comprehensiveness of NCCPs and generation of timely, achievable, and evidence-informed, context-specific plans that use the latest data.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
AI can uncover subtle cardiac risks in routine scans, improving sudden death prediction. This discovery could enable earlier identification of thousands at risk for sudden cardiac death, allowing for timely interventions.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
An AI-powered system can precisely predict and generate personalized visual percepts in a blind individual with a brain implant by learning their unique cortical responses to electrical stimulation. Current bionic eye technologies, while offering some degree of visual perception, often struggle with precision, consistency, and the intuitive generation of meaningful visual information for the patient.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
AI-guided discovery of the natural molecule BRP offers a novel, potentially better-tolerated approach to obesity treatment than existing medications. BRP represents a potential 'Ozempic-like' treatment for obesity that may circumvent common digestive side effects and muscle loss often associated with current GLP-1 agonists.
2/5 Preclinical
Evidence Meter · 2/5
Animal & Preclinical Data
Demonstrated in living animal models before large-scale human safety and dosing trials begin.
This Viewpoint discusses the role of artificial intelligence (AI) and health system preparedness and resilience in the event of an AI failure in clinical operations. Published in JAMA, these peer-reviewed ai in medicine findings provide quantitative evidence to inform clinical risk stratification, therapeutic decision-making, and follow-up trial design.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Per the results of this cohort study, NC FAI score provides prognostic performance comparable to CCTA FAI score and improves cardiovascular risk prediction and reclassification beyond CAC score. Elevated FAI score, derived from either CCTA or NCCT, should be interpreted as a risk-enhancing factor that may prompt intensification of established, evidence-based preventive measures and may serve as a potential future gatekeeper for the use of targeted anti-inflammatory treatments.
4/5 Strong Trial
Evidence Meter · 4/5
Strong Clinical Evidence
Tested directly in patients through a prospective clinical trial or large multicenter human cohort.
Reframing student mental health as core to the mission of universities justifies investment in digitally enabled care. With appropriate guardrails, AI can be integrated as a regulated component of this ecosystem, extending the reach of effective interventions while maintaining safety, equity, and institutional accountability.
4/5 Strong Trial
Evidence Meter · 4/5
Strong Clinical Evidence
Tested directly in patients through a prospective clinical trial or large multicenter human cohort.
This Viewpoint describes the importance of continuing clinician care, especially for patients with severe mental illness, as AI is integrated into psychiatry. Published in JAMA psychiatry, these peer-reviewed psychiatry findings provide quantitative evidence to inform clinical risk stratification, therapeutic decision-making, and follow-up trial design.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
It defines the conditions under which China-originated programs can generate globally practice-changing evidence. This review links regulatory reform, disease-specific opportunity, target biology, therapeutic format, and evidence quality across a decade of solid tumor development.
4/5 Strong Trial
Evidence Meter · 4/5
Strong Clinical Evidence
Tested directly in patients through a prospective clinical trial or large multicenter human cohort.
Results of this study show that after using a state-of-the art LLM, nearly 9 in 10 ASCVD encounters with above-goal LDL-C level did not have patient LLT escalated, most often because of adverse effects, patient preference, preference for lifestyle changes, therapeutic inertia (eg, repeat laboratory tests), and near-goal LDL-C level. These findings highlight an avenue for personalizing system-level digital health interventions to help discover and minimize guideline-discordant care gaps in secondary prevention of ASCVD.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
AI-ECG-guided monitoring resulted in a modest increase in the detection of new AF, AFl, or pre-AF atrial findings. However, these findings were fragile statistically and sensitive to reclassification of 1 event.
5/5 Gold Standard
Evidence Meter · 5/5
Gold-Standard Human Evidence
Backed by randomized controlled human trials or a formal meta-analysis pooling multiple clinical studies.
These findings establish gait as an independent, multisystem biosignal, motivating integration of gait analysis into routine clinical assessment as a scalable, passive vital sign. Relative to a baseline model using age, body mass index, visceral adipose tissue and height alone, gait embeddings improved prediction in all 18 systems in males and 17 of 18 in females, as well as prediction of clinical diagnoses and medication use.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Future progress requires a shift from short-term endpoint prediction to long-term outcome validation through multicenter studies, standardized protocols, and equitable implementation strategies. After transplantation, donor-derived cell-free deoxyribonucleic acid, urinary chemokines, and advanced imaging modalities offer non-invasive early detection of graft injury.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Model complexity produced small average clinical utility gains, concentrated among patients initially classified as high risk by NEWS. These findings support prospective trials of risk-stratified monitoring based on the first NEWS assessment, testing simplified approaches for lower-risk patients while retaining full NEWS or electronic health record models for higher-risk patients.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
The goal is to make AI's role in evidence generation transparent to readers, reviewers, and editors so they can evaluate the integrity of scientific findings. The framework is operationalized by a declaration checklist that authors complete at submission.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
This article outlines a strategy of pursuing “prediction without hype” and judging AI by whether it is trustworthy, transportable, and useful at the point of care. Published in JAMA psychiatry, these peer-reviewed psychiatry findings provide quantitative evidence to inform clinical risk stratification, therapeutic decision-making, and follow-up trial design.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Therefore, LLM-as-a-judge is not a safe substitute for experts in German clinical text evaluations, and deployment thresholds should follow decision-impact analysis for LLM-as-a-judge in clinical contexts. All judges exhibited position and identity bias.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
These shifts advance medical AI from technical novelty toward trustworthy, clinically grounded, and ethically deployed foundational science. Pure data-driven artificial intelligence (AI) is insufficient for clinical adoption.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
In this randomized clinical trial of pregnant and postpartum individuals from racial and ethnic minoritized groups, access to a generative artificial intelligence maternal health chatbot did not improve maternal anxiety or depression at 12 months compared with an active control. Secondary and exploratory findings should be interpreted cautiously.
5/5 Gold Standard
Evidence Meter · 5/5
Gold-Standard Human Evidence
Backed by randomized controlled human trials or a formal meta-analysis pooling multiple clinical studies.
This cross-sectional study examines the use of artificial intelligence (AI) in clinical trials conducted starting in 2022. Published in JAMA network open, these peer-reviewed ai in medicine findings provide quantitative evidence to inform clinical risk stratification, therapeutic decision-making, and follow-up trial design.
4/5 Strong Trial
Evidence Meter · 4/5
Strong Clinical Evidence
Tested directly in patients through a prospective clinical trial or large multicenter human cohort.
This cross-sectional study evaluates the association between artificial intelligence scribes and same-da note closure by patient language preference and interpreter modality. Published in JAMA network open, these peer-reviewed ai in medicine findings provide quantitative evidence to inform clinical risk stratification, therapeutic decision-making, and follow-up trial design.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
This cross-sectional study investigated characteristics and reporting of updates to artificial intelligence (AI)/machine learning–based medical devices cleared through the Food and Drug Administration (FDA) 501(k) pathway. Published in JAMA network open, these peer-reviewed ai in medicine findings provide quantitative evidence to inform clinical risk stratification, therapeutic decision-making, and follow-up trial design.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
This study provides first longitudinal evidence of regionally coordinated DNA methylation changes during antidepressant pharmacotherapy, revealing alterations in genes involved in neuroplasticity and inflammatory processes that are associated with clinical response. Baseline methylation levels were associated with depressive symptom severity at day 28 and day 56 through two and six DMRs, respectively (e.g., TNRC6C, CAT), whereas no single DMP reached significance.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
In this quality improvement study, an ML-based delirium risk stratification model maintained acceptable discriminative performance during external deployment without retraining and was similar to its performance at the development site without retraining. Model deployment was also associated with increased diagnostic yield but a high false positive rate.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
However, clinical use should be limited to an adjunctive role rather than standalone rule-out decision-making, and prospective studies are required to evaluate safety, clinician uptake, and real-world impact. Decision curve analysis demonstrated positive net benefit across much of the evaluated threshold range.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
This framework links statistical evaluation to clinical use, model updating, and post-deployment monitoring. When executed to these standards, external validation transforms promising prototypes into dependable clinical tools, clarifying where a model performs, where it fails, and what adaptations are necessary for safe, equitable, and sustainable use.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
We make the model publicly available to facilitate large-scale studies with heterogeneous electrode setups and accelerate biomarker (measurable biological signal) discovery in sleep. Performance improves with more channels, yet remains strong when EOG is absent, or only EOG or single EEG derivations (frontal, central, or occipital) are available.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Our results indicate that individuals with combined autoimmunity and lower insulin sensitivity present with clinical diabetes earlier than classic type 1 diabetes along the β-cell decline trajectory, identifying a potential timeframe for disease-modifying interventions in specific type 1 diabetes subtypes. Adult-onset type 1 diabetes exhibits substantial heterogeneity.
4/5 Strong Trial
Evidence Meter · 4/5
Strong Clinical Evidence
Tested directly in patients through a prospective clinical trial or large multicenter human cohort.
They address in detail many of the controversial issues currently affecting everyday clinical practice and provide insightful comments on how to best triage patients presenting with suspected acute myocardial infarction. Supporters of the dual biomarker (measurable biological signal) strategy argue that a timely optimized algorithm can potentially allow the safe rule-out of myocardial infarction earlier than currently used strategies.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Prospective clinical studies are required to evaluate the safety, effectiveness and clinical utility of EVLF-FM before routine clinical deployment. A hybrid training strategy combining supervised and visual reinforcement fine-tuning enables EVLF-FM to generate clinically interpretable explanations aligned with visual evidence.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
We close with a set of questions designed to focus that speculation among the interested parties who will shape the future of AI in critical care. Within each parable we try to keep visible what current evidence already supports and what remains speculative.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
1 min read·American Journal of Respiratory and Critical Care Medicine·
Our large high-resolution snRNA-seq atlas uncovers age-associated features of CRC and provides a resource for the community to understand EO-CRC biology. Tumor epithelial cells from young patients exhibited increased expression of long noncoding RNAs and FN1, with a trend toward increased heterogeneity in copy number alterations.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Until then, that burden rests with the clinician. Finally, we review emerging understanding of troponin biology, clearance, proteolysis and fragmentation, macrotroponin, antitroponin autoantibodies, and extracellular vesicle-associated troponin, which may eventually allow the assay itself to carry more of the interpretive burden.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
1 min read·Journal of the American College of Cardiology·
This work expands the searchable bile acid metabolome and provides a computational framework for systematic metabolite discovery. In vitro functional validation showed that MS2141 modulates M2 receptor-associated Gi/o signaling and alters electrophysiological parameters in human induced pluripotent stem cell-derived cardiomyocytes.
2/5 Preclinical
Evidence Meter · 2/5
Animal & Preclinical Data
Demonstrated in living animal models before large-scale human safety and dosing trials begin.
These results suggest that BCI control is a strong predictor of outcomes following acute brain injury and provide initial evidence that a bedside, EEG-based BCI system might permit bidirectional communication in critically ill unresponsive patients. Median signal delay for BCI control was 49.8 [interquartile range (IQR) 39.9-75.6] seconds for clinically unresponsive patients, 17.1 (IQR 7.8-19.9) for conscious patients and 15.5 (IQR 12.9-21.2) for healthy volunteers.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
The FDA has created a pilot program for accelerating Phase I clinical trials that pairs drug sponsors with research organizations. Both ARPA-H and the FDA recently launched programs to help accelerate clinical trials.
4/5 Strong Trial
Evidence Meter · 4/5
Strong Clinical Evidence
Tested directly in patients through a prospective clinical trial or large multicenter human cohort.
Together, these results demonstrate a scalable in vivo framework for behavioral phenomics-driven classification of ASD risk genes into functional subtypes and discovery of targeted rescue strategies. By integrating mutant phenotypes with a large neuroactive drug phenomics database, we identified subtype-specific correlations with serotonergic, dopaminergic, and opioid receptor-modulating compounds.
2/5 Preclinical
Evidence Meter · 2/5
Animal & Preclinical Data
Demonstrated in living animal models before large-scale human safety and dosing trials begin.
Strengthening these practices may improve the usability of clinical prediction model studies and support their deployment in real-world clinical settings. Repository assessment showed substantial heterogeneity in reproducibility features.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Recognising EFs as a transdiagnostic cognitive endophenotype governed by rational control processes opens new avenues for precise, developmentally informed, and targeted interventions in youth mental health. Disruptions in reward and effort processing-manifesting as anhedonia and apathy-are common across mental health conditions and may compromise EF performance by altering these computations.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
Hospitalisation, regardless of country, is characterised by loss of short-chain fatty acid-producing taxa, functional shifts, ARG and pathway changes. Gut microbiome composition and function are associated with short-term hospitalisation risk and provide additional prognostic information beyond clinical variables in a multicountry cohort.
3/5 Observational
Evidence Meter · 3/5
Real-World Observation
Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.
1 min read·Gut·
Patient & Student Companion
Everyday Lab & Drug Translator
Instant plain-English guides for common blood tests and prescriptions—what normal ranges mean, what high/low values signal, and what to ask your clinician.
Lab Marker3-Month Blood Sugar
HbA1c
Measures the percentage of red blood cell hemoglobin coated with glucose over roughly 90 days.
Normal: below 5.7% · Prediabetes: 5.7%–6.4%
6.5% or higher on two tests diagnoses diabetes; very low values can occur alongside hypoglycemia or hemolytic anemia.
Ask your doctor: “Does my HbA1c match my daily fasting/post-meal glucose trends?”
Estimated glomerular filtration rate—how many milliliters of blood your kidneys filter every minute.
Healthy adult filter rate: 90+ mL/min/1.73m²
Values persistently below 60 for 3+ months (or elevated urine albumin) mark chronic kidney disease; single dips can simply reflect dehydration or NSAID use.
Ask your doctor: “Should we pair eGFR with a urine albumin-to-creatinine test (uACR)?”
