Add BrightSurf on Google Email

Check for copycat bias in medical AI

A scoping review found that only 77 studies validating 52 medical AI products reported demographic data, highlighting the need for more transparent reporting to confirm safe and unbiased performance. The review also showed that performance reporting for demographic subgroups is inadequate, posing a risk to patient care and outcomes.

SourceOsaka Metropolitan University·JournalEuropean Radiology·TypeSystematic review·DateSep 2, 2026

AI-enabled stethoscope can miss the beat in pets

A new study from North Carolina State University found that an AI-enabled digital stethoscope struggled to detect cardiac murmurs and arrhythmias in cats, while performing moderately well in dogs. The researchers emphasize the need for veterinarians to rely on human expertise when using AI-assisted technology.

SourceNorth Carolina State University·JournalJournal of the American Veterinary Medical Association·TypeExperimental study·DateAug 12, 2026

ADLM 2026 to explore diabetes milestones, space diagnostics, Alzheimer’s and Down syndrome linkages, and advances in cancer screening and biomarkers

The meeting will explore breakthroughs in diabetes prevention and treatment, as well as innovative approaches to monitoring astronauts' health in space. Researchers will also discuss potential targets for slowing or preventing Alzheimer's disease in people with Down syndrome, and advancements in cervical cancer screening.

Global heterogeneity and implementation gap in acute kidney injury prevention in ICUs: Results from the international AKI-PURIFY survey

The AKI-PURIFY survey reveals substantial variability in AKI prevention strategies and KDIGO implementation across ICUs. Despite strong evidence supporting structured preventive approaches, only one-third of respondents reported routine implementation of kidney-protective bundles.

SourceJournal of Intensive Medicine·JournalJournal of Intensive Medicine·TypeSurvey·DateJul 3, 2026

Mount Sinai opens Carolyn Rowan Center for Women’s Health and Wellness, a new model of coordinated care across the lifespan

The Mount Sinai Health System has opened the Carolyn Rowan Center for Women’s Health and Wellness, which brings together multidisciplinary clinical expertise, structured care pathways, and leading-edge research to deliver personalized, comprehensive care for women. The Center offers guided multi-visit experiences and coordinated care o...

International experts call for end to routine reporting of “corrected” calcium

International experts in laboratory medicine, osteoporosis, and chronic kidney disease recommend ending routine reporting of albumin-adjusted ('corrected') calcium. The practice may misclassify patients and compromise care due to unreliable correction formulas and variability in local measurements.

SourceInternational Osteoporosis Foundation·JournalClinical Chemistry and Laboratory Medicine (CCLM)·TypeCommentary/editorial·DateMay 18, 2026

Why diagnosing endometriosis often takes many years

Two new studies from Aarhus University reveal that endometriosis is often difficult to recognize in its early stages, requiring a systematic approach even when symptoms are diffuse. The studies highlight the need for improved knowledge, collaboration with specialists, and referral pathways to reduce diagnostic delays.

SourceAarhus University·JournalBritish Journal of General Practice·DateApr 22, 2026

A CNIO group contributes to identifying which breast lesions will progress to cancer, thus helping avoid overtreatment

A study by the CNIO group has identified a genetic signature in precancerous breast lesions that can predict which ones will evolve into invasive tumours. This discovery could help avoid over-treatment of women diagnosed with ductal carcinoma in situ, a common precancerous lesion.

SourceCentro Nacional de Investigaciones Oncológicas (CNIO)·JournalNature Communications·TypeExperimental study·DateApr 20, 2026

AI remains lacking in clinical reasoning abilities, according to study of 21 large language models

A study of 21 large language models found that they excel at accurate final diagnoses but falter at differential diagnoses, highlighting the need for human oversight in healthcare. The researchers developed a novel measure, PrIME-LLM, to evaluate AI's clinical competency across different stages of reasoning.

SourceMass General Brigham·JournalJAMA Network Open·TypeComputational simulation/modeling·DateApr 13, 2026

Study finds sex- and race-based disparities in IBS diagnosis rates among US adults

A national survey found significant disparities in IBS diagnosis across sex and racial groups in the US. Men and Black patients are less likely to receive a formal diagnosis compared to women and white patients, despite similar reported healthcare-seeking behavior and symptom severity.

SourceUniversity of California - Los Angeles Health Sciences·JournalClinical Gastroenterology and Hepatology·TypeData/statistical analysis·DateApr 9, 2026

Optical genome mapping detects additional genetic variants in nearly 20% of individuals with acute leukemia

A new clinical diagnostic test using optical genome mapping (OGM) has been shown to detect additional genetic variants in nearly 20% of individuals with acute leukemia. OGM offers a comprehensive view of the genome, refining diagnosis and risk stratification, and improving therapy selection. The test's high diagnostic yield and ability...

SourceElsevier·JournalJournal of Molecular Diagnostics·TypeExperimental study·DateMar 11, 2026

New study predicts real-world impact of using smartwatches to detect undiagnosed high blood pressure

A new analysis found that wearing an Apple Watch with hypertension notifications can increase the probability of having hypertension in younger adults, while decreasing it in older adults. The study also revealed racial and ethnic disparities in cardiovascular health, highlighting the need for targeted screening and treatment.

SourceUniversity of Utah Health·JournalJAMA·TypeData/statistical analysis·DateFeb 9, 2026

AI model helps diagnose often undetected heart disease from simple EKG

Researchers developed an AI model that can detect coronary microvascular dysfunction using a common electrocardiogram, outperforming previous models in diagnostic tasks. The model can accurately identify a condition often missed in emergency department visits, providing a cost-effective and non-invasive way to diagnose serious heart co...

SourceMichigan Medicine - University of Michigan·JournalNEJM AI·TypeComputational simulation/modeling·DateDec 16, 2025

FAU engineers decode dementia type using AI and EEG brainwave analysis

Researchers at Florida Atlantic University have developed a deep learning model that detects and evaluates Alzheimer's disease (AD) and frontotemporal dementia (FTD) using EEG brainwave analysis. The model achieved over 90% accuracy in distinguishing individuals with dementia from cognitively normal participants.

SourceFlorida Atlantic University·JournalBiomedical Signal Processing and Control·TypeComputational simulation/modeling·DateDec 10, 2025

FAU Engineering study takes a ‘quantum leap’ to detect kidney disease

A recent FAU Engineering study leverages quantum computing to enhance the accuracy of chronic kidney disease (CKD) diagnosis. The research team developed and compared two automated systems: Classical Support Vector Machine (CSVM) and Quantum Support Vector Machine (QSVM). CSVM achieved remarkable 98.75% accuracy, while QSVM reached 87....

SourceFlorida Atlantic University·JournalInformatics and Health·TypeData/statistical analysis·DateNov 12, 2025

Association for Molecular Pathology develops standardized biomarker report template for providers

The Association for Molecular Pathology has created a standardized biomarker report template to simplify complex molecular profiling data presentation to oncologists and healthcare providers. The template includes guidelines for clear formatting, therapeutic guidance, and references to clinical practice guidelines.

SourceAssociation for Molecular Pathology·JournalJournal of Molecular Diagnostics·DateOct 8, 2025

Achalasia diagnosis simplified to AI plus X-ray

Researchers developed an AI model that diagnoses achalasia using plain chest X-rays, outperforming physicians' reviews. The diagnostic performance of the AI model demonstrated higher sensitivity and specificity, enabling early diagnosis and potentially improving treatment efficacy.

SourceOsaka Metropolitan University·JournalClinical Gastroenterology and Hepatology·TypeObservational study·DateSep 18, 2025

FAU/Baptist Health AI spine model could transform lower back pain treatment

Researchers developed a fully automated finite element analysis pipeline to transform spine diagnostics and personalized treatment planning. The new approach enables rapid, patient-specific simulations that support preoperative planning, spinal implant optimization, and early detection of degenerative spine conditions.

SourceFlorida Atlantic University·JournalWorld Neurosurgery·TypeComputational simulation/modeling·DateSep 17, 2025

A practical tool to support harmonization and quality improvement in vitamin D testing

A new study published in Clinical Chemistry and Laboratory Medicine has developed a practical tool to support harmonization and quality improvement in vitamin D testing. The multicentre study evaluates the measurement uncertainty of various 25-(OH)D assays and their ability to detect physiologically relevant changes over time.

SourceInternational Osteoporosis Foundation·JournalClinical Chemistry and Laboratory Medicine (CCLM)·TypeExperimental study·DateSep 11, 2025

Fast, accurate, low-cost diagnostics: No lab required

Researchers at Arizona State University have developed a rapid and accurate diagnostic test called NasRED that can detect diseases like COVID-19 with high sensitivity. The test uses tiny gold nanoparticles to identify disease-related proteins in a sample of bodily fluid, providing lab-quality accuracy without expensive equipment.

SourceArizona State University·JournalACS Nano·TypeExperimental study·DateAug 12, 2025

CNIO researcher develops a test aimed to detect early-stage tumors with a blood sample

Researchers developed a test to detect early-stage solid tumors using a blood sample, identifying patterns in amino acid concentrations that can translate into diagnostic signals. The test achieved an 87% positive rate and showed potential for precision medicine in choosing treatments.

SourceCentro Nacional de Investigaciones Oncológicas (CNIO)·JournalNature Communications·TypeExperimental study·DateJul 31, 2025

Reliance on administrative billing codes to track medical conditions can lead to high diagnostic error rates

Researchers found that billing codes may mistakenly identify diseases in up to 45% of cases, highlighting a significant limitation in using administrative data for clinical research. The study examined records of 1.36 million patients and found discrepancies between coded diagnoses and actual disease presence.

Electromagnetic navigation bronchoscopy: an optimal strategy for localizing multiple pulmonary nodules

A study of 203 patients shows that electromagnetic navigation bronchoscopy (ENBDM) is a safer and faster alternative to CT-guided localization for preoperative treatment of multiple pulmonary nodules in the same lung. ENBDM achieved comparable accuracy with lower complication rates, making it an optimal strategy.

SourceNational Center for Respiratory Medicine·JournalTranslational Lung Cancer Research·TypeObservational study·DateJun 20, 2025