For how we live.
A six-site randomised trial of point-of-care high-sensitivity troponin cut emergency-department length of stay by 47 minutes, with no change in 30-day heart attacks or cardiac deaths.
A final order published 9 October classifies systems that let people collect their own specimens for non-viral STI testing as class II, moving them out of the automatic class III that demands premarket approval.
A CMS and CDC proposed rule would codify pandemic-era remote review of digital lab data, allow digital images in gynaecologic cytology proficiency testing, and ease 2024 staffing rules. Comments close 7 December.
Computer-aided detection lifts polyp pickup in ordinary screening. In 757 patients having surveillance for an inherited cancer syndrome, a randomised trial could not show the same gain.
In a 200-patient prospective validation, a DNA-methylation assay reached an AUC of 0.91 and, by one analysis, could have averted about 55% of unnecessary biopsies without missing significant cancers.
The FDA logged the recall of 8,939 StatStrip Glucose and B-Ketone meters on 23 September, after a software flaw let a scanned barcode linger and file a reading to the wrong patient. It is the agency's most serious tier.
Cleared on 10 July under NDA 218579, the Provepharm agent fluoresces in near-infrared light to map vessels, perfusion and lymph nodes during surgery. Efficacy rests on studies of an earlier formulation.
In the TB-Speed project, trained nurses produced valid Xpert Ultra results in 99.6% to 100% of child samples and returned hospital results within three hours far more often than laboratories.
A deep-learning model reads the pancreas on non-contrast CT taken for other reasons. It reached very high accuracy in large tests — none of them a prospective screening trial.
Nail changes can hint at systemic disease — clubbing, spoon-shaped nails, splinter haemorrhages. But the everyday worries, like lengthwise ridges and little white marks, are usually harmless.
In the 142,250-person NHS-Galleri trial, three rounds of screening did not reduce stage III or IV cancers versus usual care. A fall in stage IV cancers alone leaves the case unproven.
An observational study across four DR Congo outbreak sites estimates that a third of positive mpox PCR results reflect environmental viral DNA, not infection — and that a stricter cutoff fixes most of it.
Commercial full-body scans promise early detection to people with no symptoms. The data show they find something to chase in nearly half, and cancer in about one in a hundred.
A multicentre reader study found AI raised early-career dentists' caries sensitivity from 67% to 82% without more false positives. Independent testing shows the same tools still miss early lesions.
External validation of the PAANTHER decision algorithm in 277 children across four African countries recorded 93.3% negative predictive value and 97.4% sensitivity against a composite reference standard.
For adults with no symptoms, the US Preventive Services Task Force recommends against carotid ultrasound screening — a rare 'D' grade, because finding the narrowing does more harm than good.
Wrist and body sensors detect roughly 9 in 10 tonic-clonic seizures. A 192-patient validation against video-EEG found the harder focal seizures still slip past, or bury the alarm in false alerts.
Two 2026 studies posted high accuracy for AI reading Pap-smear cells and colposcopy images in settings short of pathologists. Both were validated internally, which is where such numbers usually shrink.
Commercial software reads an X-ray for breaks about as well as a radiologist. A prospective paediatric emergency study found that accuracy did not translate into fewer missed-fracture recalls.
In the 500-man PRECISION trial, MRI-guided biopsy detected clinically significant cancer in 38% of men versus 26% with the old blind biopsy — and spared 28% a biopsy altogether.
In a prospective African validation, TB-detection AI matched radiologists but neither hit the WHO sensitivity target. In an Indian field programme, AI-led screening lifted case-finding sharply.
In a study of 750 women, those with 'low' ovarian-reserve hormones were no less likely to conceive. Professional guidance says the test shouldn't be used to counsel women who aren't already infertile.
Systems that give a diagnosis with no clinician in the loop post high sensitivity in trials. In real-world use, one in six images was too poor to grade — and the strongest numbers come from company-run studies.
A prescribed home apnea test can diagnose clear-cut cases, and one under-mattress sensor flagged severe apnea with 86% sensitivity — but both miss milder disease and events a lab would catch.
New at-home molecular tests catch most established colorectal cancers, but find only 13–43% of the advanced precancerous polyps a colonoscopy is meant to remove before they become cancer.
Consumer kits reliably estimate sperm concentration, and a smartphone assay matched lab classification ~98% of the time. But a normal count can't rule out the motility, shape and DNA problems a full analysis checks.
Pooled diagnostic accuracy is high in specialist settings, but performance falls on Fitzpatrick IV–VI skin and on smartphone images, and most studies never report skin tone at all.
A Polish study found endoscopists' unaided polyp-detection fell after AI arrived. A Norwegian trial that tracked doctors before, during and after AI use found no such deskilling.
Algorithms that read short voice recordings can pick up acoustic signs of some conditions. In the largest and most careful studies the signals are real but narrow, sex-specific, and often fail to generalise.
A meta-analysis of 155 studies puts photo-based skin diagnosis close to a face-to-face visit for common conditions. For skin cancer the agreement is lower, and hinges on dermoscopy.
A 2,234-patient UK trial gave people with unexplained syncope a 14-day ECG monitor or usual care. A year on, fainting episodes were no fewer — a caution against confusing better detection with better outcomes.
TARGET-CTCA randomised 3,170 emergency patients whose troponin had cleared them of a heart attack. Outpatient CT angiography-guided care matched standard care on later infarction or cardiac death.
Adult TB incidence and mortality are projected to fall 46% and 54% by 2030, short of the 80% and 90% goals. Wider symptom-driven testing matters most to closing the gap, the analysis suggests.
A study of more than 72,000 women found simple ovarian cysts carried no higher cancer risk than normal ovaries, while complex or solid masses did. A large screening cohort found most cysts resolve on their own.
The approved tests are for patients already showing cognitive decline. Used on the worried well, a positive result mostly signals a risk that may never become disease — and no treatment follows from it.
Where AI clot-detection was tested head-to-head, it still missed more emboli than radiology trainees, especially small peripheral ones. Its clearest win was cutting time to diagnosis.
US government metrologists sent one homogenised faecal standard to seven consumer testing services. Species counts came back ranging from 20 to 1,701 for the same material.
Two 2026 studies found people with no ultrasound background produced diagnostic-quality echocardiograms after about a day of AI-guided training. Quality varied sharply by view, finding, and who was holding the probe.
In DigiSep, adding metagenomic sequencing to standard cultures did not improve the main 28-day outcome, though ventilation time and shock resolution were shorter in exploratory analyses.
Three February papers push plasma p-tau217 past detection: clock models estimating years to symptom onset, four assays compared head to head, and a real-world audit of what the result changes.
A transformer model trained on 17,119 scans beat expert and non-expert examiners on every metric and cut simulated referrals by 63%. The catch is who built it and the validation the rest of the field still lacks.
At a Mayo Clinic cohort of 252 patients, 40% of amyloid-negative people tested positive. The manufacturer says it has found a manufacturing problem and put the product on hold.
The external validation of a micro-RNA signature outperformed imaging in 971 symptomatic patients. How it would perform in a lower-prevalence population is the question the study does not answer.
Two BMJ reviews found high-risk usability problems in 18 of 30 tests, and use judged contrary to evidence-based guidance for 11 of the 19 conditions covered.