For how we live.
A final FDA guidance treats the on-screen output of software sent with a prescription drug as a type of drug labelling, and says how the prescribing information should describe it and when sponsors submit it for review.
In 143 people with poorly controlled type 1 diabetes, a system that prompts injections through glucose-sensor alerts was non-inferior to standard monitoring — and acting on the alerts drove the benefit.
An observational study of 8,127 UK women on GLP-1 drugs, almost all tirzepatide, reported 16.1 kg average loss at six months and 91.4% retention. There was no control arm.
In preregistered trials of more than 90,000 patients, telling people an algorithm flagged them as high-risk lifted vaccination by a few points — and saying the algorithm was involved changed nothing.
A new draft guidance sets out the agency's current thinking on the non-clinical and clinical data it expects in premarket submissions for robotically-assisted surgical devices. Comments are due 24 November.
A January 2025 draft guidance lays out the documentation the agency expects across an AI device's whole life, including bias checks across demographic groups and postmarket monitoring. It is not yet binding.
Wrist trackers infer light, deep and REM sleep from movement and pulse. Two validation studies find they track total sleep passably but each misjudges the stage breakdown its own way.
Writing about your thoughts and feelings has a real but small average effect across 146 trials; a web-based journaling study eased anxiety in medical patients. Useful, not a cure.
The advice to look 20 feet away for 20 seconds every 20 minutes is everywhere. A two-week trial in symptomatic computer users found it cut eye-strain and dry-eye symptoms, but changed no measurable sign of eye health.
A dormant breach-notification rule became an enforcement tool in 2023, when the FTC fined GoodRx and BetterHelp for sharing users' health data with ad platforms. A 2024 rule change locked apps into its reach.
Under Article 6, AI that is or sits inside a device already needing an independent safety check counts as high-risk. A 70-study review finds the trouble is overlap with existing device law.
In a 230-patient randomised trial, self-guided app hypnotherapy produced a 33% pain response versus 48% with an in-person therapist and 22% with education — falling short of non-inferiority.
Abilify MyCite embeds a sensor in an antipsychotic tablet to log each dose to an app. Nearly a decade on, its own FDA label still says it has not been shown to improve whether patients take their medicine.
Compulsively scrolling bad news tracks with worse mental and physical health — but the strongest studies show association, not proof, and the scariest prevalence figure shrank by half on replication.
Across 17 randomised trials, blue-light filtering lenses showed no clear benefit for eye strain, vision or sleep. The evening-screen problem they target is real; this is not the fix.
A randomised trial put a number on how much misinformation lowers vaccination intent. A systematic review mapped how common it is. And inoculation studies show the skill of spotting it can be trained at scale.
Contactless photoplethysmography turns an ordinary camera into a heart-rate monitor, and pooled studies show it tracks pulse well. Oxygen, respiration and the stress scores layered on top rest on far thinner evidence.
Digital adherence gadgets promise to fix forgotten doses. In a 53,480-person randomised trial, low-cost reminder devices did not raise adherence at all. Text reminders did more, but on short, self-reported trials.
Dopamine is a learning signal that tracks surprise, not a pleasure tank you drain and refill. Stripped of the neuroscience label, the practice is ordinary stimulus control — and that narrower version has some support.
Smart rings and watches measure peripheral skin temperature and report drift from your own baseline, not a thermometer reading. That makes them decent trend sensors and poor fever detectors.
Medicare paid over $500 million for remote monitoring in 2024, but a watchdog found 43% of patients didn't get the full service — and rigorous evidence that it improves outcomes remains limited.
Reviews find portals may improve awareness and the patient–doctor relationship, with unclear effect on efficiency. Under new US rules, patients now see 40% of results before their clinician does.
A 2025 rule created billing codes for FDA-cleared mental-health software. The 2026 rule adds short-episode remote-monitoring codes but declines to widen the digital-therapy benefit.
Randomised trials show acute care delivered at home costs less, uses fewer tests and readmits fewer patients — while making little or no difference to whether they survive.
A predetermined change control plan is the FDA's answer to a model that keeps learning: pre-approve a bounded set of future changes, and the manufacturer can ship them without returning for a fresh review.
A review of 23 women's health apps found 87% shared user data with outside firms. The main US rule that covers them orders breach disclosure — it does not stop the sharing.
Sensors and reminder inhalers get patients to take more doses — one trial lifted adherence from 30% to 84%. That this translates into meaningfully better control is real but a smaller effect.
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.
Toilet seats and mirrors that read your heart and blood pressure are real engineering. The published validation is mostly small, single-lab or company-run — and outcome evidence is absent.
A meta-analysis of consumer neurofeedback found no benefit for cognition, mindfulness or physical health and only a small effect on distress — even though the headbands do record real brain activity.
One found doctors stopped using it as shifts got busier. The other, in 9,691 Kenyan patients, found it safe but no better than the electronic record alone. Neither supports deployment.
A trial in India found calling tuberculosis survivors was non-inferior to visiting them, on a combined measure. Split into survivors and their contacts, the picture reverses for the group at highest risk.
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.
Researchers built an AI pipeline to convert decades of narrative reports into one modern TNM staging system, reaching 95% accuracy for tumour classification in an expert-labelled test set.
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.
In 216 patients with chronic patellofemoral pain across 10 Korean hospitals, an 8-week digital therapeutic beat education and exercise instruction on pain — by 12.5 mm on a 100 mm scale.
In 6,772 users of a US health system's AI triage tool, people engaged about twice as often when the AI matched what they already planned — raising a hard question about what the tools are steering.
A review of 41 studies found that the great majority of AI medication-adherence prediction models carried high risk of bias, and that fancier algorithms did not reliably predict better.
Thirty-two interviews across Uruguay, Argentina, Chile and Mexico find implementation turned on governance, not software. A separate patent analysis shows where digital therapeutics are not being built.
Head-to-head against an ECG chest strap, popular optical wrist devices differed substantially, and one graded test found a smartwatch running a couple of beats low with a 28-bpm spread in its limits of agreement.
Endometriosis takes up to a decade to diagnose. A modelling study estimated a digital symptom checker could cut that by 4.36 years — but the tools still lack the external validation to trust in practice.
An umbrella review of 42 reviews found only two wearable measures — heart rate and atrial fibrillation — with comparably strong support. Getting any device into a trial is harder than buying it.
Eye strain is close to universal among heavy device users, and it is temporary. The evidence that screen time causes myopia is real but weak, and every study of it measured screen time by questionnaire.
In a 22,785-user study of one temperature-based app, typical use failed 6.9 per 100 woman-years and perfect use 1.0 — but the study came from the maker, and traditional methods vary widely.
Two 2026 meta-analyses of type 2 diabetes apps found HbA1c reductions of 0.39 and 0.58 points versus usual care — modest, clinically meaningful, and consistent, though the trials vary widely in quality.
A review of Paige Prostate Detect and Ibex Prostate Detect finds the tools mainly help less-specialized pathologists, and warns performance shifts when a tool meets a new population.
A low-probability alert still sends most recipients to a doctor. Researchers are now naming the flip side of continuous self-monitoring — a device-driven health anxiety they call technohypochondria.
In 230 adults followed a year, lower heart-rate variability and less moderate-to-vigorous activity at baseline were independently linked to developing hypertension. It is a risk signal, in one unreplicated cohort.
An audit of 17 manufacturers' privacy policies found transparency the weakest area, with wide variation between brands. The data these devices generate largely falls outside HIPAA and GDPR's clinical protections.
A month-long trial that blocked mobile internet improved mental health and attention, and a one-week social-media break lifted wellbeing. The wider literature is thinner.
These features are verifiable and occasionally decisive. The one study of Medical ID in trauma found most unconscious patients had no usable emergency info on their phone at all.
A meta-analysis of fully automated programmes found a large effect on insomnia severity. A review of 68 studies found the field has barely measured whether recipients find them acceptable.
Smart-ring studies report flagging COVID nearly three days before symptoms and IBD flares weeks ahead. But two-thirds of that research carries a high risk of bias, and clinical usefulness is largely unproven.
Wrist temperature rises after ovulation, not before it. That makes the watch's retrospective estimate biologically sound and useless as a way to predict the fertile window.
Pooled against the sleep lab, finger-worn devices call sleep versus wake at 87% but fall to the mid-60s on light sleep. An Oura meta-analysis found no significant gap on total sleep time.
In the FDA study, self-fitted AirPods matched a professional fitting for perceived benefit. Independent testing finds the hearing test accurate to about 10 dB — and the amplification short of a fitted aid.
A network meta-analysis put pooled accuracy for the fertile window at 0.88, best in the three days around ovulation. A wrist-temperature study hit ovulation within three days about 78% of the time.
A cross-sectional analysis of NICE evaluations found 78 supporting studies behind 30 technologies — and consistent holes in comparators, cost of delivery and adverse-event reporting.
A Nature Communications review of the continent's biomedical data science capacity found none of 36 surveyed groups using cloud high-performance computing, and named electricity outages among the most common obstacles.
A 1,298-person randomized study found people using chatbots to work through medical scenarios did no better than people without them — even though the same chatbots, tested alone, got the right answer most of the time.
Researchers ran 960 responses through ChatGPT Health using clinician-written vignettes. Failures clustered at both extremes, and crisis safeguards activated unpredictably.
A small qualitative study finds device dependency, blurred motivation and users who no longer trust their own bodies. It lands as health services keep integrating the same devices.
The FDA cleared it to sort one rhythm from one other. It cannot detect a heart attack, and about one reading in eight comes back inconclusive.
Among watch wearers told their pulse looked irregular, a third had atrial fibrillation confirmed on a follow-up ECG patch. Most who were notified did not.
A 250-person randomised trial paired a wearable tracker with just-in-time energy-management messages. Post-exertional malaise fell in both arms, and the difference between them was trivial.
A trial across five Chinese hospitals found remote robotic urological surgery non-inferior to local surgery. The sample is small, the surgeons were experts, and the network never failed.
Clinicians rated empathy at 4.6 out of 5 and quality of information at 2.7. Every chatbot produced at least one piece of guidance judged inappropriate, overstated or inaccurate.
The landmark audit found the right diagnosis listed first in 34% of cases and correct triage in 57%. A newer heart-attack test exposes the dangerous edge: most atypical cases missed, and women.
Against an ECG over 536 nights, Oura's heart-rate-variability error was under 8% and Whoop's acceptable, while Garmin and Polar lagged. The recovery scores layered on top stay proprietary and largely unvalidated.
The FDA's revised general wellness policy lets non-invasive devices infer blood pressure, glucose and other physiologic parameters. The regulated line is no longer the measurement — it is the sentence next to it.
Standard questionnaires found no daytime difference between suvorexant and placebo. Four-times-daily smartphone prompts found fatigue worse in the morning and better later. The trial had 40 people.
A mirror that scores physiological age in 30 seconds. A watch that watches your gait for dementia. The gap between what these products measure and what they imply is the story of the show.
The headline finding is noninferiority. The more useful finding is what the shared denominator was — and how wide a gap the trial was designed to tolerate.
A smartwatch bioimpedance sensor tracked body-fat percentage against DXA with about 14% average error — but muscle-mass agreement was weak, and even sitting versus standing shifted the reading.
A meta-analysis of 26 studies put pooled sensitivity at 95% and specificity at 97%. Samsung and Withings devices performed comparably to Apple — but the numbers come from people already suspected of arrhythmia.
PpgAge predicts chronological age from consumer wearable photoplethysmography and tracks disease. The same optical method has documented accuracy problems across skin tones.
Google's PH-LLM beat sampled human experts on multiple-choice tests but only matched them on real cases. A new reporting checklist published the same month explains why such claims are hard to compare.