For how we live.
AI, devices, digital health, and what the evidence supports.
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.
Rejoyn, the first prescription digital therapeutic cleared for major depression, beat a sham app on a backup analysis. Its pre-specified primary endpoint fell just short of significance.
A January 2025 draft guidance lays out the documentation the agency expects across an AI device's whole life, including bias checks across demographic groups and postmarket monitoring.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.
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.
Since 2024 the FDA has cleared over-the-counter CGMs for people who don't use insulin. The first independent accuracy check in adults without diabetes finds the sensors track the trend but miss the exact number.
A federal rule now requires certified electronic health records to publish a standard set of facts about each predictive algorithm they ship, including how it was validated and whether it was tested for fairness.
EndeavorRx is a prescription game the FDA cleared in 2020 for children with ADHD. Its pivotal trial moved a computer attention score, but the FDA says it may not help the behaviour parents notice.
Software that interprets cardiotocography in labour lifts clinicians' accuracy in reader studies. The largest randomised trial of computerised interpretation, in 47,062 women, found no benefit for mothers or babies.
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.
Companion chatbots eased loneliness as much as talking to a person in one set of studies — and the same research documents emotional dependence and users who are lonelier to begin with.
In a 64-patient randomised trial, home cardiac rehab monitored by a smart ring improved fitness. But both arms wore the ring; what separated them was a weekly call from a clinician.
RelieVRx is an authorised virtual-reality therapeutic for chronic low back pain. Its trials show real improvement — but in a 1,067-person study the edge over a placebo headset was 0.4 points on a 10-point scale.
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.
The Hypotension Prediction Index warns anaesthetists before blood pressure falls. Three 2026 trials find a plain mean-pressure alarm does the same job, and the algorithm's benefit tracks how hard clinicians treat.
TRICORDER put an AI-enabled stethoscope into UK primary care. Over a year it did not increase heart-failure diagnoses population-wide, even though the device, when actually used, flagged more disease.
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.
Every low-dose CT for lung cancer also images the heart. A 323-scan study found an AI tool matched expert calcium scoring almost exactly — and separate data show why that number carries weight.
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.
Rings and watches sold online promise needle-free glucose readings. The FDA says do not use any of them, and even research-grade non-invasive sensors miss the mark by about a fifth.
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.
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.
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.
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.
Implanted electrodes now decode attempted speech into text for people who cannot speak. Results are striking — up to 62 words a minute — but come from single participants, need brain surgery, and remain research.
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.
A closed-loop system links a glucose sensor to an insulin pump so software doses automatically. In the pivotal 6-month trial it raised time in target range by 11 points over a standard pump — a bounded gain, not a cure.
An autonomous AI for diabetic retinopathy hit 87.2% sensitivity in primary care. A smartphone acuity test agreed with a reference chart to within 0.07 logMAR. Both are triage, not diagnosis.
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.
A year of alerts at one hospital shows the safety pop-ups clinicians dismiss almost automatically — and why the field still cannot agree on how to measure the problem.
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.
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.
A smartphone app delivering CBT cut tinnitus-related distress about 20 points more than a sham app in 60 adults, and the effect held for two months. The trial was small and industry-funded.
A pandemic waiver letting clinicians prescribe stimulants and other controlled medicines without an in-person visit has been extended a fourth time, to end-2026, with the permanent framework still a proposal.
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.
23andMe's cleared BRCA report reads 3 of more than 1,000 mutations, so a negative result is not the all-clear it looks like — and the firm's bankruptcy has put customers' genetic data in play.
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.
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.
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 deep-learning system drew tumour targets and organs at risk automatically. It saved time and improved consistency — but oncologists still reviewed and edited the contours before treatment.
Automatic fall alerts are mostly tested on staged laboratory falls, with real-world validation in older people rare. A 2026 meta-analysis of fall prediction found high specificity but only moderate sensitivity.
The first randomised trial to report interval cancers found AI non-inferior to double reading, with higher sensitivity at equal specificity. Across three European programmes the extra detection is about one per 1000.
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 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.
Green-light pulse sensors raise a real concern about melanin, but independent tests find the skin-tone effect small next to device and movement errors — and the validation studies barely include darker skin.
Linking exome data to electronic medical records solved 15% of unexplained hearing-loss cases and flagged new candidate genes — while showing what the records could not supply.
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.
A Danish stepped-wedge trial gave endoscopists automated feedback on their technique after every procedure. Adenoma detection rose from 43.4% to 48.6% — a different tool from real-time polyp AI.
Trained on 1.7 million ECGs paired with clinicians' report text, ECG-CLIP reached the same accuracy as the best comparator with about 90% less training data — a bid at the field's labelling bottleneck.
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.
Relationality, self-governance, competence. The position paper's starting premise is that consensus on privacy, disclosure and fairness has not been reached, and clinicians need guidance anyway.
Across 24 official German licensing exams, the best model answered 99.31% of first-exam items correctly. On items containing an image, the error rate rose several-fold, against 1.24x for students.
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.
A network meta-analysis of 53 studies and more than 7 million admissions finds machine learning out-discriminates traditional sepsis scores — and would raise roughly two false alarms for every real one.
A system called Quicker writes clinical guideline recommendations through a GRADE workflow. A Matters Arising and its reply, published the same day, map what still has to be built around it.
European hypertension specialists found only two wrist-cuff blood pressure watches with validation studies done to established protocols. A sleep group ran a Galaxy Watch against two nights of polysomnography.
A researcher who expected the evidence base to be thin says even she was surprised by how thin. Most cleared devices never appear in a registered clinical trial at all.
The tool reads vital signs, lab results, and history the way clinicians already do — just faster and continuously. Its accuracy tops out around 90%, which means it's also still wrong a meaningful share of the time.
A new discussion paper proposes a two-axis risk framework and a physician-training analogy for evaluating generative AI devices. It is not a rule, and the agency is asking what one should look like.
Emulating a trial inside Veterans Health Administration records, researchers estimated adjusted mortality risk ratios of 0.90 to 0.84 for starting continuous glucose monitoring in older-onset type 1 diabetes.
It found no meaningful difference at six weeks. It enrolled 64 people, tested one device, and ran for six weeks. That is the entire head-to-head evidence base three years after the category opened.
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.
A Nature Reviews Drug Discovery audit says the problem isn't the models. They were built to be validated rather than used, and benchmarked against the wrong thing.
Most wellness apps make no disease claim and face no federal review. Into that gap, US states are writing their own AI-in-mental-health laws — four already diverge, leaving users unevenly protected.
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.
START-AI reads triage comments, case notes and whether anyone ordered a blood test. Adding heart rate and blood pressure to the model produced no measurable improvement — a result the team published rather than buried.
A study of 2.4 million veterans a month finds health information exchange volume moving outcomes in opposite directions depending on which side of the exchange you are on.
A blinded comparison of 180 responses from a university telehealth centre in Minas Gerais found AI matched human specialists on medical adequacy and risk, and beat them on comprehensibility.
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.
42 orthopedic physicians diagnosed 40 rare diseases twice, once alone and once after seeing AI suggestions. Accuracy jumped 20 to 26 points, but the same-day design leaves memory unaccounted for.
A Lancet Digital Health scoping review found the field's fairness metrics fragmented and rarely clinically validated. A second review found that most studies don't measure fairness at all.
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.
Maccabi Healthcare Services studied 626 of its own physicians to work out who follows algorithmic prescribing advice — and found the pattern was about practice structure, not just attitude.
Two 2026 meta-analyses pooled deep-learning systems reading retinal images for AMD. The accuracy looks near-perfect, but almost all of it comes from algorithms tested on their own data.
A paper in the journal Resuscitation lays out how a large language model could help dispatchers recognize cardiac arrest and coach CPR in real time — while acknowledging the concept still needs to prove it saves lives.
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.
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.
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.
Pooled across 48 trials, chatbots cut depression, anxiety and stress by small amounts. But a review of purpose-built mental health chatbots found crisis-referral protocols underdeveloped and missed suicidal ideation.
A small proof-of-concept study pitted several AI systems against gastroenterologists and emergency physicians on cholangitis exam questions. The gap between the best and worst AI performers was enormous.
A new structured dataset finally makes the approvals countable. Two trials published weeks apart show why counting them says little: 0.86 fewer migraine days in one, a 20-point symptom shift in the other.
The agency granted its first authorization for a software-aided adjunctive diagnostic device in wound assessment, a category built for tools that analyze a wound optically.
A study running 5.3 million evaluations through nine large language models found eligibility judgments were largely stable across identity labels — except when a patient vignette mentioned homelessness.
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 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.
DxDirector-7B beat human physicians on a benchmark of complex diagnostic cases while requesting far fewer tests. Its own authors say it isn't ready for high-risk or emergency cases.
A secondary analysis of the VITAL-AF trial reports a screening benefit only in the top risk decile — with a confidence interval whose lower bound sits at 0.01.
It is a wellness feature, not a cleared pulse oximeter, and it inherits pulse oximetry's known skin-tone bias. A patent fight also stripped it from US watches for about 19 months.
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.
GE's Critical Care Suite gains an algorithm that flags misplaced enteric tubes on a chest X-ray — a complication that reviews of the practice have linked to respiratory harm and, in some cases, death.
A content analysis of every FDA cybersecurity safety communication from 2013 to 2025 finds a small corpus, rising over time, and 94% of the flagged vulnerabilities rated severe.
The clearance is the third in a growing family of machine-learning notification algorithms built to spot serious cardiac conditions from a routine 12-lead ECG, a test most patients already get.
A new audit of China's regulatory record finds a market concentrated in radiology, dominated by deep learning, and clustered in four cities. It also finds the approval curve flattening.
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.
reSET, Somryst and EndeavorRx cleared a real regulatory bar, on real trial data. The pivotal ADHD game moved an attention score by 0.88 of a point. Clearance is not the obstacle the category keeps hitting — payment is.
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.
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.
A February theme issue documents faster notes, happier clinicians and enterprise rollouts to thousands. It also contains an editorial asking the question none of the studies answer.
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.
Ten studies, wide confidence intervals, and factual error rates of 26 to 36 percent in AI-drafted documentation. The review's own conclusion is that the evidence is preliminary and highly uncertain.
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.
An 11,018-measurement study in 24 English intensive care units found false negative rates up to 35.3 percentage points higher in patients with darker skin tones. A neonatal study published two days later did not.
The announced lab pairs robotic wet labs with computational models in a continuous loop. It is a serious bet on a real bottleneck — and, so far, entirely a forward-looking statement.
Revised guidance reverses the 2022 position that a single recommendation made software a device. The agency's own criterion — that a clinician can independently review the basis — now carries the weight.
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.
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.
The EAGLE trial ran colonoscopy AI off-site over a network and aimed it at the lesions that matter. It reports a threefold gain in serrated lesions — in a field whose main US guideline recommends nothing.
One agency asked how to measure AI devices after they are deployed. Another asked how to speed adoption up. The offices that would answer the first question are losing staff.
Germany's DINKS trial is one of the largest randomised tests of a reimbursable digital therapeutic. The effect is big, the comparator is usual care alone, and the sponsor made the app.
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.
England ran the closest thing to a national test of clinical AI anyone has published. The software sites gained more, but the comparison sites were improving on their own, and that gap is the whole result.
The WISeR model starts on 1 January in six states. The contractors running it are paid out of the savings their determinations produce — the design feature doctors keep pointing at.
Two November trials found ambient AI cut documentation time and work exhaustion. A parallel emergency department comparison found physicians spent more time in the note, not less.
A systematic review of every AI device authorised from 1995 to June 2024 found 97% cleared through the 510(k) pathway, which does not require independent clinical data on performance or safety.
Ten sonographers estimating gestational age got sharply more accurate when shown model predictions. Adding visual explanations improved the average further but made several individuals worse.
Physicians editing AI drafts wrote better notes than they did unaided, and worse notes than the AI produced alone. Both directions of that result matter.
PpgAge predicts chronological age from consumer wearable photoplethysmography and tracks disease. The same optical method has documented accuracy problems across skin tones.
Twenty experts scored three language models on ten common questions. One model cleared the content validity bar on both topics; another scored zero on jet lag.
Across 40 trials, self-guided apps moved panic severity modestly and barely touched fear-related cognitions. Clinician-guided versions moved both — which complicates the scalability pitch.
A census of 691 AI-enabled devices cleared through 2023 found demographic data missing almost everywhere, three summaries reporting patient outcomes, and 113 recalls driven mostly by software.
Across 90,670 virtual encounters at one US health system, phone visits scored lower on likelihood to recommend. A separate VA cohort of 1.2 million found telehealth cut same-day mental health access sharply.
An EHR-embedded model wrote hospital summaries residents edited less — but with more confabulations. A separate pipeline audited 21,041 trial reports against CONSORT at 91.7% agreement with experts.
EyeFM was tested as an assistant to 16 ophthalmologists screening 668 high-risk patients in China. Patients in the AI arm also followed referral advice more often.
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.
Off-the-shelf features from two published models matched retinal scans to the right patient 78% to 86% of the time. Fine-tuned for the task, one model reached 99.5% on OCT.
Singapore General Hospital randomised residents to work with and without an LLM assistant. Documentation time fell by 1.82 minutes, which was not significant. The economic model used the point estimates anyway.
EchoNext scored 77.3% accuracy on a 150-ECG set where 13 cardiologists averaged 64.0%. Its authors released the model weights and a 100,000-ECG labelled dataset alongside the paper.
A draft-reporting model cut documentation time 15.5% across 23,960 radiographs without changing report quality. A separate reader study found AI assistance raised prostate MRI accuracy by 3.3 percentage points.
Rentosertib was safe over 12 weeks in 71 patients with idiopathic pulmonary fibrosis. A lung-function signal appeared at the highest dose, in a trial not designed to prove efficacy.
Reported health-data breaches rose 100% from 2018 to 2023 and the people affected by them 950%. A federal proposal would drop the rule's 'addressable' loophole and require encryption, multi-factor login and more.