Diagnostics & Imaging

281 gains94 Traces87 problems

AI in diagnostics and imaging: what 462 records show

Every measured gain and problem on the record for this topic, newest first. Updated November 13, 2026.

The count172 more give context

The records

AI in diagnostics and imaging

What the records show

The records

AI in diagnostics and imaging: what 462 records show · Page 22 · Truvace

Where the evidence stands

The short version

Most of the evidence here is retrospective accuracy testing on past scans and records, with few randomized trials and little tracking of what happens to patients afterwards. TRV-2026-1434 TRV-2026-1490 TRV-2026-0486 Reviewers repeatedly say strong test scores have not yet been matched by proof of better care. TRV-2026-1017 TRV-2026-0486 TRV-2026-1924 Results look best on narrow detection tasks and weakest when models move to new hospitals or populations. TRV-2026-0638 TRV-2026-1244 TRV-2026-1220

What is well measured

A randomized trial of 14,665 adults showed AI-ECG-guided monitoring found new atrial fibrillation, flutter or pre-AF findings in 0.74% of intervention participants versus 0.48% of controls, though the authors call the result statistically fragile. TRV-2026-2462 In a randomized trial of 300 people with suspected inherited retinal disease, eye specialists using an AI tool had the right gene category among their top four answers 81.8% of the time versus 53.1% alone. TRV-2026-0575 A systematic review found AI-read ECGs detected weak heart pumping in people without symptoms with pooled AUROC of 0.87 to 0.93, and another review found AI detected STEMI heart attacks with sensitivity 0.91 versus 0.78 for clinicians. TRV-2026-1837 TRV-2026-2312 A systematic review of pooled studies found AI assistance raised doctors' fracture detection sensitivity to 87% from 73%, with junior clinicians gaining most. TRV-2026-1145

Where it falls short

A randomized trial of 171 veterans found AI-guided monitoring after a heart failure hospitalization did not significantly reduce rehospitalization (16.3% versus 18.7% for controls). TRV-2026-1587 In a crossover study of four commercial chest X-ray AI tools, AI assistance did not improve diagnostic accuracy for five readers reviewing 1200 patients at a single center. TRV-2026-0854 A systematic review found generative AI was 13.0 percentage points less accurate than physicians at radiology diagnosis. TRV-2026-1284 In Nepal, a study of 826 chest X-rays found only 17.89% of the AI's abnormal flags were correct at a threshold set for at least 95% sensitivity. TRV-2026-1265

Where the evidence is thin

Reviews of eye disease, echocardiography and heart ischemia AI say effects on safety, workflows and patient outcomes remain largely untested. TRV-2026-1490 TRV-2026-1924 TRV-2026-1434 A few encouraging results rest on very small samples: an AI app flagged all 13 occlusion heart attacks, but in only 33 selected, hard-to-read ECGs. TRV-2026-1923 In a study of 30 bowel disease patients, AI classifiers working on biopsy light scans did no better than chance (p = 0.51). TRV-2026-2047 A systematic review of rotator cuff tear AI found most diagnostic studies were rated high risk of bias, so reliability in real clinics is unproven. TRV-2026-1698

What is disputed

Whether AI help improves human readers is split: in a randomized crossover test, 21 physician assistants reached 92.9% accuracy on heart attack ECGs with AI versus 79.0% without it. TRV-2026-0651 A crossover study of four commercial chest X-ray tools found no accuracy gain for five readers. TRV-2026-0854 In a meta-analysis of urological cancer imaging, AI scored a pooled AUC of 0.91 against 0.83 for clinicians, yet was less sensitive than clinicians in the prostate and MRI subgroups. TRV-2026-0640

The main threads

Image reading and detection
117 gains · 41 problems
AI reading of scans, slides and ECGs often reports high accuracy for specific findings, mostly on retrospective data from one centre. TRV-2026-0676 TRV-2026-0764 TRV-2026-0640 TRV-2026-1145 TRV-2026-2312
See these 130 records
Risk and outcome prediction
115 gains · 36 problems
Models forecasting survival, complications and recurrence usually beat standard scores on past data, often by modest margins. TRV-2026-1068 TRV-2026-1828 TRV-2026-1009 TRV-2026-0919 TRV-2026-1081
See these 130 records
Testing outside the original setting
24 gains · 41 problems
Accuracy often drops when models meet new hospitals, countries or scanners; reviews say external validation is sparse. TRV-2026-0638

The count

Gains: 281
Traces: 94
Problems: 87

A Trace is one record with both a gain and a problem, so it counts on both sides: 375 records show a gain and 181 show a problem. 172 context records are in the record list but not counted, because they report no measured gain or problem.

How strong the evidence is

Evidence	Gain side	Problem side
HighStrong study design, backed by at least two independent sources	5	4
ModerateA measured study or an official source	346	141
EmergingEarly, small, unreviewed or reported second-hand	24	36

By type of evidence: 160 observational studies; 130 controlled comparisons; 74 benchmark or lab tests; 47 systematic reviews or meta-analyses; 35 commentaries or narrative reviews; 4 randomized trials; 4 news reports; 3 regulatory or legal actions; 2 sets of official statistics; 1 interview study; 1 survey; 1 case report. How evidence is scored

Strongest gains

AI matches experts at spotting cancer on scans in a 150-study review, but real-world patient benefit is mixed
In a review of 150 clinically validated studies, AI reached expert-level accuracy in medical imaging, with AUC up to 0.94 for cancer detection.
Systematic review or meta-analysis · Evidence: High · 100/100 · TRV-2026-0486
Face-photo AI's top-risk cancer patients had over triple the mortality, a study found
In a model development and validation study of cancer patients, the highest-risk quarter flagged by a face-photo AI had more than triple the mortality of the lowest (adjusted hazard ratio 3.23); its age tool erred by 5.1 years on average.
Controlled or validated comparison · Evidence: High · 97/100 · TRV-2026-1971
In 12 studies, AI-read ECGs spot weak heart pumping in people without symptoms, a review finds
In 12 externally validated studies of people without symptoms, AI-read ECGs detected weak heart pumping with pooled AUROC of 0.87 to 0.93, similar to results in people with symptoms.
Systematic review or meta-analysis · Evidence: High · 93/100 · TRV-2026-1837

Strongest problems

Heart-disease models for 2,166 kidney patients lost accuracy moving between US and China
In a study of kidney patients in the US and China, models built to classify heart disease performed worse when tested on the other country's patients, and key risk factors differed: age in the US, hypertension in China.
Observational study · Evidence: High · 87/100 · TRV-2026-1220
AI stroke scan tool caught 94% of proximal blockages but only 73% of distal M1 ones in one center
A single-center study found the software's sensitivity fell to 73% for distal M1 blockages, with only moderate agreement with experts; non-target occlusions were excluded from the main analysis, so it needs expert review rather than standalone use.

What reviews found when they combined studies

22 reviews in this topic printed a pooled result: one figure calculated across many studies. They are the reviews’ own numbers, checked word for word against their abstracts. They often measure different things, so they are listed side by side, not added up.

In a 110-study review, AI beat clinicians on urological cancer scans but lagged on prostate · TRV-2026-0640
- Specificity of AI models in radiologic diagnosis of urological cancers
  Specificity 0.83 (95% CI 0.80 to 0.86)
  110 studies · search to June 2026
  The review’s own words
  AI models achieved pooled sensitivity and specificity of 0.85 (95% CI: 0.83-0.87) and 0.83 (95% CI: 0.80-0.86), with an AUC of 0.91 (95% CI: 0.88-0.93)
- Sensitivity of clinicians in radiologic diagnosis of urological cancers
  Sensitivity 0.82 (95% CI 0.79 to 0.85)
  110 studies · search to June 2026
  The review’s own words
  Clinicians demonstrated a pooled sensitivity of 0.82 (95% CI: 0.79-0.85) and specificity of 0.68 (95% CI: 0.62-0.73), with an AUC of 0.83 (95% CI: 0.80-0.86).
- Overall diagnostic accuracy (area under the curve) of AI models for urological cancers
  AUC 0.91 (95% CI 0.88 to 0.93)
  110 studies · search to June 2026
  The review’s own words
  AI models achieved pooled sensitivity and specificity of 0.85 (95% CI: 0.83-0.87) and 0.83 (95% CI: 0.80-0.86), with an AUC of 0.91 (95% CI: 0.88-0.93)
3 more from this review

Is your study missing? Add it

The records

What the records show

The records

The records

What the records show

Where the evidence stands

The short version

What is well measured

Where it falls short

Where the evidence is thin

What is disputed

The main threads

Image reading and detection

Risk and outcome prediction

Testing outside the original setting

The count

How strong the evidence is

Strongest gains

Strongest problems

What reviews found when they combined studies

Specificity of AI models in radiologic diagnosis of urological cancers

Sensitivity of clinicians in radiologic diagnosis of urological cancers

Overall diagnostic accuracy (area under the curve) of AI models for urological cancers

Chatbots and general language models

Effects on clinicians and patients

Blood, breath and molecular tests

Pooled precision of U-Net models for detecting subdural hematoma on non-contrast CT

Pooled accuracy of U-Net models for detecting subdural hematoma on non-contrast CT

Pooled specificity of CNN models for detecting subdural hematoma on non-contrast CT

AI specificity for detecting STEMI on 12-lead ECG against a clinical reference standard

AI sensitivity for detecting STEMI on 12-lead ECG against a clinical reference standard

AI overall discrimination for detecting STEMI on 12-lead ECG against a clinical reference standard

Sensitivity of unassisted physicians in detecting bone fractures

Specificity of AI-assisted physicians in detecting bone fractures

Specificity of unassisted physicians in detecting bone fractures

Difference in AUC between best machine learning model and logistic regression for trauma mortality prediction

AUC difference between machine learning and logistic regression in studies reporting confidence intervals for both models

Image similarity (SSIM) of synthesized postcontrast T1-weighted MRI in brain tumor studies

Peak signal-to-noise ratio (PSNR) of synthesized postcontrast T1-weighted MRI in brain tumor studies

Pooled sensitivity of machine learning models for predicting pregnancy outcomes after assisted reproduction

Pooled specificity of machine learning models for predicting pregnancy outcomes after assisted reproduction

Diagnostic odds ratio of machine learning models for predicting pregnancy outcomes after assisted reproduction

Diagnostic accuracy (SROC) of AI-assisted cholangioscopy for biliary strictures

Diagnostic accuracy (SROC) of neural network cholangioscopy AI, neural network studies only

Specificity of AI-assisted cholangioscopy for indeterminate or malignant biliary strictures

Disc displacement detection by artificial intelligence on panoramic or cone-beam computed tomography: specificity

Disc displacement detection by artificial intelligence on panoramic or cone-beam computed tomography: sensitivity

Disc displacement detection on temporomandibular joint magnetic resonance imaging by artificial intelligence: specificity

False negative proportion of AI reading screening mammograms at Transpara threshold 9

False positive proportion of AI reading screening mammograms at Transpara threshold 3

False positive proportion of AI reading screening mammograms at Transpara threshold 9

Area under summary ROC curve for AI echocardiography detecting HFpEF or elevated filling pressure

Diagnostic odds ratio of AI echocardiography for detecting HFpEF or elevated filling pressure

Sensitivity of AI-enabled echocardiography for detecting HFpEF, elevated filling pressure or diastolic dysfunction

Sensitivity of AI systems in detecting acute otitis media

Specificity of AI systems in detecting acute otitis media

Sensitivity of MRI-based machine learning for distinguishing true progression from pseudoprogression in glioblastoma (external test cohorts)

Summary AUC of MRI-based machine learning for distinguishing true progression from pseudoprogression in glioblastoma (external test cohorts)

Specificity of MRI-based machine learning for distinguishing true progression from pseudoprogression in glioblastoma (external test cohorts)

AI-ECG discrimination of left ventricular ejection fraction 35% or lower in symptomatic people

AI-ECG discrimination of left ventricular ejection fraction 50% or lower in asymptomatic people

AI-ECG discrimination of left ventricular ejection fraction 40% or lower in asymptomatic people

Specificity of deep learning in detecting ocular toxoplasmosis from fundus photographs

Sensitivity of deep learning in detecting ocular toxoplasmosis from fundus photographs

Diagnostic odds ratio of deep learning for ocular toxoplasmosis on fundus photographs

Adjusted difference in AUROC of surgical prediction models, NSQIP vs non-NSQIP data sources

Pooled diagnostic accuracy of generative AI on free-text radiology diagnostic tasks

Difference in accuracy of generative AI between image-only and text-only input

Pooled diagnostic accuracy of generative AI on choice-based radiology diagnostic tasks

Sensitivity of imaging AI models in detecting avascular necrosis of the femoral head

Specificity of imaging AI models in detecting avascular necrosis of the femoral head

Specificity of AI-assisted intraoral mobile photographs for detecting oral potentially malignant disorders

Sensitivity of AI-assisted intraoral mobile photographs for detecting oral potentially malignant disorders

Discrimination of machine learning models for in-hospital or early mortality in infective endocarditis

Discrimination of machine learning models for 6-month mortality in infective endocarditis

Discrimination of AI/ML models predicting tuberculosis treatment failure

Discrimination of clinical-radiomics models for predicting poor functional outcome in intracerebral hemorrhage

Discrimination of clinical-radiomics models for predicting mortality in intracerebral hemorrhage

Discrimination of clinical-radiomics models for predicting hematoma expansion in intracerebral hemorrhage

The records