Truace
Subscribe
Good Space a ranking of the record

TheGood surrounding AI

278 gains match this view. 97% rest on at least one peer-reviewed study, and 3% clear the high-evidence bar. The latest was filed Oct 16, 2026.

Every gain in this view, one square each, shaded by the strength of its evidence. High 9 Moderate 269 Emerging 0
278 results
Show filters and sorting
Reset all
Sector: health

Matching records · page 9 of 10

241
Evidence-backed gainPeer-reviewedHealth

Medical large language models have potential to streamline healthcare delivery and improve patient outcomes by assisting clinicians, educators, and patients in daily practice.

Source article: A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions

IEEE Transactions on Knowledge and Data Engineering
Reader signal

How should this claim be treated?

242
Evidence-backed gainPeer-reviewedHealth

Virchow, the largest pathology foundation model to date, enables pan-cancer detection with 0.95 specimen-level AUC across nine common and seven rare cancers and matches production tissue-specific models using less training data.

Source article: A foundation model for clinical-grade computational pathology and rare cancers detection

Nature Medicine
Reader signal

How should this claim be treated?

243
Evidence-backed gainPeer-reviewedHealth

AI techniques including machine learning and deep learning accelerate drug discovery and delivery and improve patient outcomes and treatment regimens in personalized medicine.

Source article: Artificial Intelligence (AI) Applications in Drug Discovery and Drug Delivery: Revolutionizing Personalized Medicine

Pharmaceutics
Reader signal

How should this claim be treated?

244
Model-prefilled gainPeer-reviewedHealth

A gradient boosting classifier trained on eight routine treatment-time features improved prediction of local control after Gamma Knife radiosurgery to post-resection cavities from brain metastases, achieving ROC-AUC 0.735 compared to chance-level baseline.

Source article: Machine learning prediction of local control after Gamma Knife radiosurgery to post-resection cavities from brain metastases: a proof-of-concept study

Journal of Neuro-Oncology
Reader signal

How should this claim be treated?

245
Model-prefilled gainPeer-reviewedHealth

AI-enhanced insertable cardiac monitors reduced nonactionable alerts from 5,078 to 2,110 per year for a 600-patient clinic, saving 559 staffing hours and $29,470 annually compared to non-AI monitors.

Source article: Impact of Artificial Intelligence-Enhanced Insertable Cardiac Monitors on Device Clinic Workflow and Resource Utilization

JACC: Advances
Reader signal

How should this claim be treated?

246
Model-prefilled gainPeer-reviewedHealth

AI models applied to neurosurgical data achieved Dice scores of 0.82-0.84 for tumor segmentation and AUC values of 0.80-0.90 for molecular prediction and outcome forecasting, supporting lesion detection, surgical navigation, and prognostication.

Source article: From severity scoring to predictive analytics: the emerging role of AI in neurosurgery

Frontiers in Neurology
Reader signal

How should this claim be treated?

247
Model-prefilled gainPeer-reviewedHealth

In real-world use among 254 young children with developmental concern, the AI-based Canvas Dx provided accurate autism predictions with high negative and positive predictive values and enabled diagnosis at a median age of 37.2 months.

Source article: An analysis of the real world performance of an artificial intelligence based autism diagnostic

Scientific Reports
Reader signal

How should this claim be treated?

248
Evidence-backed gainPeer-reviewedHealth

A transformer-based deep learning framework using clinically indicated non-contrast chest CT stratified risk of refractory Mycoplasma pneumoniae pneumonia in children with AUCs around 0.89-0.90 on internal and external test cohorts.

Source article: A CT-based deep learning model for the automated risk stratification of refractory Mycoplasma pneumoniae pneumonia in children

BMC Medical Imaging
Reader signal

How should this claim be treated?

250
Evidence-backed gainPeer-reviewedHealth

Machine learning models that incorporate compressed respiratory and oxygenation timeseries improved early prediction of BPD at 7 days after birth compared to clinical-data-only models.

Source article: Prediction of bronchopulmonary dysplasia seven days after birth using respiratory and oxygenation timeseries with machine learning

Pediatric Research
Reader signal

How should this claim be treated?

251
Evidence-backed gainPeer-reviewedHealth

Explainable ML models used after Wells/Geneva triage improved early PTE prediction in ED patients, with Extra Trees reaching 0.82 accuracy and 0.83 AUC.

Source article: Explainable machine learning for early prediction and anatomical classification of pulmonary embolism in the emergency department

BMC Emergency Medicine
Reader signal

How should this claim be treated?

252
Evidence-backed gainPeer-reviewedHealth

A six-protein plasma signature tested with SVM distinguished fibrotic hypersensitivity pneumonitis from idiopathic pulmonary fibrosis on an independent test set with 71.4% accuracy, offering a non-invasive diagnostic aid.

Source article: Plasma proteomics and machine learning deliver non-invasive distinction between fibrotic hypersensitivity pneumonitis and idiopathic pulmonary fibrosis

Journal of Translational Medicine
Reader signal

How should this claim be treated?

253
Evidence-backed gainPeer-reviewedHealth

LightGBM model trained on 282 Lenke 1/2 AIS patients predicted postoperative coronal imbalance with AUC 0.885 training and 0.824 internal validation, identifying LIV-LSTV, Lumbar Modifier, and Risser grade as key predictors.

Source article: Predicting postoperative coronal imbalance in Lenke 1/2 adolescent idiopathic scoliosis: A machine learning model with clinical interpretability

International Orthopaedics
Reader signal

How should this claim be treated?

254
Evidence-backed gainPeer-reviewedHealth

Multi-Scale Feature Fusion model combining U-Net segmentation, EfficientNet and attention autoencoder features fused via CCA and YOLO classification achieved 99.95% accuracy on apple leaf disease datasets, enabling early detection for sustainable agriculture.

Source article: Comprehensive plant disease classification and severity estimation for sustainable farming via automatic segmentation and multi-scale feature fusion

BMC Plant Biology
Reader signal

How should this claim be treated?

255
Evidence-backed gainPeer-reviewedHealth

AI-assisted caries annotation increased dental students' diagnostic accuracy, sensitivity, and confidence while reducing interpretation time on panoramic radiographs.

Source article: Effect of AI-assisted caries annotation on dental students' performance in caries detection on panoramic radiographs

BMC Medical Education
Reader signal

How should this claim be treated?

256
Evidence-backed gainPeer-reviewedHealth

Convolutional neural networks trained on four Scheimpflug-based corneal maps differentiated keratoconus from normal astigmatic eyes with up to 99.2% accuracy and AUC 1.00, with external validation retaining 97-98% accuracy.

Source article: Artificial intelligence for diagnosis of keratoconus using Scheimpflug based corneal tomography

International Journal of Ophthalmology
Reader signal

How should this claim be treated?

259
Evidence-backed gainPeer-reviewedHealth

General-purpose LLMs can encode EHRs as plain-text descriptions to produce embeddings for clinical prediction without private medical training data, matching a specialized EHR foundation model across 15 tasks and improving on some tasks in UK Biobank external validation.

Source article: Large language models are powerful electronic health record encoders

npj Digital Medicine
Reader signal

How should this claim be treated?

260
Evidence-backed gainPeer-reviewedHealth

Machine learning classifiers using demographic, clinicopathological and inflammatory markers predicted 5-year overall survival and second primary cancer occurrence in a European nasopharyngeal carcinoma cohort.

Source article: Machine learning prognostication in nasopharyngeal carcinoma: a european multicentre analysis of survival and risk of second malignancy

European Archives of Oto-Rhino-Laryngology
Reader signal

How should this claim be treated?

261
Evidence-backed gainPeer-reviewedHealth

XGBoost model integrating UHR and iPTH predicted protein-energy wasting in incident hemodialysis patients with AUC 0.801, enabling individualized risk assessment.

Source article: Predictive value of the uric acid to high-density cholesterol ratio (UHR) combined with intact parathyroid hormone for protein-energy wasting after incident hemodialysis: a multicenter study

Renal Failure
Reader signal

How should this claim be treated?

262
Evidence-backed gainPeer-reviewedHealth

Deep learning CT segmentation using Comp2Comp enabled compartment-specific measurement of visceral adipose tissue, subcutaneous fat, and muscle, revealing sustained visceral fat reduction after metabolic and bariatric surgery that BMI alone does not capture.

Source article: Beyond BMI: Deep Learning Segmentation-Driven CT Reveals Body Composition Changes after Metabolic and Bariatric Surgery

Journal of the American College of Surgeons
Reader signal

How should this claim be treated?

263
Evidence-backed gainPeer-reviewedHealth

AI-optimized monoclonal antibody GB-0669 was safe and well-tolerated in healthy adults with dose-proportional pharmacokinetics and a 54-day half-life and dose-dependent serum live virus neutralization.

Source article: Randomized, Double-Blind, Placebo-Controlled First-in-Human Trial of a First-in-Class AI-Designed Monoclonal Antibody (GB-0669) Against the Conserved SARS-CoV-2 Spike S2 Stem Helix

The Journal of Infectious Diseases
Reader signal

How should this claim be treated?

264
Evidence-backed gainPeer-reviewedHealth

Machine learning screening identified MMP1, CXCR7, and TPST1 and built a NET-inflammation-associated model that predicted prognosis for idiopathic pulmonary fibrosis patients.

Source article: Comprehensive analysis of neutrophil extracellular traps-associated inflammatory genes for patients with idiopathic pulmonary fibrosis

Molecular Genetics and Genomics
Reader signal

How should this claim be treated?

265
Evidence-backed gainPeer-reviewedHealth

Machine learning-derived metabolic age from urinary NMR metabolites tracks longitudinal aging trajectories and predicts incident diseases and mortality beyond chronological age.

Source article: Urinary Metabolic Age from High-Resolution NMR Reveals Longitudinal Aging Patterns

The Journals of Gerontology, Series A: Biological Sciences and Medical Sciences
Reader signal

How should this claim be treated?

266
Evidence-backed gainPeer-reviewedHealth

In a real-world care facility test by April 2026, the ZigBee-based AI telehealth framework monitoring elderly and chronically ill patients achieved 95% accuracy with 100% recall for health discrepancy detection while operating at 120 ms transmission delay and 3.8 mW/h power consumption.

Source article: ZigBee Based Low Latency IoT and AI Integrated Framework for Real Time Telehealth Monitoring

Emerging Science Journal
Reader signal

How should this claim be treated?

267
Evidence-backed gainPeer-reviewedHealth

Co-design workshops with 32 young people generated system requirements for reconceptualising the professional-focused Mia genAI chatbot for young consumers and integrating it into Australian youth services, with potential to benefit youth mental health.

Source article: Young people’s perceptions and recommendations for conversational generative artificial intelligence in youth mental health

npj Digital Medicine
Reader signal

How should this claim be treated?

268
Evidence-backed gainPeer-reviewedHealth

A Random Forest model trained on linguistic, emotional, cognitive, behavioral and temporal features from Weibo posts predicted Self-Rating Anxiety Scale scores among consenting Chinese college students with R2 0.77 on the test set.

Source article: Leveraging social media footprints for predicting college student anxiety: a machine learning approach

BMC Psychology
Reader signal

How should this claim be treated?

269
Evidence-backed gainPeer-reviewedHealth

In a survey of 241 people with MS, respondents reported higher comfort with AI when used for low-risk supportive roles like chronic management and symptom screening, with most preferring a joint model where clinicians retain final responsibility.

Source article: Exploring attitudes and acceptance of artificial intelligence in multiple sclerosis from the patient perspective

PLOS Digital Health
Reader signal

How should this claim be treated?

270
Evidence-backed gainJournalismHealth

An interpretable model built on augmented data and real participant data from a culturally adapted assessment identified contributing factors such as self-blame, loneliness, and family pride to prompt culturally safe clinical discussion.

Source article: The world’s oldest living culture leads the way with interpretable generative AI: Aboriginal women shaping the future of perinatal mental health services

PLOS (Public Library of Science)
Reader signal

How should this claim be treated?