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 5 of 10

121
Evidence-backed gainPeer-reviewedHealth

An integrated ligand-based machine learning and structure-based docking funnel screened 22,823 compounds and identified HY-18,623 as a potent dual CDK4/6 inhibitor with low-nanomolar IC50s.

Source article: Harnessing machine learning, docking and molecular dynamics for the virtual screening of compounds as CDK4/6 dual inhibitors

Molecular Diversity
Reader signal

How should this claim be treated?

122
Evidence-backed gainPeer-reviewedHealth

A multimodal deep learning model analyzing resting 12-lead ECG and clinical data was feasible for pre-participation cardiovascular screening and achieved moderate discrimination for fitness for competitive sports.

Source article: Ai-based multimodal analysis of ECG and clinical data for evaluation for competitive sports participation: The VALETUDO trial

International Journal of Cardiology
Reader signal

How should this claim be treated?

124
Evidence-backed gainPeer-reviewedHealth

A Random Forest model using eight routinely available variables predicted subsequent vasopressor need after two fluid boluses in pediatric suspected sepsis with AUROC 0.827 and stratified patients into four tiers with a 6.6% to 63.6% gradient.

Source article: Development of a machine-learning risk stratification tool for vasoactive medication need after two-bolus fluid resuscitation in pediatric suspected sepsis

Pediatric Research
Reader signal

How should this claim be treated?

125
Evidence-backed gainPeer-reviewedHealth

A CatBoost model integrating 22 granular nursing and emergency department features collected within the first 24 hours improved early in-hospital mortality prediction for acute ischemic stroke patients, achieving higher discrimination than established ICU scores in both internal and external validation.

Source article: An Interpretable Machine Learning Framework with Clinical Nomogram for Predicting In-Hospital Mortality in Acute Ischemic Stroke Using High-Granularity Bedside Data

Journal of Stroke and Cerebrovascular Diseases
Reader signal

How should this claim be treated?

126
Evidence-backed gainPeer-reviewedHealth

TrialScout using a large language model matched registered trials to result publications with 92.5% sensitivity and located publications for 63.6% of a 9,600-trial sample, accelerating locating trial results.

Source article: TrialScout links published results to trial registrations using a large language model

Journal of Clinical Epidemiology
Reader signal

How should this claim be treated?

127
Evidence-backed gainPeer-reviewedHealth

Machine learning models using 7T SWI vascular topology, density and intensity features enabled noninvasive preoperative differentiation of glioma IDH status and WHO grade, with improved performance when integrated with clinical factors.

Source article: Noninvasive Profiling of the Glioma Vascular Microenvironment via 7T MRI: Decoding Angiogenic Signatures for Isocitrate Dehydrogenase and World Health Organization Grade Differentiation

Journal of Magnetic Resonance Imaging
Reader signal

How should this claim be treated?

129
Evidence-backed gainPeer-reviewedHealth

A prespecified EfficientNet plus Random Forest model classified gross pathology photographs to distinguish NIFTP from IEFVPTC with pooled AUC 0.788, sensitivity 0.588 and specificity 0.944 in 87 patients.

Source article: Deep Learning-Based Classification of NIFTP and Invasive Encapsulated Follicular Variant of Papillary Thyroid Carcinoma Using Gross Pathology Images

Journal of Imaging Informatics in Medicine
Reader signal

How should this claim be treated?

130
Evidence-backed gainPeer-reviewedHealth

Automated AI quantification of pulmonary artery-to-vein volume difference achieved the highest discrimination for high/intermediate-high risk acute pulmonary embolism with low missed-diagnosis risk.

Source article: Pulmonary Artery-to-Vein Volume Difference: A New Imaging Biomarker for Risk Stratification in Acute Pulmonary Embolism

Academic Radiology
Reader signal

How should this claim be treated?

131
Evidence-backed gainPeer-reviewedHealth

A three-stage explainable framework that fuses deep representations from multiple pretrained CNNs and classifies them with an RBF-kernel SVM achieved 88% accuracy and 88% F1 for skin lesion classification while adding LIME-based explanations.

Source article: An Explainable Computer-Aided Framework for Skin Lesion Classification Using Deep Learning

Journal of Visualized Experiments
Reader signal

How should this claim be treated?

132
Evidence-backed gainPeer-reviewedHealth

AI-based ICE module created left atrial shell from the right atrium without a pre-ablation mapping catheter and guided pulsed field ablation with 100% acute success and 77.7% paroxysmal and 71.8% non-paroxysmal freedom from arrhythmia at 270 days after blanking.

Source article: AI-ICE Guided Pulsed Field Ablation of Atrial Fibrillation with Variable Loop Circular Catheter

Europace
Reader signal

How should this claim be treated?

133
Evidence-backed gainPeer-reviewedHealth

AI-assisted ultrasound of the rectus femoris quantified intramuscular fat percentage (FATi), which was independently associated with diabetic nephropathy and adverse metabolic profiles in patients with diabetes.

Source article: Intramuscular Fat Assessed by AI-Assisted Muscle Ultrasound: Association With Cardiometabolic Risk Factors and Diabetic Nephropathy in Diabetes Mellitus

Diabetes, Obesity and Metabolism
Reader signal

How should this claim be treated?

134
Evidence-backed gainPeer-reviewedHealth

Stacked ensembles combining five CNN backbones improved automated detection and size stratification of periapical lesions on cropped intraoral radiographs, reaching high accuracy and high sensitivity for very small lesions on internal testing.

Source article: Stacked Ensemble Deep Learning Models for Accurate Detection and Size Stratification of Periapical Lesions on Intraoral Radiographs

Australian Endodontic Journal
Reader signal

How should this claim be treated?

135
Evidence-backed gainPeer-reviewedHealth

Adapted iPsRS model using 13 individual-level SDoH predictors predicted 1-year all-cause hospitalization in a general adult cohort with AUROC up to 0.671, enabling equity-aware risk stratification for clinical care.

Source article: Adaptation of a fair individualized polysocial risk score for hospitalization risk prediction

JAMIA Open
Reader signal

How should this claim be treated?

136
Evidence-backed gainPeer-reviewedHealth

Dynamic class-specific F1-score weighting with ECF1V increased ensemble classification accuracy to 98.25% on Breast Cancer Wisconsin and 89.47% on UCI Heart Disease datasets, outperforming conventional voting under non-linear and imbalanced conditions.

Source article: Dynamic F1-score-based voting strategies for multi-class classification: an adaptive ensemble approach for non-linear and imbalanced datasets

Scientific Reports
Reader signal

How should this claim be treated?

138
Evidence-backed gainPeer-reviewedHealth

Adding individual-level social determinants of health and clinical features to machine learning models improved suicide risk prediction over demographic-only baselines in a Maryland sample of 1214 suicide deaths and 815,544 living patients.

Source article: Assessing the Utility of Social Determinants of Health Data in Suicide Prediction Models

Archives of Suicide Research
Reader signal

How should this claim be treated?

139
Evidence-backed gainPeer-reviewedHealth

An unsupervised AI framework discovered a 13-marker cellular morphometric signature from colorectal whole-slide images that transferred to gastric and esophageal cancers and enabled risk stratification of precancerous lesions and early-stage cancers to guide surveillance and intervention.

Source article: Tissue-Agnostic Cellular Morphometric Biomarkers for Risk-Adapted Management Across Gastrointestinal Precancerous Lesions and Cancers

Advanced Science
Reader signal

How should this claim be treated?

140
Evidence-backed gainPeer-reviewedHealth

Machine learning and deep learning models trained on MALDI-TOF spectra improved rapid classification of bacteria versus viruses, Gram-positive versus Gram-negative, and individual species, with Extra Trees showing best generalization to an external highly pathogenic bacteria dataset.

Source article: Enhanced classification and identification of bacterial and viral microorganisms by integration of MALDI-TOF mass spectrometry with artificial intelligence

Scientific Reports
Reader signal

How should this claim be treated?

141
Evidence-backed gainPeer-reviewedHealth

An ITO/CuBi2O4/LaNiO3 heterojunction sensor with machine learning analysis identified 9 biocide types and 5 ethanol concentration gradients with 98.7% overall accuracy.

Source article: Dynamic liquid with shape-shifting induced photocurrent variation in a CuBi<sub>2</sub>O<sub>4</sub> film for antimicrobial biocide recognition

Nanoscale
Reader signal

How should this claim be treated?

142
Evidence-backed gainPeer-reviewedHealth

An interpretable machine learning model integrating genetic risk scores, corneal biomechanical parameters, and tear molecular biomarkers was developed and validated to predict progression risk in patients with confirmed normal-tension glaucoma, providing a quantitative reference for risk stratification and personalised

Source article: A Risk Prediction Model for Normal-Tension Glaucoma Progression Integrating Genetic Markers and Corneal Biomechanics

Seminars in Ophthalmology
Reader signal

How should this claim be treated?

143
Evidence-backed gainPeer-reviewedHealth

Integrated single-cell analysis and three machine learning algorithms identified GLS and LPIN2 as upregulated key genes in kidney stones that promote fibroblast-to-myofibroblast transition, ROS production, calcium deposition and osteogenic-like differentiation, supporting a risk prediction nomogram and drug prediction.

Source article: Targeting GLS and LPIN2 in renal fibroblasts: potential therapeutic targets for kidney stone disease identified by integrated multi-omics analysis

Urolithiasis
Reader signal

How should this claim be treated?

144
Evidence-backed gainPeer-reviewedHealth

A 16-gene macrophage-associated signature developed with ridge regression and XGBoost stratified HCC patients and achieved high diagnostic discrimination, with LGALS1 emerging as a top feature linked to survival and treatment response.

Source article: Integrative single-cell and machine-learning analysis identifies LGALS1 as a macrophage-associated diagnostic and prognostic biomarker in hepatocellular carcinoma

Translational Oncology
Reader signal

How should this claim be treated?

145
Evidence-backed gainPeer-reviewedHealth

An interpretable logistic regression model trained on YRBS data predicted lifetime marijuana use among male high school students with high accuracy, enabling early identification of at-risk boys for targeted school and community prevention.

Source article: Identifying risk factors for marijuana use among male high school students using machine learning: Implications for public health

Public Health
Reader signal

How should this claim be treated?

146
Evidence-backed gainPeer-reviewedHealth

A model combining clinical and sociodemographic variables predicted overall survival in cervical squamous cell carcinoma with acceptable discrimination.

Source article: Combining Statistical Modeling and Machine Learning for Prognostic Feature Selection in Cervical Cancer: A Retrospective Study Based on SEER 2004 to 2015 Data

American Journal of Clinical Oncology
Reader signal

How should this claim be treated?

147
Evidence-backed gainPeer-reviewedHealth

An interpretable multi-instance learning method for accurate differentiation of malignant and benign laryngeal lesions in laryngoscopy: Results IMIL-Net achieved the highest diagnostic performance, with a mean area under the curve (AUC) of 0.975 (95% CI 0.959-0.991), accuracy of 0.915 (95% CI 0.883-0.947), sensitivity of 0.876 (95% CI 0.803-0.949), and specificity of 0.945 (95% CI 0.910-0.980).

Source article: An interpretable multi-instance learning method for accurate differentiation of malignant and benign laryngeal lesions in laryngoscopy

European Archives of Oto-Rhino-Laryngology
Reader signal

How should this claim be treated?

148
Evidence-backed gainPeer-reviewedHealth

Artificial intelligence-based deep learning model (DLM) analysis may improve accuracy. Results Intraclass correlation between Fick- and DLM-derived Qp:Qs was 0.782 (P 1.5: 90% specificity, 98% sensitivity, area under the receiver operating characteristic curve [AUROC] 98%; predicting Qp:Qs Conclusion Deep learning-based analysis of CXRs enables accurate evaluation of pulmonary vascularity and outperforms structured assessment by clinicians.

Source article: Radiological assessment of pulmonary vascularity in congenital heart disease: standardized clinician assessment versus deep learning-based prediction

Journal of Cardiovascular Imaging
Reader signal

How should this claim be treated?

149
Evidence-backed gainPeer-reviewedHealth

Statistically significant improvements were observed in 10 of 12 clinical domains, including core consultation skills such as comprehensive history taking, identifying key symptoms, adapting questioning and formulating a management plan, and differential diagnoses (all p Conclusion AI-simulated patients are feasible to implement and are associated with meaningful improvements in consultation confidence among CMTs.

Source article: AI patients, real practice: exploring the use of AI-simulated patients to support primary healthcare training for combat medical technicians

Education for Primary Care
Reader signal

How should this claim be treated?

150
Evidence-backed gainPeer-reviewedHealth

Evaluation of Differential Diagnosis of Odontogenic Lesions in Cone Beam Computed Tomography Images Using Radiomics-Based Machine Learning: The best single-segment performance was achieved in the left mandibular corpus with Logistic Regression (Accuracy=0.833, F1=0.832, AUC=0.958).

Source article: Evaluation of Differential Diagnosis of Odontogenic Lesions in Cone Beam Computed Tomography Images Using Radiomics-Based Machine Learning

Dentomaxillofacial Radiology
Reader signal

How should this claim be treated?