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

Sector: health

Matching records · page 6 of 10

151

Evidence-backed gainPeer-reviewedHealth

Computational AI analysis of HRCT provides automated, objective quantification of interstitial lung disease in patients with inflammatory rheumatic disorders, enabling precise volumetric measurement and pattern classification.

Source article: Beyond Visual Scoring: Computational CT-analysis for HRCT based quantification of Interstitial Lung Disease in Inflammatory Rheumatic Disease

Arthritis Care & Research

Reader signal

How should this claim be treated?

152

Evidence-backed gainPeer-reviewedHealth

Deep-learning based AIIR reconstruction improved CT image quality and diagnostic accuracy for gastric cancer, increasing tumor conspicuity and raising AUC for detecting serosal invasion compared to hybrid iterative reconstruction.

Source article: Evaluation of gastric cancer using artificial intelligence iterative reconstruction on abdominal CT: image quality and diagnostic accuracy

Abdominal Radiology

Reader signal

How should this claim be treated?

153

Evidence-backed gainPeer-reviewedHealth

An integrated framework using WBAF preprocessing, MResU-Net segmentation, IPHOG feature extraction and IShuffleNet-PCNN classification achieved 0.933 accuracy and 0.991 NPV for spinal cord injury-related fracture classification from CT images.

Source article: IShuffleNet-PCNN hybrid classifier within an MResU-Net-based framework for spinal cord injury detection and classification using CT images

European Spine Journal

Reader signal

How should this claim be treated?

154

Evidence-backed gainPeer-reviewedHealth

A CNN with contrastive learning and mixed-attention fusion of multimodal MRI and demographic data achieved test set ACC 0.855 and AUC 0.919 for preoperative identification of pineal region germinoma, outperforming single-modality models.

Source article: A multimodal MRI-based deep learning model for non-invasive diagnosis of pineal region germinoma

Neuroradiology

Reader signal

How should this claim be treated?

155

Evidence-backed gainPeer-reviewedHealth

Automated fundus-image analysis for diabetic retinopathy enables earlier screening and classification that can prevent vision loss in diabetic patients.

Source article: A comprehensive review on automated diabetic retinopathy detection and classification using fundus image

Graefe's Archive for Clinical and Experimental Ophthalmology

Reader signal

How should this claim be treated?

156

Evidence-backed gainPeer-reviewedHealth

Unsupervised hierarchical clustering integrated BMI, activity, comorbidities, HAQ and TNF pathway genetics to identify three RA subgroups with differing TNFi response rates, including a better-prognosis cluster with 73.5% response.

Source article: Clustering of rheumatoid arthritis patients: an unsupervised machine learning approach for characterizing the TNFi response

Immunologic Research

Reader signal

How should this claim be treated?

157

Evidence-backed gainPeer-reviewedHealth

Psychiatric nursing internship students who used the ChatGPT-based virtual patient with a structured prompting framework showed higher MSE competency after the intervention.

Source article: An AI-Supported Virtual Patient Application Using a Structured Prompting Framework to Develop Mental Status Examination Skills in Psychiatric Nursing Internship Students: An Interventional Mixed-Methods Study

Issues in Mental Health Nursing

Reader signal

How should this claim be treated?

158

Evidence-backed gainPeer-reviewedHealth

A CoxBoost + survivalSVM prognostic model built from resistance-associated cluster genes achieved C-index 0.686 and stratified LUAD patients with HR 2.54-10.51, with low-risk patients showing greater immune infiltration and ARNTL2 knockdown suppressing proliferation and invasion in A549 and H1299 cells.

Source article: Integration of single-cell transcriptomics and genomic mutation analysis identifies an immunotherapy-resistant tumor subcluster and validates ARNTL2 as a malignant driver in lung adenocarcinoma

Translational Oncology

Reader signal

How should this claim be treated?

159

Evidence-backed gainPeer-reviewedHealth

AI-enabled intervention delivery for adult cancer survivors was associated with reported improvements in clinical and psychosocial outcomes, with model performance generally moderate to high across symptom tasks.

Source article: Application of Artificial Intelligence (AI) in cancer symptom management for adult cancer survivors: a scoping review

International Journal of Medical Informatics

Reader signal

How should this claim be treated?

160

Evidence-backed gainPeer-reviewedHealth

A hybrid attention-enhanced segmentation plus morphological feature classification framework classified OA progression stages at 18-month and 30-month follow-ups from OAI longitudinal knee MRI, achieving 86.67% accuracy with Random Forest to support timely treatment decisions.

Source article: Automated diagnostic system for classification of progression stages of osteoarthritis using magnetic resonance imaging

Physica Medica

Reader signal

How should this claim be treated?

161

Evidence-backed gainPeer-reviewedHealth

A DWT-HVG framework with Soft Voting Ensemble enabled automated classification of resting-state EEG for ASD screening with 93.54% accuracy and 98.17% AUC in stratified 10-fold cross-validation.

Source article: Automated autism spectrum disorder detection using EEG signals and time-frequency visibility graphs

Neuroscience

Reader signal

How should this claim be treated?

162

Evidence-backed gainPeer-reviewedHealth

A multi-modal deep learning framework using Heckmatt scores from six key muscles improved speed and diagnostic performance for muscle ultrasound, predicting neuromuscular pathology with an area under the precision-recall curve of 0.87 on a test set of 320 patients.

Source article: A Combined Deep Learning Approach to Screen Patients for Neuromuscular Pathology

Ultrasound in Medicine & Biology

Reader signal

How should this claim be treated?

163

Evidence-backed gainPeer-reviewedHealth

An AI system using modified U-Net segmentation automatically classified inferior alveolar nerve proximity to impacted mandibular third molars on CBCT with 90.1% accuracy and reduced analysis time from ~189 seconds to ~4.8 seconds compared to expert radiologists.

Source article: Validation of artificial intelligence-assisted CBCT analysis for predicting inferior alveolar nerve proximity to impacted mandibular third molars: a diagnostic accuracy study

BMC Oral Health

Reader signal

How should this claim be treated?

164

Evidence-backed gainPeer-reviewedHealth

Converting numerical clinical data into 24-bit rectangular coded images and training ResNet architectures improved heart failure survival prediction, reaching reported accuracy up to 0.9617.

Source article: A novel approach for predicting heart failure survival using a rectangular coded network

Physical and Engineering Sciences in Medicine

Reader signal

How should this claim be treated?

165

Evidence-backed gainPeer-reviewedHealth

An AI model trained on surgical video frames achieved automated real-time detection and segmentation of bladder neck, adenoma and peripheral zone during robot-assisted prostate enucleation with high Dice scores and >60 fps inference.

Source article: Real-time artificial intelligence-based anatomy recognition in single-port transvesical enucleation of the prostate

BJU International

Reader signal

How should this claim be treated?

166

Evidence-backed gainPeer-reviewedHealth

An AI reinforcement learning model trained on Swedish population data produced efficient, low-cost diagnostic sequences for moderate to severe breathlessness with high diagnostic yield, prioritizing BMI, anxiety/depression, physical activity, and spirometry before lung diffusion, CT, and hemoglobin tests.

Source article: Using AI to determine optimal cost-effective diagnostic pathways for chronic breathlessness

npj Primary Care Respiratory Medicine

Reader signal

How should this claim be treated?

167

Evidence-backed gainPeer-reviewedHealth

Causal AI integrated into healthcare informatics systems improves personalized clinical decision-making by estimating individual treatment effects and simulating intervention outcomes.

Source article: CAUSAL artificial intelligence and data-driven decision intelligence in personalized medicine: a review of healthcare informatics systems

Personalized Medicine

Reader signal

How should this claim be treated?

168

Evidence-backed gainPeer-reviewedHealth

Integration of multi-omics and machine learning can improve cardiovascular disease management by supporting definitive and early diagnosis, severity assessment, full-course risk stratification, and individualized prediction of drug and surgical benefit-risk to inform decisions.

Source article: Machine learning and multi-omics technologies for precision cardiovascular medicine: advancing diagnosis, risk prediction, and therapeutic guidance

Frontiers in Cardiovascular Medicine

Reader signal

How should this claim be treated?

169

Evidence-backed gainPeer-reviewedHealth

Integrating pathology foundation models and multimodal AI to connect histology, genomics, spatial biology and longitudinal monitoring enables evolution-aware prediction of lymph-node metastasis and recurrence risk in colorectal cancer.

Source article: Beyond Morphology: Reframing Lymph-Node Metastasis Prediction Through Clonal Ecology-Decades-Long Genomic Instability and Polyclonal-to-Monoclonal Transitions as the Missing Dimension in Cancer

Stem Cells and Development

Reader signal

How should this claim be treated?

170

Evidence-backed gainPeer-reviewedHealth

A random forest model using nine routine blood-based predictors can screen for erectile dysfunction risk with high external validation performance, enabling early non-invasive detection during health check-ups.

Source article: Identification of Erectile Dysfunction From Routine Blood Test Data: Development and Validation of a Machine Learning-Based Prediction Model

Andrology

Reader signal

How should this claim be treated?

171

Evidence-backed gainPeer-reviewedHealth

A convolutional neural network using standard 12-lead ECGs can estimate elevated NT-proBNP levels with strong correlation and good discrimination in internal and external validation.

Source article: Development and External Validation of an AI-ECG Algorithm for Estimating Elevated Serum NT-proBNP Levels

European Heart Journal - Quality of Care and Clinical Outcomes

Reader signal

How should this claim be treated?

172

Evidence-backed gainPeer-reviewedHealth

Applying FDA-cleared SubtleHD enhancement to already diagnostic-quality T1 MRI improved Alzheimer's disease classification performance and allowed models trained on only 70% of enhanced data to match full-data standard-of-care performance.

Source article: Deep Learning-Based Enhancement of Already Diagnostic-Quality MRI for Alzheimer's Disease Classification: Effects on Model Performance and Training Data Requirements

Journal of Magnetic Resonance Imaging

Reader signal

How should this claim be treated?

173

Evidence-backed gainPeer-reviewedHealth

ML-based phenomapping of 106,490 Danish KC patients identified 7 distinct subgroups differentiated by disease burden, comorbidities and socioeconomic status, providing a basis for tailored clinical pathways.

Source article: Machine-learning-based Phenomapping of Patients with Keratinocyte Carcinoma: Data-driven Subgrouping by Disease Burden, Comorbidities and Socioeconomic Status

Acta Dermato-Venereologica

Reader signal

How should this claim be treated?

174

Evidence-backed gainPeer-reviewedHealth

Automated AI segmentation of macular OCT quantified selective inner retinal thinning during silicone oil tamponade and identified RNFL, GCL+IPL and PR+RPE as strongest predictors of visual acuity change, enabling prognostication after oil removal.

Source article: PREDICTIVE OCT BIOMARKERS OF RETINAL CHANGES AND VISUAL OUTCOMES IN SILICONE OIL ENDOTAMPONADE IDENTIFIED BY ARTIFICIAL INTELLIGENCE

Retina

Reader signal

How should this claim be treated?

175

Evidence-backed gainPeer-reviewedHealth

AI assistance during routine mammography was associated with higher overall cancer detection and no increase in average interpretation time.

Source article: Impact of AI assistance on reading time, cancer detection rate, and abnormal interpretation rate in screening and diagnostic mammography: a prospective alternating-month study

European Radiology

Reader signal

How should this claim be treated?

176

Evidence-backed gainPeer-reviewedHealth

CURL-AID automated analysis of parasternal long-axis echocardiograms quantified posterior annular hypermobility and classified posterior systolic curling with AUC 0.865 and accuracy 0.82.

Source article: CURL-AID: Automated Echocardiographic Motion Analysis for Quantitative Assessment of Posterior Systolic Curling

Ultrasound in Medicine & Biology

Reader signal

How should this claim be treated?

177

Evidence-backed gainPeer-reviewedHealth

Random survival forests models incorporating oxidative stress index score improved prediction of disease-free and overall survival for locally advanced rectal cancer patients receiving neoadjuvant therapy, outperforming conventional ypStage and enabling risk stratification.

Source article: Building Machine Learning Models Based on Oxidative Stress Index Score to Predict Survival of Locally Advanced Rectal Cancer Receiving Different Neoadjuvant Therapy Patterns

Diseases of the Colon & Rectum

Reader signal

How should this claim be treated?

178

Evidence-backed gainPeer-reviewedHealth

The CODEX Action Incubator at UCSF convened 30 stakeholders and reached consensus on two priority metrics of AI scribe usage by primary care physicians to assess diagnostic excellence, including timely follow-up of abnormal breast and colorectal cancer screening results.

Source article: The CODEX action incubator: a consensus-driven approach to identify and implement diagnostic excellence measures in the context of artificial intelligence

Diagnosis

Reader signal

How should this claim be treated?

179

Evidence-backed gainPeer-reviewedHealth

Solvent extraction of urine analyzed by GC-MS and XGBoost distinguished bladder cancer patients from controls with AUROC 0.869 and 85% balanced sensitivity and specificity using an 8-metabolite panel.

Source article: Urinary volatilomics using liquid-liquid extraction and gas chromatography-mass spectrometry (GC-MS) combined with machine learning algorithms as a tool for diagnosis and surveillance of urothelial bladder cancer

BJC Reports

Reader signal

How should this claim be treated?

180

Evidence-backed gainPeer-reviewedHealth

YOLOv8x-pose and YOLOv8x-seg models automated landmark detection and apical segmentation for the Cameriere European method in children aged 5-13, achieving high detection accuracy and low measurement error in a first-stage validation.

Source article: First-stage assessment of AI-based anatomical measurement accuracy for the Cameriere European dental age estimation method

International Journal of Legal Medicine

Reader signal

How should this claim be treated?