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 3 of 10

Evidence-backed gainPeer-reviewedHealth

A Super Learner ensemble and derived 17-feature point-based scorecard predicted 1-year pneumonia hospitalization among community-dwelling Japanese adults aged 75+ with good discrimination and calibration on internal test data.

Source article: A Machine Learning-Derived Risk Scorecard for Pneumonia Hospitalization in Japanese Old-Old Adults

Geriatrics & Gerontology International

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Researchers used machine learning and LASSO regression on single-cell data to identify seven PANoptosis key genes and build a validated IDD risk diagnosis model, with experimental knockdown of ACSBG1 reducing degeneration in a rat model.

Source article: Identification and Experimental Validation of PANoptosis Key Genes for Constructing a PANoptosis Risk Diagnostic Model in Intervertebral Disc Degeneration

The Journal of Gene Medicine

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Researchers built and externally validated a machine learning model that identifies DCIS at high risk of progressing to invasive disease, enabling more precise risk stratification and clinical management.

Source article: Integrated Multi-Omics Reveals Cellular States and Microenvironmental Remodeling in Coexisting DCIS and IDC

Advanced Science

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

A Random Forest model combining two tryptophan metabolites (kynurenine and neopterin) with five routine clinical tests discriminated MASLD from healthy controls with high diagnostic performance.

Source article: Machine learning-based discrimination of metabolic dysfunction-associated steatotic liver disease: implications of tryptophan metabolites as potential biomarkers

Clinica Chimica Acta

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

An interpretable machine learning nomogram using eGFR, anhepatic phase time, postoperative log D-dimer and ALT available within 1 hour after liver transplantation predicted AKI with AUC 0.861 in training and 0.761 in validation, with SVM reaching 0.846, to enable early identification for intensified renal monitoring.

Source article: Machine learning-based nomogram for acute kidney injury after liver transplantation

Renal Failure

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Parent-report ML model combining expressive vocabulary and joint attention items achieved over 0.7 sensitivity and specificity for both autism and developmental delay at 18-month visits, approximately doubling sensitivity versus existing screens.

Source article: Exploring the Potential of Parent Report for Autism/Developmental Screening at the 18-Month Visit

Journal of Autism and Developmental Disorders

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Machine learning models trained on perioperative data achieved high discrimination for 30-day postoperative mortality and identified clinically meaningful predictors, supporting more transparent surgical risk assessment and patient counseling.

Source article: Toward Clinically Interpretable Perioperative Decision Support: Explainable Machine Learning for 30-Day Postoperative Mortality Prediction

The American Surgeon™

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Patient-specific 3D point-cloud model predicted motor improvement within 5 MDS-UPDRS-III points for 15 of 24 test cases, outperforming a voxelized CNN baseline in this fixed split.

Source article: Three-Dimensional Point-Cloud Learning for Patient-Specific Deep Brain Stimulation Motor Response Prediction in Parkinson Disease

BME Frontiers

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Unsupervised hierarchical clustering of 20,352 VLBW infants identified eight diagnosis-independent clusters of intestinal injury vulnerability, with high-risk Cluster 8 further split into five etiologic subclusters, creating a framework for a more precise taxonomy beyond traditional NEC staging.

Source article: Distinct clinical patterns of preterm infants vulnerable to intestinal injury identified by unsupervised clustering

Pediatric Research

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

PPV for high-confidence was superior to low-confidence detections (99.1% vs 59.1%, p Conclusion The algorithm showed good diagnostic performance for extremity fracture detection on radiographs.

Source article: Diagnostic accuracy & clinical importance of AI confidence for extremity fracture detection: 2,508-patient retrospective cohort

Emergency Radiology

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

We further clarify that predictive accuracy, interpretability and causal explanation are related but distinct aims, and that machine learning should complement rather than replace psychological theory, causal reasoning and clinical judgement.

Source article: Methodological transitions in mental health research driven by machine learning

BJPsych Open

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Serum Protein Glycopatterns as Biomarkers for Machine Learning Diagnosis of Major Depressive Disorder: These features were used to train seven machine-learning models, among which K-nearest neighbours (KNN) performed best, achieving 95.3% ± 2.7% accuracy and an AUC (Micro) of 0.990 ± 0.010 in a nested 5-fold cross-validation framework.

Source article: Serum Protein Glycopatterns as Biomarkers for Machine Learning Diagnosis of Major Depressive Disorder

Glycobiology

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Results The AI model achieved an overall accuracy of 72.2%, a macro F1 score of 0.64, and a weighted F1 score of 0.73 compared with psychiatrists' ratings.

Source article: Development of an artificial intelligence model to estimate psychiatrist-assessed mental health-related presenteeism

Journal of Occupational Health

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Smartphone AI-Enabled Lateral Flow Immunoassay Platform Using Advanced Quantum Dots for Intelligent Quantitative Diagnostics: Lateral flow immunoassays (LFIAs) are widely used in point-of-care diagnostics for their low cost and simplicity, but conventional formats rely on subjective visual readout and lack quantitative accuracy and sensitivity.

Source article: Smartphone AI-Enabled Lateral Flow Immunoassay Platform Using Advanced Quantum Dots for Intelligent Quantitative Diagnostics

ACS Applied Materials & Interfaces

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Using 1-month EHR data, the LLM achieved an accuracy of 87.0%, AUC of 0.921, F1 score of 0.579, sensitivity of 89.1%, specificity of 86.8%, and detection rate for early kidney injury of 42.2%.

Source article: Leveraging time-series electronic health records with large language models for chronic kidney disease diagnosis in primary care

BMJ Health & Care Informatics

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Compared to unassisted diagnosis, AI significantly improved pooled sensitivity (87%, 95% confidence interval [CI]: 84-89%, versus 73%, 95% CI: 69-78%) and maintained high specificity (95%, 95% CI: 92-97%, versus 94%, 95% CI: 89-96%).

Source article: Diagnostic accuracy of AI-assisted versus independent physician interpretation for bone fractures: a systematic review and meta-analysis

European Radiology Experimental

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Three ML approaches were evaluated: logistic regression (LR), Convolutional Neural Network (CNN) Attention-Multiple Instance Learning (MIL) (EfficientNet-V2-S), and a CNN-Extreme Gradient Boosting Hybrid (XGBoost).Patients/ParticipantsForty pediatric participants aged 2 to 17, including individuals with VPD, conditions associated with VPD, and healthy participants.Main Outcome Measure(s)Model performance was tested in binary hypernasality classification compared to SLP consensus at two CAPS-A-AM thresholds: absent (0) versus any hypernasality (1-4) and absent/borderline (0-1) versus mild-to-severe hypernasality (2-4).ResultsMultiple independent modeling approaches were able to detect clinically rated hypernasality.

Source article: Artificial Intelligence-Based Hypernasality Diagnosis Using CAPS-A-AM Rated Speech Samples in Pediatric Velopharyngeal Dysfunction

The Cleft Palate Craniofacial Journal

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Self-supervised patient-specific neural network with physics-based simulation aligns intraoperative X-ray fluoroscopy to preoperative 3D volumes in seconds with order-of-magnitude accuracy improvement across anatomies and hospitals.

Source article: Rapid patient-specific neural networks for X-ray to volume registration

Nature

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

AI-based digital pathology models have been qualified by regulators for endpoint determination in MASH trials, with additional AI risk models and large language models applied to patient enrollment, recruitment and retention.

Source article: How to apply artificial intelligence (AI) to facilitate and enhance MASH trials

Hepatology International

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

A random survival forest clinicogenomic model integrating a 21-gene recurrence score, 14-gene immunoglobulin signature, and clinicopathologic features improved prognostic stratification in ER-positive/HER2-negative early breast cancer, identifying larger low-risk groups and improving discrimination in external datasets

Source article: Development and validation of a machine learning clinicogenomic model to improve prognostic stratification in ER-positive/HER2-negative early breast cancer

Breast Cancer Research

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Deep learning-augmented plasmonic system PANDA profiled alpha-synuclein aggregate size distributions from human serum and classified Parkinson's disease stages with correlation to clinical scores and dopaminergic PET imaging.

Source article: Deep Learning-Powered Plasmonic Platform for Decoding Dynamic Protein Aggregation Landscapes in Parkinson's Disease Progression

Advanced Materials

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

An explainable XGBoost model using six routine preoperative variables enabled individualized reflux esophagitis risk prediction for metabolic bariatric surgery candidates with AUC 0.881 training and 0.825 internal test.

Source article: Development of an Explainable Machine Learning Model for Predicting Reflux Esophagitis Among Candidates for Metabolic Bariatric Surgery

Obesity Surgery

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

A reliability-oriented hybrid framework combining a periocular ResNet18 and a facial ensemble of ResNet50, EfficientNet-B0 and DenseNet121 increased early ASD risk indication to 90% sensitivity in the periocular pathway, 87.1% sensitivity with 0.948 AUC in the facial pathway, and an analytically estimated 98.71% system

Source article: A hybrid deep learning framework for early autism screening

Primary Health Care Research & Development

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Machine learning models trained on clinical, radiomics and dosiomics features predicted radionecrosis after stereotactic radiotherapy for brain metastases with ROC-AUC up to 80%, offering decision support that may improve patient-specific treatment and reduce radiotherapy-induced toxicity severity.

Source article: Radiomics and dosiomics in radionecrosis prediction in brain metastasis treated with Stereotactic Radiation Therapy: a machine learning approach

Physica Medica

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Random forest with SHAP and network analysis among 6573 adolescents ranked key contributors to IGD risk and identified central nodes, which may inform early risk identification.

Source article: Identifying key risk factors of adolescent Internet Gaming Disorder using explainable machine learning and network analysis

Journal of Affective Disorders

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

A 3D-ResNet18 multi-task model reduced error in estimating rib fracture age from chest CT to 7.94 days MAE, outperforming manual expert evaluation at 10.65 days, while also classifying healing stage and fracture type.

Source article: A multi-task learning-based deep learning model for precise estimation of rib fracture age on chest CT

International Journal of Legal Medicine

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Among Medicare fee-for-service beneficiaries aged 65+ with ADRD hospitalized in 2023, greater hospital adoption of patient-related AI/ML tools was associated with lower odds of frequent hospitalizations, 30-day readmissions, and preventable acute hospitalizations, with inpatient risk prediction tools also linked to no

Source article: Hospital Artificial Intelligence Tools and Inpatient Utilization and Costs in Older Adults with Alzheimer's Disease and Related Dementias

Journal of the American Geriatrics Society

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

GPT-4-generated, accessibility-optimised discharge letters increased comprehension of diagnosis, treatment, investigations and follow-up compared with conventional letters.

Source article: Comprehension of an AI-generated discharge letter versus a traditional discharge letter: two controlled quasi-experimental parallel-group studies

International Journal for Quality in Health Care

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

A 1-D CNN with sharpness-aware minimization applied to Raman spectra distinguished unstimulated, activated, and exhausted T cells with >97% accuracy and quantified exhaustion percentage in heterogeneous populations with R2 = 1.

Source article: Nucleic Acid Turnover and Lipid Remodeling Distinguish T Cell Activation and Exhaustion States via Label-Free Raman Spectroscopy

ACS Sensors

Reader signal

How should this claim be treated?

Evidence-backed gainPeer-reviewedHealth

Interpretable random survival forest model predicted all-cause mortality in adults with unrepaired PAH-CHD and stratified survival in both Eisenmenger and non-Eisenmenger subgroups where the ESC model did not.

Source article: Interpretable machine learning-enabled risk stratification for pulmonary arterial hypertension associated with unrepaired congenital heart disease: results from a national prospective registry

International Journal of Cardiology

Reader signal

How should this claim be treated?