Ranks distinct AI gain and problem claims from the published record. Scores reward impact, independent source strength, scale, confidence, and recency.
Researchers developed and internally validated machine-learning models to estimate the probability of urine-culture positivity using routinely collected urinalysis data from 2530 sample records across three university hospitals. Using a stratified 75:25 sample-level split, 13 supervised algorithms were tested, with CatBoost showing the highest test-set AUC of 0.858 (95% CI 0.829-0.892) and similar performance to other gradient-boosting models.
In a study published September 9, 2026, investigators built a machine learning calculator to estimate 1-year mortality after primary total knee and hip arthroplasty using 43 routinely available preoperative variables from the TriNetX Research Network. On internal validation the model achieved AUROC 0.761 with Brier score 0.006, and stratified risk monotonically from 0.574% overall to 3.57% in the top 5% of predicted risk.
Researchers retrospectively analyzed 600 patients with Hashimoto's thyroiditis and 650 pathology-confirmed thyroid nodules to test whether combining grayscale ultrasound, contrast-enhanced ultrasound, and serum anti-thyroid peroxidase antibody improves malignancy differentiation. They built a logistic regression model on patients with complete data and performed stratified 5-fold cross-validation, also comparing six machine learning classifiers.
Accurate Ultrasound (US) prostate cancer (PCa) segmentation images hold significant value for organ interventional guidance and clinical disease diagnosis. However, this task still poses substantial challenges.
Researchers defined LLM dark patterns as manipulative behaviors enacted in dialogue and conducted a scenario-based study with 34 participants who compared manipulative and neutral responses. Recognition often depended on cues such as exaggerated agreement, biased framing, or privacy intrusions, but participants sometimes treated those behaviors as normal help.
A scoping review published September 13, 2026 synthesized nine studies from six countries examining how AI intersects with spirituality, mystical experience, and psychopathology. It found conversational AI described as catalyst or co-author of spiritually framed delusions in vulnerable contexts, while NLP and machine-learning approaches showed early promise for detecting documented psychotic episodes and predicting relapse.
The DEEP READ prospective study across 13 Italian provinces followed 322 adults with major depressive disorder discharged from inpatient care and tested whether routinely collected clinical information could predict unplanned psychiatric readmission within 90 days. A Random Forest classifier trained on 22 predictors achieved a mean test AUC of 0.74 in internal cross-validation, with 50 patients (15.5%) readmitted.
The I3LUNG study enrolled 2,396 patients with non-small cell lung cancer to develop AI models for immunotherapy selection, integrating clinical and blood data, CT, digital pathology and genomics into early and intermediate fusion models. CB-only models reached AUC up to 0.77 in the independent TEST set and outperformed PD-L1, ECOG PS, NLR, LDH and LIPI, and a usability study found physicians improved predictions with the explainable AI tool.
ace