In a 2026 study of 138 teens with ADHD at a clinic in Turkey, school discipline, frequent absences, family factors and gaps in ADHD treatment were far more common in those who also had conduct disorder.1 A machine-learning model built from school, family and treatment records rarely flagged the wrong teen, but it missed about …
Adding socioeconomic background to EEG brain recordings slightly improved how well a deep-learning model sorted 127 US university students by ADHD screening status. Accuracy rose on all 4 brain-recording tasks, but the gain was not statistically significant on any of them.1 Research Highlights About 9 in 10 classified correctly from EEG alone: tested on students …
A professional esports team’s voices in the minute before a match carried clues about whether it would win, according to a 2026 study of 89 Counter-Strike matches played by one 5-player team. Voice helped most when combined with the gap in team rankings.1 Research Highlights Voice plus ranking did best: a decision-tree model using 60 …
Chinese teens aged 10 to 15 who trusted the people around them less had more depressive symptoms 2 years later, in a 2026 study that followed 971 teens. Frequent arguments with parents and low satisfaction with teachers were also linked to higher scores.1 Research Highlights Social trust ranked first: of 13 factors measured in 2020, …
A 2026 PLOS One machine-learning study reported 95.0% accuracy for a hybrid FT-Transformer plus long short-term memory (LSTM) model predicting student mental-health risk. The technical result is strong inside the dataset, but the clinical claim is still limited because the labels came from repository data rather than prospective clinical diagnosis.1 Research Highlights 95.0% accuracy was …
A 2026 ADNI/A4 validation study found that Alzheimer’s plasma-biomarker machine-learning models still ranked amyloid PET status well across cohorts, but the practical rule-out number moved hard: negative predictive value fell from 0.831 inside ADNI to 0.644 when the ADNI-trained model was applied to A4.1 Research Highlights 1,707-person ADNI/A4 test: researchers trained amyloid PET prediction models …
A 2026 TADPOLE modeling study reported that a sequential neural process with normalizing flows predicted future Alzheimer diagnostic stage with mAUC 0.965 ± 0.006, ahead of the authors’ earlier sequential-neural-process model at 0.937 ± 0.014.1 The result is a strong benchmark signal for uncertainty-aware disease-progression AI, but it is still retrospective modeling evidence rather than …