For how we live.
A review of 41 studies found that the great majority of AI medication-adherence prediction models carried high risk of bias, and that fancier algorithms did not reliably predict better.
ABYSS and SMART-DECISION together cover 6,238 stable patients. Discontinuation cleared both noninferiority margins, though the authors say the primary endpoint's composition limits what it shows.
An updated systematic review of 25 randomised trials found small effects, concentrated in neuropathic pain, alongside moderate to large increases in dizziness, sedation and nausea. Long-term data barely exist.
The pooled effect on self-reported stress was g = -0.35 from 785 participants. The authors of the meta-analysis warn against a miscalibration between the hype and the evidence — their phrase, not ours.
A network meta-analysis of 331 trials and 34,285 adults found no significant differences between the main psychotherapies, with one exception. In children and adolescents the picture is narrower.
A network meta-analysis of 101 trials and 11,910 patients found no significant difference between psychotherapy and medication for adult depression — and a consistent advantage for combining them.