Artificial intelligence promises to revolutionize mental health care, but small dataset sizes and lack of robust methods raise concerns about result generalizability. To provide insights on minimal necessary data set sizes, we explore domain-specific learning curves for digital intervention dropout predictions based on 3654 users from a single study (ISRCTN13716228, 26/02/2016). Prediction performance is analyzed based on dataset size (N = 100-3654), feature groups (F = 2-129), and algorithm choice (from Naive Bayes to Neural Networks).
View Article and Find Full Text PDFVitamin B (VB) is a flexible and sustainable catalyst both in nature and the reaction flask, facilitating varied organic transformations of high value to both enzymatic processes and synthetic chemists. Key to this value is the breadth of reactivity it possesses, capable of both ionic, 2 electron chemistry, and radical, 1 electron chemistry. In particular, the ability to generate carbon-centered radical intermediates via photolysis of organocobalt intermediates formed from alkyl electrophiles opens the door to powerful new radical transformations challenging to achieve using classical photoredox or ligand-to-metal charge transfer (LMCT) catalysis.
View Article and Find Full Text PDF