Back

Leveraging Artificial Intelligence to Mitigate Adolescent Risky Behaviors: A Scoping Review Protocol

Sadeghsalehi, H.; Joulaei, H.

2024-06-11 public and global health
10.1101/2024.06.11.24308749 medRxiv
Show abstract

Adolescents are particularly vulnerable to engaging in risky behaviors such as violence, unprotected sex, and substance abuse, which have significant negative impacts on their health and development. Recent advancements in artificial intelligence (AI) offer innovative solutions to address these behaviors, yet the evidence regarding the efficacy and implementation of AI-based interventions remains fragmented. This scoping review aims to systematically explore and map the literature on AI-based interventions designed to reduce risky behaviors among adolescents. This review will follow the methodological frameworks outlined by Arksey and OMalley (2005) and improved by Levac, Colquhoun, and OBrien (2010), in line with the Joanna Briggs Institute guidelines. The PRISMA Extension for Scoping Reviews (PRISMA-ScR) will guide the reporting. The search strategy will be executed across PubMed, Scopus, Web of Science Core Collection, CINAHL, PsycINFO, Cochrane Central Register of Controlled Trials, Embase, SID, and Magiran, focusing on articles published up to June 2024 in English and Farsi. Titles and abstracts will be screened by two independent reviewers using Rayyan, followed by full-text screening of relevant studies. Data will be charted using a standardized form, and discrepancies will be resolved through discussion or by consulting a third reviewer. Data will be synthesized descriptively and presented in tables, figures, and diagrams.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.