Search Articles

View query in Help articles search

Search Results (1 to 10 of 2662 Results)

Download search results: CSV END BibTex RIS


Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks

Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks

Victor et al [23] and Perron et al [24,25] applied machine learning algorithms such as random forest and k-nearest neighbors on caseworker summaries to identify domestic violence events and opioid-related maltreatment risks, respectively. In addition, Saxena et al [26] used topic modeling to explore the concept and definitions of “risk” on child maltreatment records with promising performance.

Wilson Lukmanjaya, Tony Butler, Sarah Cox, Oscar Perez-Concha, Leah Bromfield, George Karystianis

JMIR Pediatr Parent 2025;8:e73579

Improving Large Language Models’ Summarization Accuracy by Adding Highlights to Discharge Notes: Comparative Evaluation

Improving Large Language Models’ Summarization Accuracy by Adding Highlights to Discharge Notes: Comparative Evaluation

Their method outperformed 3 baseline approaches, namely frequency-based, graph-based, and K-means centroid-based extractive summarization, demonstrating better content preservation and semantic alignment with the original notes. In the study by Alsentzer and Kim [38], they explored extractive summarization of discharge notes from the MIMIC-III database.

Mahshad Koohi Habibi Dehkordi, Yehoshua Perl, Fadi P Deek, Zhe He, Vipina K Keloth, Hao Liu, Gai Elhanan, Andrew J Einstein

JMIR Med Inform 2025;13:e66476