Hospital Injury Encounters of Children Identified by a Predictive Risk Model for Screening Child Maltreatment Referrals: Evidence from the Allegheny Family Screening Tool
This paper confirms that children identified as at risk by the Allegheny Family Screening Tool (AFST), a predictive risk modelling tool that supports child protection decisions in Allegheny County (PA, United States), are also at considerably heightened risk of hospitalisation injury. The authors, including Rhema Vaithianathan and Diana Benavides Prado, used a one-off linkage between the child protection system and Pittsburgh Children’s Hospital data to show that children identified as at risk by the AFST are indeed at considerably heightened risk of injury, abuse, and self-harm hospitalisation. The authors also identified a sharply heightened hospitalisation risk for children receiving the highest AFST scores and found that the AFST is particularly sensitive to the risk facing White children, which means the child protection system is potentially under protecting those children.
Vaithianathan R, Putnam-Hornstein E, Chouldechova A, Benavides-Prado D, Berger R. Hospital Injury Encounters of Children Identified by a Predictive Risk Model for Screening Child Maltreatment Referrals: Evidence From the Allegheny Family Screening Tool. JAMA Pediatr. Published online August 03, 2020. doi:10.1001/jamapediatrics.2020.2770
Allegheny Family Screening Tool
Digital Contact Tracing for COVID-19: A Primer for Policymakers
This working paper is intended as a guide for policymakers considering the use of digital contact tracing solutions for Covid-19. The authors, including Rhema Vaithianathan and Nina Anchugina, use a simple graphical model of infection transmissions to illustrate why COVID-19 is particularly challenging to manage with traditional manual contact tracing. They find that digital contact tracing solutions for COVID-19 must offer exceptional speed and achieve high take-up rates to be useful. The paper discusses the importance of social licence for take-up, and explains how a commitment to impact evaluation can help build trust.
Vaithianathan, R., Ryan, M., Anchugina, N., Selvey, L., Dare, T., & Brown, A. (2020). Digital Contact Tracing for Covid-19: A Primer for Policymakers (Working Paper). Centre for Social Data Analytics: Auckland University of Technology & The University of Queensland.
Towards Knowledgeable Supervised Lifelong Learning Systems
This paper co-authored by Diana Benavides-Prado offers a potential solution to challenges associated with machine learning systems that learn sequentially. The authors propose a framework for long-term learning systems (Proficiente), which relies on transferring knowledge across tasks in two directions using Support Vector Machines (SVM). Proficiente makes it possible to transfer knowledge acquired from a previous task forward to a new target task and to transfer knowledge acquired from recent tasks backward to refine knowledge acquired from previous tasks. The authors demonstrate that transferring selected knowledge forward and backwards has the potential to encourage learning systems to become more knowledgeable while observing tasks sequentially.
Benavides-Prado, D., Koh, Y. S., & Riddle, P. (2020). Towards Knowledgeable Supervised Lifelong Learning Systems. Journal of Artificial Intelligence Research, 68, 159-224.