Pediatric Predictive Artificial Intelligence Implemented in Clinical Practice from 2010-2021: A Systematic Review

Swaminathan Kandaswamy; Lindsey A Knake; Adam Dziorny; Sean Hernandez; Allison B McCoy; Lauren M. Hess; Evan Orenstein; Mia S White; Eric S. Kirkendall; Matthew Molloy; Philip Hagedorn; Naveen Muthu; Avinash Murugan; Jonathan M Beus; Mark Mai; Brooke Luo; Juan Demetrio Chaparro

doi:10.1055/a-2521-1508

Applied Clinical Informatics, Table of Contents

Appl Clin Inform
DOI: 10.1055/a-2521-1508

Review

Pediatric Predictive Artificial Intelligence Implemented in Clinical Practice from 2010-2021: A Systematic Review

Swaminathan Kandaswamy

¹Emory University, Atlanta, United States (Ringgold ID: RIN1371)

,

Lindsey A Knake

²Neonatology, University of Iowa Health Care, Iowa City, United States (Ringgold ID: RIN21710)

,

Adam Dziorny

³Pediatrics, University of Rochester School of Medicine and Dentistry, Rochester, United States (Ringgold ID: RIN12299)

,

Sean Hernandez

⁴General Internal Medicine, Wake Forest School of Medicine, Winston-Salem, United States (Ringgold ID: RIN12279)

,

Allison B McCoy

⁵Biomedical Informatics, Vanderbilt University School of Medicine, Nashville, United States (Ringgold ID: RIN12327)

,

Lauren M. Hess

⁶Section of Pediatric Hospital Medicine, Baylor College of Medicine, Houston, United States (Ringgold ID: RIN3989)

,

Evan Orenstein

⁷Pediatrics, Children's Healthcare of Atlanta Egleston Hospital, Atlanta, United States (Ringgold ID: RIN138610)

,

Mia S White

¹Emory University, Atlanta, United States (Ringgold ID: RIN1371)

,

Eric S. Kirkendall

⁸Pediatrics, Wake Forest Baptist Health, Winston-Salem, United States

,

Matthew Molloy

⁹Pediatrics, Cincinnati Children's Hospital Medical Center, Cincinnati, United States (Ringgold ID: RIN2518)

,

Philip Hagedorn

¹⁰Hospital Medicine, Cincinnati Children's Hospital Medical Center, Cincinnati, United States (Ringgold ID: RIN2518)

,

Naveen Muthu

¹¹Pediatric Hospital Medicine, Children's Healthcare of Atlanta Inc, Atlanta, United States (Ringgold ID: RIN1367)

,

Avinash Murugan

¹²Internal Medicine, Yale New Haven Hospital, New Haven, United States (Ringgold ID: RIN25047)

,

Jonathan M Beus

¹³Pediatrics, Children's Healthcare of Atlanta Inc, Atlanta, United States (Ringgold ID: RIN1367)

¹⁴Pediatrics, Emory University, Atlanta, United States (Ringgold ID: RIN1371)

,

Mark Mai

⁷Pediatrics, Children's Healthcare of Atlanta Egleston Hospital, Atlanta, United States (Ringgold ID: RIN138610)

,

Brooke Luo

¹⁵Childrens Hospital of Philadelphia, Philadelphia, United States

,

Juan Demetrio Chaparro

¹⁶Pediatrics, Ohio State University College of Medicine, Columbus, United States (Ringgold ID: RIN12305)

¹⁷Pediatrics, Nationwide Children's Hospital, Columbus, United States (Ringgold ID: RIN2650)

› Author Affiliations

Abstract

PDF Download

Objective: To review pediatric artificial intelligence (AI) implementation studies from 2010-2021 and analyze reported performance measures. Methods: We searched PubMed/Medline, Embase CINHAL, Cochrane Library CENTRAL, IEEE and Web of Science with controlled vocabulary. Inclusion criteria: AI intervention in a pediatric clinical setting that learns from data (i.e., data-driven, as opposed to rule-based) and takes actions to make patient-specific recommendations; published between 01/2010 to 10/2021; must have agency (AI must provide guidance that affects clinical care, not merely running in background). We extracted study characteristics, target users, implementation setting, time span, and performance measures. Results: Of 126 articles reviewed as full text, 17 met inclusion criteria. Eight studies (47%) reported both clinical outcomes and process measures, six (35%) reported only process measures, and two (12%) reported only clinical outcomes. Five studies (30%) reported no difference in clinical outcomes with AI, four (24%) reported improvement in clinical outcomes compared to controls, two (12%) reported positive effects on clinical outcomes with use of AI but had no formal comparison or controls, and one (6%) reported poor clinical outcomes with AI. Twelve studies (71%) reported improvement in process measures, while two (12%) reported no improvement. Five (30%) studies reported on at least 1 human performance measure. Conclusions : While there are many published pediatric AI models, the number of AI implementations is minimal with no standardized reporting of outcomes, care processes, or human performance measures. More comprehensive evaluations will help elucidate mechanisms of impact.

PDF (3879 kb)