Ryan M McAdams1, Ravneet Kaur2, Yao Sun3, Harlieen Bindra2, Su Jin Cho4, Harpreet Singh5. 1. Department of Pediatrics, University of Wisconsin School of Medicine and Public Health, Madison, WI, USA. 2. Child Health Imprints (CHIL) USA Inc, Madison, WI, USA. 3. Division of Neonatology, University of California San Francisco, San Francisco, CA, USA. 4. College of Medicine, Ewha Womans University Seoul, Seoul, Korea. 5. Child Health Imprints (CHIL) USA Inc, Madison, WI, USA. harpreet@childhealthimprints.com.
Abstract
BACKGROUND: Advances in technology, data availability, and analytics have helped improve quality of care in the neonatal intensive care unit. OBJECTIVE: To provide an in-depth review of artificial intelligence (AI) and machine learning techniques being utilized to predict neonatal outcomes. METHODS: The PRISMA protocol was followed that considered articles from established digital repositories. Included articles were categorized based on predictions of: (a) major neonatal morbidities such as sepsis, bronchopulmonary dysplasia, intraventricular hemorrhage, necrotizing enterocolitis, and retinopathy of prematurity; (b) mortality; and (c) length of stay. RESULTS: A total of 366 studies were considered; 68 studies were eligible for inclusion in the review. The current set of predictor models are primarily built on supervised learning and mostly used regression models built on retrospective data. CONCLUSION: With the availability of EMR data and data-sharing of NICU outcomes across neonatal research networks, machine learning algorithms have shown breakthrough performance in predicting neonatal disease.
BACKGROUND: Advances in technology, data availability, and analytics have helped improve quality of care in the neonatal intensive care unit. OBJECTIVE: To provide an in-depth review of artificial intelligence (AI) and machine learning techniques being utilized to predict neonatal outcomes. METHODS: The PRISMA protocol was followed that considered articles from established digital repositories. Included articles were categorized based on predictions of: (a) major neonatal morbidities such as sepsis, bronchopulmonary dysplasia, intraventricular hemorrhage, necrotizing enterocolitis, and retinopathy of prematurity; (b) mortality; and (c) length of stay. RESULTS: A total of 366 studies were considered; 68 studies were eligible for inclusion in the review. The current set of predictor models are primarily built on supervised learning and mostly used regression models built on retrospective data. CONCLUSION: With the availability of EMR data and data-sharing of NICU outcomes across neonatal research networks, machine learning algorithms have shown breakthrough performance in predicting neonatal disease.
Authors: Mohammed Saeed; Mauricio Villarroel; Andrew T Reisner; Gari Clifford; Li-Wei Lehman; George Moody; Thomas Heldt; Tin H Kyaw; Benjamin Moody; Roger G Mark Journal: Crit Care Med Date: 2011-05 Impact factor: 7.598
Authors: Pascale Carayon; Tosha B Wetterneck; Bashar Alyousef; Roger L Brown; Randi S Cartmill; Kerry McGuire; Peter L T Hoonakker; Jason Slagle; Kara S Van Roy; James M Walker; Matthew B Weinger; Anping Xie; Kenneth E Wood Journal: Int J Med Inform Date: 2015-04-15 Impact factor: 4.046
Authors: Neil Bodagh; R Andrew Archbold; Roshan Weerackody; Meredith K D Hawking; Michael R Barnes; Aaron M Lee; Surjeet Janjuha; Charles Gutteridge; John Robson; Adam Timmis Journal: BMJ Open Date: 2018-03-08 Impact factor: 2.692