Lara J Kanbar1, Wissam Shalish2, Charles C Onu3, Samantha Latremouille4, Lajos Kovacs5, Martin Keszler6, Sanjay Chawla7, Karen A Brown8, Doina Precup3, Robert E Kearney1, Guilherme M Sant'Anna9. 1. Department of Biomedical Engineering, McGill University, Montreal, QC, Canada. 2. Department of Pediatrics, Neonatology, McGill University Health Center, Montreal, QC, Canada. 3. School of Computer Science, McGill University, Montreal, QC, Canada. 4. Department of Experimental Medicine, McGill University, Montreal, QC, Canada. 5. Department of Neonatology, Jewish General Hospital, McGill University, Montreal, QC, Canada. 6. Department of Pediatrics, Women and Infants Hospital of Rhode Island, Brown University, Providence, RI, USA. 7. Division of Neonatal-Perinatal Medicine, Hutzel Women's Hospital, Children's Hospital of Michigan, Central Michigan University, Pleasant, MI, USA. 8. Department of Anesthesia, McGill University Health Center, Montreal, QC, Canada. 9. Department of Pediatrics, Neonatology, McGill University Health Center, Montreal, QC, Canada. guilherme.santanna@mcgill.ca.
Abstract
BACKGROUND: Extremely preterm infants are frequently subjected to mechanical ventilation. Current prediction tools of extubation success lacks accuracy. METHODS: Multicenter study including infants with birth weight ≤1250 g undergoing their first extubation attempt. Clinical data and cardiorespiratory signals were acquired before extubation. Primary outcome was prediction of extubation success. Automated analysis of cardiorespiratory signals, development of clinical and cardiorespiratory features, and a 2-stage Clinical Decision-Balanced Random Forest classifier were used. A leave-one-out cross-validation was done. Performance was analyzed by ROC curves and determined by balanced accuracy. An exploratory analysis was performed for extubations before 7 days of age. RESULTS: A total of 241 infants were included and 44 failed (18%) extubation. The classifier had a balanced accuracy of 73% (sensitivity 70% [95% CI: 63%, 76%], specificity 75% [95% CI: 62%, 88%]). As an additional clinical-decision tool, the classifier would have led to an increase in extubation success from 82% to 93% but misclassified 60 infants who would have been successfully extubated. In infants extubated before 7 days of age, the classifier identified 16/18 failures (specificity 89%) and 73/105 infants with success (sensitivity 70%). CONCLUSIONS: Machine learning algorithms may improve a balanced prediction of extubation outcomes, but further refinement and validation is required. IMPACT: A machine learning-derived predictive model combining clinical data with automated analyses of individual cardiorespiratory signals may improve the prediction of successful extubation and identify infants at higher risk of failure with a good balanced accuracy. Such multidisciplinary approach including medicine, biomedical engineering and computer science is a step forward as current tools investigated to predict extubation outcomes lack sufficient balanced accuracy to justify their use in future trials or clinical practice. Thus, this individualized assessment can optimize patient selection for future trials of extubation readiness by decreasing exposure of low-risk infants to interventions and maximize the benefits of those at high risk.
BACKGROUND: Extremely preterm infants are frequently subjected to mechanical ventilation. Current prediction tools of extubation success lacks accuracy. METHODS: Multicenter study including infants with birth weight ≤1250 g undergoing their first extubation attempt. Clinical data and cardiorespiratory signals were acquired before extubation. Primary outcome was prediction of extubation success. Automated analysis of cardiorespiratory signals, development of clinical and cardiorespiratory features, and a 2-stage Clinical Decision-Balanced Random Forest classifier were used. A leave-one-out cross-validation was done. Performance was analyzed by ROC curves and determined by balanced accuracy. An exploratory analysis was performed for extubations before 7 days of age. RESULTS: A total of 241 infants were included and 44 failed (18%) extubation. The classifier had a balanced accuracy of 73% (sensitivity 70% [95% CI: 63%, 76%], specificity 75% [95% CI: 62%, 88%]). As an additional clinical-decision tool, the classifier would have led to an increase in extubation success from 82% to 93% but misclassified 60 infants who would have been successfully extubated. In infants extubated before 7 days of age, the classifier identified 16/18 failures (specificity 89%) and 73/105 infants with success (sensitivity 70%). CONCLUSIONS: Machine learning algorithms may improve a balanced prediction of extubation outcomes, but further refinement and validation is required. IMPACT: A machine learning-derived predictive model combining clinical data with automated analyses of individual cardiorespiratory signals may improve the prediction of successful extubation and identify infants at higher risk of failure with a good balanced accuracy. Such multidisciplinary approach including medicine, biomedical engineering and computer science is a step forward as current tools investigated to predict extubation outcomes lack sufficient balanced accuracy to justify their use in future trials or clinical practice. Thus, this individualized assessment can optimize patient selection for future trials of extubation readiness by decreasing exposure of low-risk infants to interventions and maximize the benefits of those at high risk.
Authors: Christopher Harris; Alessandra Bisquera; Alan Lunt; Janet L Peacock; Anne Greenough Journal: N Engl J Med Date: 2020-08-13 Impact factor: 91.245
Authors: Michele C Walsh; Brenda H Morris; Lisa A Wrage; Betty R Vohr; W Kenneth Poole; Jon E Tyson; Linda L Wright; Richard A Ehrenkranz; Barbara J Stoll; Avroy A Fanaroff Journal: J Pediatr Date: 2005-06 Impact factor: 4.406
Authors: Sanjay Chawla; Girija Natarajan; Seetha Shankaran; Benjamin Carper; Luc P Brion; Martin Keszler; Waldemar A Carlo; Namasivayam Ambalavanan; Marie G Gantz; Abhik Das; Neil Finer; Ronald N Goldberg; C Michael Cotten; Rosemary D Higgins Journal: J Pediatr Date: 2017-06-07 Impact factor: 4.406
Authors: Dan Milea; Raymond P Najjar; Jiang Zhubo; Daniel Ting; Caroline Vasseneix; Xinxing Xu; Masoud Aghsaei Fard; Pedro Fonseca; Kavin Vanikieti; Wolf A Lagrèze; Chiara La Morgia; Carol Y Cheung; Steffen Hamann; Christophe Chiquet; Nicolae Sanda; Hui Yang; Luis J Mejico; Marie-Bénédicte Rougier; Richard Kho; Tran Thi Ha Chau; Shweta Singhal; Philippe Gohier; Catherine Clermont-Vignal; Ching-Yu Cheng; Jost B Jonas; Patrick Yu-Wai-Man; Clare L Fraser; John J Chen; Selvakumar Ambika; Neil R Miller; Yong Liu; Nancy J Newman; Tien Y Wong; Valérie Biousse Journal: N Engl J Med Date: 2020-04-14 Impact factor: 91.245
Authors: Erik A Jensen; Sara B DeMauro; Michael Kornhauser; Zubair H Aghai; Jay S Greenspan; Kevin C Dysart Journal: JAMA Pediatr Date: 2015-11 Impact factor: 16.193
Authors: Barbara J Stoll; Nellie I Hansen; Edward F Bell; Michele C Walsh; Waldemar A Carlo; Seetha Shankaran; Abbot R Laptook; Pablo J Sánchez; Krisa P Van Meurs; Myra Wyckoff; Abhik Das; Ellen C Hale; M Bethany Ball; Nancy S Newman; Kurt Schibler; Brenda B Poindexter; Kathleen A Kennedy; C Michael Cotten; Kristi L Watterberg; Carl T D'Angio; Sara B DeMauro; William E Truog; Uday Devaskar; Rosemary D Higgins Journal: JAMA Date: 2015-09-08 Impact factor: 56.272