2
|
Meeus M, Beirnaert C, Mahieu L, Laukens K, Meysman P, Mulder A, Van Laere D. Clinical Decision Support for Improved Neonatal Care: The Development of a Machine Learning Model for the Prediction of Late-onset Sepsis and Necrotizing Enterocolitis. J Pediatr 2024; 266:113869. [PMID: 38065281 DOI: 10.1016/j.jpeds.2023.113869] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Revised: 11/24/2023] [Accepted: 12/04/2023] [Indexed: 01/08/2024]
Abstract
OBJECTIVE To develop an artificial intelligence-based software system for predicting late-onset sepsis (LOS) and necrotizing enterocolitis (NEC) in infants admitted to the neonatal intensive care unit (NICU). STUDY DESIGN Single-center, retrospective cohort study, conducted in the NICU of the Antwerp University Hospital. Continuous monitoring data of 865 preterm infants born at <32 weeks gestational age, admitted to the NICU in the first week of life, were used to train an XGBoost machine learning (ML) algorithm for LOS and NEC prediction in a cross-validated setup. Afterward, the model's performance was assessed on an independent test set of 148 patients (internal validation). RESULTS The ML model delivered hourly risk predictions with an overall sensitivity of 69% (142/206) for all LOS/NEC episodes and 81% (67/83) for severe LOS/NEC episodes. The model showed a median time gain of ≤10 hours (IQR, 3.1-21.0 hours), compared with historical clinical diagnosis. On the complete retrospective dataset, the ML model made 721 069 predictions, of which 9805 (1.3%) depicted a LOS/NEC probability of ≥0.15, resulting in a total alarm rate of <1 patient alarm-day per week. The model reached a similar performance on the internal validation set. CONCLUSIONS Artificial intelligence technology can assist clinicians in the early detection of LOS and NEC in the NICU, which potentially can result in clinical and socioeconomic benefits. Additional studies are required to quantify further the effect of combining artificial and human intelligence on patient outcomes in the NICU.
Collapse
Affiliation(s)
- Marisse Meeus
- Department of Neonatal Intensive Care, Antwerp University Hospital, Edegem, Belgium; Laboratory of Experimental Medicine and Pediatrics, Faculty of Medicine and Health Sciences, University of Antwerp, Antwerpen, Belgium.
| | - Charlie Beirnaert
- Department of Neonatal Intensive Care, Antwerp University Hospital, Edegem, Belgium; Innocens BV, Antwerpen, Belgium; Department of Computer Science, University of Antwerp, Antwerpen, Belgium
| | - Ludo Mahieu
- Department of Neonatal Intensive Care, Antwerp University Hospital, Edegem, Belgium; Laboratory of Experimental Medicine and Pediatrics, Faculty of Medicine and Health Sciences, University of Antwerp, Antwerpen, Belgium
| | - Kris Laukens
- Department of Computer Science, University of Antwerp, Antwerpen, Belgium
| | - Pieter Meysman
- Department of Computer Science, University of Antwerp, Antwerpen, Belgium
| | - Antonius Mulder
- Department of Neonatal Intensive Care, Antwerp University Hospital, Edegem, Belgium; Laboratory of Experimental Medicine and Pediatrics, Faculty of Medicine and Health Sciences, University of Antwerp, Antwerpen, Belgium
| | - David Van Laere
- Department of Neonatal Intensive Care, Antwerp University Hospital, Edegem, Belgium; Laboratory of Experimental Medicine and Pediatrics, Faculty of Medicine and Health Sciences, University of Antwerp, Antwerpen, Belgium; Innocens BV, Antwerpen, Belgium
| |
Collapse
|
3
|
Nayak SP, Sánchez-Rosado M, Reis JD, Brown LS, Mangona KL, Sharma P, Nelson DB, Wyckoff MH, Pandya S, Mir IN, Brion LP. Development of a Prediction Model for Surgery or Early Mortality at the Time of Initial Assessment for Necrotizing Enterocolitis. Am J Perinatol 2024. [PMID: 38272063 DOI: 10.1055/a-2253-8656] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/27/2024]
Abstract
OBJECTIVE No available scale, at the time of initial evaluation for necrotizing enterocolitis (NEC), accurately predicts, that is, with an area under the curve (AUC) ≥0.9, which preterm infants will undergo surgery for NEC stage III or die within a week. STUDY DESIGN This is a retrospective cohort study (n = 261) of preterm infants with <33 weeks' gestation or <1,500 g birthweight with either suspected or with definite NEC born at Parkland Hospital between 2009 and 2021. A prediction model using the new HASOFA SCORE (H: yperglycemia, H: yperkalemia, use of inotropes for H: ypotension during the prior week, A: cidemia, Neonatal S: equential O: rgan F: ailure A: ssessment [nSOFA: ] score) was compared with a similar model using the nSOFA score. RESULTS Among 261 infants, 112 infants had NEC stage I, 68 with NEC stage II, and 81 with NEC stage III based on modified Bell's classification. The primary outcome, surgery for NEC stage III or death within a week, occurred in 81 infants (surgery in 66 infants and death in 38 infants). All infants with pneumoperitoneum or abdominal compartment syndrome either died or had surgery. The HASOFA and the nSOFA scores were evaluated in 254 and 253 infants, respectively, at the time of the initial workup for NEC. Both models were internally validated. The HASOFA model was a better predictor of surgery for NEC stage III or death within a week than the nSOFA model, with greater AUC 0.909 versus 0.825, respectively, p < 0.001. Combining HASOFA at initial assessment with concurrent or later presence of abdominal wall erythema or portal gas improved the prediction surgery for NEC stage III or death with AUC 0.942 or 0.956, respectively. CONCLUSION Using this new internally validated prediction model, surgery for NEC stage III or death within a week can be accurately predicted at the time of initial assessment for NEC. KEY POINTS · No available scale, at initial evaluation, accurately predicts which preterm infants will undergo surgery for NEC stage III or die within a week.. · In this retrospective cohort study of 261 preterm infants with either suspected or definite NEC we developed a new prediction model (HASOFA score).. · The HASOFA-model had high discrimination (AUC 0.909) and excellent calibration and was internally validated..
Collapse
Affiliation(s)
- Sujir P Nayak
- Division of Neonatal-Perinatal Medicine, Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Mariela Sánchez-Rosado
- Division of Neonatal-Perinatal Medicine, Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, Texas
- Division of Neonatology, Joe DiMaggio Children's Hospital, Hollywood, Florida
| | - Jordan D Reis
- Division of Neonatal-Perinatal Medicine, Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, Texas
- Department of Pediatrics, Baylor Scott and White, Dallas, Texas
| | - L Steven Brown
- Department of Research, Parkland Health and Hospital System, Dallas, Texas
| | - Kate L Mangona
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Priya Sharma
- Division of Neonatal-Perinatal Medicine, Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, Texas
- Department of Pediatrics, Baylor Scott and White, Dallas, Texas
| | - David B Nelson
- Division of Maternal-Fetal Medicine, Department of Obstetrics and Gynecology, University of Texas Southwestern Medical Center, and Parkland Health, Dallas, Texas
| | - Myra H Wyckoff
- Division of Neonatal-Perinatal Medicine, Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Samir Pandya
- Division of Pediatric Surgery, Department of Surgery, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Imran N Mir
- Division of Neonatal-Perinatal Medicine, Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Luc P Brion
- Division of Neonatal-Perinatal Medicine, Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, Texas
| |
Collapse
|
8
|
De Francesco D, Reiss JD, Roger J, Tang AS, Chang AL, Becker M, Phongpreecha T, Espinosa C, Morin S, Berson E, Thuraiappah M, Le BL, Ravindra NG, Payrovnaziri SN, Mataraso S, Kim Y, Xue L, Rosenstein MG, Oskotsky T, Marić I, Gaudilliere B, Carvalho B, Bateman BT, Angst MS, Prince LS, Blumenfeld YJ, Benitz WE, Fuerch JH, Shaw GM, Sylvester KG, Stevenson DK, Sirota M, Aghaeepour N. Data-driven longitudinal characterization of neonatal health and morbidity. Sci Transl Med 2023; 15:eadc9854. [PMID: 36791208 PMCID: PMC10197092 DOI: 10.1126/scitranslmed.adc9854] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2022] [Accepted: 01/11/2023] [Indexed: 02/17/2023]
Abstract
Although prematurity is the single largest cause of death in children under 5 years of age, the current definition of prematurity, based on gestational age, lacks the precision needed for guiding care decisions. Here, we propose a longitudinal risk assessment for adverse neonatal outcomes in newborns based on a deep learning model that uses electronic health records (EHRs) to predict a wide range of outcomes over a period starting shortly before conception and ending months after birth. By linking the EHRs of the Lucile Packard Children's Hospital and the Stanford Healthcare Adult Hospital, we developed a cohort of 22,104 mother-newborn dyads delivered between 2014 and 2018. Maternal and newborn EHRs were extracted and used to train a multi-input multitask deep learning model, featuring a long short-term memory neural network, to predict 24 different neonatal outcomes. An additional cohort of 10,250 mother-newborn dyads delivered at the same Stanford Hospitals from 2019 to September 2020 was used to validate the model. Areas under the receiver operating characteristic curve at delivery exceeded 0.9 for 10 of the 24 neonatal outcomes considered and were between 0.8 and 0.9 for 7 additional outcomes. Moreover, comprehensive association analysis identified multiple known associations between various maternal and neonatal features and specific neonatal outcomes. This study used linked EHRs from more than 30,000 mother-newborn dyads and would serve as a resource for the investigation and prediction of neonatal outcomes. An interactive website is available for independent investigators to leverage this unique dataset: https://maternal-child-health-associations.shinyapps.io/shiny_app/.
Collapse
Affiliation(s)
- Davide De Francesco
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Jonathan D. Reiss
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Jacquelyn Roger
- Bakar Computational Health Sciences Institute, University of California, San Francisco, CA 94143, USA
- Graduate Program in Biological and Medical Informatics, University of California, San Francisco, CA 94143, USA
| | - Alice S. Tang
- Bakar Computational Health Sciences Institute, University of California, San Francisco, CA 94143, USA
- Graduate Program in Biological and Medical Informatics, University of California, San Francisco, CA 94143, USA
- Graduate Program in Bioengineering, University of California, San Francisco, CA 94158, USA
| | - Alan L. Chang
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Martin Becker
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Thanaphong Phongpreecha
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
- Department of Pathology, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Camilo Espinosa
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Susanna Morin
- Bakar Computational Health Sciences Institute, University of California, San Francisco, CA 94143, USA
- Graduate Program in Biological and Medical Informatics, University of California, San Francisco, CA 94143, USA
| | - Eloïse Berson
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
- Department of Pathology, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Melan Thuraiappah
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Brian L. Le
- Bakar Computational Health Sciences Institute, University of California, San Francisco, CA 94143, USA
- Department of Pediatrics, University of California, San Francisco, CA 94143, USA
| | - Neal G. Ravindra
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Seyedeh Neelufar Payrovnaziri
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Samson Mataraso
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Yeasul Kim
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Lei Xue
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Melissa G. Rosenstein
- Department of Obstetrics, Gynecology, and Reproductive Sciences, University of California, San Francisco, CA 94158, USA
| | - Tomiko Oskotsky
- Bakar Computational Health Sciences Institute, University of California, San Francisco, CA 94143, USA
- Department of Pediatrics, University of California, San Francisco, CA 94143, USA
| | - Ivana Marić
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| | - Brice Gaudilliere
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Brendan Carvalho
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Brian T. Bateman
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Martin S. Angst
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Lawrence S. Prince
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Yair J. Blumenfeld
- Department of Obstetrics and Gynecology, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - William E. Benitz
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Janene H. Fuerch
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Gary M. Shaw
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Karl G. Sylvester
- Department of Surgery, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - David K. Stevenson
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Marina Sirota
- Bakar Computational Health Sciences Institute, University of California, San Francisco, CA 94143, USA
- Department of Pediatrics, University of California, San Francisco, CA 94143, USA
| | - Nima Aghaeepour
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA
| |
Collapse
|