Reassessing acquired neonatal intestinal diseases using unsupervised machine learning.

Journal

Pediatric research
ISSN: 1530-0447
Titre abrégé: Pediatr Res
Pays: United States
ID NLM: 0100714

Informations de publication

Date de publication:
27 Feb 2024
Historique:
received: 07 08 2023
accepted: 02 01 2024
revised: 11 12 2023
medline: 28 2 2024
pubmed: 28 2 2024
entrez: 27 2 2024
Statut: aheadofprint

Résumé

Acquired neonatal intestinal diseases have an array of overlapping presentations and are often labeled under the dichotomous classification of necrotizing enterocolitis (which is poorly defined) or spontaneous intestinal perforation, hindering more precise diagnosis and research. The objective of this study was to take a fresh look at neonatal intestinal disease classification using unsupervised machine learning. Patients admitted to the University of Florida Shands Neonatal Intensive Care Unit January 2013-September 2019 diagnosed with an intestinal injury, or had imaging findings of portal venous gas, pneumatosis, abdominal free air, or had an abdominal drain placed or exploratory laparotomy during admission were included. Congenital gastroschisis, omphalocele, intestinal atresia, malrotation were excluded. Data was collected via retrospective chart review with subsequent hierarchal, unsupervised clustering analysis. Five clusters of intestinal injury were identified: Cluster 1 deemed the "Low Mortality" cluster, Cluster 2 deemed the "Mature with Inflammation" cluster, Cluster 3 deemed the "Immature with High Mortality" cluster, Cluster 4 deemed the "Late Injury at Full Feeds" cluster, and Cluster 5 deemed the "Late Injury with High Rate of Intestinal Necrosis" cluster. Unsupervised machine learning can be used to cluster acquired neonatal intestinal injuries. Future study with larger multicenter datasets is needed to further refine and classify types of intestinal diseases. Unsupervised machine learning can be used to cluster types of acquired neonatal intestinal injury. Five major clusters of acquired neonatal intestinal injury are described, each with unique features. The clusters herein described deserve future, multicenter study to determine more specific early biomarkers and tailored therapeutic interventions to improve outcomes of often devastating neonatal acquired intestinal injuries.

Sections du résumé

BACKGROUND BACKGROUND
Acquired neonatal intestinal diseases have an array of overlapping presentations and are often labeled under the dichotomous classification of necrotizing enterocolitis (which is poorly defined) or spontaneous intestinal perforation, hindering more precise diagnosis and research. The objective of this study was to take a fresh look at neonatal intestinal disease classification using unsupervised machine learning.
METHODS METHODS
Patients admitted to the University of Florida Shands Neonatal Intensive Care Unit January 2013-September 2019 diagnosed with an intestinal injury, or had imaging findings of portal venous gas, pneumatosis, abdominal free air, or had an abdominal drain placed or exploratory laparotomy during admission were included. Congenital gastroschisis, omphalocele, intestinal atresia, malrotation were excluded. Data was collected via retrospective chart review with subsequent hierarchal, unsupervised clustering analysis.
RESULTS RESULTS
Five clusters of intestinal injury were identified: Cluster 1 deemed the "Low Mortality" cluster, Cluster 2 deemed the "Mature with Inflammation" cluster, Cluster 3 deemed the "Immature with High Mortality" cluster, Cluster 4 deemed the "Late Injury at Full Feeds" cluster, and Cluster 5 deemed the "Late Injury with High Rate of Intestinal Necrosis" cluster.
CONCLUSION CONCLUSIONS
Unsupervised machine learning can be used to cluster acquired neonatal intestinal injuries. Future study with larger multicenter datasets is needed to further refine and classify types of intestinal diseases.
IMPACT CONCLUSIONS
Unsupervised machine learning can be used to cluster types of acquired neonatal intestinal injury. Five major clusters of acquired neonatal intestinal injury are described, each with unique features. The clusters herein described deserve future, multicenter study to determine more specific early biomarkers and tailored therapeutic interventions to improve outcomes of often devastating neonatal acquired intestinal injuries.

Identifiants

DOI: 10.1038/s41390-024-03074-x PMID: 38413766
pubmed: 38413766
doi: 10.1038/s41390-024-03074-x
pii: 10.1038/s41390-024-03074-x
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

© 2024. The Author(s), under exclusive licence to the International Pediatric Research Foundation, Inc.

Références

Mizrahi, A., Barlow, O., Berdon, W., Blanc, W. A. & Silverman, W. A. Necrotizing enterocolitis in premature infants. J. Pediatr. 66, 697–706 (1965).
doi: 10.1016/S0022-3476(65)80003-8 pubmed: 14271359
Lueschow, S. R., Boly, T. J., Jasper, E., Patel, R. M. & McElroy, S. J. A critical evaluation of current definitions of necrotizing enterocolitis. Pediatr. Res. 91, 590–597 (2022).
doi: 10.1038/s41390-021-01570-y pubmed: 34021272
Alda, E. Why so many published studies and so little progress in necrotizing enterocolitis? Arch. Argent. Pediatr. 118, 372–374 (2020).
pubmed: 33231041
Patel, R. M., Ferguson, J., McElroy, S. J., Khashu, M. & Caplan, M. S. Defining necrotizing enterocolitis: current difficulties and future opportunities. Pediatr. Res 88, 10–15 (2020).
doi: 10.1038/s41390-020-1074-4 pubmed: 32855506 pmcid: 8096612
Neu, J., Modi, N. & Caplan, M. Necrotizing enterocolitis comes in different forms: Historical perspectives and defining the disease. Semin. Fetal Neonatal Med. 23, 370–373 (2018).
doi: 10.1016/j.siny.2018.07.004 pubmed: 30100524
Neu, J. Necrotizing Enterocolitis: The future. Neonatology 117, 240–244 (2020).
doi: 10.1159/000506866 pubmed: 32155645
Neu, J. Prevention of necrotizing Enterocolitis. Clin. Perinatol. 49, 195–206 (2022).
doi: 10.1016/j.clp.2021.11.012 pubmed: 35210001
Bell, M. J. et al. Neonatal necrotizing enterocolitis. Therapeutic decisions based upon clinical staging. Ann. Surg. 187, 1–7 (1978).
doi: 10.1097/00000658-197801000-00001 pubmed: 413500 pmcid: 1396409
Walsh, M. C. & Kliegman, R. M. Necrotizing enterocolitis: treatment based on staging criteria. Pediatr. Clin. North Am. 33, 179–201 (1986).
doi: 10.1016/S0031-3955(16)34975-6 pubmed: 3081865 pmcid: 7131118
Nagaraj, H. S., Sandhu, A. S., Cook, L. N., Buchino, J. J. & Groff, D. B. Gastrointestinal perforation following indomethacin therapy in very low birth weight infants. J. Pediatr. Surg. 16, 1003–1007 (1981).
doi: 10.1016/S0022-3468(81)80865-2 pubmed: 7338750
Aschner, J. L., Deluga, K. S., Metlay, L. A., Emmens, R. W. & Hendricks-Munoz, K. D. Spontaneous focal gastrointestinal perforation in very low birth weight infants. J. Pediatr. 113, 364–367 (1988).
doi: 10.1016/S0022-3476(88)80285-3 pubmed: 3397802
De La Cruz, D., Lure, A. & Neu, J. Necrotizing Enterocolitis. World Rev. Nutr. Diet. 122, 367–378 (2021).
doi: 10.1159/000514760 pubmed: 34352768
Moss, R. L. et al. Laparotomy versus peritoneal drainage for necrotizing enterocolitis and perforation. N. Engl. J. Med 354, 2225–2234 (2006).
doi: 10.1056/NEJMoa054605 pubmed: 16723614
Rees, C. M. et al. Peritoneal drainage or laparotomy for neonatal bowel perforation? A randomized controlled trial. Ann. Surg. 248, 44–51 (2008).
doi: 10.1097/SLA.0b013e318176bf81 pubmed: 18580206
Blakely, M. L. et al. Initial laparotomy versus peritoneal drainage in extremely low birthweight infants with surgical necrotizing enterocolitis or isolated intestinal perforation: a multicenter randomized clinical trial. Ann. Surg. 274, e370–e380 (2021).
doi: 10.1097/SLA.0000000000005099 pubmed: 34506326
2022 Manual of Operations, Part 2, Release 26.1 (PDF) – Help Center. https://vtoxford.zendesk.com/hc/en-us/articles/4405064008467-2022-Manual-of-Operations-Part-2-Release-26-1-PDF - .
CDC, Ncezid & DHQP. CDC/NHSN Surveillance Definitions for Specific Types of Infections. (2022).
Ji, J. et al. A data-driven algorithm integrating clinical and laboratory features for the diagnosis and prognosis of necrotizing enterocolitis. PLoS One 9, e89860 (2014).
doi: 10.1371/journal.pone.0089860 pubmed: 24587080 pmcid: 3938509
Battersby, C., Longford, N., Costeloe, K. & Modi, N. Development of a gestational age-specific case definition for neonatal necrotizing Enterocolitis. JAMA Pediatr. 171, 256–263 (2017).
doi: 10.1001/jamapediatrics.2016.3633 pubmed: 28046187
Gephart, S. M. et al. Changing the paradigm of defining, detecting, and diagnosing NEC: Perspectives on Bell’s stages and biomarkers for NEC. Semin. Pediatr. Surg. 27, 3–10 (2018).
doi: 10.1053/j.sempedsurg.2017.11.002 pubmed: 29275814
Caplan, M. S. et al. Necrotizing Enterocolitis: Using regulatory science and drug development to improve outcomes. J. Pediatr. 212, 208–215.e1 (2019).
doi: 10.1016/j.jpeds.2019.05.032 pubmed: 31235383
Noorbakhsh-Sabet, N., Zand, R., Zhang, Y. & Abedi, V. Artificial intelligence transforms the future of health care. Am. J. Med 132, 795–801 (2019).
doi: 10.1016/j.amjmed.2019.01.017 pubmed: 30710543 pmcid: 6669105
Hamamoto, R. Application of artificial intelligence for medical research. Biomolecules 11, 90 (2021).
doi: 10.3390/biom11010090 pubmed: 33445802 pmcid: 7828229
De Francesco, D. et al. Data-driven longitudinal characterization of neonatal health and morbidity. Sci. Transl. Med. 15, eadc9854 (2023).
doi: 10.1126/scitranslmed.adc9854 pubmed: 36791208 pmcid: 10197092
Campbell, J. P. et al. Applications of artificial intelligence for retinopathy of prematurity screening. Pediatrics 147, e2020016618 (2021).
doi: 10.1542/peds.2020-016618 pubmed: 33637645
Matsushita, F. Y., Krebs, V. L. J. & de Carvalho, W. B. Identifying clinical phenotypes in extremely low birth weight infants—an unsupervised machine learning approach. Eur. J. Pediatr. 181, 1085–1097 (2022).
doi: 10.1007/s00431-021-04298-3 pubmed: 34734319
Lure, A. C. et al. Using machine learning analysis to assist in differentiating between necrotizing enterocolitis and spontaneous intestinal perforation: A novel predictive analytic tool. J. Pediatr. Surg. 56, 1703–1710 (2021).
doi: 10.1016/j.jpedsurg.2020.11.008 pubmed: 33342603
Pammi, M., Aghaeepour, N. & Neu, J. Multiomics, artificial intelligence, and precision medicine in perinatology. Pediatr. Res. 2022 1–8 (2022) https://doi.org/10.1038/s41390-022-02181-x .
Lin, Y. C., Salleb-Aouissi, A. & Hooven, T. A. Interpretable prediction of necrotizing enterocolitis from machine learning analysis of premature infant stool microbiota. BMC Bioinforma. 23, 104 (2022).
doi: 10.1186/s12859-022-04618-w
Martin, C. R. Definitions of necrotizing enterocolitis: What are we defining and is machine learning the answer? Pediatr. Res. 91, 488–489 (2021).
doi: 10.1038/s41390-021-01687-0 pubmed: 34465874
Jarman, A. Hierarchical cluster analysis: Comparison of single linkage, complete linkage, average linkage and centroid linkage method. (2020).
Espinosa, C. A. et al. Multiomic signals associated with maternal epidemiological factors contributing to preterm birth in low- and middle-income countries. Sci. Adv. 9, eade7692 (2023).
doi: 10.1126/sciadv.ade7692 pubmed: 37224249 pmcid: 10208584
Jehan, F. et al. Multiomics characterization of preterm birth in low- and middle-income countries. JAMA Netw. Open 3, e2029655 (2020).
doi: 10.1001/jamanetworkopen.2020.29655 pubmed: 33337494 pmcid: 7749442
Ghaemi, M. S. et al. Multiomics modeling of the immunome, transcriptome, microbiome, proteome and metabolome adaptations during human pregnancy. Bioinformatics 35, 95–103 (2019).
doi: 10.1093/bioinformatics/bty537 pubmed: 30561547
Kelleher, S. T., McMahon, C. J. & James, A. Necrotizing Enterocolitis in children with congenital heart disease: a literature review. Pediatr. Cardiol. 42, 1688–1699 (2021).
doi: 10.1007/s00246-021-02691-1 pubmed: 34510235 pmcid: 8557173
Pammi, M. et al. Intestinal dysbiosis in preterm infants preceding necrotizing enterocolitis: a systematic review and meta-analysis. Microbiome 5, 31 (2017).
doi: 10.1186/s40168-017-0248-8 pubmed: 28274256 pmcid: 5343300

Auteurs

Daniel R Gipson (DR)

University of Florida College of Medicine, Department of Pediatrics, Division of Neonatology, Gainesville, FL, USA. daniel.gipson@ufl.edu.

Alan L Chang (AL)

Stanford University School of Medicine, Department of Anesthesiology, Pain, and Perioperative Medicine, Department of Pediatrics, and Department of Biomedical Data Science, Stanford, CA, USA.

Allison C Lure (AC)

Nationwide Children's Hospital, The Ohio State University College of Medicine, Department of Pediatrics, Division of Neonatology, Columbus, OH, USA.
University of Florida College of Medicine, Department of Pediatrics, Gainesville, FL, USA.

Sonia A Mehta (SA)

University of Florida College of Medicine, Department of Pediatrics, Gainesville, FL, USA.
University of California, Irvine Medical Center, Department of Pediatrics, Division of Neonatology, Irvine, CA, USA.

Taylor Gowen (T)

University of Florida College of Medicine, Department of Pediatrics, Gainesville, FL, USA.
University of Florida College of Medicine, Department of Anesthesiology, Gainesville, FL, USA.

Erin Shumans (E)

University of Florida College of Medicine, Department of Pediatrics, Gainesville, FL, USA.

David Stevenson (D)

Stanford University School of Medicine, Department of Pediatrics, Division of Neonatology, Stanford, CA, USA.

Diomel de la Cruz (D)

University of Florida College of Medicine, Department of Pediatrics, Division of Neonatology, Gainesville, FL, USA.

Nima Aghaeepour (N)

Stanford University School of Medicine, Department of Anesthesiology, Pain, and Perioperative Medicine, Department of Pediatrics, and Department of Biomedical Data Science, Stanford, CA, USA.

Josef Neu (J)

University of Florida College of Medicine, Department of Pediatrics, Division of Neonatology, Gainesville, FL, USA.

Classifications MeSH