Identifying two distinct subphenotypes of patent ductus arteriosus in preterm infants using machine learning
Nenhuma Miniatura disponível
Citações na Scopus
1
Tipo de produção
article
Data de publicação
2023
Título da Revista
ISSN da Revista
Título do Volume
Editora
SPRINGER
Citação
EUROPEAN JOURNAL OF PEDIATRICS, v.182, n.5, p.2173-2179, 2023
Resumo
To use unsupervised machine learning to identify potential subphenotypes of preterm infants with patent ductus arteriosus (PDA). The study was conducted retrospectively at a neonatal intensive care unit in Brazil. Patients with a gestational age < 28 weeks who had undergone at least one echocardiogram within the first two weeks of life and had PDA size > 1.5 or LA/AO ratio > 1.5 were included. Agglomerative hierarchical clustering on principal components was used to divide the data into different clusters based on common characteristics. Two distinct subphenotypes of preterm infants with hemodynamically significant PDA were identified: ""inflamed,"" characterized by high leukocyte, neutrophil, and neutrophil-to-lymphocyte ratio, and ""respiratory acidosis,"" characterized by low pH and high pCO(2) levels. Conclusions: This study suggests that there may be two distinct subphenotypes of preterm infants with hemodynamically significant PDA: ""inflamed"" and ""respiratory acidosis."" By dividing the population into different subgroups based on common characteristics, it is possible to get a more nuanced understanding of the effectiveness of PDA interventions. What is Known: Treatment of PDA in preterm infants has been controversial. Stratification of preterm infants with PDA into subgroups is important in order to determine the best treatment. What is New: Unsupervised machine learning was used to identify two subphenotypes of preterm infants with hemodynamically significant PDA. The 'inflamed' cluster was characterized by higher values of leukocyte, neutrophil, and neutrophil-to-lymphocyte ratio. The 'respiratory acidosis' cluster was characterized by lower pH values and higher pCO2 values.
Palavras-chave
Patent ductus arteriosus, Preterm infants, Unsupervised machine learning, Agglomerative hierarchical clustering, Subphenotypes
Referências
- Ahsan MM, 2021, TECHNOLOGIES, V9, DOI 10.3390/technologies9030052
- Alloghani M., 2020, Supervised and Unsupervised Learning for Data Science, P3, DOI [10.1007/978-3-030-22475-2_1, DOI 10.1007/978-3-030-22475-2_1]
- Cruz RS, 2021, COCHRANE DB SYST REV, DOI 10.1002/14651858.CD009098.pub3
- Fenton TR, 2013, BMC PEDIATR, V13, DOI 10.1186/1471-2431-13-59
- Gewers FL, 2021, ACM COMPUT SURV, V54, DOI 10.1145/3447755
- Hamrick SEG, 2020, PEDIATRICS, V146, DOI 10.1542/peds.2020-1209
- Hundscheid T, 2023, NEW ENGL J MED, V388, P980, DOI 10.1056/NEJMoa2207418
- Maddali MV, 2022, LANCET RESP MED, V10, P367, DOI 10.1016/S2213-2600(21)00461-6
- MASSEY FJ, 1951, J AM STAT ASSOC, V46, P68, DOI 10.2307/2280095
- Matsushita FY, 2022, EUR J PEDIATR, V181, P1085, DOI 10.1007/s00431-021-04298-3
- PAPILE LA, 1978, J PEDIATR-US, V92, P529, DOI 10.1016/S0022-3476(78)80282-0
- Parkerson S, 2021, FRONT PEDIATR, V8, DOI 10.3389/fped.2020.590578
- Reddy K, 2020, LANCET RESP MED, V8, P631, DOI 10.1016/S2213-2600(20)30124-7
- Sasirekha K, 2013, INT J SCI RES PUBL, VPubl3, P2
- Singh P, 2019, UNSUPERVISED MACHINE, DOI [10.1007/978-1-4842-4961-1_7, DOI 10.1007/978-1-4842-4961-1_7]
- Terrin G, 2020, FRONT PEDIATR, V8, DOI 10.3389/fped.2020.582735
- Varoquaux G., 2015, GETMOBILE-MOB COMPU, V19, P29, DOI [10.1145/2786984.2786995, DOI 10.1145/2786984.2786995]
- Wilson JG, 2020, CRIT CARE, V24, DOI 10.1186/s13054-020-2778-x