Table 1.
Papers identified by a structured search of MEDLINE using machine learning techniques to investigate the nutritional and growth of preterm infants in the past 10 years.
| Data type | Authors | Title | Year | Journal | Main topic of focus | Type of statistical technique |
|---|---|---|---|---|---|---|
| Clinical | Porcelli et al.32 | Comparison of new modelling methods for postnatal weight in ELBW infants using prenatal and postnatal data | 2015 | J Pediatr Gastroenterol Nutr | Modelling influences on early weight gain | Neural networks |
| Clinical | Irles et al.33 | Estimation of neonatal intestinal perforation associated with necrotising enterocolitis by machine learning reveals new key factors | 2019 | Int J Environ Res Public Health | Risk of intestinal perforation | Neural networks |
| Clinical | Fu et al.34 | Integration of an interpretable machine learning algorithm to identify early life risk factors of childhood obesity among preterm infants: a prospective birth cohort | 2020 | BMC Medicine | Development of obesity in ex-preterm infants | Gradient-boosted trees |
| Clinical | Wong et al.35 | Predicting protein and fat content in human donor milk using machine learning | 2021 | J Nutr | Modelling influences on donor breastmilk composition | Random forest; Gradient-boosted trees |
| Clinical/microbiome | Lugo-Martinez et al.14 | Integrating longitudinal clinical and microbiome data to predict growth faltering in preterm infants | 2022 | J Biomed Inform | Clinical and microbiomic influences on growth faltering | Random forest; Hidden Markov |
| Metabolomics | Wilcock et al.36 | The metabolomics of necrotising enterocolitis in preterm babies: an exploratory study | 2016 | J Matern Fetal Neonatal Med | Necrotising enterocolitis | Principal component analysis |
| Metabolomics | Younge et al.37 | Disrupted maturation of the microbiota and metabolome among extremely preterm infants with postnatal growth failure | 2019 | Sci Rep | Growth failure | Partitioning around medoid (PAM) clustering |
| Service delivery | Greenbury et al.38 | Identification of variation in nutritional practice in neonatal units in England and association with clinical outcomes using agnostic machine learning | 2021 | Sci Rep | Defining clusters of practice | Unsupervised clustering |
Papers identified by a MEDLINE search: (“preterm” OR “premature” OR “neonatal” OR “newborn”) AND (nutrition OR growth) AND (“big data” OR “artificial intelligence” OR “machine learning” OR “modeling” OR “modelling”) AND “last 10 years”[dp]. Papers identified by search: 375. Papers selected after screening of titles and abstracts: 8.