BACKGROUND: Current strategies for risk stratification and prediction of neonatal early-onset sepsis (EOS) are inefficient and lack diagnostic performance. The aim of this study was to use machine learning to analyze the diagnostic accuracy of risk factors (RFs), clinical signs and biomarkers and to develop a prediction model for culture-proven EOS. We hypothesized that the contribution to diagnostic accuracy of biomarkers is higher than of RFs or clinical signs. STUDY DESIGN: Secondary analysis of the prospective international multicenter NeoPInS study. Neonates born after completed 34 weeks of gestation with antibiotic therapy due to suspected EOS within the first 72 hours of life participated. Primary outcome was defined as predictive performance for culture-proven EOS with variables known at the start of antibiotic therapy. Machine learning was used in form of a random forest classifier. RESULTS: One thousand six hundred eighty-five neonates treated for suspected infection were analyzed. Biomarkers were superior to clinical signs and RFs for prediction of culture-proven EOS. C-reactive protein and white blood cells were most important for the prediction of the culture result. Our full model achieved an area-under-the-receiver-operating-characteristic-curve of 83.41% (±8.8%) and an area-under-the-precision-recall-curve of 28.42% (±11.5%). The predictive performance of the model with RFs alone was comparable with random. CONCLUSIONS: Biomarkers have to be considered in algorithms for the management of neonates suspected of EOS. A 2-step approach with a screening tool for all neonates in combination with our model in the preselected population with an increased risk for EOS may have the potential to reduce the start of unnecessary antibiotics.

Department of Computer Science ETH Zurich Switzerland

Department of Health Sciences and Medicine Head Biostatistics and Methodology University of Lucerne Lucerne Switzerland

Department of Jeroen Bosch Academy Research Jeroen Bosch Hospital 's Hertogenbosch

Department of Neonatal Intensive Care Unit Isala Women and Children's Hospital Zwolle

Department of Neonatology Albert Schweitzer Hospital Dordrecht

Department of Neonatology Amsterdam UMC Vrije Universiteit Amsterdam Amsterdam

Department of Neonatology Reinier de Graaf Gasthuis Delft

Department of Neonatology Sint Franciscus Gasthuis Rotterdam The Netherlands

Department of Neonatology St Josephs Healthcare Hamilton Health Sciences Hamilton ON Canada

Department of Neonatology University Children's Hospital Regensburg University of Regensburg Regensburg Germany

Department of Neonatology Zuyderland Medical Centre Heerlen

Department of Obstetrics and Gynecology Motol University Hospital 2nd Medical Faculty Prague Czech Republic

Department of Paediatrics Division of Neonatology Erasmus MC University Medical Centre Sophia Children's Hospital Rotterdam

Department of Paediatrics Division of Paediatric Infectious Diseases and Immunology Erasmus MC University Medical Centre Sophia Children's Hospital Rotterdam The Netherlands

Department of Paediatrics Haaglanden Medical Centre 's Gravenhage The Netherlands

Department of Paediatrics Kantonsspital Winterthur Winterthur

Department of Paediatrics Maxima Medical Centre Veldhoven The Netherlands

Department of Paediatrics Stadtspital Triemli Zürich Switzerland

Department of Pediatrics Tergooi Hospital Blaricum the Netherlands and Amsterdam University Medical Center Department of Pediatrics Amsterdam The Netherlands

Department of Tranzo Tilburg University Tilburg

Division of Neonatology McMaster University Children's Hospital Hamilton Health Sciences Hamilton ON Canada

From the Department of Paediatrics Neonatal and Paediatric Intensive Care Unit Children's Hospital Lucerne Lucerne

Neonatal and Pediatric Intensive Care Unit Children`s Research Center University Children's Hospital Zurich Zurich Switzerland

Therapeuticum Utrecht Utrecht

Zobrazit více v PubMed

Shane AL, Sánchez PJ, Stoll BJ. Neonatal sepsis. Lancet. 2017;390:1770–1780.

Weiss SL, Fitzgerald JC, Balamuth F, et al. Delayed antimicrobial therapy increases mortality and organ dysfunction duration in pediatric sepsis. Crit Care Med. 2014;42:2409–2417.

Benitz WE, Achten NB. Finding a role for the neonatal early-onset sepsis risk calculator. EClinicalMedicine. 2020;19:100255.

Johansson Gudjónsdóttir M, Elfvin A, Hentz E, et al. Changes in incidence and etiology of early-onset neonatal infections 1997-2017 - a retrospective cohort study in western Sweden. BMC Pediatr. 2019;19:490.

Schulman J, Benitz WE, Profit J, et al. Newborn antibiotic exposures and association with proven bloodstream infection. Pediatrics. 2019;144:e20191105.

Stiemsma LT, Michels KB. The role of the microbiome in the developmental origins of health and disease. Pediatrics. 2018;141:e20172437.

Rooney AM, Timberlake K, Brown KA, et al. Each additional day of antibiotics is associated with lower gut anaerobes in neonatal intensive care unit patients. Clin Infect Dis. 2020;70:2553–2560.

Escobar GJ, Puopolo KM, Wi S, et al. Stratification of risk of early-onset sepsis in newborns ≥ 34 weeks’ gestation. Pediatrics. 2014;133:30–36.

Beam AL, Kohane IS. Big data and machine learning in health care. JAMA. 2018;319:1317–1318.

Wiens J, Saria S, Sendak M, et al. Do no harm: a roadmap for responsible machine learning for health care. Nat Med. 2019;25:1337–1340.

Ngiam KY, Khor IW. Big data and machine learning algorithms for health-care delivery. Lancet Oncol. 2019;20:e262–e273.

Christodoulou E, Ma J, Collins GS, et al. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 2019;110:12–22.

Ramgopal S, Horvat CM, Yanamala N, et al. Machine learning to predict serious bacterial infections in young febrile infants. Pediatrics. 2020;146:e20194096.

Roth JA, Battegay M, Juchler F, et al. Introduction to machine learning in digital healthcare epidemiology. Infect Control Hosp Epidemiol. 2018;39:1457–1462.

Stocker M, van Herk W, El Helou S, et al.; NeoPInS Study Group. Procalcitonin-guided decision making for duration of antibiotic therapy in neonates with suspected early-onset sepsis: a multicentre, randomised controlled trial (NeoPIns). Lancet. 2017;390:871–881.

Collins GS, Reitsma JB, Altman DG, et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ. 2015;350:g7594.

Klingenberg C, Kornelisse RF, Buonocore G, et al. Culture-negative early-onset neonatal sepsis - at the crossroad between efficient sepsis care and antimicrobial stewardship. Front Pediatr. 2018;6:285.

Breiman L. Random forest. Mach Learn. 2001;45:5–32.

Kuhn M, Johnson K. Applied Predictive Modeling. Springer-Verlag; 2013:61–92.

van Herk W, el Helou S, Janota J, et al. Variation in current management of term and late-preterm neonates at risk for early-onset sepsis: an international survey and review of guidelines. Pediatr Infect Dis J. 2016;35:494–500.

Newman TB, Puopolo KM, Wi S, et al. Interpreting complete blood counts soon after birth in newborns at risk for sepsis. Pediatrics. 2010;126:903–909.

Ruan L, Chen GY, Liu Z, et al. The combination of procalcitonin and C-reactive protein or presepsin alone improves the accuracy of diagnosis of neonatal sepsis: a meta-analysis and systematic review. Crit Care. 2018;22:316.

Puopolo KM, Draper D, Wi S, et al. Estimating the probability of neonatal early-onset infection on the basis of maternal risk factors. Pediatrics. 2011;128:e1155–e1163.

Vatne A, Klingenberg C, Øymar K, et al. Reduced antibiotic exposure by serial physical examinations in term neonates at risk of early-onset sepsis. Pediatr Infect Dis J. 2020;39:438–443.

Berardi A, Bedetti L, Spada C, et al. Serial clinical observation for management of newborns at risk of early-onset sepsis. Curr Opin Pediatr. 2020;32:245–251.

Stocker M, Berger C, McDougall J, et al.; Taskforce for the Swiss Society of Neonatology and the Paediatric Infectious Disease Group of Switzerland. Recommendations for term and late preterm infants at risk for perinatal bacterial infection. Swiss Med Wkly. 2013;143:w13873.

Berardi A, Spada C, Reggiani MLB, et al.; GBS Prevention Working Group of Emilia-Romagna. Group B Streptococcus early-onset disease and observation of well-appearing newborns. PLoS One. 2019;14:e0212784.

Ohlin A, Björkqvist M, Montgomery SM, et al. Clinical signs and CRP values associated with blood culture results in neonates evaluated for suspected sepsis. Acta Paediatr. 2010;99:1635–1640.

Escobar GJ, Li DK, Armstrong MA, et al. Neonatal sepsis workups in infants >/=2000 grams at birth: a population-based study. Pediatrics. 2000;106(2 pt 1):256–263.

Bromberger P, Lawrence JM, Braun D, et al. The influence of intrapartum antibiotics on the clinical spectrum of early-onset group B streptococcal infection in term infants. Pediatrics. 2000;106(2 pt 1):244–250.

Capin I, Hinds A, Vomero B, et al. Are early-onset sepsis evaluations and empiric antibiotics mandatory for all neonates admitted with respiratory distress? [published online ahead of print September 18, 2020]. Am J Perinatol. doi: 10.1055/s-0040-1717070. DOI

Achten NB, Klingenberg C, Benitz WE, et al. Association of use of the neonatal early-onset sepsis calculator with reduction in antibiotic therapy and safety: a systematic review and meta-analysis. JAMA Pediatr. 2019;173:1032–1040.

Achten NB, Plötz FB, Klingenberg C, et al. Stratification of culture-proven early-onset sepsis cases by the neonatal early-onset sepsis calculator: an individual patient data meta-analysis. J Pediatr. 2021;234:77–84.e8.

Cantey JB, Baird SD. Ending the culture of culture-negative sepsis in the neonatal ICU. Pediatrics. 2017;140:e20170044.

Investigators of the Delhi Neonatal Infection Study (DeNIS) collaboration. Characterisation and antimicrobial resistance of sepsis pathogens in neonates born in tertiary care centres in Delhi, India: a cohort study. Lancet Glob Health. 2016;4:e752–e7760.

Zobrazit více v PubMed

ClinicalTrials.gov
NCT00854932