-
Je něco špatně v tomto záznamu ?
Machine Learning Used to Compare the Diagnostic Accuracy of Risk Factors, Clinical Signs and Biomarkers and to Develop a New Prediction Model for Neonatal Early-onset Sepsis
M. Stocker, I. Daunhawer, W. van Herk, S. El Helou, S. Dutta, FABA. Schuerman, RK. van den Tooren-de Groot, JW. Wieringa, J. Janota, LH. van der Meer-Kappelle, R. Moonen, SD. Sie, E. de Vries, AE. Donker, U. Zimmerman, LJ. Schlapbach, AC. de Mol,...
Jazyk angličtina Země Spojené státy americké
Typ dokumentu časopisecké články
- MeSH
- antibakteriální látky terapeutické užití MeSH
- biologické markery krev MeSH
- C-reaktivní protein analýza MeSH
- kojenec MeSH
- lidé MeSH
- novorozenec MeSH
- novorozenecká sepse diagnóza farmakoterapie MeSH
- prospektivní studie MeSH
- rizikové faktory MeSH
- ROC křivka MeSH
- strojové učení * MeSH
- Check Tag
- kojenec MeSH
- lidé MeSH
- mužské pohlaví MeSH
- novorozenec MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
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 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 Zuyderland Medical Centre Heerlen
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
Citace poskytuje Crossref.org
- 000
- 00000naa a2200000 a 4500
- 001
- bmc22010904
- 003
- CZ-PrNML
- 005
- 20220506130143.0
- 007
- ta
- 008
- 220425s2022 xxu f 000 0|eng||
- 009
- AR
- 024 7_
- $a 10.1097/INF.0000000000003344 $2 doi
- 035 __
- $a (PubMed)34508027
- 040 __
- $a ABA008 $b cze $d ABA008 $e AACR2
- 041 0_
- $a eng
- 044 __
- $a xxu
- 100 1_
- $a Stocker, Martin $u From the Department of Paediatrics, Neonatal and Paediatric Intensive Care Unit, Children's Hospital Lucerne, Lucerne
- 245 10
- $a Machine Learning Used to Compare the Diagnostic Accuracy of Risk Factors, Clinical Signs and Biomarkers and to Develop a New Prediction Model for Neonatal Early-onset Sepsis / $c M. Stocker, I. Daunhawer, W. van Herk, S. El Helou, S. Dutta, FABA. Schuerman, RK. van den Tooren-de Groot, JW. Wieringa, J. Janota, LH. van der Meer-Kappelle, R. Moonen, SD. Sie, E. de Vries, AE. Donker, U. Zimmerman, LJ. Schlapbach, AC. de Mol, A. Hoffmann-Haringsma, M. Roy, M. Tomaske, RF. Kornelisse, J. van Gijsel, FB. Plötz, S. Wellmann, NB. Achten, D. Lehnick, AMC. van Rossum, JE. Vogt
- 520 9_
- $a 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.
- 650 _2
- $a antibakteriální látky $x terapeutické užití $7 D000900
- 650 _2
- $a biologické markery $x krev $7 D015415
- 650 _2
- $a C-reaktivní protein $x analýza $7 D002097
- 650 _2
- $a ženské pohlaví $7 D005260
- 650 _2
- $a lidé $7 D006801
- 650 _2
- $a kojenec $7 D007223
- 650 _2
- $a novorozenec $7 D007231
- 650 12
- $a strojové učení $7 D000069550
- 650 _2
- $a mužské pohlaví $7 D008297
- 650 _2
- $a novorozenecká sepse $x diagnóza $x farmakoterapie $7 D000071074
- 650 _2
- $a prospektivní studie $7 D011446
- 650 _2
- $a ROC křivka $7 D012372
- 650 _2
- $a rizikové faktory $7 D012307
- 655 _2
- $a časopisecké články $7 D016428
- 700 1_
- $a Daunhawer, Imant $u Department of Computer Science, ETH Zurich, Switzerland
- 700 1_
- $a van Herk, Wendy $u Department of Paediatrics, Division of Paediatric Infectious Diseases and Immunology, Erasmus MC University Medical Centre-Sophia Children's Hospital, Rotterdam, The Netherlands
- 700 1_
- $a El Helou, Salhab $u Division of Neonatology, McMaster University Children's Hospital, Hamilton Health Sciences, Hamilton, ON, Canada
- 700 1_
- $a Dutta, Sourabh $u Division of Neonatology, McMaster University Children's Hospital, Hamilton Health Sciences, Hamilton, ON, Canada
- 700 1_
- $a Schuerman, Frank A B A $u Department of Neonatal Intensive Care Unit, Isala Women and Children's Hospital, Zwolle
- 700 1_
- $a van den Tooren-de Groot, Rita K $u Department of Paediatrics, Haaglanden Medical Centre, 's Gravenhage, The Netherlands
- 700 1_
- $a Wieringa, Jantien W $u Department of Paediatrics, Haaglanden Medical Centre, 's Gravenhage, The Netherlands
- 700 1_
- $a Janota, Jan $u Department of Obstetrics and Gynecology, Motol University Hospital, Second Medical Faculty, Prague, Czech Republic
- 700 1_
- $a van der Meer-Kappelle, Laura H $u Department of Neonatology, Reinier de Graaf Gasthuis, Delft
- 700 1_
- $a Moonen, Rob $u Department of Neonatology, Zuyderland Medical Centre, Heerlen
- 700 1_
- $a Sie, Sintha D $u Department of Neonatology, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam
- 700 1_
- $a de Vries, Esther $u Department of Jeroen Bosch Academy Research, Jeroen Bosch Hospital, 's-Hertogenbosch $u Department of Tranzo, Tilburg University, Tilburg
- 700 1_
- $a Donker, Albertine E $u Department of Paediatrics, Maxima Medical Centre, Veldhoven, The Netherlands
- 700 1_
- $a Zimmerman, Urs $u Department of Paediatrics, Kantonsspital Winterthur, Winterthur
- 700 1_
- $a Schlapbach, Luregn J $u Neonatal and Pediatric Intensive Care Unit, Children`s Research Center, University Children's Hospital Zurich, Zurich, Switzerland
- 700 1_
- $a de Mol, Amerik C $u Department of Neonatology, Albert Schweitzer Hospital, Dordrecht
- 700 1_
- $a Hoffmann-Haringsma, Angelique $u Department of Neonatology, Sint Franciscus Gasthuis, Rotterdam, The Netherlands
- 700 1_
- $a Roy, Madan $u Department of Neonatology, St. Josephs Healthcare, Hamilton Health Sciences, Hamilton, ON, Canada
- 700 1_
- $a Tomaske, Maren $u Department of Paediatrics, Stadtspital Triemli, Zürich, Switzerland
- 700 1_
- $a Kornelisse, René F $u Department of Paediatrics, Division of Neonatology, Erasmus MC University Medical Centre-Sophia Children's Hospital, Rotterdam
- 700 1_
- $a van Gijsel, Juliette $u Therapeuticum Utrecht, Utrecht
- 700 1_
- $a Plötz, Frans B $u Department of Pediatrics, Tergooi Hospital, Blaricum, the Netherlands and Amsterdam University Medical Center, Department of Pediatrics, Amsterdam, The Netherlands
- 700 1_
- $a Wellmann, Sven $u Department of Neonatology, University Children's Hospital Regensburg (KUNO), University of Regensburg, Regensburg, Germany
- 700 1_
- $a Achten, Niek B $u Department of Pediatrics, Tergooi Hospital, Blaricum, the Netherlands and Amsterdam University Medical Center, Department of Pediatrics, Amsterdam, The Netherlands
- 700 1_
- $a Lehnick, Dirk $u Department of Health Sciences and Medicine, Head Biostatistics and Methodology, University of Lucerne, Lucerne, Switzerland
- 700 1_
- $a van Rossum, Annemarie M C $u Department of Paediatrics, Division of Paediatric Infectious Diseases and Immunology, Erasmus MC University Medical Centre-Sophia Children's Hospital, Rotterdam, The Netherlands
- 700 1_
- $a Vogt, Julia E $u From the Department of Paediatrics, Neonatal and Paediatric Intensive Care Unit, Children's Hospital Lucerne, Lucerne
- 773 0_
- $w MED00003732 $t The Pediatric infectious disease journal $x 1532-0987 $g Roč. 41, č. 3 (2022), s. 248-254
- 856 41
- $u https://pubmed.ncbi.nlm.nih.gov/34508027 $y Pubmed
- 910 __
- $a ABA008 $b sig $c sign $y p $z 0
- 990 __
- $a 20220425 $b ABA008
- 991 __
- $a 20220506130136 $b ABA008
- 999 __
- $a ok $b bmc $g 1788833 $s 1162102
- BAS __
- $a 3
- BAS __
- $a PreBMC
- BMC __
- $a 2022 $b 41 $c 3 $d 248-254 $e 20220301 $i 1532-0987 $m The Pediatric infectious disease journal $n Pediatr Infect Dis J $x MED00003732
- LZP __
- $a Pubmed-20220425
