Dataset Information

Prediction of Late-Onset Sepsis in Preterm Infants Using Monitoring Signals and Machine Learning.

ABSTRACT:

Objectives

Prediction of late-onset sepsis (onset beyond day 3 of life) in preterm infants, based on multiple patient monitoring signals 24 hours before onset.

Design

Continuous high-resolution electrocardiogram and respiration (chest impedance) data from the monitoring signals were extracted and used to create time-interval features representing heart rate variability, respiration, and body motion. For each infant with a blood culture-proven late-onset sepsis, a Cultures, Resuscitation, and Antibiotics Started Here moment was defined. The Cultures, Resuscitation, and Antibiotics Started Here moment served as an anchor point for the prediction analysis. In the group with controls (C), an "equivalent crash moment" was calculated as anchor point, based on comparable gestational and postnatal age. Three common machine learning approaches (logistic regressor, naive Bayes, and nearest mean classifier) were used to binary classify samples of late-onset sepsis from C. For training and evaluation of the three classifiers, a leave-k-subjects-out cross-validation was used.

Setting

Level III neonatal ICU.

Patients

The patient population consisted of 32 premature infants with sepsis and 32 age-matched control patients.

Interventions

No interventions were performed.

Measurements and main results

For the interval features representing heart rate variability, respiration, and body motion, differences between late-onset sepsis and C were visible up to 5 hours preceding the Cultures, Resuscitation, and Antibiotics Started Here moment. Using a combination of all features, classification of late-onset sepsis and C showed a mean accuracy of 0.79 ± 0.12 and mean precision rate of 0.82 ± 0.18 3 hours before the onset of sepsis.

Conclusions

Information from routine patient monitoring can be used to predict sepsis. Specifically, this study shows that a combination of electrocardiogram-based, respiration-based, and motion-based features enables the prediction of late-onset sepsis hours before the clinical crash moment.

SUBMITTER: Cabrera-Quiros L

PROVIDER: S-EPMC7846455 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Host immune responses during late-onset sepsis (LOS) in very preterm infants are poorly characterised due to a complex and dynamic pathophysiology and challenges in working with small available blood volumes. We present here an unbiased transcriptomic analysis of whole peripheral blood from very preterm infants at the time of LOS. METHODS:RNA-Seq was performed on peripheral blood samples (6-29 days postnatal age) taken at the time of suspected LOS from very preterm infants <30 weeks gestational age. Infants were classified based on blood culture positivity and elevated C-reactive protein concentrations as having confirmed LOS (n = 5), possible LOS (n = 4) or no LOS (n = 9). Bioinformatics and statistical analyses performed included pathway over-representation and protein-protein interaction network analyses. Plasma cytokine immunoassays were performed to validate differentially expressed cytokine pathways. RESULTS:The blood leukocyte transcriptional responses of infants with confirmed LOS differed significantly from infants without LOS (1,317 differentially expressed genes). However, infants with possible LOS could not be distinguished from infants with no LOS or confirmed LOS. Transcriptional alterations associated with LOS included genes involved in pathogen recognition (mainly TLR pathways), cytokine signalling (both pro-inflammatory and inhibitory responses), immune and haematological regulation (including cell death pathways), and metabolism (altered cholesterol biosynthesis). At the transcriptional-level cytokine responses during LOS were characterised by over-representation of IFN-?/?, IFN-?, IL-1 and IL-6 signalling pathways and up-regulation of genes for inflammatory responses. Infants with confirmed LOS had significantly higher levels of IL-1? and IL-6 in their plasma. CONCLUSIONS:Blood responses in very preterm infants with LOS are characterised by altered host immune responses that appear to reflect unbalanced immuno-metabolic homeostasis.

Project description:Preeclampsia is one of the leading causes of maternal and fetal morbidity and mortality. Due to the lack of effective preventive measures, its prediction is essential to its prompt management. This study aimed to develop models using machine learning to predict late-onset preeclampsia using hospital electronic medical record data. The performance of the machine learning based models and models using conventional statistical methods were also compared. A total of 11,006 pregnant women who received antenatal care at Yonsei University Hospital were included. Maternal data were retrieved from electronic medical records during the early second trimester to 34 weeks. The prediction outcome was late-onset preeclampsia occurrence after 34 weeks' gestation. Pattern recognition and cluster analysis were used to select the parameters included in the prediction models. Logistic regression, decision tree model, naïve Bayes classification, support vector machine, random forest algorithm, and stochastic gradient boosting method were used to construct the prediction models. C-statistics was used to assess the performance of each model. The overall preeclampsia development rate was 4.7% (474 patients). Systolic blood pressure, serum blood urea nitrogen and creatinine levels, platelet counts, serum potassium level, white blood cell count, serum calcium level, and urinary protein were the most influential variables included in the prediction models. C-statistics for the decision tree model, naïve Bayes classification, support vector machine, random forest algorithm, stochastic gradient boosting method, and logistic regression models were 0.857, 0.776, 0.573, 0.894, 0.924, and 0.806, respectively. The stochastic gradient boosting model had the best prediction performance with an accuracy and false positive rate of 0.973 and 0.009, respectively. The combined use of maternal factors and common antenatal laboratory data of the early second trimester through early third trimester could effectively predict late-onset preeclampsia using machine learning algorithms. Future prospective studies are needed to verify the clinical applicability algorithms.