AUTHOR=Ribeiro Maria , Nunes Inês , Castro Luísa , Costa-Santos Cristina , S. Henriques Teresa 

TITLE=Machine learning models based on clinical indices and cardiotocographic features for discriminating asphyxia fetuses—Porto retrospective intrapartum study

JOURNAL=Frontiers in Public Health

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2023.1099263

DOI=10.3389/fpubh.2023.1099263

ISSN=2296-2565

ABSTRACT=Introduction: Perinatal asphyxia is one of the most frequent causes of neonatal mortality, affecting approximately four million newborns worldwide each year and causing the death of one million individuals. One of the main reasons for these high incidences is the lack of consensual methods of early diagnosis for this pathology. Estimating risk-appropriate health care for mother and baby is essential for increasing the quality of the health care system. Thus, it is necessary to investigate models that improve the prediction of perinatal asphyxia. Access to the cardiotocographic~(CTG) signal in conjunction with various clinical parameters can be crucial developing of a successful model.

Objectives: This work aims to develop predictive models of perinatal asphyxia based on clinical parameters and fetal heart rate (fHR) indices.

Methods:  Single gestations data from a retrospective unicentric study from Centro Hospitalar e Universit\'ario do Porto de S\~ao Jo\~ao~(CHUSJ) between 2010 and 2018 was probed. 
The cardiotocograms~(CTG) were acquired and analyzed by Omniview-SisPorto, estimating several fHR features. The clinical variables were obtained from the electronic clinical records stored by ObsCare. Entropy and compression characterized the complexity of the fHR time series. These variables' contribution to the prediction of asphyxia perinatal was probed by binary logistic regression~(BLR) and Naive-Bayes~(NB)~models.

Results: The data consisted of 517 cases, with 15 pathological cases. The asphyxia prediction models showed promising results, with an area under the receiver operator characteristic curve (AUC) greater than 70\%. In NB approaches, the best models combined clinical and SisPorto features. The best model was the univariate BLR with the variable compression ratio scale 2 (CR2) and an AUC of 94.93 [94.55; 95.31].

Conclusion: Both LR and Bayesian models have advantages and disadvantages. The model with the best performance predicting perinatal asphyxia was the univariate BLR with the CR2 variable, demonstrating the importance of non-linear indices in perinatal asphyxia detection. Future studies should explore decision support systems to detect sepsis, including clinical and CTG features~(linear and non-linear).