Exploring the use of machine learning to assess the respiratory function of preterm infants

Q: What is the main goal of using machine learning in this study?

To predict the post-menstrual age (PMA) associated with healthy preterm lung functioning using inter-breath interval data extracted from vital-sign monitoring.

Q: How were data and respiratory features collected for model training?

Inter-breath intervals were longitudinally recorded in healthy preterm infants, then respiratory and statistical features were extracted from two datasets for model input.

Q: Which factors were tested for their impact on model accuracy?

Model performance was assessed for possible effects of sex, ventilation method, and post-natal age using paired t-tests, ANOVA, and linear regression.

Aug 5, 2026

Upload by Genevieve

Preterm birth is linked to multiple conditions that impair respiratory function, and timely recognition of reduced lung performance can support earlier diagnosis and intervention. This study evaluates whether inter-breath interval patterns can estimate the post-menstrual age at which healthy preterm infants’ lungs function. Longitudinal vital-sign recordings from healthy preterm infants were used to extract respiratory features and train machine learning models, selecting approaches by mean absolute error. Significant feature–age relationships were identified, enabling a basis for a potential clinical assessment tool.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages55

Reading Time2 h 19 min

AccessFree to download

Introduction

Foetal Lung Development

Pathologies and factors that affect preterm lung function

Artificial Intelligence and Machine Learning

Methods

Data Collection

Analysis

Feature selection

Dataset 1

Dataset 2

Results

Respiratory features correlate with PMA

Can respiratory features predict age?

Does model accuracy improve with increased data length?

Do clinical and demographic factors impact model accuracy?

Discussion

References

Exploring the use of machine learning to assess the respiratory function of preterm infants Vith Ketheeswaranathan Pembroke College University of Oxford Abstract Background: Preterm birth is associated with a number of pathologies that affect respiratory function. The identification of reduced lung function could aid with clinical diagnosis, earlier intervention and improved clinical outcomes for preterm infants. We explored the use of interbreath intervals to predict the age at which healthy preterm infants’ lungs are functioning. This can provide the groundwork to build a clinical tool that can assess preterm lung function in clinical practice. Methods: Inter-breath intervals, measured through vital signs monitoring, were longitudinally recorded in healthy preterm infants with a post-menstrual age (PMA) < 37 weeks. Dataset 1, consisting of data from 32 infants, was analysed to compute 49 respiratory and statistical features. The relationship of these features with PMA was assessed through linear regression models. All features were used as inputs to train selected machine learning models to produce a predicted PMA. Mean Absolute Error (MAE) values were used to assess model accuracy. Machine learning models with higher levels of accuracy were selected for the next stage of analysis. Inter-breath interval data from dataset 2 were analysed, consisting of 66 infants across 161 recordings. 50 features were extracted and used as inputs to train the selected models to output a predicted PMA. The most accurate model was used for further analysis to assess whether performance is affected by sex (paired t-test), ventilation method (ANOVA), and post-natal age (linear regression) . Results: 12 features from dataset 1 and 31 features from dataset 2 had a significant relationship with PMA (p < 0.05) . The most accurate model was the bagged trees model trained on all 50 features, with a MAE of 1.30 weeks. Sex (p = 0.17), ventilation method (p = 0.79) and post-natal age (p = 0.99) did not affect model performance. Conclusion: Inter-breath interval data offers novel directions for assessing the respiratory function of preterm infants. Table of Contents Introduction........................................................ 4 Foetal Lung Development................................................................................. 6 Pathologies and factors that affect preterm lung function ...................................... 10 Artificial Intelligence and Machine Learning...................................................... 15 Methods.......................................................... 18 Data Collection............................................................................................. 23 Analysis...................................................................................................... 24 Feature selection ........................................................................................... 26 Dataset 1..................................................................................................... 31 Dataset 2..................................................................................................... 32 Results............................................................ 34 Respiratory features correlate with PMA........................................................... 34 Can respiratory features predict age? Initial model training (Dataset 1) ..................35 Does model accuracy improve with increased data length? (Dataset 2) .....................38 Do clinical and demographic factors impact model accuracy?................................40 Discussion........................................................ 41 References........................................................ 46 Introduction Preterm birth is defined by The World Health Organisation (WHO) as births before the completion of the 37th gestational week of pregnancy.(1) Pre

FAQs

What is the main goal of using machine learning in this study?

To predict the post-menstrual age (PMA) associated with healthy preterm lung functioning using inter-breath interval data extracted from vital-sign monitoring.

How were data and respiratory features collected for model training?

Inter-breath intervals were longitudinally recorded in healthy preterm infants, then respiratory and statistical features were extracted from two datasets for model input.

Which factors were tested for their impact on model accuracy?

Model performance was assessed for possible effects of sex, ventilation method, and post-natal age using paired t-tests, ANOVA, and linear regression.

Aug 5, 2026

Upload by Genevieve