Advisors: Hugues Patural (Professor – PU-PH – CHU Saint-Etienne) and Olivier Alata (Professor, Hubert Curien Lab, UMR CNRS 5516)
Host laboratory: Sainbiose Lab – DVH UMR 1059 INSERM / Université Jean Monnet, Saint-Étienne, France.
Starting date: Spring 2026 – Application deadline : 15th of December, 2025 – Possibility of continuation as a PhD project
Keywords: heart rate variability, neurodevelopment, neonate, deep learning, NeuroCoach, medical
device.
Context:
The SAINBIOSE laboratory has internationally recognized expertise in neonatal autonomic
assessment and clinical applications of physiological signal analysis. The project will be conducted in
collaboration with Life Medical Control®, the industrial partner developing the NeuroCoach®
medical device.
Early detection of atypical neurodevelopmental trajectories in preterm or brain-at-risk newborns is a
major challenge in clinical practice. Current assessments, such as the Bayley Scales, identify
developmental delays only between 6 and 24 months after birth. Recently, Artificial Intelligence (AI)
has been applied to neonatal EEG, showing promise in predicting neurodevelopmental outcomes;
however, EEG interpretation remains a subjective and time-consuming process.
Heart Rate Variability (HRV), derived from electrocardiographic (ECG) signals, reflects cortical and subcortical brain activity and can serve as a non-invasive, continuous biomarker of autonomic and
neurodevelopmental function. The NeuroCoach® medical device, developed by the partner company Life Medical Control®, integrates non-invasive external sensors to acquire cardiac and oximetric signals. Its AI-based algorithm detects ECG anomalies (ventricular/supraventricular extrasystoles, atrial fibrillation) and apneic episodes during sleep, while also quantifying SpO₂ and autonomic balance indices.
See also the references at the end of the proposal.
This internship will focus on enhancing the embedded software and deep learning algorithms of the NeuroCoach® system, adapting them to the specific physiological characteristics of high-risk
neonates (high heart and respiratory rates, postural and environmental artifacts in neonatal
incubators).
Mission:
The primary objective of the internship is to develop and validate deep learning models that can
identify early neurodevelopmental alterations from HRV and ECG data collected by the NeuroCoach
device.
Page | 2
The intern will:
- Analyze HRV indices in temporal (SDNN, rMSSD, SD1, SD2), spectral (LF, HF, VLF), and nonlinear
domains (entropy, Hurst exponent, Lyapunov, etc.). - Normalize HRV predictors and implement regression-based and deep learning models.
- Evaluate statistical hypotheses differentiating normal vs. impaired neurodevelopmental outcomes
based on Bayley-3 scores at 2 years. - Test advanced learning architectures (ensemble models, tolerance-margin networks, multi-level
learners). - Draft a scientific report or paper summarizing model design, training, and performance outcomes.
Potential Impact and Perspectives
By improving early prediction of neurodevelopmental disorders via cardiac autonomic analysis, this research could revolutionize neonatal screening and preventive care. The NeuroCoach® system, enhanced by deep learning, could serve as a non-invasive preclinical diagnostic tool for early detection of neurocognitive risk, complementing EEG and behavioral assessments. This work aligns with ongoing research programs such as AGMA and BABYCRY, and contributes to the emergence of AI-driven personalized neonatal health monitoring.
Candidate profile:
- Final year master or engineering school student in biomedical engineering, computer science, or data science.
- Strong skills in signal processing, neural networks, and Python programming (TensorFlow/PyTorch).
- Interest in medical devices and physiological modeling.
- Experience with time-series or biosignal analysis is an asset.
Application: Please send before December 15, 2025, to: hugues.patural@univ-st-etienne.fr and olivier.alata@univ-st-etienne.fr:
- Cover letter explaining their motivation and relevant skills,
- Curriculum Vitae,
- Transcript of Bachelor and Master/Engineering school grades,
- Any additional documents if any (References, GitHub repository, …)
Feel free to contact us beforehand for any further pieces of information !
Funding: The selected candidate will obtain a 5/6 months funding (starting between March and April 2026). The salary is provided as intership allowance (4.35 €/hour, for a 35h week around 152€, 4 weeks 609 €).
Host laboratory: : SAINBIOSE Laboratory – UJM / CHU Saint-Étienne (France)
References
[1] C. Del Rosario, M. Slevin, E. J. Molloy et al. (2020) ‘‘How to use the bayley scales of infant and toddler development,’’ Archives of Disease in Childhood-Education and Practice.
[2] A. Temko, O. Doyle, D. Murray, G et al. (2015) ‘‘Multimodal predictor of neurodevelopmental outcome in newborns with hypoxic-ischaemic encephalopathy,’’ Computers in biology and medicine, 63 ; 169–177.
[3] N. Alotaibi, D. Bakheet, D. Konn, B et al. (2022) ‘‘Cognitive outcome prediction in infants with neonatal hypoxic-ischemic encephalopathy based on functional connectivity and complexity of the electroencephalography signal,’’ Frontiers in human neuroscience, 15 ; 795006.
[4] G. Thiriez, C. Mougey, D. Vermeylen, et al. (2015) ‘‘Altered autonomic control in preterm newborns with impaired neurological outcomes,’’ Clinical autonomic research, 25 ; 233–42.
[5] Thayer, J. F., Ahs, F., Fredrikson, M., Sollers, et al. (2012). A meta-analysis of heart rate variability and neuroimaging studies: implications for heart rate variability as a marker of stress and health. Neurosci. Biobehav. Rev. 36, 747–756.
[6] Jennings, J. R., Sheu, L. K., Kuan, D. C. H., Manuck, et al. (2016). Resting state connectivity of the medial prefrontal cortex covaries with individual differences in high-frequency heart rate variability. Psychophysiology 53, 444–454.
[7] Nikolin, S., Boonstra, T. W., Loo, C. K., and Martin, D. (2017). Combined effect of prefrontal transcranial direct current stimulation and a working memory task on heart rate variability. PLoS One 12:e0181833.
[8] Anderson, P. (2002). Assessment and development of executive function (EF) during childhood. Child Neuropsychol. 8, 71–82.
[9] Appelhans, B. M., and Luecken, L. J. (2006). Heart rate variability as an index of regulated emotional responding. Rev. Gen. Psychol. 10, 229–240.
[10] Golkar, A., Lonsdorf, T. B., Olsson, A., Lindstrom, K. M., et al. (2012). Distinct contributions of the dorsolateral prefrontal and orbitofrontal cortex during emotion regulation. PLoS One 11:e48107.
[11] R. M. Goulding, N. J. Stevenson, D. M. Murray, V. Livingstone and G. B. Boylan (2015) ‘‘Heart rate variability in hypoxic ischemic encephalopathy: correlation with eeg grade and 2-y neurodevelopmental outcome,’’ Pediatric research, 77, 5, 681–87
