applied
sciences
Perspective
Applications of Artificial Intelligence in Neonatology
Roberto Chioma † , Annamaria Sbordone † , Maria Letizia Patti, Alessandro Perri
and Stefano Nobile *
Citation: Chioma, R.; Sbordone, A.;
Patti, M.L.; Perri, A.; Vento, G.;
Nobile, S. Applications of Artificial
Intelligence in Neonatology. Appl. Sci.
2023, 13, 3211. https://doi.org/
10.3390/app13053211
Academic Editor: Jongsung Lee
Received: 30 January 2023
Revised: 22 February 2023
Accepted: 26 February 2023
Published: 2 March 2023
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Appl. Sci. 2023, 13, 3211. https://doi.org/10.3390/app13053211
, Giovanni Vento
Department of Life Sciences and Public Health, Fondazione Policlinico Universitario Agostino Gemelli IRCCS,
00168 Rome, Italy
* Correspondence: stefano.nobile@policlinicogemelli.it
† These authors contributed equally to this work.
Abstract: The development of artificial intelligence methods has impacted therapeutics, personalized
diagnostics, drug discovery, and medical imaging. Although, in many situations, AI clinical decision-
support tools may seem superior to rule-based tools, their use may result in additional challenges.
Examples include the paucity of large datasets and the presence of unbalanced data (i.e., due to the
low occurrence of adverse outcomes), as often seen in neonatal medicine. The most recent and impact-
ful applications of AI in neonatal medicine are discussed in this review, highlighting future research
directions relating to the neonatal population. Current AI applications tested in neonatology include
tools for vital signs monitoring, disease prediction (respiratory distress syndrome, bronchopulmonary
dysplasia, apnea of prematurity) and risk stratification (retinopathy of prematurity, intestinal per-
foration, jaundice), neurological diagnostic and prognostic support (electroencephalograms, sleep
stage classification, neuroimaging), and novel image recognition technologies, which are particularly
useful for prompt recognition of infections. To have these kinds of tools helping neonatologists in
daily clinical practice could be something extremely revolutionary in the next future. On the other
hand, it is important to recognize the limitations of AI to ensure the proper use of this technology.
Keywords: infant; machine learning; predictive models; clinical algorithm
1. Introduction
The term “artificial intelligence” (AI) refers to the general ability of computing algo-
rithms to emulate human decision-making, while machine learning (ML) is a subdivision
of AI that includes techniques that enable machines to learn from data without explicit pro-
gramming [1]. Over recent decades, both have deeply influenced personalized diagnostics
and therapeutics, drug discovery, and medical imaging [2]. Potentially, these approaches
could significantly improve our understanding of disease and therapeutic efficacy in both
children and infants [3]. Algorithms are employed in ML for the classification of data and to
make predictions. ML encompasses three broad subgroups: supervised ML, unsupervised
ML, and neural networks. Supervised ML employs labeled datasets to train an algorithm
to perform data classification; in particular, for prognostic applications. Unsupervised ML
is generally used as a tool to explore data and requires less human input. Neural networks
take inspiration from biological neural networks, can “learn” from missed predictions,
and are useful to process imaging data. To date, supervised ML has mostly been used in
pediatrics and neonatology to design predictive models. For example, applying readily
understandable methods, algorithms designed to identify patients at risk of pneumonia,
urinary tract infection, bacterial meningitis, intra-abdominal injury, or clinically relevant
traumatic brain injury have been obtained [4].
Although in many situations AI clinical decision-support tools may seem superior to
rule-based tools, their use may result in additional challenges. These include the need for
vast datasets, the challenges of generalizability, the presence of unbalanced data (i.e., due
https://www.mdpi.com/journal/applsci
Appl. Sci. 2023, 13, 3211 2 of 14

to the low occurrence of adverse outcomes), a lack of evidence-based care, maturational

variation in children, and costs [4].
Neonatal critical care units usually produce consistent amounts of generally under-
utilized data that can be computed and analyzed with AI. In this review, we present and
discuss the most recent and impactful applications of AI in neonatology and highlight the
future directions for research relating to this population of patients.

2. Applications of Artificial Intelligence

2.1. AI and Neuromonitoring
The revolution in AI—and, particularly, the subcategory of ML—has influenced re-
search on the neuromonitoring of critically sick neonates over the last couple of decades.
With the advancement in processing power and data storage, AI now enables computer
systems to scrutinize and analyze enormous volumes of information, deciphering illness
patterns. Clinical neuromonitoring can generate big data, particularly in terms of elec-
troencephalogram (EEG) data [5]. An EEG is a non-invasive recording of cerebral cortex
electrical activity that permits real-time assessment of cortical background function, which
has prognostic utility for neonates. As EEGs also permit the differentiation of epileptic
seizures from nonepileptic events and can detect nonconvulsive seizures, they are also
the reference tool for diagnosing seizures [6]. Continuous EEG (cEEG) recordings max-
imize the diagnostic utility of this tool, as they are more likely to record electrographic
events, but also its prognostic significance, permitting the assessment of the evolution in
background activity over time [7,8]. In any case, interpreting the plethora of information
generated requires expertise and is resource-consuming, aspects that limit the diffusion of
cEEG monitoring.
A number of ML algorithms based on EEG background activity have been proposed
with various aims. Much research has been undertaken in the area of automated EEG inter-
pretation regarding the early severity grading of perinatal hypoxic-ischemic encephalopa-
thy (HIE) in order to provide diagnostic decision support [9–11]. Recently, advanced
techniques for signal processing and ML, such as convolutional neural network structures
able to self-extract convolutional features from raw EEGs [12], have demonstrated strong
performance metrics for classifying HIE severity grades [13]. Pavel et al. also investigated
the potential role of AI in predictive modeling for electrographic seizures in neonates with
HIE [14], aiming to identify infants at the highest risk of subsequent seizures early. ML
models were developed separately and in combination for qualitative EEG (assessed by
a neurophysiologist) and quantitative EEG (automatically generated by weighting the
quantity of discontinuous activity) features, as well as for clinical features. Interestingly,
the automated quantitative EEG analysis performed as well as the analysis executed by
an expert neurophysiologist, augmenting the predictive value of these models by adding
clinical information. These reports emphasize the potential of using ML to process the
background EEG activity of neonates with HIE.
AI has also been extensively investigated in sleep studies of term and preterm infants,
using EEG data to automatically classify neonatal sleep stages [15,16]. Sleep studies are
particularly relevant in the management of sick infants due to their prognostic value, as the
expression of alternating vigilance states (i.e., sleep–wake cycling) is a positive prognostic
factor and a global marker of neurological well-being [17,18]. Detection of sleep states
could also enhance neuroprotective care, as less interruption during deep sleep can be a
therapeutic approach. In any case, the research on AI-driven tools evaluating neonatal
cortical background activity is still in the preclinical stage.
Appl. Sci. 2023, 13, 3211 3 of 14

The detection of paroxysmal events is another key purpose of EEG monitoring. The
neonatal population is at the highest risk of seizures compared with any other time in life,
and seizures are the most frequent neurological emergency in this age group [19]. The
incidence of seizures is estimated at approximately 8% in neonates and has a parabolical
relation to gestational age, with seizures being more frequent in infants born at less than
30 and more than 36 weeks of gestation [19]. Early recognition of seizures is crucial as
they are oftentimes a manifestation of an underlying pathological condition, such as HIE,
meningitis, or stroke [20,21], and because recent evidence suggests that early diagnosis
and treatment of seizures improve the response to medication [22]. Furthermore, it is
widely established that impaired long-term neurodevelopmental outcomes are associated
with an increased seizure burden [23–25]. The recurrence of seizures itself appears to
bring additional neurodevelopmental repercussions, independently of the underlying
etiology [26]. On the other hand, treatment for nonepileptic events exposes neonates to
unneeded harmful medications [27]. The diagnosis of seizures is particularly difficult in the
neonatal population as the events are usually electrographic only, their manifestation can
be masked by medication, and, even when present, they can be challenging to differentiate
from normal neonatal movements [28]. EEG monitoring is thus crucial to identify neonatal
seizures, and cEEG monitoring is the recommended standard of care for this aim [29].
According to current guidelines, 24 h cEEG monitoring should be performed for high-risk
neonates to screen for seizures, and 24 h of seizure freedom are recommended if seizing
activity is detected. Among infants with HIE undergoing therapeutic hypothermia, up
to 72 h of EEG recording should be considered, as rewarming is the most likely phase
for delayed seizures [29]. In any case, cEEG monitoring is not available in many NICUs
due to resource restrictions. The interpretation of data generated with cEEGs is difficult
and time-consuming and requires the availability of experienced neurophysiologists on a
24/7 basis. These aspects limit the availability of this crucial neuromonitoring tool, as only
half of NICUs report the use of cEEGs, indicating an implementation issue [30]. Amplitude-
integrated EEG (aEEG) monitoring has been adopted as a surrogate for cEEG monitoring,
gaining universal approval and use in NICUs worldwide. An aEEG is a simplified bedside
tool that displays one—or, more commonly, two—channels of EEG data quantitatively
converted via smoothing, rectification, and filtering. Then, the cortical electrical activity
is time-compressed and presented in a semi-logarithmic chart [31]. The role of aEEG
monitoring in the assessment of background cortical activity is well-established [32] and,
compared with cEEG monitoring, faster and more straightforward to apply and review. In
any case, its sensitivity, specificity, and interobserver agreement are critically suboptimal in
detecting seizures [33,34], and experts suggest a complementary role, rather than replacing
cEEG monitoring, for it [7,35].
Hence, given the key role but the limited accessibility of cEEGs, significant research
effort has been invested over recent decades into the development of automatic seizure
detection algorithms (SDAs) [36]. After the pioneering work of Liu et al. [37], who pro-
posed a computerized detection system for neonatal seizures back in 1992, several different
approaches have been reported, improved, and validated. While the initial SDAs origi-
nated from modifications of algorithms designed for adults [37,38], showing performances
far from acceptable for clinical purposes, the progressive complexity of the algorithmic
solutions and the techniques for signal processing led to reliable SDAs capable of analyzing
channels of raw EEG data in real time and continuously, as shown in Figure 1 [39,40].
Appl. Sci. 2023, 13, x FOR PEER REVIEW 4 of 14

Appl. Sci. 2023, 13, 3211 4 of 14

Figure 1. An EEG viewer incorporating an SDA. In the upper panel the output of the SDA is displayed
Figure 1. An EEG viewer incorporating an SDA. In the upper panel the output of the SDA is dis-
as a graph of seizure probability. The trace changes to red and an annotation is made when a seizure
played as a graph of seizure probability. The trace changes to red and an annotation is made when
aisseizure
identified. The interface
is identified. The also displays
interface also the cEEG the
displays andcEEG
aEEGand
(source:
aEEG[39]).
(source: [39]).

An important theoretical limitation of these systems is that the definition of ground

An important theoretical limitation of these systems is that the definition of ground
truth is not absolute in the detection of seizures. An SDA can only perform as well as
truth is not absolute in the detection of seizures. An SDA can only perform as well as the
the neurophysiologist who performed the annotation of the training data. The insightful
neurophysiologist who performed the annotation of the training data. The insightful re-
report by Stevenson et al. employed the gold standard for EEG monitoring—multichannel
port by Stevenson et al. employed the gold standard for EEG monitoring—multichannel
cEEG monitoring—to determine the interobserver agreement regarding neonatal seizure
cEEG monitoring—to determine the interobserver agreement regarding neonatal seizure
identification among three international experts, which was reported to be 83% [41].
identification among three international experts, which was reported to be 83% [41]. These
These results can be understood as the upper limit for the performance of any machine
results can be understood as the upper limit for the performance of any machine detecting
detecting seizures.
seizures.
In recent years, the first important steps in the transition of SDAs to the cot-side
haveIn recent
been years,
made. Asthe first
part ofimportant
the monitoringsteps inframework
the transition used of to
SDAs to thean
conduct cot-side have
antiseizure
been made. As part of the monitoring framework used to conduct
medication trial, a 2019 study introduced an SDA in the clinical setting [42]. The real- an antiseizure medica-
tion
timetrial, a 2019
review study introduced
systematically includedan SDA in the clinical
the algorithm, setting
sending [42]. email
direct The real-time
alerts toreview
study
systematically included the algorithm, sending direct
neurologists if they chose to activate this function. Although all the studyemail alerts to study neurologists
neurologists if
they chose to activate this function. Although all the study neurologists
found the SDA useful, a high false detection rate was reported, and only two out of nine found the SDA
useful,
used the a high false
instant detection alert
messaging rate was reported,
function, othersandfinding
only two out of nine used
false-positive alertstheto instant
be too
messaging
disruptive. Eventually, the first randomized clinical trial evaluating the impact ofEventu-
alert function, others finding false-positive alerts to be too disruptive. ML on
ally, the first randomized
the recognition of neonatal clinical
seizurestrialinevaluating
real time in theanimpact
NICU of wasMLpublished
on the recognition
in 2020 [43]. of
neonatal seizures in real time in an NICU was published in 2020
After repeated training and offline analysis [11,39], the SDA developed by a group from [43]. After repeated train-
ing
Corkand offline
was tested analysis [11,39], theclinical
in a multicenter SDA developed
investigation by a by
group from Cork
assessing was tested
the accuracy of in a
the
multicenter clinical investigation by assessing the accuracy of the
recognition of electrographic seizures with and without the algorithm as a cot-side support recognition of electro-
graphic
tool for seizures
the clinical withteam.
and without
Although the thealgorithm as a cot-side
predefined target of support tool for
enhancing thethe clinical
detection
team. Although
of individual the predefined
infants with seizures target
was ofnot
enhancing
met, thethe detection
algorithm of individual
significantly infants
improved
with seizures was
the recognition ofnot met, the
seizure algorithm
hours. These significantly
results were improved
more pronouncedthe recognition of seizure
on weekends as
hours.
compared These results were
to weekdays moreinpronounced
(45.3% the non-algorithm on weekends
group vs. as compared
66.0% in the to weekdays
algorithm
(45.3%
group).in theauthors
The non-algorithm
speculated group
that vs.
the66.0% in the algorithm
latter finding may havegroup). The authors
more reflected specu-
the situation
lated that the latter finding may have more reflected the situation
in NICUs in which no EEG expertise is readily available, suggesting that the advantage in NICUs in which no
EEG expertise
offered by the is SDAreadily
couldavailable,
be greater suggesting that the
if tested with advantage
teams offered byinthe
less experienced SDA could
bedside EEG
be greater if tested
interpretation. with teams
Although lessresearch
further experienced in bedsidetoEEG
is warranted interpretation.
demonstrate Although
improvements
in diagnostic
further research performance,
is warranted ML to techniques
demonstrate can be safely applied
improvements in clinical
in diagnostic care, and it
performance,
Appl. Sci. 2023, 13, 3211 5 of 14

appears likely that they will become an integral part of the neurological evaluation of
vulnerable neonates.
Recently, AI has also been employed in the field of neonatal neuroimaging and devel-
opmental follow-up. The internal capsule is a subcortical white matter structure composed
of afferent and efferent fiber tracts connecting the cerebral hemispheres to other subcortical
structures, the brainstem, and the spinal cord. The posterior limb of the internal capsule
(PLIC) is one of the structures in which myelination commences in the neonatal brain.
Importantly, the correct and timely maturation of the PLIC, particularly in terms of myeli-
nation, is crucial to neurological outcomes in term and preterm neonates. Abnormal or
asymmetrical signals detected through magnetic resonance imaging (MRI) in the PLIC
have been associated with perinatal complications, development of hemiplegia, and poor
neurodevelopmental outcomes [44]. These findings are especially relevant in neonatal care,
as the rate of neurodevelopmental abnormalities among infants with perinatal problems
remains high despite advances in clinical practice [45]. In particular, the prevalence of cere-
bral palsy, a severe condition carrying important life-long burdens and associated with an
abnormal PLIC MRI signal, has been increasing over recent decades, being reported as well
above 2.0 per 1000 live births [46], with a significant increase with decreasing gestational
age [47]. A recent study proposed an ML pipeline for the automated segmentation and
quantification of the PLIC in premature infants undergoing MRI [48]. The authors showed
good accuracy for the AI method compared to expert analysis, and successfully applied
their ML pipeline to data from a large dataset, proving generalizability. Although the
proposed method seems particularly promising, assessment of its translation into clinical
practice is warranted.
Valavani et al. used ML to predict language abilities at 2 years of corrected age in
premature infants by analyzing MRI features and perinatal clinical information [49]. In
their study, patterns of delayed myelination and some clinical features (i.e., twin status,
sex, antenatal steroid administration, breastfeeding) could predict language delay. The
authors concluded that ML might support services and facilitate targeted early interven-
tions, potentially improving the life quality of children born preterm. Other authors have
proposed a self-training deep neural network model using MRI data (brain functional
connectome) obtained in very preterm infants at term-equivalent age to predict neurode-
velopmental deficit at 2 years of age [50]. They applied a self-training technique with a
small cohort, obtaining good predictive accuracy; the results will need to be replicated
in large cohorts. Balta et al. recently provided new insight into the automated analysis
of infants’ general movements [51], an important screening examination for childhood
neuromotor disorders. The assessment of infants’ spontaneous movements is particularly
informative, as some patterns have been identified to reliably predict cerebral palsy at
the age of 3 to 5 months (i.e., the absence of fidgety movements or the presence of pre-
dominantly cramped synchronized movements). The authors demonstrated the feasibility
of analyzing infants’ general movements with an automated method they developed in-
volving processing videos obtained with an inexpensive RGB-D camera at their homes.
The proposed protocol seems promising, as it makes it possible to perform this screening
assessment in a familiar environment, improving infants’ compliance and providing an
evaluation of the true neurodevelopmental performance, which is sometimes challenging
in the clinical environment. Furthermore, this approach could be particularly helpful to
overcome logistic barriers in families with reduced access to health services; for example,
those living in rural and remote areas. However, despite demonstrating feasibility, the
authors could not conduct meaningful statistical analyses due to the small sample size.
Research on the validation of the developed protocol and its application in clinical practice
with a larger number of infants is warranted.
Appl. Sci. 2023, 13, 3211 6 of 14

2.2. AI and the Respiratory System

Respiratory distress syndrome (RDS) is the most common respiratory consequence of
prematurity. It is caused by primary pulmonary surfactant deficiency and affects more than
80% of infants born before 29 weeks of gestational age [52,53]. Bronchopulmonary dysplasia
(BPD) is a chronic respiratory condition experienced by neonates born at the early stages of
pulmonary development [54] that leads to poor long-term respiratory, cardiovascular, and
neurodevelopmental outcomes. Its prevalence is around 45% in infants born <28 weeks
of gestational age and it is associated with longer hospitalization and a higher risk of
comorbidities, such as poor somatic growth and neurodevelopmental impairment [55,56].
BPD also carries substantial social and economic costs [57,58]. The risk of developing BPD
is higher in subgroups of infants who experience worse RDS and a worse early respiratory
course [59]. The diagnosis of RDS is clinical and is not based on a single specific diagnostic
test. As previously mentioned, RDS is caused by lung immaturity and the derived deficit
of surfactant in the alveoli, leading to high surface tension and the collapse of respira-
tory units. The cornerstone of the management of patients with RDS is administrating
exogenous surfactant, aiming to enhance pulmonary compliance and minimize exposure
to mechanical ventilation and the derived ventilator-induced lung injury [60]. In any case,
prophylactic therapy with surfactant is not a cost-effective strategy [53], and unnecessary
or inappropriate administration can lead to potentially dangerous side effects (i.e., airway
lesions, pneumothorax, pulmonary hemorrhage). Some authors have investigated the role
of biomarkers of RDS, such as the lecithin/sphingomyelin ratio (L/S ratio) from gastric
aspirates or amniotic fluid samples. The L/S ratio can give information about endogenous
pulmonary surfactant production, which is decreased in preterm infants with RDS. Unfor-
tunately, the calculation of the L/S ratio is still confined to research and not available at the
bedside due to technical complexities. To overcome these limitations and provide a bedside
point-of-care test method useful for clinicians, Ahmed et al. tested a machine-learning
algorithm also useful for the study of other biological samples that are interpretable in
the mid-infrared spectrum [61]. Their findings are particularly insightful as, after clinical
validation, the employment of ML-guided devices able to quantify biomarkers of RDS in
real time might potentially guide interventions in preterm infants with respiratory symp-
toms. In any case, considerable concerns about signal-to-noise and signal-to-background
limitations remain, and the applicability of this new technology at the bedside does not
appear forthcoming.
Raimondi et al. focused on lung ultrasound, a technique able to quantify pulmonary
aeration, and its ability to correlate with respiratory status in sick neonates, applying
AI-assisted analysis [62]. They built a dataset of scans (600 ultrasound frames) to perform a
texture and ML analysis with the aim of correlating the ultrasound and the mean grayscale
intensity with the oxygenation status. To do so, they enrolled a cohort of 75 neonates
with various degrees of respiratory distress of diverse origin. Despite a significant linear
correlation between the grayscale ML analysis and blood gases indexes being found, the
relatively small sample size, the inhomogeneous etiology of the respiratory distress, and the
variable postnatal age warrant further research on this topic with larger datasets derived
from more uniform cohorts. The representative lung ultrasound findings and the calculated
intensity histograms are shown in Figure 2.
A particular topic of research interest in pediatric respiratory care is risk stratification
for BPD, aiming to identify infants that could benefit from preventive interventions, such
as corticosteroids, or treatment for a patent ductus arteriosus using a standardized risk
estimation tool. The US National Institute of Child Health and Human Development has
recently endorsed a prognostic tool, the BPD Outcome Estimator [63], which is widely
employed to guide steroid administration and family counseling. In any case, the estimator
is only applicable to neonates of White, Black, or Hispanic descent. Patel et al. recently
designed an ML algorithm for respiratory outcome prediction for extremely premature
infants of Asian heritage, aiming to fill this gap in knowledge [64]. As a demonstration
of the model, a Web app was developed and is currently consultable online. In any
Appl. Sci. 2023, 13, 3211 7 of 14

case, the algorithm was tested on a small dataset derived from 29 patients and needs
extensive and prospective validation before being employed for clinical purposes, majorly
limiting the results of the study. Wenyu Xing et al. proposed an AI method capable of
predicting the severity of BPD, defined as mild, moderate, or severe, by studying the chest
X-ray recorded on the 28th day of oxygen administration using deep learning and image
segmentation [65]. Their model was developed with a relatively large cohort (121 preterm
infants with at least 28 days of oxygen need) and has the advantages of being non-invasive,
rapid, and independent of neonatologists’ experience. The proposed algorithm is based
on the segmentation of the lungs in chest X-ray images and showed good predictive
performance. Other groups focused on different data that could help predict BPD. For
instance, in a recent work by Dai et al., the combination of genetic and clinical factors
was studied: exome sequencing was performed for more than 200 preterm infants and
integrated with clinical features [66]. This dataset was then employed to create an ML
model capable of identifying early infants with a high risk of developing BPD with good
accuracy. Leigh and colleagues retrospectively analyzed the perinatal factors and the
respiratory support needed in the first days of life in a population of preterm babies with
the aim of obtaining an ML algorithm able to predict BPD-free survival. They trained the
Appl. Sci. 2023, 13, x FOR PEER REVIEW
model and tested it, finding good performance in terms of the area under the curve. 7Theyof 14
also designed simulation scenarios to validate and use the model to solve clinical questions
about BPD [67].

Figure 2. Representative lung ultrasound images used for scoring and calculated histograms
Figure 2. Representative lung ultrasound images used for scoring and calculated histograms
(source: [62]).
(source: [62]).
Apnea of prematurity (AOP) is another common issue detected in premature infants
A particular topic of research interest in pediatric respiratory care is risk stratification
admitted to NICUs. It is correlated with the immaturity of the respiratory control system
for BPD, aiming
in these fragile to identify
patients and infants that couldby
can be triggered benefit from
several preventive
conditions, interventions,
including such
infections,
as corticosteroids, or treatment for a patent ductus arteriosus using
gastroesophageal reflux, and seizures [68]. AOP is diagnosed in more than 50% of preterma standardized risk
estimation tool. The US National Institute of Child Health and Human Development
babies and is almost universal in infants with extremely low birth weight [69]. It is associ- has
recently
ated with endorsed
brain damage a prognostic
and poortool, the BPD Outcome
neurodevelopmental Estimator
outcomes and[63],
thuswhich
needsisprompt
widely
employed to guide steroid administration and family counseling. In any
recognition and treatment. AOP can be categorized as central (lack of diaphragmatic con- case, the estima-
tor is only
traction dueapplicable to neonates
to the cessation of White,drive),
of respiratory Black,obstructive
or Hispanic(due
descent. Patel obstruction),
to airway et al. recently
or mixed apnea (characterized by both central and obstructive features). As a premature
designed an ML algorithm for respiratory outcome prediction for extremely standard
ofinfants of Asianmonitors
care, bedside heritage,areaiming
set totogenerate
fill this gap in knowledge
an alarm [64].
in cases of As a demonstration
a temporary drop in theof
the model, a Web app was developed and is currently consultable online. In any case, the
algorithm was tested on a small dataset derived from 29 patients and needs extensive and
prospective validation before being employed for clinical purposes, majorly limiting the
results of the study. Wenyu Xing et al. proposed an AI method capable of predicting the
severity of BPD, defined as mild, moderate, or severe, by studying the chest X-ray rec-
Appl. Sci. 2023, 13, 3211 8 of 14

amplitude of the thoracic impedance, as it reflects a drop in thoracic motion and, indirectly,
in respiratory effort [70]. This strategy permits the identification of central apneas with
suboptimal accuracy, as reported in clinical studies, showing a high rate of false positive
episodes [71]. Varisco and colleagues developed and validated an enhanced AOP detec-
tion model based on ML to automatically recognize true apnea by analyzing data from
the electrocardiographic monitoring of infants [72]. The authors found that AOP often
occurred in clusters and that breathing patterns were more disturbed in patients with more
frequent central AOP and concluded that AI leads to improved apnea detection compared
to traditional methods with fewer false alarms. Considering how alarm fatigue is becoming
a common issue in modern NICUs, exposing sick infants to the risk of missed alarms and
potentially disrupting consequences, AI may radically change daily clinical practice. In any
case, the limited sample size (20 preterm infants overall) constitutes an important flaw in
the proposed method, as does the lack of external or prospective validation.

2.3. AI and the Eye

Retinopathy of prematurity (ROP), one of the most frequent causes of childhood
blindness, is a multifactorial disease related to risk factors such low birth weight (BW), low
gestational age (GA), oxygen exposure, infections, and blood transfusions [73]. To detect
and possibly treat this condition in a timely manner, it is important to start the screening
at the right time and to continue with regular monitoring and evaluations. Current ROP
screening involves a first eye examination and several follow-up examinations performed
longitudinally during hospitalization and after discharge if needed. The examination
can be quite stressful for the baby and laborious for the ophthalmologists. Moreover, it
is not always possible to follow a correct ROP screening program in remote areas [74].
Over the last few years, applications of AI in the diagnosis of this condition have been
evaluated: in a recent large, international, multicenter study, a deep-learning method
was trained to detect one of the features of the affected retina and to give an automated
score, showing good results [75]. This important report provided a proof of concept,
demonstrating that a deep-learning comprehensive screening platform could potentially
improve objective ROP diagnosis and screening accessibility. Another set of authors have
recently developed a deep-learning approach for the prediction of ROP and its severity in a
large multicenter study [74]. The model they trained is based on retinal images from the
first ROP screening and clinical data for the patient available before or at the time of the
first ROP screening, making it possible to include retinal status in the predictive model.
The artificial intelligence’s training was based on three schemes (majority voting, one-vote
veto, and image-level methods) and allowed it to generate the predictive probability of
retinal photographs coupled with clinical risk factors. The deep learning-based system
had similar accuracy compared to a commonly used ROP score algorithm (the ROP score)
and could even have better efficiency in the detection and interpretation of pathological
features compared to the classical medical evaluation. Despite the promising results of the
study, larger external validation with other prospective multicenter datasets is warranted.
Potentially, more sophisticated ML algorithms could provide more important prognostic
details about the condition (i.e., precise staging, zone, plus disease).

2.4. AI and Vital Signs Monitoring

The monitoring of vital signs in newborns, such as respiratory and heart rates and body
temperature, is one of the key elements of modern neonatal care. For example, an imbalance
in vital signs is one of the early signs of infectious diseases, which represent one of the main
causes of mortality and morbidity worldwide. To monitor these parameters in newborns,
sensors are placed in direct contact with the skin, potentially causing skin injury, stress,
and discomfort for babies. Non-contact measurement methods (i.e., camera recordings,
laser Doppler vibrometry, and others) have recently been developed to continuously
record vital parameters and avoid such complications in fragile patients [76,77]. Advanced
algorithms are needed to work on the images deriving from automatic camera-based
Appl. Sci. 2023, 13, 3211 9 of 14

measurements of vital signs. The tracking of regions of interest (ROIs) and signal fusion for
vital signs extraction are important steps in the performance of camera-based temperature
monitoring. Deep learning-based approaches may lead to robust, real-time assessment of
vital parameters, such as body temperature alterations, as suggested by Lyra et al. [78]. In
their work, clinical data for neonates were used to train a model based on deep learning
in order to achieve real-time extraction of surface temperature. The analysis of the results
was challenging for several reasons (e.g., the parameters and data related to the changes in
the positions of infants’ bodies during the recording). However, the authors showed the
feasibility of low-cost, embedded GPUs for real-time temperature monitoring of neonates,
and further studies are expected to expand this method in clinical practice.

2.5. AI and the Gastrointestinal System

Intestinal perforation (IP) in preterm infants is a life-threatening condition. It can
be spontaneous or secondary to necrotizing enterocolitis and requires urgent surgical
intervention. Even if risk factors for IP have been elucidated, preventive measures and
prediction models are not easily developed because the pathogenesis of this condition in
preterm babies is still not fully understood. ML can be helpful, allowing a meticulous
assessment of complex conditions starting from large datasets. Given the deep clinical
impact of such conditions on outcomes such as death and quality of life, it is undeniable
that having an AI tool helping and supporting clinicians in management could be extremely
helpful. A recent study developed an AI algorithm trained on a large national dataset
relating to the clinical features of infants [79]. The proposed algorithm predicted and
characterized IP preterm infants with excellent accuracy, outperforming all other classic
ML algorithms. The authors speculated that the assessment of different clinical data, such
as vital signs, radiologic findings, biomarkers, and laboratory results, might enable the
development of a more accurate ML model, eventually making it possible to achieve
early prediction of IP and improved outcomes for preterm babies. In the nutrition field,
a recent study by Han et al. focused on the possibility of using AI to predict postnatal
growth failure and thus plan timely interventions. ML models were developed employing
different techniques with a large dataset (approximately 8000 very low birth weight infants
from various Chinese NICUs), and their feasibility and good predictive performance
were demonstrated [80]. In any case, despite the vast size of the dataset, it did not include
important information regarding enteral and parenteral nutrition, limiting the study results.

2.6. AI and Neonatal Jaundice

A very interesting application of AI for the future is in jaundice diagnosis. A Saudi
Arabian group explored the possibility of using deep learning and ML models for the
diagnosis of neonatal jaundice using a dataset comprising images from a smartphone
camera. The study population included late preterm and term newborns. In this study, the
authors trained a neural network to recognize jaundice from the information obtained from
the images of the skin and the eyes [81]. Guardalia et al. studied the clinical data for a large
population of newborns with the intention of building a risk stratification tool for neonatal
jaundice using an ML approach and without using bilirubin measurements. Their model
showed good accuracy in the risk stratification of neonatal jaundice [82].

3. Discussion
Artificial intelligence has great potential to improve our understanding of disease
and to enhance therapeutic effectiveness—in neonatal medicine as well as elsewhere—as
reported in recent studies. We presented the most relevant studies in this field and found
that the most important applications of AI involved neuromonitoring, assessment, and
prediction of significant respiratory diseases and prediction of retinopathy of prematurity,
neonatal sepsis, jaundice, and intestinal perforation. These conditions represent serious
complications of prematurity and may lead to permanent consequences and even death.
The development of point-of-care tools is another promising approach, enabling clinicians
Appl. Sci. 2023, 13, 3211 10 of 14

to predict and effectively treat some conditions, such as RDS. In any case, there are some
ethical challenges in the application of AI to neonatal clinical care. Permission to partic-
ipate is typically provided by parents acting as legally authorized representatives since
neonates are not capable of consenting. Considering the need for proxy consent, newborn
infants need additional protection as research participants. Furthermore, parents of sick or
premature infants have to face numerous difficulties in the early weeks and months of life
of their babies. Mental, physical, and emotional fatigue may impair the capacity of parents
to provide informed consent. Hence, particular attention has been given to the respect for
rigorous ethical standards in perinatal research [83]. There are also several ethical and juris-
dictional pitfalls regarding the application of ML in clinical decision-making. For example,
if the validated algorithm were to make a mistake, who should be considered accountable
for it? Other limitations of AI include the need for large datasets to “train” the models, the
presence of unbalanced data, issues of generalizability, a lack of evidence-based care for
some neonatal conditions, maturational variation, and costs. Further important issues to be
faced when applying AI to neonatal care are the need for proper performance assessment,
the need for external validation to enhance generalizability, and the interpretability of the
model. The results of the studies presented in our manuscript are promising. Moreover,
the majority of the diseases we discussed represent serious neonatal conditions and may
lead to permanent consequences and even death. The prevalence of the diseases discussed
in this narrative review, along with estimates of related direct and indirect costs, have been
previously reported [84–86] and, in our opinion, justify including the assessment of AI on
the research agenda.

4. Conclusions
There is a growing interest in the medical field regarding the modern applications of
artificial intelligence in neonatal care. In this narrative review, we presented some of the
most recent and significant findings related to the topic in order to provide an overview of
the potential of AI applications in neonatology.

Author Contributions: Conceptualization, S.N.; methodology, R.C., A.S. and S.N.; writing—original
draft preparation, R.C., A.S. and S.N.; writing—review and editing, S.N., R.C., A.S., M.L.P., A.P. and
G.V. All authors have read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Institutional Review Board Statement: Ethical review and approval were waived for this study due
to the nature of the manuscript.
Informed Consent Statement: Not applicable.
Data Availability Statement: No new data were created.
Acknowledgments: We thank Geraldine B. Boylan, Sean Mathieson, and Francesco Raimondi for
providing us with insightful images.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Helm, J.M.; Swiergosz, A.M.; Haeberle, H.S.; Karnuta, J.M.; Schaffer, J.L.; Krebs, V.E.; Spitzer, A.I.; Ramkumar, P.N. Machine
Learning and Artificial Intelligence: Definitions, Applications, and Future Directions. Curr. Rev. Musculoskelet. Med. 2020, 13,
69–76. [CrossRef]
2. Gutierrez, G. Artificial Intelligence in the Intensive Care Unit. Crit. Care 2020, 24, 101. [CrossRef] [PubMed]
3. Shah, N.; Arshad, A.; Mazer, M.B.; Carroll, C.L.; Shein, S.L.; Remy, K.E. The use of machine learning and artificial intelligence
within pediatric critical care. Pediatr. Res. 2022, 93, 405–412. [CrossRef] [PubMed]
4. Ramgopal, S.; Sanchez-Pinto, L.N.; Horvat, C.M.; Carroll, M.S.; Luo, Y.; Florin, T.A. Artificial intelligence-based clinical decision
support in pediatrics. Pediatr. Res. 2022, 93, 334–341. [CrossRef] [PubMed]
5. Brinkmann, B.H.; Bower, M.R.; Stengel, K.A.; Worrell, G.A.; Stead, M. Large-scale electrophysiology: Acquisition, compression,
encryption, and storage of big data. J. Neurosci. Methods 2009, 180, 185–192. [CrossRef]
Appl. Sci. 2023, 13, 3211 11 of 14

6. Shellhaas, R.A.; Clancy, R.R. Characterization of neonatal seizures by conventional EEG and single-channel EEG. Clin. Neurophysiol.
2007, 118, 2156–2161. [CrossRef]
7. McCoy, B.; Hahn, C.D. Continuous EEG monitoring in the neonatal intensive care unit. J. Clin. Neurophysiol. 2013, 30, 106–114.
[CrossRef]
8. Connell, J.; Oozeer, R.; de Vries, L.; Dubowitz, L.M.; Dubowitz, V. Continuous EEG monitoring of neonatal seizures: Diagnostic
and prognostic considerations. Arch. Dis. Child. 1989, 64, 452–458. [CrossRef]
9. Matic, V.; Cherian, P.J.; Koolen, N.; Naulaers, G.; Swarte, R.M.; Govaert, P.; Van Huffel, S.; De Vos, M. Holistic approach for
automated background EEG assessment in asphyxiated full-term infants. J. Neural. Eng. 2014, 11, 066007. [CrossRef]
10. Moghadam, S.M.; Pinchefsky, E.; Tse, I.; Marchi, V.; Kohonen, J.; Kauppila, M.; Airaksinen, M.; Tapani, K.; Nevalainen, P.; Hahn,
C.; et al. Building an Open Source Classifier for the Neonatal EEG Background: A Systematic Feature-Based Approach From
Expert Scoring to Clinical Visualization. Front. Hum. Neurosci. 2021, 15, 675154. [CrossRef]
11. Stevenson, N.J.; Korotchikova, I.; Temko, A.; Lightbody, G.; Marnane, W.P.; Boylan, G.B. An automated system for grading EEG
abnormality in term neonates with hypoxic-ischaemic encephalopathy. Ann. Biomed. Eng. 2013, 41, 775–785. [CrossRef]
12. Raurale, S.A.; Boylan, G.B.; Mathieson, S.R.; Marnane, W.P.; Lightbody, G.; O’Toole, J.M. Grading hypoxic-ischemic en-
cephalopathy in neonatal EEG with convolutional neural networks and quadratic time-frequency distributions. J. Neural.
Eng. 2021, 18, 046007. [CrossRef] [PubMed]
13. O’Sullivan, M.E.; Lightbody, G.; Mathieson, S.R.; Marnane, W.P.; Boylan, G.B.; O’Toole, J.M. Development of an EEG artefact
detection algorithm and its application in grading neonatal hypoxic-ischemic encephalopathy. Expert. Syst. Appl. 2023, 213,
118917. [CrossRef]
14. Pavel, A.M.; O’Toole, J.M.; Proietti, J.; Livingstone, V.; Mitra, S.; Marnane, W.P.; Finder, M.; Dempsey, E.M.; Murray, D.M.;
Boylan, G.B. Machine learning for the early prediction of infants with electrographic seizures in neonatal hypoxic-ischemic
encephalopathy. Epilepsia 2023, 64, 456–468. [CrossRef]
15. Koolen, N.; Oberdorfer, L.; Rona, Z.; Giordano, V.; Werther, T.; Klebermass-Schrehof, K.; Stevenson, N.; Vanhatalo, S. Automated
classification of neonatal sleep states using EEG. Clin. Neurophysiol. 2017, 128, 1100–1108. [CrossRef] [PubMed]
16. Ghimatgar, H.; Kazemi, K.; Helfroush, M.S.; Pillay, K.; Dereymaker, A.; Jansen, K.; Vos, M.; Aarabi, A. Neonatal EEG sleep stage
classification based on deep learning and HMM. J. Neural. Eng. 2020, 17, 036031. [CrossRef] [PubMed]
17. Natalucci, G.; Rousson, V.; Bucher, H.U.; Bernet, V.; Hagmann, C.; Latal, B. Delayed cyclic activity development on early
amplitude-integrated EEG in the preterm infant with brain lesions. Neonatology 2013, 103, 134–140. [CrossRef]
18. Klebermass, K.; Olischar, M.; Waldhoer, T.; Fuiko, R.; Pollak, A.; Weninger, M. Amplitude-integrated EEG pattern predicts further
outcome in preterm infants. Pediatr. Res. 2011, 70, 102–108. [CrossRef]
19. Sheth, R.D.; Hobbs, G.R.; Mullett, M. Neonatal seizures: Incidence, onset, and etiology by gestational age. J. Perinatol. 1999, 19,
40–43. [CrossRef]
20. Vasudevan, C.; Levene, M. Epidemiology and aetiology of neonatal seizures. Semin. Fetal. Neonatal. Med. 2013, 18, 185–191.
[CrossRef]
21. Glass, H.C.; Shellhaas, R.A.; Wusthoff, C.J.; Chang, T.; Abend, N.S.; Chu, C.J.; Cilio, M.R.; Glidden, D.V.; Bonifacio, S.L.; Massey,
S.; et al. Contemporary Profile of Seizures in Neonates: A Prospective Cohort Study. J. Pediatr. 2016, 174, 98–103.e101. [CrossRef]
[PubMed]
22. Williams, R.P.; Banwell, B.; Berg, R.A.; Dlugos, D.J.; Donnelly, M.; Ichord, R.; Kessler, S.K.; Lavelle, J.; Massey, S.L.; Hewlett, J.; et al.
Impact of an ICU EEG monitoring pathway on timeliness of therapeutic intervention and electrographic seizure termination.
Epilepsia 2016, 57, 786–795. [CrossRef] [PubMed]
23. Glass, H.C.; Glidden, D.; Jeremy, R.J.; Barkovich, A.J.; Ferriero, D.M.; Miller, S.P. Clinical Neonatal Seizures are Independently
Associated with Outcome in Infants at Risk for Hypoxic-Ischemic Brain Injury. J. Pediatr. 2009, 155, 318–323. [CrossRef] [PubMed]
24. Payne, E.T.; Zhao, X.Y.; Frndova, H.; McBain, K.; Sharma, R.; Hutchison, J.S.; Hahn, C.D. Seizure burden is independently
associated with short term outcome in critically ill children. Brain 2014, 137 Pt 5, 1429–1438. [CrossRef]
25. Srinivasakumar, P.; Zempel, J.; Trivedi, S.; Wallendorf, M.; Rao, R.; Smith, B.; Inder, T.; Mathur, A.M. Treating EEG Seizures in
Hypoxic Ischemic Encephalopathy: A Randomized Controlled Trial. Pediatrics 2015, 136, e1302–e1309. [CrossRef] [PubMed]
26. Chapman, K.E.; Specchio, N.; Shinnar, S.; Holmes, G.L. Seizing control of epileptic activity can improve outcome. Epilepsia 2015,
56, 1482–1485. [CrossRef]
27. Slaughter, L.A.; Patel, A.D.; Slaughter, J.L. Pharmacological treatment of neonatal seizures: A systematic review. J. Child. Neurol.
2013, 28, 351–364. [CrossRef]
28. Murray, D.M.; Boylan, G.B.; Ali, I.; Ryan, C.A.; Murphy, B.P.; Connolly, S. Defining the gap between electrographic seizure burden,
clinical expression and staff recognition of neonatal seizures. Arch. Dis. Child. Fetal. Neonatal. Ed. 2008, 93, F187–F191. [CrossRef]
29. Shellhaas, R.A.; Chang, T.; Tsuchida, T.; Scher, M.S.; Riviello, J.J.; Abend, N.S.; Nguyen, S.; Wusthoff, C.J.; Clancy, R.R. The
American Clinical Neurophysiology Society’s Guideline on Continuous Electroencephalography Monitoring in Neonates. J. Clin.
Neurophysiol. 2011, 28, 611–617. [CrossRef]
30. Tagin, M.A.; Woolcott, C.G.; Vincer, M.J.; Whyte, R.K.; Stinson, D.A. Hypothermia for neonatal hypoxic ischemic encephalopathy:
An updated systematic review and meta-analysis. Arch. Pediatr. Adolesc. Med. 2012, 166, 558–566. [CrossRef]
31. de Vries, L.S.; Toet, M.C. Amplitude integrated electroencephalography in the full-term newborn. Clin. Perinatol. 2006, 33,
619–632. [CrossRef] [PubMed]
Appl. Sci. 2023, 13, 3211 12 of 14

32. de Vries, L.S.; Hellström-Westas, L. Role of cerebral function monitoring in the newborn. Arch. Dis. Child. Fetal. Neonatal. Ed.
2005, 90, F201–F207. [CrossRef] [PubMed]
33. Rakshasbhuvankar, A.; Rao, S.; Palumbo, L.; Ghosh, S.; Nagarajan, L. Amplitude Integrated Electroencephalography Compared
With Conventional Video EEG for Neonatal Seizure Detection: A Diagnostic Accuracy Study. J. Child. Neurol. 2017, 32, 815–822.
[CrossRef] [PubMed]
34. Rennie, J.M.; Chorley, G.; Boylan, G.B.; Pressler, R.; Nguyen, Y.; Hooper, R. Non-expert use of the cerebral function monitor for
neonatal seizure detection. Arch. Dis. Child. Fetal. Neonatal. Ed. 2004, 89, F37–F40. [CrossRef] [PubMed]
35. Appendino, J.P.; McNamara, P.J.; Keyzers, M.; Stephens, D.; Hahn, C.D. The impact of amplitude-integrated electroencephalogra-
phy on NICU practice. Can. J. Neurol. Sci. 2012, 39, 355–360. [CrossRef] [PubMed]
36. Temko, A.; Lightbody, G. Detecting Neonatal Seizures With Computer Algorithms. J. Clin. Neurophysiol. 2016, 33, 394–402.
[CrossRef] [PubMed]
37. Liu, A.; Hahn, J.S.; Heldt, G.P.; Coen, R.W. Detection of neonatal seizures through computerized EEG analysis. Electroencephalogr.
Clin. Neurophysiol. 1992, 82, 30–37. [CrossRef]
38. Gotman, J.; Flanagan, D.; Zhang, J.; Rosenblatt, B. Automatic seizure detection in the newborn: Methods and initial evaluation.
Electroencephalogr. Clin. Neurophysiol. 1997, 103, 356–362. [CrossRef]
39. Mathieson, S.R.; Stevenson, N.J.; Low, E.; Marnane, W.P.; Rennie, J.M.; Temko, A.; Lightbody, G.; Boylan, G.B. Validation of an
automated seizure detection algorithm for term neonates. Clin. Neurophysiol. 2016, 127, 156–168. [CrossRef]
40. Temko, A.; Boylan, G.; Marnane, W.; Lightbody, G. Robust neonatal EEG seizure detection through adaptive background
modeling. Int. J. Neural. Syst. 2013, 23, 1350018. [CrossRef]
41. Stevenson, N.J.; Clancy, R.R.; Vanhatalo, S.; Rosén, I.; Rennie, J.M.; Boylan, G.B. Interobserver agreement for neonatal seizure
detection using multichannel EEG. Ann. Clin. Transl. Neurol. 2015, 2, 1002–1011. [CrossRef] [PubMed]
42. Sharpe, C.; Davis, S.L.; Reiner, G.E.; Lee, L.I.; Gold, J.J.; Nespeca, M.; Wang, S.G.; Joe, P.; Kuperman, R.; Gardner, M.; et al.
Assessing the Feasibility of Providing a Real-Time Response to Seizures Detected With Continuous Long-Term Neonatal
Electroencephalography Monitoring. J. Clin. Neurophysiol. 2019, 36, 9–13. [CrossRef] [PubMed]
43. Pavel, A.M.; Rennie, J.M.; de Vries, L.S.; Blennow, M.; Foran, A.; Shah, D.K.; Pressler, R.M.; Kapellou, O.; Dempsey, E.M.;
Mathieson, S.R.; et al. A machine-learning algorithm for neonatal seizure recognition: A multicentre, randomised, controlled trial.
Lancet. Child. Adolesc. Health 2020, 4, 740–749. [CrossRef]
44. De Vries, L.S.; Groenendaal, F.; van Haastert, I.C.; Eken, P.; Rademaker, K.J.; Meiners, L.C. Asymmetrical myelination of the
posterior limb of the internal capsule in infants with periventricular haemorrhagic infarction: An early predictor of hemiplegia.
Neuropediatrics 1999, 30, 314–319. [CrossRef]
45. Hutchinson, E.A.; De Luca, C.R.; Doyle, L.W.; Roberts, G.; Anderson, P.J. School-age outcomes of extremely preterm or extremely
low birth weight children. Pediatrics 2013, 131, e1053–e1061. [CrossRef]
46. Odding, E.; Roebroeck, M.E.; Stam, H.J. The epidemiology of cerebral palsy: Incidence, impairments and risk factors. Disabil.
Rehabil. 2006, 28, 183–191. [CrossRef] [PubMed]
47. Drougia, A.; Giapros, V.; Krallis, N.; Theocharis, P.; Nikaki, A.; Tzoufi, M.; Andronikou, S. Incidence and risk factors for cerebral
palsy in infants with perinatal problems: A 15-year review. Early Hum. Dev. 2007, 83, 541–547. [CrossRef] [PubMed]
48. Gruber, N.; Galijasevic, M.; Regodic, M.; Grams, A.E.; Siedentopf, C.; Steiger, R.; Hammerl, M.; Haltmeier, M.; Gizewski, E.R.;
Janjic, T. A deep learning pipeline for the automated segmentation of posterior limb of internal capsule in preterm neonates. Artif.
Intell. Med. 2022, 132, 102384. [CrossRef]
49. Valavani, E.; Blesa, M.; Galdi, P.; Sullivan, G.; Dean, B.; Cruickshank, H.; Sitko-Rudnicka, M.; Bastin, M.E.; Chin, R.F.M.;
MacIntyre, D.J.; et al. Language function following preterm birth: Prediction using machine learning. Pediatr. Res. 2022, 92,
480–489. [CrossRef]
50. Ali, R.; Li, H.; Dillman, J.R.; Altaye, M.; Wang, H.; Parikh, N.A.; He, L. A self-training deep neural network for early prediction of
cognitive deficits in very preterm infants using brain functional connectome data. Pediatr. Radiol. 2022, 52, 2227–2240. [CrossRef]
51. Balta, D.; Kuo, H.; Wang, J.; Porco, I.G.; Morozova, O.; Schladen, M.M.; Cereatti, A.; Lum, P.S.; Della Croce, U. Characterization of
Infants&rsquo; General Movements Using a Commercial RGB-Depth Sensor and a Deep Neural Network Tracking Processing
Tool: An Exploratory Study. Sensors 2022, 22, 7426.
52. Dell’Orto, V.; Nobile, S.; Correani, A.; Marchionni, P.; Giretti, I.; Rondina, C.; Burattini, I.; Palazzi, M.L.; Carnielli, V.P. Early
nasal continuous positive airway pressure failure prediction in preterm infants less than 32 weeks gestational age suffering from
respiratory distress syndrome. Pediatr. Pulmonol. 2021, 56, 3879–3886. [CrossRef]
53. Sweet, D.G.; Carnielli, V.; Greisen, G.; Hallman, M.; Ozek, E.; Te Pas, A.; Plavka, R.; Roehr, C.C.; Saugstad, O.D.; Simeoni, U.; et al.
European Consensus Guidelines on the Management of Respiratory Distress Syndrome—2019 Update. Neonatology 2019, 115,
432–450. [CrossRef]
54. Lee, S.M.; Sie, L.; Liu, J.; Profit, J.; Lee, H.C. Evaluation of Trends in Bronchopulmonary Dysplasia and Respiratory Support
Practice for Very Low Birth Weight Infants: A Population-Based Cohort Study. J. Pediatr. 2022, 243, 47–52.e42. [CrossRef]
55. Katz-Salamon, M.; Gerner, E.M.; Jonsson, B.; Lagercrantz, H. Early motor and mental development in very preterm infants with
chronic lung disease. Arch. Dis. Child. Fetal. Neonatal. Ed. 2000, 83, F1–F6. [CrossRef]
Appl. Sci. 2023, 13, 3211 13 of 14

56. Cotten, C.M.; Oh, W.; McDonald, S.; Carlo, W.; Fanaroff, A.A.; Duara, S.; Stoll, B.; Laptook, A.; Poole, K.; Wright, L.L.; et al.
Prolonged hospital stay for extremely premature infants: Risk factors, center differences, and the impact of mortality on selecting
a best-performing center. J. Perinatol. 2005, 25, 650–655. [CrossRef] [PubMed]
57. McAleese, K.A.; Knapp, M.A.; Rhodes, T.T. Financial and emotional cost of bronchopulmonary dysplasia. Clin. Pediatr. 1993, 32,
393–400. [CrossRef] [PubMed]
58. Brady, J.M.; Zhang, H.; Kirpalani, H.; DeMauro, S.B. Living with Severe Bronchopulmonary Dysplasia-Parental Views of Their
Child’s Quality of Life. J. Pediatr. 2019, 207, 117–122. [CrossRef] [PubMed]
59. Nobile, S.; Marchionni, P.; Vento, G.; Vendettuoli, V.; Marabini, C.; Lio, A.; Ricci, C.; Mercadante, D.; Colnaghi, M.; Mosca, F.; et al.
New Insights on Early Patterns of Respiratory Disease among Extremely Low Gestational Age Newborns. Neonatology 2017, 112,
53–59. [CrossRef] [PubMed]
60. Vento, G.; Ventura, M.L.; Pastorino, R.; van Kaam, A.H.; Carnielli, V.; Cools, F.; Dani, C.; Mosca, F.; Polglase, G.; Tagliabue, P.;
et al. Lung recruitment before surfactant administration in extremely preterm neonates with respiratory distress syndrome
(IN-REC-SUR-E): A randomised, unblinded, controlled trial. Lancet Respir. Med. 2021, 9, 159–166. [CrossRef] [PubMed]
61. Ahmed, W.; Veluthandath, A.V.; Rowe, D.J.; Madsen, J.; Clark, H.W.; Postle, A.D.; Wilkinson, J.S.; Murugan, G.S. Prediction of
Neonatal Respiratory Distress Biomarker Concentration by Application of Machine Learning to Mid-Infrared Spectra. Sensors
2022, 22, 1744. [CrossRef]
62. Raimondi, F.; Migliaro, F.; Verdoliva, L.; Gragnaniello, D.; Poggi, G.; Kosova, R.; Sansone, C.; Vallone, G.; Capasso, L. Visual
assessment versus computer-assisted gray scale analysis in the ultrasound evaluation of neonatal respiratory status. PLoS ONE
2018, 13, e0202397. [CrossRef] [PubMed]
63. Laughon, M.M.; Langer, J.C.; Bose, C.L.; Smith, P.B.; Ambalavanan, N.; Kennedy, K.A.; Stoll, B.J.; Buchter, S.; Laptook, A.R.;
Ehrenkranz, R.A.; et al. Prediction of bronchopulmonary dysplasia by postnatal age in extremely premature infants. Am. J. Respir.
Crit. Care Med. 2011, 183, 1715–1722. [CrossRef] [PubMed]
64. Patel, M.; Sandhu, J.; Chou, F.S. Developing a machine learning-based tool to extend the usability of the NICHD BPD Outcome
Estimator to the Asian population. PLoS ONE 2022, 17, e0272709. [CrossRef] [PubMed]
65. Xing, W.; He, W.; Li, X.; Chen, J.; Cao, Y.; Zhou, W.; Shen, Q.; Zhang, X.; Ta, D. Early severity prediction of BPD for premature
infants from chest X-ray images using deep learning: A study at the 28th day of oxygen inhalation. Comput. Methods Programs
Biomed. 2022, 221, 106869. [CrossRef] [PubMed]
66. Dai, D.; Chen, H.; Dong, X.; Chen, J.; Mei, M.; Lu, Y.; Yang, L.; Wu, B.; Cao, Y.; Wang, J.; et al. Bronchopulmonary Dysplasia
Predicted by Developing a Machine Learning Model of Genetic and Clinical Information. Front. Genet. 2021, 12, 689071. [CrossRef]
[PubMed]
67. Leigh, R.M.; Pham, A.; Rao, S.S.; Vora, F.M.; Hou, G.; Kent, C.; Rodriguez, A.; Narang, A.; Tan, J.B.C.; Chou, F.S. Machine learning
for prediction of bronchopulmonary dysplasia-free survival among very preterm infants. BMC Pediatr. 2022, 22, 542. [CrossRef]
68. Nobile, S.; Marchionni, P.; Noviello, C.; Carnielli, V.P. Correlation between cardiorespiratory events and gastro-esophageal reflux
in preterm and term infants: Analysis of predisposing factors. Early Hum. Dev. 2019, 134, 14–18. [CrossRef]
69. Finer, N.N.; Higgins, R.; Kattwinkel, J.; Martin, R.J. Summary Proceedings From the Apnea-of-Prematurity Group. Pediatrics 2006,
117 (Suppl. S1), S47–S51. [CrossRef]
70. Eichenwald, E.C. Apnea of Prematurity. Pediatrics 2016, 137, e20153757. [CrossRef]
71. Amin, S.B.; Burnell, E. Monitoring apnea of prematurity: Validity of nursing documentation and bedside cardiorespiratory
monitor. Am. J. Perinatol. 2013, 30, 643–648. [CrossRef]
72. Varisco, G.; Peng, Z.; Kommers, D.; Zhan, Z.; Cottaar, W.; Andriessen, P.; Long, X.; van Pul, C. Central apnea detection in
premature infants using machine learning. Comput. Methods Programs Biomed. 2022, 226, 107155. [CrossRef] [PubMed]
73. Nobile, S.; Gnocchini, F.; Pantanetti, M.; Battistini, P.; Carnielli, V.P. The importance of oxygen control reaffirmed: Experience of
ROP reduction at a single tertiary care center. J. Pediatr. Ophthalmol. Strabismus. 2014, 51, 112–115. [CrossRef] [PubMed]
74. Wu, Q.; Hu, Y.; Mo, Z.; Wu, R.; Zhang, X.; Yang, Y.; Liu, B.; Xiao, Y.; Zeng, X.; Lin, Z.; et al. Development and Validation of a
Deep Learning Model to Predict the Occurrence and Severity of Retinopathy of Prematurity. JAMA Netw. Open 2022, 5, e2217447.
[CrossRef] [PubMed]
75. Redd, T.K.; Campbell, J.P.; Brown, J.M.; Kim, S.J.; Ostmo, S.; Chan, R.V.P.; Dy, J.; Erdogmus, D.; Ioannidis, S.; Kalpathy-Cramer, J.; et al.
Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity. Br. J. Ophthalmol. 2018, ahead
of print. [CrossRef]
76. Antognoli, L.; Marchionni, P.; Nobile, S.; Carnielli, V.; Scalise, L. Assessment of cardio-respiratory rates by non-invasive
measurement methods in hospitalized preterm neonates. In Proceedings of the 2018 IEEE International Symposium on Medical
Measurements and Applications (MeMeA), Rome, Italy, 11–13 June 2018; pp. 1–5.
77. Vats, V.; Nagori, A.; Singh, P.; Dutt, R.; Bandhey, H.; Wason, M.; Lodha, R.; Sethi, T. Early Prediction of Hemodynamic Shock in
Pediatric Intensive Care Units With Deep Learning on Thermal Videos. Front. Physiol. 2022, 13, 862411. [CrossRef] [PubMed]
78. Lyra, S.; Rixen, J.; Heimann, K.; Karthik, S.; Joseph, J.; Jayaraman, K.; Orlikowsky, T.; Sivaprakasam, M.; Leonhardt, S.; Hoog
Antink, C. Camera fusion for real-time temperature monitoring of neonates using deep learning. Med. Biol. Eng. Comput. 2022, 60,
1787–1800. [CrossRef]
79. Son, J.; Kim, D.; Na, J.Y.; Jung, D.; Ahn, J.-H.; Kim, T.H.; Park, H.-K. Development of artificial neural networks for early prediction
of intestinal perforation in preterm infants. Sci. Rep. 2022, 12, 12112. [CrossRef]
Appl. Sci. 2023, 13, 3211 14 of 14

80. Han, J.H.; Yoon, S.J.; Lee, H.S.; Park, G.; Lim, J.; Shin, J.E.; Eun, H.S.; Park, M.S.; Lee, S.M. Application of Machine Learning
Approaches to Predict Postnatal Growth Failure in Very Low Birth Weight Infants. Yonsei Med. J. 2022, 63, 640–647. [CrossRef]
81. Althnian, A.; Almanea, N.; Aloboud, N. Neonatal Jaundice Diagnosis Using a Smartphone Camera Based on Eye, Skin, and
Fused Features with Transfer Learning. Sensors 2021, 21, 7038. [CrossRef]
82. Guedalia, J.; Farkash, R.; Wasserteil, N.; Kasirer, Y.; Rottenstreich, M.; Unger, R.; Grisaru Granovsky, S. Primary risk stratification
for neonatal jaundice among term neonates using machine learning algorithm. Early Hum. Dev. 2022, 165, 105538. [CrossRef]
83. Walsh, V.; Oddie, S.; McGuire, W. Ethical Issues in Perinatal Clinical Research. Neonatology 2019, 116, 52–57. [CrossRef]
84. Alvarez-Fuente, M.; Arruza, L.; Muro, M.; Zozaya, C.; Avila, A.; López-Ortego, P.; González-Armengod, G.; Torrent, A.; Luis
Gavilán, J.; del Cerro, M.J. The economic impact of prematurity and bronchopulmonary dysplasia. Eur. J. Pediatr. 2017, 176,
1587–1593. [CrossRef] [PubMed]
85. Pinto, F.; Fernandes, E.; Virella, D.; Abrantes, A.; Neto, M.T. Born Preterm: A Public Health Issue. Port. J. Public Health 2019, 37,
38–49. [CrossRef]
86. Zejin Ou, Z.; Yu, D.; Liang, Y.; He, H.; He, W.; Li, Y.; Zhang, M.; Gao, Y.; Wu, F.; Chen, Q. Yongzhi LiGlobal trends in incidence and
death of neonatal disorders and its specific causes in 204 countries/territories during 1990–2019. BMC Public Health 2022, 22, 360.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.