Current Applications of Artificial Intelligence in the Neonatal Intensive Care Unit

1. Introduction

During the last decades, artificial intelligence (AI) has been introduced in several aspects of human life, including the healthcare industry [1]. AI refers to computer algorithms that replicate the cognitive function of humans, using specified operational models produced from the statistical assessments of big data sets [2].

Machine learning (ML) and deep learning (DL) are subsets of AI that have been widely applied to the healthcare industry [3]. ML uses both unstructured data that are difficult to arrange using predetermined structures (e.g., clinical notes), as well as structured data that are easily organized into predefined structures. Furthermore, ML models generate software algorithms to develop AI decision-support systems [3]. The majority of these systems are created using standard algorithms, which consistently produce the same outcome for a given input, and thus, decision-support systems help healthcare professionals analyze enormous amounts of information [4,5,6]. Unlike this broader definition of ML, the fundamental idea behind DL is derived from the neural networks of the human brain that process and interpret information. To simulate this process, DL uses artificial neurons in a computer neural network, and when the number of layers is large (i.e., deep) simulates more intricate links between input and output [7,8]. By training, the network gradually obtains increasingly complex data representations. Finally, natural language processing is an AI technology that aids computers in comprehending and interpreting human language, organizing clinical notes and unstructured data, and thus, enabling better decision-making [9,10].

In this narrative review, we aim to present the current application of AI in the neonatal intensive care unit (NICU) and explore its future perspectives.

2. Application of Artificial Intelligence in Neonatology

2.1. Neurocritical Care

The previous decades have seen increased research on the neuromonitoring of critically ill neonates, thanks to the advancements in AI. AI, and especially ML, has made it possible for computer systems to examine and analyze massive amounts of data, including medical patterns, mainly applied to the electroencephalogram (EEG) and magnetic resonance imaging (MRI) [11].

2.1.1. Electroencephalography

Seizures are the most common neurological emergency in the neonatal population, and most likely occur during the first days of life [12]. Seizures are more common in neonates born at less than 30 and more than 36 weeks of gestation, with the frequency of seizures in neonates estimated to be around 8% [12]. Additionally, evidence suggests that treating seizures early on enhances the patient's response to medication [13], while it is well known that recurrent seizures are linked to worse long-term neurodevelopmental outcomes, regardless of the underlying cause [14,15]. Seizures are particularly difficult to diagnose in the neonatal population because they can be difficult to distinguish from normal infant movements even when they do occur, or they can be limited to electrographic episodes [16]. Although neonatal seizures need to be treated right away, it can be extremely challenging to recognize, since up to 85% of neonatal seizures may not have any clear clinical symptoms.

In the NICU, EEG has emerged as a crucial component of neurocritical care, as it is crucial to identify neonatal seizures and allows the distinction between epileptic seizures and nonepileptic episodes [17]. Additionally, EEG monitoring helps uncouple clinical and EEG seizures after antiseizure treatment [18], detecting the electrical discharge that may persist after therapy, while the clinical manifestation of the seizure that may have existed before treatment disappeared. EEG records non-invasively the electrical activity of the cerebral cortex allowing for the real-time evaluation of cortical background function; however, real-time review and implementation of EEG can be challenging. Moreover, continuous EEG (cEEG) increases the diagnostic and prognostic potential, since it allows the evaluation of the background activity over time [19]. Thus, cEEG monitoring is the recommended standard of care for identifying and treating all seizures quickly [20,21]. Due to the challenges in acquiring traditional EEG, NICUs have currently adopted a less precise but more straightforward method of EEG monitoring, the amplitude-integrated EEG (aEEG). As opposed to cEEG monitoring, aEEG is a bedside device that shows one or two channels of filtered, smoothed, and quantitatively converted EEG data, while the cortical electrical activity is compressed in duration and converted in a semi-logarithmic chart [22,23]. However, aEEG does not have an ideal sensitivity, specificity, and interobserver agreement for identifying seizures [24], and thus, it is recommended to serve as an adjunct to cEEG monitoring [19,25].

During the past few decades, research in AI, and particularly DL, has evolved in the field of the creation of automatic seizure detection algorithms [26]. These algorithms exhibit remarkable seizure detection accuracy, comparable to that of human specialists [27]. In 1992, Liu et al. proposed a computerized detection system for neonatal seizures, and thereafter, numerous methods have been documented, refined, and verified [28]. The performance of the initial automatic seizure detection algorithms was suboptimal for therapeutic use as they had been created by modifying algorithms intended for adult users [28,29]; however, to date many seizure detection algorithms have been developed mainly for full-term but also preterm neonates [30]. The development of these algorithms requires the labeling of seizures by several specialists as well as obtaining enough data for testing, training, and validation.

In 2020, a randomized clinical trial assessing the effect of ML on the real-time identification of neonatal seizures in a NICU was published [31]. According to that report, more seizures were recognized in real-time, when AI algorithms were applied in the NICU [31]. Following extensive training and offline analysis, the accuracy of the recognition of electrographic seizures both with and without the automatic seizure detection algorithms was tested in a multicenter clinical trial, suggesting that the algorithm could serve as a bebside tool in clinical practice [32,33]. The model greatly enhanced the recognition of seizure hours, even though the set aim of improving the detection of specific neonates with seizures was not fulfilled.

In addition to monitoring and treating newborn seizures, EEG is also a valuable diagnostic tool for neonatal encephalopathy, namely hypoxic-ischemic encephalopathy (HIE). AI research is being conducted to create algorithms, many of which use DL techniques, that can evaluate brain maturation, estimate sleep stages [34], and grade background EEG patterns in HIE [35]. Automated EEG interpretation based on ML technology has recently shown good performance in detecting HIE severity and can be helpful in the early severity grading of neonatal HIE [36,37]. Such an example of advanced signal processing included the convolutional neural network structures, which can self-extract convolutional features from raw EEGs [35]. Besides, the possible application of AI in predictive modeling for electrographic seizures in newborns with HIE was examined by Pavel et al., with the goal of early detection of infants most at risk of recurrent seizures [38]. ML algorithms were created for clinical and both qualitative and quantitative EEG characteristics. Notably, both the automated quantitative EEG analysis and the analysis carried out by a skilled neurophysiologist (qualitative) increased the predictive value of these models by incorporating clinical data. These studies highlight the possibility of using ML in evaluating the EEG background of neonates with HIE.

2.1.2. Magnetic Resonance Imaging

The application of AI to enhance the utility and inference from brain MRI has advanced significantly during the last few years. Technical advancements in AI techniques include methods to reduce movement artifact effects and boost information yield, as well as advancements in tissue classification [39]. These have made it possible for a deeper evaluation of the developing brain, and a new understanding of the effects of prenatal events on structural and functional network topologies [40].

One of the regions in the neonatal brain where myelination starts is the posterior limb of the internal capsule (PLIC). Crucially, both term and preterm newborns' neurological outcomes depend on the proper and timely maturation of the PLIC. Abnormalities in the PLIC detected on MRI have been linked to hemiplegia, and worse neurodevelopmental outcomes [41]. Over the past few decades, there has been a noticeable rise in the prevalence of cerebral palsy to over 2.0 per 1000 live births, which is inversely proportional to the gestational age and carries significant lifetime burdens [42,43]. An ML algorithm for the automated segmentation and quantification of the PLIC in preterm newborns undergoing MRI was proposed in a recent work [44], where authors demonstrated good accuracy for the ML model when compared to expert analysis, indicating the successful application of their algorithm to a large dataset. Although promising, it is necessary to evaluate how well this approach will work in clinical settings.

Identifying neuroanatomic phenotypes and predicting the outcome are the major areas in the clinical domain where AI is facilitating innovation. Preterms are characterized by a specific phenotype including abnormal brain development, cerebral palsy, autism spectrum disorder, attention deficit hyperactivity disorder, psychiatric illness, and issues with language, behavior, and socioemotional functions [45]. Abnormalities of structural and functional networks are frequent in preterm neonates as they have been obtained from structural, diffusion, and functional MRI [46]. Models that combine data from two or more imaging modalities into a single framework, can reveal previously unknown patterns of neuroanatomic variants in preterm neonates that are related to cognitive and motor outcomes [47]. Diffusion tensor metrics, neurite orientation dispersion, regional volumes, and density imaging measurements are among the several forms of MRI data that are integrated into a single model to compute morphometric similarity networks [48]. This kind of research helps identify the neural roots of cognition and behavior, identify the networks that most contribute to atypical brain development, and examine the drivers of brain dysmaturation and resilience.

Current research also aims to compare traditional computer vision approaches with efficient networks that generate reliable and accurate segmentation. To evaluate methods for segmenting newborn tissue, T1W, and T2W pictures were provided with manually segmented structures; segmenting myelinated from unmyelinated white matter is, nevertheless, still challenging [49]. The limited number of high-quality labeled data must also be acknowledged as a key limitation when comparing earlier attempts on newborn brain segmentation [50].

2.2. Respiratory System

One of the main causes of infant mortality and morbidity in preterm deliveries is bronchopulmonary dysplasia (BPD). Although several biomarkers have been associated with the emergence of respiratory distress syndrome (RDS), there are currently no meaningful prenatal diagnostic tests for BPD [51]. In a previous study, Ahmed et al. evaluated an ML technique also suitable for the analysis of other biological materials and created a helpful bedside point-of-care test approach for neonatal RDS [52]. According to the authors’ findings, following clinical validation, the use of ML-guided devices that can measure RDS biomarkers in real time may be used to direct therapies for preterm infants exhibiting respiratory symptoms. Moreover, Raimondi et al. concentrated on AI-assisted analysis of lung ultrasonography and its capacity to correlate with respiratory status in critically ill neonates with RDS [53]. The authors constructed a dataset of scans for texturing and a correlation between the oxygenation status, the ultrasound findings, and the mean grayscale intensity was established by an ML model. They enrolled a cohort of neonates of different origins and varying degrees of respiratory distress, and they demonstrated a significant correlation between blood gas indices and the grayscale ML analysis [53]; however, the relatively small sample size, the heterogeneous etiology of the respiratory distress, and the variable postnatal age suggested that further research on this topic with larger datasets is warranted.

Regarding BPD, Dai et al. investigated the combination of genetic and clinical factors, where exome sequencing was carried out for preterm neonates and integrated with clinical aspects [54]. The authors demonstrated that by using ML for the genomic analysis they could predict the development of BPD with an accuracy of 90% [54]. Also, the combination of gastric aspirate after birth and clinical information analysis could predict BPD development with a sensitivity of 88% [51]. Besides, Leigh et al., in a retrospective analysis of the perinatal and the respiratory factors in a sample of preterm neonates, created an ML algorithm that, after testing and training, could predict BPD-free survival well in terms of accuracy [55]. An AI approach has been proposed using DL and image segmentation, that can predict the severity of BPD by analyzing the segmentation of the lungs in chest X-ray taken on the 28th day of oxygen delivery [56]. The benefits of the aforementioned algorithm included non-invasiveness, speed, and independence from the experience of neonatologists, whereas demonstrated strong prediction performance.

Moreover, research on BPD with ML predictive models has shown that long-term invasive ventilation is one of the most significant risk factors for BPD and longer hospital stays. ML models using long-term invasive ventilation data could predict extubation failure with significant accuracy [57,58,59]. The risk stratification for BPD is a specific area of interest, aiming to identify infants who may benefit from preventive measures like corticosteroids or treatment for specific morbidities such as patent ductus arteriosus (PDA). The BPD Outcome Estimator is a predictive tool approved by the US National Institute of Child Health and Human Development useful in directing steroid treatment and family counseling [60]. The estimator was initially limited to White, Black, or Hispanic neonates, however, Patel et al. recently created a a web application based on an ML system for extremely preterm neonates of Asian descent [61]. Nonetheless, the study's conclusions were limited because the method was tested on a small dataset, requiring further comprehensive and prospective validation before being used in clinical practice.

Apnea of prematurity, another common morbidity in preterm neonates, is either obstructive (caused by airway obstruction), central (caused by cessation of respiratory drive), or mixed (a combination of both). Bedside monitors are programmed to sound an alarm when detect a decreased respiratory effort due to a decrease in thoracic motion [62]. A substantial number of false positive episodes have been observed in clinical tests indicating that this approach can identify central apneas with suboptimal accuracy [63]. Varisco et al. created an ML-based improved apnea detection model to automatically identify real apnea using data from the electrocardiographic monitoring of neonates [64]. The authors concluded that the AI algorithm resulted in better detection of apneas compared to traditional approaches with fewer false alarms, and they also showed that breathing patterns were altered more often in neonates with more frequent central apneas [64]. Although AI may drastically alter routine clinical practice, given that alarm fatigue is a growing problem in NICUs putting neonates in danger of missing alarms, the lack of external validation, along with the small sample size represents serious flaws in the suggested methodology.

2.3. Ophthalmology

ML models have been also applied is retinopathy of prematurity (ROP), which is a severe complication of prematurity and a major cause of childhood blindness in high- and middle-income countries. ROP affects mainly extremely preterm (less than 28 weeks), very preterm (28-32 weeks), or very low-birthweight (1500 g) neonates [65]. Telemedicine and AI are being considered as potential diagnostic tools for ROP, given the dearth of ophthalmologists who can treat neonates with ROP. Gaussian mixture models are among several ML techniques, to diagnose and categorize ROP from retinal fundus pictures [65,66]. In a previous study, the i-ROP system was shown to have a 95% accuracy in classifying pre-plus and plus illness. This performance was significantly better than the performance achieved by nonexperts (81%) and comparable to that achieved by experts (92% to 96%) [66].

Furthermore, a DL automated score model was generated in a recent multicenter trial, to identify one of the features of the affected retina [67]. This study showed how a DL comprehensive screening platform may enhance screening accessibility and objective ROP diagnosis. In another large-scale multicenter trial, a different group of scientists created a DL method for predicting ROP and its severity [68]. Retinal images from the initial ROP screening and neonatal clinical risk variables were obtained to develop an AI predictive algorithm. When compared to the traditional ROP score, the DL-based system demonstrated comparable accuracy, while it was found more effective in identifying and interpreting abnormal signs than the classical ophthalmoscopy.

Moreover, in previous studies, telemedicine has been compared with Binocular Indirect Ophthalmoscope, demonstrating that both techniques are equally sensitive in detecting zone disease, plus disease, and ROP, although Binocular Indirect Ophthalmoscope was more accurate in recognizing zone III and stage 3 ROP [69,70]. Besides, using DL algorithms, the accuracy of ROP examination was 94% for normal diagnosis and 98% for illness and diagnosis, outperforming ROP experts [71]. Finally, in previous studies, DL algorithms were constructed to estimate the clinical progression of the ROP by assigning vascular severity scores [72] or detect disease requiring therapy with an accuracy of 98% [73]. Overall, introducing AI into ROP screening programs might improve access to care for secondary ROP prevention [73]; however, despite the encouraging results, more extensive external validation using additional multicenter datasets is necessary. Additionally, the development of more advanced ML algorithms may be able to provide more significant prognostic information regarding the accurate staging, zone, and disease.

2.4. Vital Signs

In previous studies, ML analysis has been developed to analyze physiologic data that are electronically captured as signal data to identify artifact patterns [74], predict neonatal morbidity [75], or identify late-onset sepsis [76]. An ML algorithm using electronically recorded vital signs within the first three hours of life, including heart rate and respiration rate of preterm neonates with a birth weight ≤2000 grams and gestational age ≤34 weeks predicted overall morbidity with an accuracy of 91% [75]. Furthermore, Lyra et al. developed DL-based techniques that could result in a reliable, real-time assessment of crucial indicators, such as changes in body temperature [77]. Although the analysis proved difficult for several factors during the recording, the authors demonstrated the viability of using inexpensive, embedded graphics processing units to monitor neonates' temperatures in real-time, although more research is warranted to broaden the application of this technique in clinical settings [77].

2.5. Gastrointestinal System

Recently, an AI algorithm was created based on a large dataset about the clinical characteristics of neonates who developed intestinal perforation [78]. The suggested algorithm evaluated various clinical data, including vital signs, radiologic findings, biomarkers, and laboratory results, and led to a more accurate and early prediction of intestinal perforation of preterm neonates compared to all other traditional ML methods [78]. Furthermore, regarding nutrition, a previous study in England demonstrated that ML techniques can be used to evaluate nutritional practices that were found to be associated with body weight on discharge and the development of BPD [79]. Finally, Han et al. recently examined the potential application of AI to predict postnatal growth failure. Using a large dataset of very low birth weight neonates from several NICUs, ML models were created using a variety of methodologies, showing a strong predictive performance [80]. Nevertheless, the study's findings were limited since it lacked crucial information about enteral and parenteral feeding.

2.6. Jaundice

The application of ML and DL models was explored in a previous study investigating the potential of using a dataset made up of photos taken using a smartphone camera for the identification of neonatal jaundice in term and late preterm neonates. The authors used data from pictures of the skin and eyes to train a neural network to identify jaundice [81]. Furthermore, Guardalia et al. used an ML approach to analyze clinical data for a large neonatal population in order to develop a risk assessment tool for neonatal jaundice that did not rely on bilirubin readings, that performed well in the risk categorization of newborn jaundice [82].

2.7. Sepsis

Early and late-onset neonatal sepsis is a major cause of infant mortality and morbidity [83]. Diagnosing neonatal sepsis and starting antibiotics is challenging in clinical practice, which emphasizes the need for a comprehensive approach. Previous studies have explored the role of heart rate variability in predicting early-onset sepsis with an accuracy of 64–94% [84]. Also, regarding the detection of late-onset sepsis, ML decision algorithms have utilized clinical and laboratory biomarkers obtaining an optimal accuracy and a mean precision rate of 0.82 3 hours before the onset of sepsis [76].

2.8. Patent Ductus Arteriosus

The ductus arteriosus which is patent during the intrauterine life may have significant hemodynamic consequences in preterm neonates and is associated with higher rates of morbidity and mortality. Therefore, it should be assessed whether closing the PDA could increase survival chances relative to the risk of side effects [85]. ML techniques have been developed for the detection of PDA from electronic health records [86] and auscultation records [87]. This resulted in an accuracy of 76% for the prediction of PDA in very low birth weight infants based on the analysis of 47 perinatal factors using 5 different ML techniques [86] and 74% for the analysis of 250 auscultation records [87].

2.9. Neurodevelopmental Outcome

ML techniques have been widely used for the neurodevelopmental evaluation and follow-up of preterm neonates. Numerous studies used ML techniques to examine brain connections [88,89,90,91], brain structure analysis, and brain segmentation in preterm neonates [92,93]. Evidence suggests an association between lower brain volume, cortical folding, axonal integrity, and microstructural connectivity with preterm birth [94,95]. Additional effects of prematurity on the developing connectome have been found in studies examining functional markers of brain maturation [91,96].

Neurocognitive assessments are among the most significant domains of neurodevelopment outcomes at two years of age. Previous studies assessed how the brain's morphological alterations relate to neurocognitive outcomes [97,98,99] and the prediction of brain age [100]. It has been demonstrated that multivariate models combining near-term structural MRI findings and white matter microstructure on diffusion tensor imaging may help identify preterm neonates at risk for language impairment and guide early intervention [97,99]. Moreover, to predict neurodevelopmental impairment at two years of age, a self-training deep neural network model has been suggested, using MRI data obtained in very preterm neonates at term-equivalent age [101]. Besides, according to a study that used ML techniques to assess the impact of PPAR gene activity on brain development, a significant correlation was found between aberrant brain connectivity and PPAR gene signaling's role in aberrant white matter development [102].

ML models have been used to evaluate the association of the developmental outcome regarding language skills with the near-term MRI findings in previous studies. By examining MRI characteristics and perinatal clinical data, Valavani et al. employed ML to predict language skills at two years of corrected age in preterm neonates [103]. Language delay could be accurately predicted by delayed myelination patterns and specific clinical characteristics. The authors concluded that ML models could be useful for healthcare services and enhance the long-term outcomes of preterm neonates. Furthermore, in a recent study, Balta et al. proposed an AI-based automated monitoring of newborns' general motions, a crucial screening test for detecting neuromotor problems in children [104]. The authors created an automated model to analyze infants' overall motions, by processing videos taken with a simple camera at home. Certain patterns of spontaneous movements, such as the absence of fidgety movements or the presence of predominately contracted coordinated movements, were particularly indicative in predicting cerebral palsy in infants between the ages of 3 and 5 months of age. [104].

2.10. Mortality

Even with the recent advances in neonatal care, preterm neonates are still very vulnerable to death because of their immature organ systems, [105]. ML models have been developed for the prediction of neonatal mortality by exploring causative factors [106,107]. A recent review including term and preterm neonates between the gestational ages of 22 and 40 weeks reported that neural networks, random forests, and logistic regression were common models developed by the investigators [108]. Among the included studies, only two studies finished external validation, five studies published calibration plots, five studies reported sensitivity and specificity of their models that ranged from 63 to 80% and 78 to 98% respectively, and eight reported accuracy that ranged from 58.3 to 97.0% [108]. Despite having 17 features, the best model overall was linear regression analysis [108]. Recent studies exploring the application of AI models in severely low birthweight and preterm neonatal populations reported an accuracy of 68.9-93.3% [109,110]. Among the several limitations of these studies was the lack of inclusion of vital parameters to depict dynamic changes, while gestational age, birth weight, and Apgar scores were the most significant variables in the models [111,112]. These limitations suggest that further implementation, calibration, and external validation of AI healthcare applications is warranted in future studies.

3. Limitations and Future Perspectives

AI has been currently established as a useful component in several parts of neonatal care, to help physicians to provide improved, more effective, and safer care (Table 1). However, specific issues need to be addressed before the wide application of AI models. At first, healthcare providers need to improve their digital literacy, so that they can comprehend the fundamental principles and limitations of AI. That would help healthcare providers evaluate recently created AI tools and focus on their appropriate and safe application in clinical settings. Also, to develop and implement AI tools, cross-disciplinary, worldwide collaborations involving data scientists, computer scientists, healthcare providers, attorneys, and legislators are required. Additional drawbacks of AI include the lack of larger datasets to train the models, the heterogeneity of the data, generalizability problems, the lack of evidence-based guidelines for some diseases affecting neonates, and the cost. Applying AI to newborn care also involves addressing critical challenges such as the model's interpretability, the necessity of external validation to improve generalizability, and the necessity of appropriate evaluation of performance (Table 2).

Finally, there are serious ethical issues to be considered. Important decisions in neonatology are often accompanied by a complex and difficult ethical component, and multidisciplinary methods are necessary for advancement [113]. Informed consent, bias, safety, privacy of the patients, and allocation are among the ethical issues with AI applications in healthcare [114]. The use of AI in neonatology has become more challenging due to the necessary transparency, viability limitations, life-sustaining therapies, and various international restrictions [115]. To date, there hasn't been any reporting on how an ethics framework would be applied in neonatology yet.

4. Conclusions

AI is becoming more and more important in healthcare services following our contemporary culture that moves toward automated decision support systems. The main advantage of using AI in healthcare is its ability to evaluate large volumes of medical data from multidisciplinary studies. This type of data is too complex for medical professionals to study quickly enough to find the diagnosis and determine a treatment plan. When trained with the right data, AI models function like human neurons and can quickly and accurately solve problems. Finding the appropriate treatment strategy requires accuracy and time, especially in intensive care units. When integrating AI models into NICU clinical practices including treatment and transport, trust is a crucial component. AI-based solutions can be used in NICUs mainly to confirm the current treatment plans rather than implement their recommendations. The current evidence regarding the application of AI in neonatology is encouraging, however, further research is warranted including retraining clinical trials and validating the outcomes to make AI algorithms more useful in the future.