Bronchopulmonary dysplasia predicted at birth by artificial intelligence

Artificial Intelligence in Pediatrics: Learning to Walk Together

In this era of rapidly advancing technology, artificial intelligence (AI) has emerged as a transformative force, even being called the Fourth Industrial Revolution, along with gene editing and robotics. While it has undoubtedly become an increasingly important part of our daily lives, it must be recognized that it is not an additional tool, but rather a complex concept that poses a variety of challenges. AI, with considerable potential, has found its place in both medical care and clinical research. Within the vast field of pediatrics, it stands out as a particularly promising advancement. As pediatricians, we are indeed witnessing the impactful integration of AI-based applications into our daily clinical practice and research efforts. These tools are being used for simple to more complex tasks such as diagnosing clinically challenging conditions, predicting disease outcomes, creating treatment plans, educating both patients and healthcare professionals, and generating accurate medical records or scientific papers. In conclusion, the multifaceted applications of AI in pediatrics will increase efficiency and improve the quality of healthcare and research. However, there are certain risks and threats accompanying this advancement including the biases that may contribute to health disparities and, inaccuracies. Therefore, it is crucial to recognize and address the technical, ethical, and legal challenges as well as explore the benefits in both clinical and research fields.

Prediction of bronchopulmonary dysplasia in very preterm infants: competitive risk model nomogram

Objective

To develop predictive clinical models of bronchopulmonary dysplasia (BPD) through competing risk analysis.

Methods

Retrospective observational cohort study, including preterm newborns ≤32 weeks gestational age, conducted between January 1, 2013 and September 30, 2022 in a third-level Neonatal Intensive Care Unit in Spain. A prediction study was carried out using competing risk models, where the event of interest was BPD and the competing event was death. A multivariate competing risk model was developed separately for each postnatal day (days 1, 3, 7 and 14). Nomograms to predict BPD risk were developed from the coefficients of the final models and internally validated.

Results

A total of 306 patients were included in the study, of which 73 (23.9%) developed BPD and 29 (9.5%) died. On day 1, the model with the greatest predictive capacity was that including birth weight, days since rupture of membranes, and surfactant requirement (area under the receiver operating characteristic (ROC) curve (AUC), 0.896; 95% CI, 0.792-0.999). On day 3, the final predictive model was based on the variables birth weight, surfactant requirement, and Fraction of Inspired Oxygen (FiO2) (AUC, 0.891; 95% CI, 0.792-0.989).

Conclusions

Competing risk analysis allowed accurate prediction of BPD, avoiding the potential bias resulting from the exclusion of deceased newborns or the use of combined outcomes. The resulting models are based on clinical variables measured at bedside during the first 3 days of life, can be easily implemented in clinical practice, and can enable earlier identification of patients at high risk of BPD.

Bridging the Gap: Exploring Bronchopulmonary Dysplasia through the Lens of Biomedical Informatics

Bronchopulmonary dysplasia (BPD), a chronic lung disease predominantly affecting premature infants, poses substantial clinical challenges. This review delves into the promise of biomedical informatics (BMI) in reshaping BPD research and care. We commence by highlighting the escalating prevalence and healthcare impact of BPD, emphasizing the necessity for innovative strategies to comprehend its intricate nature. To this end, we introduce BMI as a potent toolset adept at managing and analyzing extensive, diverse biomedical data. The challenges intrinsic to BPD research are addressed, underscoring the inadequacies of conventional approaches and the compelling need for data-driven solutions. We subsequently explore how BMI can revolutionize BPD research, encompassing genomics and personalized medicine to reveal potential biomarkers and individualized treatment strategies. Predictive analytics emerges as a pivotal facet of BMI, enabling early diagnosis and risk assessment for timely interventions. Moreover, we examine how mobile health technologies facilitate real-time monitoring and enhance patient engagement, ultimately refining BPD management. Ethical and legal considerations surrounding BMI implementation in BPD research are discussed, accentuating issues of privacy, data security, and informed consent. In summation, this review highlights BMI's transformative potential in advancing BPD research, addressing challenges, and opening avenues for personalized medicine and predictive analytics.

The past, current, and future of neonatal intensive care units with artificial intelligence: a systematic review

Machine learning and deep learning are two subsets of artificial intelligence that involve teaching computers to learn and make decisions from any sort of data. Most recent developments in artificial intelligence are coming from deep learning, which has proven revolutionary in almost all fields, from computer vision to health sciences. The effects of deep learning in medicine have changed the conventional ways of clinical application significantly. Although some sub-fields of medicine, such as pediatrics, have been relatively slow in receiving the critical benefits of deep learning, related research in pediatrics has started to accumulate to a significant level, too. Hence, in this paper, we review recently developed machine learning and deep learning-based solutions for neonatology applications. We systematically evaluate the roles of both classical machine learning and deep learning in neonatology applications, define the methodologies, including algorithmic developments, and describe the remaining challenges in the assessment of neonatal diseases by using PRISMA 2020 guidelines. To date, the primary areas of focus in neonatology regarding AI applications have included survival analysis, neuroimaging, analysis of vital parameters and biosignals, and retinopathy of prematurity diagnosis. We have categorically summarized 106 research articles from 1996 to 2022 and discussed their pros and cons, respectively. In this systematic review, we aimed to further enhance the comprehensiveness of the study. We also discuss possible directions for new AI models and the future of neonatology with the rising power of AI, suggesting roadmaps for the integration of AI into neonatal intensive care units.

Can we balance early exogenous surfactant therapy and non-invasive respiratory support to optimise outcomes in extremely preterm infants? A nuanced review of the current literature

Therapeutic advances have significantly improved the survival of premature infants. However, a high burden of bronchopulmonary dysplasia (BPD) persists. Aiming at prevention of neonatal lung injury, continuous positive airway pressure (CPAP) and non-invasive ventilation (NIV) strategies have replaced mechanical ventilation for early respiratory support and treatment of respiratory distress syndrome. Multiple randomised controlled trials have demonstrated that broad application of CPAP/NIV decreases exposure to mechanical ventilation and reduces rates of BPD. Here, we explore why this treatment effect is not larger. We discuss that today's neonatal intensive care unit population evolving from the premature to the extremely premature infant demands better targeted therapy, and indicate how early and accurate identification of preterm infants likely to fail CPAP/NIV could increase the treatment effect and minimise the potential harm of delaying exogenous surfactant therapy in these infants. Finally, we argue that less invasive modes of surfactant administration may represent both a pragmatic and beneficial approach in combining CPAP/NIV and early surfactant. Beneficial treatment effects might be higher than reported in the literature when targeting this approach to preterm infants suffering from respiratory failure primarily due to surfactant deficiency. Considering ongoing limitations of current approaches and focusing both on prospects and potential harm of modified strategies, this commentary ultimately addresses the need and the challenge to prove that pushing early CPAP/NIV and strategies of early and less invasive surfactant application prevents lung injury in the long term.

Neonatal sequential organ failure assessment score within 72 h after delivery reliably predicts bronchopulmonary dysplasia in very preterm infants

Background

The neonatal sequential organ failure assessment (nSOFA) score is an operational definition of organ dysfunction employed to predict sepsis-associated mortality. However, the relationship between the nSOFA score and bronchopulmonary dysplasia (BPD) has not been investigated clearly. This study evaluates whether the nSOFA score within 72 h after delivery could be used to predict the occurrence of BPD in very preterm infants.

Methods

In this retrospective, single-center cohort study, preterm infants born between 2019 and 2021 were investigated, the nSOFA score was calculated from medical records after admission to the neonatal intensive care unit (NICU) within 72 h after delivery, and the peak value was used for calculation. A logistic regression model was used to evaluate the relationship between the nSOFA score and BPD. Propensity score matching and subgroup analysis were performed to verify the reliability of the results.

Results

Of 238 infants meeting the inclusion criteria, 93 infants (39.1%) were diagnosed with BPD. The receiver operating characteristic curve of the nSOFA score in predicting BPD was 0.790 [95% confidence interval (CI): 0.731-0.849]. The logistic regression model showed that an increment of one in the nSOFA score was related to a 2.09-fold increase in the odds of BPD (95% CI: 1.57-2.76) and 6.36-fold increase when the nSOFA score was higher than 1.5 (95% CI: 2.73-14.79).

Conclusions

The nSOFA score within 72 h after delivery is independently related to BPD and can be used to identify high-risk infants and implement early interventions.

The future of neonatal lung ultrasound: Validation of an artificial intelligence model for interpreting lung scans. A multicentre prospective diagnostic study

BACKGROUND

Artificial intelligence (AI) is a promising field in the neonatal field. We focused on lung ultrasound (LU), a useful tool for the neonatologist. Our aim was to train a neural network to create a model able to interpret LU.

METHODS

Our multicentric, prospective study included newborns with gestational age (GA) ≥ 33 + 0 weeks with early tachypnea/dyspnea/oxygen requirements. For each baby, three LU were performed: within 3 h of life (T0), at 4-6 h of life (T1), and in the absence of respiratory support (T2). Each scan was processed to extract the region of interest used to train a neural network to classify it according to the LU score (LUS). We assessed sensitivity, specificity, positive and negative predictive value of the AI model's scores in predicting the need for respiratory assistance with nasal continuous positive airway pressure and for surfactant, compared to an already studied and established LUS.

RESULTS

We enrolled 62 newborns (GA = 36 ± 2 weeks). In the prediction of the need for CPAP, we found a cutoff of 6 (at T0) and 5 (at T1) for both the neonatal lung ultrasound score (nLUS) and AI score (AUROC 0.88 for T0 AI model, 0.80 for T1 AI model). For the outcome "need for surfactant therapy", results in terms of area under receiver operator characteristic (AUROC) are 0.84 for T0 AI model and 0.89 for T1 AI model. In the prediction of surfactant therapy, we found a cutoff of 9 for both scores at T0, at T1 the nLUS cutoff was 6, while the AI's one was 5. Classification accuracy was good both at the image and class levels.

CONCLUSIONS

This is, to our knowledge, the first attempt to use an AI model to interpret early neonatal LUS and can be extremely useful for neonatologists in the clinical setting.

High-Resolution and Multidimensional Phenotypes Can Complement Genomics Data to Diagnose Diseases in the Neonatal Population

Advances in genomic medicine have greatly improved our understanding of human diseases. However, phenome is not well understood. High-resolution and multidimensional phenotypes have shed light on the mechanisms underlying neonatal diseases in greater details and have the potential to optimize clinical strategies. In this review, we first highlight the value of analyzing traditional phenotypes using a data science approach in the neonatal population. We then discuss recent research on high-resolution, multidimensional, and structured phenotypes in neonatal critical diseases. Finally, we briefly introduce current technologies available for the analysis of multidimensional data and the value that can be provided by integrating these data into clinical practice. In summary, a time series of multidimensional phenome can improve our understanding of disease mechanisms and diagnostic decision-making, stratify patients, and provide clinicians with optimized strategies for therapeutic intervention; however, the available technologies for collecting multidimensional data and the best platform for connecting multiple modalities should be considered.

Artificial intelligence in bronchopulmonary dysplasia- current research and unexplored frontiers

Provide an overview of bronchopulmonary dysplasia, its definitions, and their shortcomings. Explore the areas where machine learning may be used to further our understanding of bronchopulmonary dysplasia.

Risk factors and machine learning prediction models for bronchopulmonary dysplasia severity in the Chinese population

BACKGROUND

Bronchopulmonary dysplasia (BPD) is a common chronic lung disease in extremely preterm neonates. The outcome and clinical burden vary dramatically according to severity. Although some prediction tools for BPD exist, they seldom pay attention to disease severity and are based on populations in developed countries. This study aimed to develop machine learning prediction models for BPD severity based on selected clinical factors in a Chinese population.

METHODS

In this retrospective, single-center study, we included patients with a gestational age < 32 weeks who were diagnosed with BPD in our neonatal intensive care unit from 2016 to 2020. We collected their clinical information during the maternal, birth and early postnatal periods. Risk factors were selected through univariable and ordinal logistic regression analyses. Prediction models based on logistic regression (LR), gradient boosting decision tree, XGBoost (XGB) and random forest (RF) models were implemented and assessed by the area under the receiver operating characteristic curve (AUC).

RESULTS

We ultimately included 471 patients (279 mild, 147 moderate, and 45 severe cases). On ordinal logistic regression, gestational diabetes mellitus, initial fraction of inspiration O₂ value, invasive ventilation, acidosis, hypochloremia, C-reactive protein level, patent ductus arteriosus and Gram-negative respiratory culture were independent risk factors for BPD severity. All the XGB, LR and RF models (AUC = 0.85, 0.86 and 0.84, respectively) all had good performance.

CONCLUSIONS

We found risk factors for BPD severity in our population and developed machine learning models based on them. The models have good performance and can be used to aid in predicting BPD severity in the Chinese population.

Corticosteroids in the prevention and treatment of infants with bronchopulmonary dysplasia: Part II. Inhaled corticosteroids alone or in combination with surfactants

This paper is the second in a two-part State-of-the-Art series that reviews the latest relevant clinical trials investigating the short-term and long-term effects of corticosteroids in the prevention and treatment of bronchopulmonary dysplasia (BPD). Inhaled postnatal corticosteroids demonstrate low systemic bioavailability and rapid systemic clearance with high pulmonary deposition and were expected to reduce the incidence of BPD with reduced adverse effects, however, increased rate of mortality in the neonatal period and at the 18-24 months follow-up was observed. In a milestone study, intratracheal instillation of corticosteroids combined with surfactant decreased the incidence of BPD without increasing the mortality or the long-term neurodevelopmental adverse outcomes. However, subsequent trials using different types of surfactants, different surfactant to budesonide ratio, different time of the drug administration for infants with different severity of respiratory distress syndrome could not reproduce all the beneficial effects. Future perspectives for the identification of premature infants at high risk of BPD and the prevention or treatment of established BPD are discussed.

Co-expression network analysis for identification of novel biomarkers of bronchopulmonary dysplasia model

BACKGROUND

Bronchopulmonary dysplasia (BPD) is the most common neonatal chronic lung disease. However, its exact molecular pathogenesis is not understood. We aimed to identify relevant gene modules that may play crucial roles in the occurrence and development of BPD by weighted gene co-expression network analysis (WGCNA).

METHODS

We used RNA-Seq data of BPD and healthy control rats from our previous studies, wherein data from 30 samples was collected at days 1, 3, 7, 10, and 14. Data for preprocessing analysis included 17,613 differentially expressed genes (DEGs) with false discovery rate <0.05.

RESULTS

We grouped the highly correlated genes into 13 modules, and constructed a network of mRNA gene associations, including the 150 most associated mRNA genes in each module. Lgals8, Srpra, Prtfdc1, and Thap11 were identified as the key hub genes. Enrichment analyses revealed Golgi vesicle transport, coated vesicle, actin-dependent ATPase activity and endoplasmic reticulum pathways associated with these genes involved in the pathological process of BPD in module.

CONCLUSIONS

This is a study to analyze data obtained from BPD animal model at different time-points using WGCNA, to elucidate BPD-related susceptibility modules and disease-related genes.

Prediction Models for Bronchopulmonary Dysplasia in Preterm Infants: A Systematic Review

OBJECTIVE

To provide an overview and critical appraisal of prediction models for bronchopulmonary dysplasia (BPD) in preterm infants.

METHODS

We searched PubMed, Embase, and the Cochrane Library to identify relevant studies (up to November 2021). We included studies that reported prediction model development and/or validation of BPD in preterm infants born at ≤32 weeks and/or ≤1,500 g birth weight. We extracted the data independently based on the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS). We assessed risk of bias and applicability independently using the Prediction model Risk Of Bias ASsessment Tool (PROBAST).

RESULTS

Twenty-one prediction models from 13 studies reporting on model development and 21 models from 10 studies reporting on external validation were included. Oxygen dependency at 36 weeks' postmenstrual age was the most frequently reported outcome in both development studies (71%) and validation studies (81%). The most frequently used predictors in the models were birth weight (67%), gestational age (62%), and sex (52%). Nearly all included studies had high risk of bias, most often due to inadequate analysis. Small sample sizes and insufficient event patients were common in both study types. Missing data were often not reported or were discarded. Most studies reported on the models' discrimination, while calibration was seldom assessed (development, 19%; validation, 10%). Internal validation was lacking in 69% of development studies.

CONCLUSION

The included studies had many methodological shortcomings. Future work should focus on following the recommended approaches for developing and validating BPD prediction models.

Bronchopulmonary dysplasia predicted at birth by artificial intelligence

Aim

To develop a fast bedside test for prediction and early targeted intervention of bronchopulmonary dysplasia (BPD) to improve the outcome.

Methods

In a multicentre study of preterm infants with gestational age 24‐31 weeks, clinical data present at birth were combined with spectral data of gastric aspirate samples taken at birth and analysed using artificial intelligence. The study was designed to develop an algorithm to predict development of BPD. The BPD definition used was the consensus definition of the US National Institutes of Health: Requirement of supplemental oxygen for at least 28 days with subsequent assessment at 36 weeks postmenstrual age.

Results

Twenty‐six (43%) of the 61 included infants developed BPD. Spectral data analysis of the gastric aspirates identified the most important wave numbers for classification and surfactant treatment, and birth weight and gestational age were the most important predictive clinical data. By combining these data, the resulting algorithm for early diagnosis of BPD had a sensitivity of 88% and a specificity of 91%.

Conclusion

A point‐of‐care test to predict subsequent development of BPD at birth has been developed using a new software algorithm allowing early targeted intervention of BPD which could improve the outcome.

Risk Identification of Bronchopulmonary Dysplasia in Premature Infants Based on Machine Learning

Bronchopulmonary dysplasia (BPD) is one of the most common complications in premature infants. This disease is caused by long-time use of supplemental oxygen, which seriously affects the lung function of the child and imposes a heavy burden on the family and society. This research aims to adopt the method of ensemble learning in machine learning, combining the Boruta algorithm and the random forest algorithm to determine the predictors of premature infants with BPD and establish a predictive model to help clinicians to conduct an optimal treatment plan. Data were collected from clinical records of 996 premature infants treated in the neonatology department of Liuzhou Maternal and Child Health Hospital in Western China. In this study, premature infants with congenital anomaly, premature infants who died, and premature infants with incomplete data before the diagnosis of BPD were excluded from the data set. After exclusion, we included 648 premature infants in the study. The Boruta algorithm and 10-fold cross-validation were used for feature selection in this study. Six variables were finally selected from the 26 variables, and the random forest model was established. The area under the curve (AUC) of the model was as high as 0.929 with excellent predictive performance. The use of machine learning methods can help clinicians predict the disease so as to formulate the best treatment plan.