Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data

Continuous prediction and clinical alarm management of late-onset sepsis in preterm infants using vital signs from a patient monitor

BACKGROUND AND OBJECTIVE

Continuous prediction of late-onset sepsis (LOS) could be helpful for improving clinical outcomes in neonatal intensive care units (NICU). This study aimed to develop an artificial intelligence (AI) model for assisting the bedside clinicians in successfully identifying infants at risk for LOS using non-invasive vital signs monitoring.

METHODS

In a retrospective study from the NICU of the Máxima Medical Center in Veldhoven, the Netherlands, a total of 492 preterm infants less than 32 weeks gestation were included between July 2016 and December 2018. Data on heart rate (HR), respiratory rate (RR), and oxygen saturation (SpO2) at 1 Hz were extracted from the patient monitor. We developed multiple AI models using 102 extracted features or raw time series to provide hourly LOS risk prediction. Shapley values were used to explain the model. For the best performing model, the effect of different vital signs and also the input type of signals on model performance was tested. To further assess the performance of applying the best performing model in a real-world clinical setting, we performed a simulation using four different alarm policies on continuous real-time predictions starting from three days after birth.

RESULTS

A total of 51 LOS patients and 68 controls were finally included according to the patient inclusion and exclusion criteria. When tested by seven-fold cross-validations, the mean (standard deviation) area under the receiver operating characteristic curve (AUC) six hours before CRASH was 0.875 (0.072) for the best performing model, compared to the other six models with AUC ranging from 0.782 (0.089) to 0.846 (0.083). The best performing model performed only slightly worse than the model learning from raw physiological waveforms (0.886 [0.068]), successfully detecting 96.1 % of LOS patients before CRASH. When setting the expected alarm window to 24 h and using a multi-threshold alarm policy, the sensitivity metric was 71.6 %, while the positive predictive value was 9.9 %, resulting in an average of 1.15 alarms per day per patient.

CONCLUSIONS

The proposed AI model, which learns from routinely collected vital signs, has the potential to assist clinicians in the early detection of LOS. Combined with interpretability and clinical alarm management, this model could be better translated into medical practice for future clinical implementation.

Machine Learning: A Potential Therapeutic Tool to Facilitate Neonatal Therapeutic Decision Making

Bacterial infection is one of the major causes of neonatal morbidity and mortality worldwide. Finding rapid and reliable methods for early recognition and diagnosis of bacterial infections and early individualization of antibacterial drug administration are essential to eradicate these infections and prevent serious complications. However, this is often difficult to perform due to non-specific clinical presentations, low accuracy of current diagnostic methods, and limited knowledge of neonatal pharmacokinetics. Although neonatal medicine has been relatively late to embrace the benefits of machine learning (ML), there have been some initial applications of ML for the early prediction of neonatal sepsis and individualization of antibiotics. This article provides a brief introduction to ML and discusses the current state of the art in diagnosing and treating neonatal bacterial infections, gaps, potential uses of ML, and future directions to address the limitations of current studies. Neonatal bacterial infections involve a combination of physiologic development, disease expression, and treatment response outcomes. To address this complex relationship, future models could consider appropriate ML algorithms to capture time series features while integrating influences from the host, microbes, and drugs to optimize antimicrobial drug use in neonates. All models require prospective clinical trials to validate their clinical utility before clinical use.

Artificial Intelligence vs. Doctors: Diagnosing Necrotizing Enterocolitis on Abdominal Radiographs

BACKGROUND

Radiographic diagnosis of necrotizing enterocolitis (NEC) is challenging. Deep learning models may improve accuracy by recognizing subtle imaging patterns. We hypothesized it would perform with comparable accuracy to that of senior surgical residents.

METHODS

This cohort study compiled 494 anteroposterior neonatal abdominal radiographs (214 images NEC, 280 other) and randomly divided them into training, validation, and test sets. Transfer learning was utilized to fine-tune a ResNet-50 deep convolutional neural network (DCNN) pre-trained on ImageNet. Gradient-weighted Class Activation Mapping (Grad-CAM) heatmaps visualized image regions of greatest relevance to the pretrained neural network. Senior surgery residents at a single institution examined the test set. Resident and DCNN ability to identify pneumatosis on radiographic images were measured via area under the receiver operating curves (AUROC) and compared using DeLong's method.

RESULTS

The pretrained neural network achieved AUROC of 0.918 (95% CI, 0.837-0.978) with an accuracy of 87.8% with five false negative and one false positive prediction. Heatmaps confirmed appropriate image region emphasis by the pretrained neural network. Senior surgical residents had a median area under the receiver operating curve of 0.896, ranging from 0.778 (95% CI 0.615-0.941) to 0.991 (95% CI 0.971-0.999) with zero to five false negatives and one to eleven false positive predictions. The deep convolutional neural network performed comparably to each surgical resident's performance (p > 0.05 for all comparisons).

CONCLUSIONS

A deep convolutional neural network trained to recognize pneumatosis can quickly and accurately assist clinicians in promptly identifying NEC in clinical practice.

LEVEL OF EVIDENCE

III (study type: Study of Diagnostic Test, study of nonconsecutive patients without a universally applied "gold standard").

Computational Approaches for Predicting Preterm Birth and Newborn Outcomes

Preterm birth (PTB) and its associated morbidities are a leading cause of infant mortality and morbidity. Accurate predictive models and a better biological understanding of PTB-associated morbidities are critical in reducing their adverse effects. Increasing availability of multimodal high-dimensional data sets with concurrent advances in artificial intelligence (AI) have created a rich opportunity to gain novel insights into PTB, a clinically complex and multifactorial disease. Here, the authors review the use of AI to analyze 3 modes of data: electronic health records, biological omics, and social determinants of health metrics.

Sepsis Huddles in the Neonatal Intensive Care Unit: A Retrospective Cohort Study of Late-onset Infection Recognition and Severity Assessment

OBJECTIVE

To analyze relationships between provider-documented signs prompting sepsis evaluations, assessments of illness severity, and late-onset infection (LOI).

STUDY DESIGN

Retrospective cohort study of all infants receiving a sepsis huddle in conjunction with a LOI evaluation. Participants were ≥3 days old and admitted to a level IV neonatal intensive care unit (NICU) from September 2018 through May 2021. Data were extracted from standardized sepsis huddle notes in the electronic health record, including clinical signs prompting LOI evaluations, illness severity assessments (from least to most severe: green, yellow, and red), and management plans. To analyze relationships of sepsis huddle characteristics with the detection of culture-confirmed LOI (bacteremia, urinary tract infection, or meningitis), we utilized diagnostic test statistics, area under the receiver-operator characteristic analyses, and multivariable logistic regression.

RESULTS

We identified 1209 eligible sepsis huddles among 604 infants. There were 111 culture-confirmed LOI episodes (9% of all huddles). Twelve clinical signs of infection poorly distinguished infants with and without LOI, with sensitivity for each ranging from 2% to 36% and area under the receiver-operator characteristic ranging 0.49-0.53. Multivariable logistic regression identified increasing odds of infection with higher perceived illness severity at the time of sepsis huddle, adjusted for gestational age and receipt of intensive care supports.

CONCLUSIONS

Clinical signs prompting sepsis huddles were nonspecific and not predictive of concurrent LOI. Higher perceived illness severity was associated with presence of infection, despite some misclassification based on objective criteria. In level IV NICUs, antimicrobial stewardship through development of criteria for antibiotic noninitiation may be challenging, as presenting signs of LOI are similar among infants with and without confirmed infection.

Congenital diaphragmatic hernia: automatic lung and liver MRI segmentation with nnU-Net, reproducibility of pyradiomics features, and a machine learning application for the classification of liver herniation

Prenatal assessment of lung size and liver position is essential to stratify congenital diaphragmatic hernia (CDH) fetuses in risk categories, guiding counseling, and patient management. Manual segmentation on fetal MRI provides a quantitative estimation of total lung volume and liver herniation. However, it is time-consuming and operator-dependent. In this study, we utilized a publicly available deep learning (DL) segmentation system (nnU-Net) to automatically contour CDH-affected fetal lungs and liver on MRI sections. Concordance between automatic and manual segmentation was assessed by calculating the Jaccard coefficient. Pyradiomics standard features were then extracted from both manually and automatically segmented regions. The reproducibility of features between the two groups was evaluated through the Wilcoxon rank-sum test and intraclass correlation coefficients (ICCs). We finally tested the reliability of the automatic-segmentation approach by building a ML classifier system for the prediction of liver herniation based on support vector machines (SVM) and trained on shape features computed both in the manual and nnU-Net-segmented organs. We compared the area under the classifier receiver operating characteristic curve (AUC) in the two cases. Pyradiomics features calculated in the manual ROIs were partly reproducible by the same features calculated in nnU-Net segmented ROIs and, when used in the ML procedure, to predict liver herniation (both AUC around 0.85).          Conclusion: Our results suggest that automatic MRI segmentation is feasible, with good reproducibility of pyradiomics features, and that a ML system for liver herniation prediction offers good reliability.          Trial registration: https://clinicaltrials.gov/ct2/show/NCT04609163?term=NCT04609163&draw=2&rank=1 ; Clinical Trial Identification no. NCT04609163. What is Known: • Magnetic resonance imaging (MRI) is crucial for prenatal congenital diaphragmatic hernia (CDH) assessment. It enables the quantification of the total lung volume and the extent of liver herniation, which are essential for stratifying the severity of CDH, guiding counseling, and patient management. • The manual segmentation of MRI scans is a time-consuming process that is heavily reliant upon the skill set of the operator. What is New: • MRI lung and liver automatic segmentation using the deep learning nnU-Net system is feasible, with good Jaccard coefficient values and satisfactory reproducibility of pyradiomics features compared to manual results. • A feasible ML system for predicting liver herniation could improve prenatal assessments and CDH patient management.

Artificial Intelligence-Based Diagnostic Support System for Patent Ductus Arteriosus in Premature Infants

Background: Patent ductus arteriosus (PDA) is a prevalent congenital heart defect in premature infants, associated with significant morbidity and mortality. Accurate and timely diagnosis of PDA is crucial, given the vulnerability of this population. Methods: We introduce an artificial intelligence (AI)-based PDA diagnostic support system designed to assist medical professionals in diagnosing PDA in premature infants. This study utilized electronic health record (EHR) data from 409 premature infants spanning a decade at Severance Children's Hospital. Our system integrates a data viewer, data analyzer, and AI-based diagnosis supporter, facilitating comprehensive data presentation, analysis, and early symptom detection. Results: The system's performance was evaluated through diagnostic tests involving medical professionals. This early detection model achieved an accuracy rate of up to 84%, enabling detection up to 3.3 days in advance. In diagnostic tests, medical professionals using the system with the AI-based diagnosis supporter outperformed those using the system without the supporter. Conclusions: Our AI-based PDA diagnostic support system offers a comprehensive solution for medical professionals to accurately diagnose PDA in a timely manner in premature infants. The collaborative integration of medical expertise and technological innovation demonstrated in this study underscores the potential of AI-driven tools in advancing neonatal diagnosis and care.

Clinical Decision Support for Improved Neonatal Care: The Development of a Machine Learning Model for the Prediction of Late-onset Sepsis and Necrotizing Enterocolitis

OBJECTIVE

To develop an artificial intelligence-based software system for predicting late-onset sepsis (LOS) and necrotizing enterocolitis (NEC) in infants admitted to the neonatal intensive care unit (NICU).

STUDY DESIGN

Single-center, retrospective cohort study, conducted in the NICU of the Antwerp University Hospital. Continuous monitoring data of 865 preterm infants born at <32 weeks gestational age, admitted to the NICU in the first week of life, were used to train an XGBoost machine learning (ML) algorithm for LOS and NEC prediction in a cross-validated setup. Afterward, the model's performance was assessed on an independent test set of 148 patients (internal validation).

RESULTS

The ML model delivered hourly risk predictions with an overall sensitivity of 69% (142/206) for all LOS/NEC episodes and 81% (67/83) for severe LOS/NEC episodes. The model showed a median time gain of ≤10 hours (IQR, 3.1-21.0 hours), compared with historical clinical diagnosis. On the complete retrospective dataset, the ML model made 721 069 predictions, of which 9805 (1.3%) depicted a LOS/NEC probability of ≥0.15, resulting in a total alarm rate of <1 patient alarm-day per week. The model reached a similar performance on the internal validation set.

CONCLUSIONS

Artificial intelligence technology can assist clinicians in the early detection of LOS and NEC in the NICU, which potentially can result in clinical and socioeconomic benefits. Additional studies are required to quantify further the effect of combining artificial and human intelligence on patient outcomes in the NICU.

The Finnegan Score for Neonatal Opioid Withdrawal Revisited With Routine Electronic Data: Retrospective Study

Background

The severity of neonatal abstinence syndrome (NAS) may be assessed with the Finnegan score (FS). Since the FS is laborious and subjective, alternative ways of assessment may improve quality of care.

Objective

In this pilot study, we examined associations between the FS and routine monitoring data obtained from the electronic health record system.

Methods

The study included 205 neonates with NAS after intrauterine (n=23) or postnatal opioid exposure (n=182). Routine monitoring data were analyzed at 60±10 minutes (t-1) and 120±10 minutes (t-2) before each FS assessment. Within each time period, the mean for each variable was calculated. Readings were also normalized to individual baseline data for each patient and parameter. Mixed effects models were used to assess the effect of different variables.

Results

Plots of vital parameters against the FS showed heavily scattered data. When controlling for several variables, the best-performing mixed effects model displayed significant effects of individual baseline-controlled mean heart rate (estimate 0.04, 95% CI 0.02-0.07) and arterial blood pressure (estimate 0.05, 95% CI 0.01-0.08) at t-1 with a goodness of fit (R2m) of 0.11.

Conclusions

Routine electronic data can be extracted and analyzed for their correlation with FS data. Mixed effects models show small but significant effects after normalizing vital parameters to individual baselines.

Integrating Multi-Omics Data With EHR for Precision Medicine Using Advanced Artificial Intelligence

With the recent advancement of novel biomedical technologies such as high-throughput sequencing and wearable devices, multi-modal biomedical data ranging from multi-omics molecular data to real-time continuous bio-signals are generated at an unprecedented speed and scale every day. For the first time, these multi-modal biomedical data are able to make precision medicine close to a reality. However, due to data volume and the complexity, making good use of these multi-modal biomedical data requires major effort. Researchers and clinicians are actively developing artificial intelligence (AI) approaches for data-driven knowledge discovery and causal inference using a variety of biomedical data modalities. These AI-based approaches have demonstrated promising results in various biomedical and healthcare applications. In this review paper, we summarize the state-of-the-art AI models for integrating multi-omics data and electronic health records (EHRs) for precision medicine. We discuss the challenges and opportunities in integrating multi-omics data with EHRs and future directions. We hope this review can inspire future research and developing in integrating multi-omics data with EHRs for precision medicine.

Prediction of Postnatal Growth Failure in Very Low Birth Weight Infants Using a Machine Learning Model

Accurate prediction of postnatal growth failure (PGF) can be beneficial for early intervention and prevention. We aimed to develop a machine learning model to predict PGF at discharge among very low birth weight (VLBW) infants using extreme gradient boosting. A total of 729 VLBW infants, born between 2013 and 2017 in four hospitals, were included. PGF was defined as a decrease in z-score between birth and discharge that was greater than 1.28. Feature selection and addition were performed to improve the accuracy of prediction at four different time points, including 0, 7, 14, and 28 days after birth. A total of 12 features with high contribution at all time points by feature importance were decided upon, and good performance was shown as an area under the receiver operating characteristic curve (AUROC) of 0.78 at 7 days. After adding weight change to the 12 features-which included sex, gestational age, birth weight, small for gestational age, maternal hypertension, respiratory distress syndrome, duration of invasive ventilation, duration of non-invasive ventilation, patent ductus arteriosus, sepsis, use of parenteral nutrition, and reach at full enteral nutrition-the AUROC at 7 days after birth was shown as 0.84. Our prediction model for PGF performed well at early detection. Its potential clinical application as a supplemental tool could be helpful for reducing PGF and improving child health.

The use of probabilistic graphical models in pediatric sepsis: a feasibility and scoping review

Background

Recent research has demonstrated that machine learning (ML) has the potential to improve several aspects of medical application for critical illness, including sepsis. This scoping review aims to evaluate the feasibility of probabilistic graphical model (PGM) methods in pediatric sepsis application and describe the use of pediatric sepsis definition in these studies.

Methods

Literature searches were conducted in PubMed, Scopus, Cumulative Index to Nursing and Allied Health Literature (CINAHL+), and Web of Sciences from 2000-2023. Keywords included "pediatric", "neonates", "infants", "machine learning", "probabilistic graphical model", and "sepsis".

Results

A total of 3,244 studies were screened, and 72 were included in this scoping review. Sepsis was defined using positive microbiology cultures in 19 studies (26.4%), followed by the 2005's international pediatric sepsis consensus definition in 11 studies (15.3%), and Sepsis-3 definition in seven studies (9.7%). Other sepsis definitions included: bacterial infection, the international classification of diseases, clinicians' assessment, and antibiotic administration time. Among the most common ML approaches used were logistic regression (n=27), random forest (n=24), and Neural Network (n=18). PGMs were used in 13 studies (18.1%), including Bayesian classifiers (n=10), and the Markov Model (n=3). When applied on the same dataset, PGMs show a relatively inferior performance to other ML models in most cases. Other aspects of explainability and transparency were not examined in these studies.

Conclusions

Current studies suggest that the performance of probabilistic graphic models is relatively inferior to other ML methods. However, its explainability and transparency advantages make it a potentially viable method for several pediatric sepsis studies and applications.

Intelligent Framework for Early Detection of Severe Pediatric Diseases from Mild Symptoms

Children's health is one of the most significant fields in medicine. Most diseases that result in children's death or long-term morbidity are caused by preventable and treatable etiologies, and they appear in the child at the early stages as mild symptoms. This research aims to develop a machine learning (ML) framework to detect the severity of disease in children. The proposed framework helps in discriminating children's urgent/severe conditions and notifying parents whether a child needs to visit the emergency room immediately or not. The model considers several variables to detect the severity of cases, which are the symptoms, risk factors (e.g., age), and the child's medical history. The framework is implemented by using nine ML methods. The results achieved show the high performance of the proposed framework in identifying serious pediatric diseases, where decision tree and random forest outperformed the other methods with an accuracy rate of 94%. This shows the reliability of the proposed framework to be used as a pediatric decision-making system for detecting serious pediatric illnesses. The results are promising when compared to recent state-of-the-art studies. The main contribution of this research is to propose a framework that is viable for use by parents when their child suffers from any commonly developed symptoms.

Examining explainable clinical decision support systems with think aloud protocols

Machine learning tools are increasingly used to improve the quality of care and the soundness of a treatment plan. Explainable AI (XAI) helps users in understanding the inner mechanisms of opaque machine learning models and is a driver of trust and adoption. Explanation methods for black-box models exist, but there is a lack of user studies on the interpretability of the provided explanations. We used a Think Aloud Protocol (TAP) to explore oncologists' assessment of a lung cancer relapse prediction system with the aim of refining the purpose-built explanation model for better credibility and utility. Novel to this context, TAP is used as a neutral methodology to elicit experts' thought processes and judgements of the AI system, without explicit prompts. TAP aims to elicit the factors which influenced clinicians' perception of credibility and usefulness of the system. Ten oncologists took part in the study. We conducted a thematic analysis of their verbalized responses, generating five themes that help us to understand the context within which oncologists' may (or may not) integrate an explainable AI system into their working day.

Development and clinical impact assessment of a machine-learning model for early prediction of late-onset sepsis

BACKGROUND AND AIM

Preterm infants are prone to neonatal infections such as late-onset sepsis (LOS). The consequences of LOS can be severe and potentially life-threatening. Unfortunately, LOS often presents with unspecific symptoms, and early screening laboratory tests have limited diagnostic value and are often late. This study aimed to build a predictive algorithm to aid doctors in the early detection of LOS in very preterm infants.

METHODS

In a retrospective cohort study, all consecutively admitted preterm infants (GA ≤ 32 weeks) from 2008 until 2019 were included. They were classified as LOS or control according to blood culture results, currently the gold standard. To generate features, routine and continuously measured oxygen saturation and heart rate data with a minute-by-minute sampling rate were extracted from electronic medical records. Care was taken not to include variables indicative of existing LOS suspicion. The timing of a positive blood culture served as a proxy for LOS-onset. An equivalent timestamp was generated in gestational-age-matched control patients without a positive blood culture. Three machine learning (ML) techniques (generalized additive models, logistic regression, and XGBoost) were used to build a classification algorithm. To simulate the performance of the algorithm in clinical practice, a simulation using multiple alarm thresholds was performed on hourly predictions for the total hospitalization period.

RESULTS

292 infants with LOS were matched to 1497 controls. The median gestational age before matching was 28.1 and 30.3 weeks, respectively. Evaluation of the overall discriminative power of the LR algorithm yielded an AUC of 0.73 (p < 0.05) at the moment of clinical suspicion (t = 0). In the longitudinal simulation, our algorithm detects LOS in at least 47% of the patients before clinical suspicion without exceeding the alarm fatigue threshold of 3 alarms per day. Furthermore, medical experts evaluated the algorithm as clinically relevant regarding the feature contributions in the model explanations.

CONCLUSIONS

An ML algorithm was trained for the early detection of LOS. Performance was evaluated on both prediction horizons and in a clinical impact simulation. To the best of our knowledge, our assessment of clinical impact with a retrospective simulation on longitudinal data is the most extensive in the literature on LOS prediction to date. The clinically relevant algorithm, based on routinely collected data, can potentially accelerate clinical decisions in the early detection of LOS, even with limited inputs.

Machine learning applications on neonatal sepsis treatment: a scoping review

INTRODUCTION

Neonatal sepsis is a major cause of health loss and mortality worldwide. Without proper treatment, neonatal sepsis can quickly develop into multisystem organ failure. However, the signs of neonatal sepsis are non-specific, and treatment is labour-intensive and expensive. Moreover, antimicrobial resistance is a significant threat globally, and it has been reported that over 70% of neonatal bloodstream infections are resistant to first-line antibiotic treatment. Machine learning is a potential tool to aid clinicians in diagnosing infections and in determining the most appropriate empiric antibiotic treatment, as has been demonstrated for adult populations. This review aimed to present the application of machine learning on neonatal sepsis treatment.

METHODS

PubMed, Embase, and Scopus were searched for studies published in English focusing on neonatal sepsis, antibiotics, and machine learning.

RESULTS

There were 18 studies included in this scoping review. Three studies focused on using machine learning in antibiotic treatment for bloodstream infections, one focused on predicting in-hospital mortality associated with neonatal sepsis, and the remaining studies focused on developing machine learning prediction models to diagnose possible sepsis cases. Gestational age, C-reactive protein levels, and white blood cell count were important predictors to diagnose neonatal sepsis. Age, weight, and days from hospital admission to blood sample taken were important to predict antibiotic-resistant infections. The best-performing machine learning models were random forest and neural networks.

CONCLUSION

Despite the threat antimicrobial resistance poses, there was a lack of studies focusing on the use of machine learning for aiding empirical antibiotic treatment for neonatal sepsis.

A sepsis trigger tool reduces time to antibiotic administration in the NICU

OBJECTIVE

Prolonged time to antibiotic administration is associated with increased morbidity and mortality. Interventions to decrease the time to antibiotic administration may improve mortality and morbidity.

STUDY DESIGN

We identified possible change concepts for reducing time to antibiotic usage in the NICU. For the initial intervention, we developed a sepsis screening tool based on NICU-specific parameters. The main goal of the project was to reduce time to antibiotic administration by 10%.

RESULTS

The project was conducted from April 2017 until April 2019. There were no missed cases of sepsis in the project period. Time to antibiotic administration for patients who were started on antibiotics decreased during the project, with the mean shifting from 126 to 102 min, a reduction of 19%.

CONCLUSIONS

We successfully reduced time to antibiotic delivery in our NICU using a trigger tool to identifying potential cases of sepsis in the NICU environment. The trigger tool requires broader validation.

Leveraging machine learning to identify acute myeloid leukemia patients and their chemotherapy regimens in an administrative database

BACKGROUND

Administrative datasets are useful for identifying rare disease cohorts such as pediatric acute myeloid leukemia (AML). Previously, cohorts were assembled using labor-intensive, manual reviews of patients' longitudinal chemotherapy data.

METHODS

We utilized a two-step machine learning (ML) method to (i) identify pediatric patients with newly diagnosed AML, and (ii) among the identified AML patients, their chemotherapy courses, in an administrative/billing database. Using 2558 patients previously manually reviewed, multiple ML algorithms were derived from 75% of the study sample, and the selected model was tested in the remaining hold-out sample. The selected model was also applied to assemble a new pediatric AML cohort and further assessed in an external validation, using a standalone cohort established by manual chart abstraction.

RESULTS

For patient identification, the selected Support Vector Machine model yielded a sensitivity of 0.97 and a positive predictive value (PPV) of 0.97 in the hold-out test sample. For course-specific chemotherapy regimen and start date identification, the selected Random Forest model yielded overall PPV greater than or equal to 0.88 and sensitivity greater than or equal to 0.86 across all courses in the test sample. When applied to new cohort assembly, ML identified 3016 AML patients with 10,588 treatment courses. In the external validation subset, PPV was greater than or equal to 0.75 and sensitivity was greater than or equal to 0.82 for patient identification, and PPV was greater than or equal to 0.93 and sensitivity was greater than or equal to 0.94 for regimen identifications.

CONCLUSION

A carefully designed ML model can accurately identify pediatric AML patients and their chemotherapy courses from administrative databases. This approach may be generalizable to other diseases and databases.

A Multidatabase ExTRaction PipEline (METRE) for Facile Cross Validation in Critical Care Research

Transforming raw EHR data into machine learning model-ready inputs requires considerable effort. One widely used EHR database is Medical Information Mart for Intensive Care (MIMIC). Prior work on MIMIC-III cannot query the updated and improved MIMIC-IV version. Besides, the need to use multicenter datasets further highlights the challenge of EHR data extraction. Therefore, we developed an extraction pipeline that works on both MIMIC-IV and eICU Collaborative Research Database and allows for model cross validation using these 2 databases. Under the default choices, the pipeline extracted 38,766 and 126,448 ICU records for MIMIC-IV and eICU, respectively. Using the extracted time-dependent variables, we compared the Area Under the Curve (AUC) performance with ​​prior works on clinically relevant tasks such as in-hospital mortality prediction. METRE achieved comparable performance with AUC 0.723-0.888 across all tasks with MIMIC-IV. Additionally, when we evaluated the model directly on MIMIC-IV data using a model trained on eICU, we observed that the AUC change can be as small as +0.019 or -0.015. Our open-source pipeline transforms MIMIC-IV and eICU into structured data frames and allows researchers to perform model training and testing using data collected from different institutions, which is of critical importance for model deployment under clinical contexts.

Vital sign-based detection of sepsis in neonates using machine learning

AIM

Sepsis is a leading cause of morbidity and mortality in neonates. Early diagnosis is key but difficult due to non-specific signs. We investigate the predictive value of machine learning-assisted analysis of non-invasive, high frequency monitoring data and demographic factors to detect neonatal sepsis.

METHODS

Single centre study, including a representative cohort of 325 infants (2866 hospitalisation days). Personalised event timelines including interventions and clinical findings were generated. Time-domain features from heart rate, respiratory rate and oxygen saturation values were calculated and demographic factors included. Sepsis prediction was performed using Naïve Bayes algorithm in a maximum a posteriori framework up to 24 h before clinical sepsis suspicion.

RESULTS

Twenty sepsis cases were identified. Combining multiple vital signs improved algorithm performance compared to heart rate characteristics alone. This enabled a prediction of sepsis with an area under the receiver operating characteristics curve of 0.82, up to 24 h before clinical sepsis suspicion. Moreover, 10 h prior to clinical suspicion, the risk of sepsis increased 150-fold.

CONCLUSION

The present algorithm using non-invasive patient data provides useful predictive value for neonatal sepsis detection. Machine learning-assisted algorithms are promising novel methods that could help individualise patient care and reduce morbidity and mortality.

Integrating structured and unstructured data for timely prediction of bloodstream infection among children

BACKGROUND

Hospitalized children with central venous lines (CVLs) are at higher risk of hospital-acquired infections. Information in electronic health records (EHRs) can be employed in training deep learning models to predict the onset of these infections. We incorporated clinical notes in addition to structured EHR data to predict serious bloodstream infections, defined as positive blood culture followed by at least 4 days of new antimicrobial agent administration, among hospitalized children with CVLs.

METHODS

Structured EHR information and clinical notes were extracted for a retrospective cohort including all hospitalized patients with CVLs at a single tertiary care pediatric health system from 2013 to 2018. Deep learning models were trained to determine the added benefit of incorporating the information embedded in clinical notes in predicting serious bloodstream infection.

RESULTS

A total of 24,351 patient encounters met inclusion criteria. The best-performing model restricted to structured EHR data had a specificity of 0.951 and positive predictive value (PPV) of 0.056 when the sensitivity was set to 0.85. The addition of contextualized word embeddings improved the specificity to 0.981 and PPV to 0.113.

CONCLUSIONS

Integrating clinical notes with structured EHR data improved the prediction of serious bloodstream infections among pediatric patients with CVLs.

IMPACT

Developed an advanced infection prediction model in pediatrics that integrates the structured and unstructured EHRs. Extracted information from clinical notes to do timely prediction in a clinical setting. Developed a deep learning model framework that can be employed in predicting rare events in a complex and dynamic environment.

Computer-Based Natural Language Search Applied to the Electronic Medical Record for Tonsil Triage

OBJECTIVES

To determine significant histologic findings in tonsils and categorize clinical settings in which they occur to identify cases benefiting from histopathologic examination using a computer-based natural language search (NLS) applied to the electronic medical record.

METHODS

The pathology database was queried for tonsillectomy cases accessioned between 2002 and 2018. Tonsils with microscopic examination were reviewed, and indication for examination and diagnoses were tallied. Clinical risk of malignancy was correlated with findings. A NLS was used to interrogate preoperative clinical records of the same group of patients. The search identified cases at risk of significant histologic findings and was implemented as part of standard practice.

RESULTS

Of the 18,733 bilateral tonsillectomies identified in the pathology database, 494 were palatine tonsils that underwent microscopic examination, 134 had indications concerning for malignancy, and 14 had significant findings on histologic examination. When the NLS was applied to the medical record of the same group, 223 cases were identified as having risk of malignancy, including all flagged by surgeons and pathologists and 89 additional cases. Clinical implementation resulted in identification of all cases benefiting from examination.

CONCLUSIONS

A NLS applied to the electronic medical record to select tonsils for examination was superior to relying on surgeons and pathologists.

Cardiorespiratory signature of neonatal sepsis: development and validation of prediction models in 3 NICUs

BACKGROUND

Heart rate characteristics aid early detection of late-onset sepsis (LOS), but respiratory data contain additional signatures of illness due to infection. Predictive models using cardiorespiratory data may improve early sepsis detection. We hypothesized that heart rate (HR) and oxygenation (SpO₂) data contain signatures that improve sepsis risk prediction over HR or demographics alone.

METHODS

We analyzed cardiorespiratory data from very low birth weight (VLBW, <1500 g) infants admitted to three NICUs. We developed and externally validated four machine learning models to predict LOS using features calculated every 10 m: mean, standard deviation, skewness, kurtosis of HR and SpO₂, and cross-correlation. We compared feature importance, discrimination, calibration, and dynamic prediction across models and cohorts. We built models of demographics and HR or SpO₂ features alone for comparison with HR-SpO₂ models.

RESULTS

Performance, feature importance, and calibration were similar among modeling methods. All models had favorable external validation performance. The HR-SpO₂ model performed better than models using either HR or SpO₂ alone. Demographics improved the discrimination of all physiologic data models but dampened dynamic performance.

CONCLUSIONS

Cardiorespiratory signatures detect LOS in VLBW infants at 3 NICUs. Demographics risk-stratify, but predictive modeling with both HR and SpO₂ features provides the best dynamic risk prediction.

IMPACT

Heart rate characteristics aid early detection of late-onset sepsis, but respiratory data contain signatures of illness due to infection. Predictive models using both heart rate and respiratory data may improve early sepsis detection. A cardiorespiratory early warning score, analyzing heart rate from electrocardiogram or pulse oximetry with SpO₂, predicts late-onset sepsis within 24 h across multiple NICUs and detects sepsis better than heart rate characteristics or demographics alone. Demographics risk-stratify, but predictive modeling with both HR and SpO₂ features provides the best dynamic risk prediction. The results increase understanding of physiologic signatures of neonatal sepsis.

Data harnessing to nurture the human mind for a tailored approach to the child

Big data in pediatrics is an ocean of structured and unstructured data. Big data analysis helps to dive into the ocean of data to filter out information that can guide pediatricians in their decision making, precision diagnosis, and targeted therapy. In addition, big data and its analysis have helped in the surveillance, prevention, and performance of the health system. There has been a considerable amount of work in pediatrics that we have tried to highlight in this review and some of it has been already incorporated into the health system. Work in specialties of pediatrics is still forthcoming with the creation of a common data model and amalgamation of the huge "omics" database. The physicians entrusted with the care of children must be aware of the outcome so that they can play a role to ensure that big data algorithms have a clinically relevant effect in improving the health of their patients. They will apply the outcome of big data and its analysis in patient care through clinical algorithms or with the help of embedded clinical support alerts from the electronic medical records. IMPACT: Big data in pediatrics include structured, unstructured data, waveform data, biological, and social data. Big data analytics has unraveled significant information from these databases. This is changing how pediatricians will look at the body of available evidence and translate it into their clinical practice. Data harnessed so far is implemented in certain fields while in others it is in the process of development to become a clinical adjunct to the physician. Common databases are being prepared for future work. Diagnostic and prediction models when incorporated into the health system will guide the pediatrician to a targeted approach to diagnosis and therapy.

Utilizing big data from electronic health records in pediatric clinical care

Big data has the capacity to transform both pediatric healthcare delivery and research, but its potential has yet to be fully realized. Curation of large multi-institutional datasets of high-quality data has allowed for significant advances in the timeliness of quality improvement efforts. Improved access to large datasets and computational power have also paved the way for the development of high-performing, data-driven decision support tools and precision medicine approaches. However, implementation of these approaches and tools into pediatric practice has been hindered by challenges in our ability to adequately capture the heterogeneity of the pediatric population as well as the nuanced complexities of pediatric diseases such as sepsis. Moreover, there are large gaps in knowledge and definitive evidence demonstrating the utility, usability, and effectiveness of these types of tools in pediatric practice, which presents significant challenges to provider willingness to leverage these solutions. The next wave of transformation for pediatric healthcare delivery and research through big data and sophisticated analytics will require focusing efforts on strategies to overcome cultural barriers to adoption and acceptance. IMPACT: Big data from EHRs can be used to drive improvement in pediatric clinical care. Clinical decision support, artificial intelligence, machine learning, and precision medicine can transform pediatric care using big data from the EHR. This article provides a review of barriers and enablers for the effective use of data analytics in pediatric clinical care using pediatric sepsis as a use case. The impact of this review is that it will inform influencers of pediatric care about the importance of current trends in data analytics and its use in improving outcomes of care through EHR-based strategies.

Artificial and human intelligence for early identification of neonatal sepsis

Artificial intelligence may have a role in the early detection of sepsis in neonates. Machine learning can identify patterns that predict high or increasing risk for clinical deterioration from a sepsis-like illness. In developing this potential addition to NICU care, careful consideration should be given to the data and methods used to develop, validate, and evaluate prediction models. When an AI system alerts clinicians to a change in a patient's condition that warrants a bedside evaluation, human intelligence and experience come into play to determine an appropriate course of action: evaluate and treat or wait and watch closely. With intelligently developed, validated, and implemented AI sepsis systems, both clinicians and patients stand to benefit. IMPACT: This narrative review highlights the application of AI in neonatal sepsis prediction. It describes issues in clinical prediction model development specific to this population. This article reviews the methods, considerations, and literature on neonatal sepsis model development and validation. Challenges of AI technology and potential barriers to using sepsis AI systems in the NICU are discussed.

State-of-the-art management of the acutely unwell child

Children make up around one-fifth of all emergency department visits in the USA and UK, with an increasing trend of emergency admissions requiring intensive care. Anaesthetists play a vital role in the management of paediatric emergencies contributing to stabilisation, emergency anaesthesia, transfers and non-technical skills that optimise team performance. From neonates to adolescents, paediatric patients have diverse physiology and present with a range of congenital and acquired pathologies that often differ from the adult population. With increasing centralisation of paediatric services, staff outside these centres have less exposure to caring for children, yet are often the first responders in managing these high stakes situations. Staying abreast of the latest evidence for managing complex low frequency emergencies is a challenge. This review focuses on recent evidence and pertinent clinical updates within the field. The challenges of maintaining skills and training are explored as well as novel advancements in care.

Updates in Late-Onset Sepsis: Risk Assessment, Therapy, and Outcomes

Neonatal late-onset sepsis (LOS) continues to threaten morbidity and mortality in the NICU and poses ongoing diagnostic and therapeutic challenges. Early recognition of clinical signs, rapid evaluation, and prompt initiation of treatment are critical to prevent life-threatening deterioration. Preterm infants-born at ever-decreasing gestational ages-are at particularly high risk for life-long morbidities and death. This changing NICU population necessitates continual reassessments of diagnostic and preventive measures and evidence-based treatment for LOS. The clinical presentation of LOS is varied and nonspecific. Despite ongoing research, reliable, specific laboratory biomarkers facilitating early diagnosis are lacking. These limitations drive an ongoing practice of liberal initiation of empiric antibiotics among infants with suspected LOS. Subsequent promotion of multidrug-resistant microorganisms threatens the future of antimicrobial therapy and puts preterm and chronically ill infants at even higher risk of nosocomial infection. Efforts to identify adjunctive therapies counteracting sepsis-driven hyperinflammation and sepsis-related functional immunosuppression are ongoing. However, most approaches have either failed to improve LOS prognosis or are not yet ready for clinical application. This article provides an overview of the epidemiology, risk factors, diagnostic tools, and treatment options of LOS in the context of increasing numbers of extremely preterm infants. It addresses the question of whether LOS could be identified earlier and more precisely to allow for earlier and more targeted therapy and discusses rational approaches to antibiotic therapy to avoid overuse. Finally, this review elucidates the necessity of long-term follow-up of infants with a history of LOS.

Monitoring of heart rate characteristics to detect neonatal sepsis

BACKGROUND

Monitoring of heart rate characteristics (HRC) index may improve outcomes of late-onset neonatal sepsis (LOS) through early detection. We aimed at describing the association between LOS and elevated HRC index.

METHODS

This single-center retrospective case-control study included neonates who presented with blood culture-proven hospital-acquired LOS. Controls were matched to cases (ratio 1:2) based on gestational age, postnatal age, and birthweight. We compared the highest HRC indexes in the 48 h preceding blood culture sampling in LOS cases to the highest HRC indexes at the same postnatal days in controls.

RESULTS

In 59 LOS cases and 123 controls, an HRC index > 2 was associated with LOS (OR 7.1, 95% CI 2.6-19.0). Sensitivity and specificity of an HRC index > 2 to predict LOS were 53% (32/59) and 79% (98/123). Sensitivity increased from 25% in infants born > 32 weeks to 76% in infants born < 28 weeks. Specificity decreased from 97% in infants > 32 weeks to 63% in those born < 28 weeks.

CONCLUSIONS

An increase of HRC index > 2 has a significant association with the diagnosis of LOS, supporting the use of HRC monitoring to assist early detection of LOS. Clinicians using HRC monitoring should be aware of its diagnostic accuracy and limitations in different gestational age groups.

IMPACT

There is a paucity of data regarding the predictive value of heart rate characteristics (HRC) monitoring for early diagnosis of late-onset neonatal sepsis (LOS) in daily clinical practice. Monitoring of heart rate characteristics provides valuable information to assist the early diagnosis of LOS across all gestational age groups. However, the strong influence of gestational age on positive and negative predictive values adds complexity to the interpretation of HRC indexes.

On AI Approaches for Promoting Maternal and Neonatal Health in Low Resource Settings: A Review

A significant challenge for hospitals and medical practitioners in low- and middle-income nations is the lack of sufficient health care facilities for timely medical diagnosis of chronic and deadly diseases. Particularly, maternal and neonatal morbidity due to various non-communicable and nutrition related diseases is a serious public health issue that leads to several deaths every year. These diseases affecting either mother or child can be hospital-acquired, contracted during pregnancy or delivery, postpartum and even during child growth and development. Many of these conditions are challenging to detect at their early stages, which puts the patient at risk of developing severe conditions over time. Therefore, there is a need for early screening, detection and diagnosis, which could reduce maternal and neonatal mortality. With the advent of Artificial Intelligence (AI), digital technologies have emerged as practical assistive tools in different healthcare sectors but are still in their nascent stages when applied to maternal and neonatal health. This review article presents an in-depth examination of digital solutions proposed for maternal and neonatal healthcare in low resource settings and discusses the open problems as well as future research directions.

Infectious aetiologies of neonatal illness in south Asia classified using WHO definitions: a primary analysis of the ANISA study

Background

Globally, neonatal mortality accounts for almost half of all deaths in children younger than 5 years. Aetiological agents of neonatal infection are difficult to identify because the clinical signs are non-specific. Using data from the Aetiology of Neonatal Infections in south Asia (ANISA) cohort, we aimed to describe the spectrum of infectious aetiologies of acute neonatal illness categorised post-hoc using the 2015 WHO case definitions of critical illness, clinical severe infection, and fast breathing only.

Methods

Eligible infants were aged 0–59 days with possible serious bacterial infection and healthy infants enrolled in the ANISA study in Bangladesh, India, and Pakistan. We applied a partial latent class Bayesian model to estimate the prevalence of 27 pathogens detectable on PCR, pathogens detected by blood culture only, and illness not attributed to any infectious aetiology. Infants with at least one clinical specimen available were included in the analysis. We assessed the prevalence of these aetiologies according to WHO's case definitions of critically ill, clinical severe infection, and infants with late onset, isolated fast breathing. For the clinical severe definition, we compared the prevalence of signs by bacterial versus viral aetiology.

Findings

There were 934 infants (992 episodes) in the critically ill category, 3769 (4000 episodes) in the clinical severe infection category, and 738 (771 episodes) in the late-onset isolated fast breathing category. We estimated the proportion of illness attributable to bacterial infection was 32·7% in infants in the critically ill group, 15·6% in the clinical severe infection group, and 8·8% among infants with late-onset isolated fast breathing group. An infectious aetiology was not identified in 58–82% of infants in these categories. Among 4000 episodes of clinical severe infection, those with bacterial versus viral attribution had higher proportions of hypothermia, movement only when stimulated, convulsions, and poor feeding.

Interpretation

Our modelled results generally support the revised WHO case definitions, although a revision of the most severe case definition could be considered. Clinical criteria do not clearly differentiate between young infants with and without infectious aetiologies. Our results highlight the need for improved point-of-care diagnostics, and further study into neonatal deaths and episodes with no identified aetiology, to ensure antibiotic stewardship and targeted interventions.

Funding

The Bill and Melinda Gates Foundation.

Data-Driven Nurse Staffing in the Neonatal Intensive Care Unit

ABSTRACT

The challenge of nurse staffing is amplified in the acute care neonatal intensive care unit (NICU) setting, where a wide range of highly variable factors affect staffing. A comprehensive overview of infant factors (severity, intensity), nurse factors (education, experience, preferences, team dynamics), and unit factors (structure, layout, shift length, care model) influencing pre-shift NICU staffing is presented, along with how intra-shift variability of these and other factors must be accounted for to maintain effective and efficient assignments. There is opportunity to improve workload estimations and acuity measures for pre-shift staffing using technology and predictive analytics. Nurse staffing decisions affected by intra-shift factor variability can be enhanced using novel care models that decentralize decision-making. Improving NICU staffing requires a deliberate, systematic, data-driven approach, with commitment from nurses, resources from the management team, and an institutional culture prioritizing patient safety.

Predictive Scores for Late-Onset Neonatal Sepsis as an Early Diagnostic and Antimicrobial Stewardship Tool: What Have We Done So Far?

Background: Late-onset neonatal sepsis (LOS) represents a significant cause of morbidity and mortality worldwide, and early diagnosis remains a challenge. Various ‘sepsis scores’ have been developed to improve early identification. The aim of the current review is to summarize the current knowledge on the utility of predictive scores in LOS as a tool for early sepsis recognition, as well as an antimicrobial stewardship tool. Methods: The following research question was developed: Can we diagnose LOS with accuracy in neonates using a predictive score? A systematic search was performed in the PubMed database from 1982 (first predictive score published) to December 2021. Results: Some (1352) articles were identified—out of which, 16 were included in the review. Eight were original scores, five were validations of already existing scores and two were mixed. Predictive models were developed by combining a variety of clinical, laboratory and other variables. The majority were found to assist in early diagnosis, but almost all had a limited diagnostic accuracy. Conclusions: There is an increasing need worldwide for a simple and accurate score to promptly predict LOS. Combinations of the selected parameters may be helpful, but until now, a single score has not been proven to be comprehensive.

G-Sep: A Deep Learning Algorithm for Detection of Long-Term Sepsis Using Bidirectional Gated Recurrent Unit

Sepsis is a common and deadly condition that must be treated eloquently within 19 hours. Numerous deep learning techniques, including Recurrent Neural Networks, Convolution Neural Networks, Long Short-Term Memory, and Gated Recurrent Units, have been suggested for diagnosing long-term sepsis. Regardless, a sizable portion of them are computationally risky and have precision problems. The primary issue described is that output will degrade, and resource utilization will expand proportionately as the volume of dependencies grows. To overcome these issues, we propose a G-Sep technique utilizing Bidirectional Gated Recurrent Unit Algorithm, which consumes much less resource to detect the disease and in a short time with better accuracy than the existing methods to diagnose the sepsis. AI models could assist with distinguishing potential clinical factors and give better than existing conventional low-execution models. The proposed model is implemented utilizing Conda and Tensorflow Framework using the California Inpatient Severe Sepsis (CISS) Patient Dataset. The comparative simulation of the various existing models and the proposed G-Sep model is done using Conda and Tensor frameworks. The simulation results revealed that the proposed model had outperformed other frameworks in terms of mean average precision (mAP), receiver operating characteristic curve (ROC), and Area under the ROC Curve (AUROC) metrics linearly.

Clinical Informatics and Quality Improvement in the Pediatric Intensive Care Unit

Clinical informatics can support quality improvement and patient safety in the pediatric intensive care unit (PICU) in several ways including data extraction, analysis, and decision support enabled by electronic health records (EHRs), and databases and registries. Clinical decision support (CDS), embedded in EHRs, now an integral part of the workflow in the PICU, includes several tools and is increasingly leveraging artificial intelligence (AI). Understanding the opportunities and challenges can improve the engagement of clinicians with the design, validation, and implementation of CDS, improve satisfaction with CDS, and improve patient safety, care quality, and value.

Integration of Artificial Intelligence and Blockchain Technology in Healthcare and Agriculture

Over the last decade, the healthcare sector has accelerated its digitization and electronic health records (EHRs). As information technology progresses, the notion of intelligent health also gathers popularity. By combining technologies such as the internet of things (IoT) and artificial intelligence (AI), innovative healthcare modifies and enhances traditional medical systems in terms of efficiency, service, and personalization. On the other side, intelligent healthcare systems are incredibly vulnerable to data breaches and other malicious assaults. Recently, blockchain technology has emerged as a potentially transformative option for enhancing data management, access control, and integrity inside healthcare systems. Integrating these advanced approaches in agriculture is critical for managing food supply chains, drug supply chains, quality maintenance, and intelligent prediction. This study reviews the literature, formulates a research topic, and analyzes the applicability of blockchain to the agriculture/food industry and healthcare, with a particular emphasis on AI and IoT. This article summarizes research on the newest blockchain solutions paired with AI technologies for strengthening and inventing new technological standards for the healthcare ecosystems and food industry.

Diversity in Machine Learning: A Systematic Review of Text-Based Diagnostic Applications

OBJECTIVE

 As the storage of clinical data has transitioned into electronic formats, medical informatics has become increasingly relevant in providing diagnostic aid. The purpose of this review is to evaluate machine learning models that use text data for diagnosis and to assess the diversity of the included study populations.

METHODS

 We conducted a systematic literature review on three public databases. Two authors reviewed every abstract for inclusion. Articles were included if they used or developed machine learning algorithms to aid in diagnosis. Articles focusing on imaging informatics were excluded.

RESULTS

 From 2,260 identified papers, we included 78. Of the machine learning models used, neural networks were relied upon most frequently (44.9%). Studies had a median population of 661.5 patients, and diseases and disorders of 10 different body systems were studied. Of the 35.9% (N = 28) of papers that included race data, 57.1% (N = 16) of study populations were majority White, 14.3% were majority Asian, and 7.1% were majority Black. In 75% (N = 21) of papers, White was the largest racial group represented. Of the papers included, 43.6% (N = 34) included the sex ratio of the patient population.

DISCUSSION

 With the power to build robust algorithms supported by massive quantities of clinical data, machine learning is shaping the future of diagnostics. Limitations of the underlying data create potential biases, especially if patient demographics are unknown or not included in the training.

CONCLUSION

 As the movement toward clinical reliance on machine learning accelerates, both recording demographic information and using diverse training sets should be emphasized. Extrapolating algorithms to demographics beyond the original study population leaves large gaps for potential biases.

Artificial Intelligence in NICU and PICU: A Need for Ecological Validity, Accountability, and Human Factors

Pediatric patients, particularly in neonatal and pediatric intensive care units (NICUs and PICUs), are typically at an increased risk of fatal decompensation. That being said, any delay in treatment or minor errors in medication dosage can overcomplicate patient health. Under such an environment, clinicians are expected to quickly and effectively comprehend large volumes of medical information to diagnose and develop a treatment plan for any baby. The integration of Artificial Intelligence (AI) into the clinical workflow can be a potential solution to safeguard pediatric patients and augment the quality of care. However, before making AI an integral part of pediatric care, it is essential to evaluate the technology from a human factors perspective, ensuring its readiness (technology readiness level) and ecological validity. Addressing AI accountability is also critical to safeguarding clinicians and improving AI acceptance in the clinical workflow. This article summarizes the application of AI in NICU/PICU and consecutively identifies the existing flaws in AI (from clinicians’ standpoint), and proposes related recommendations, which, if addressed, can improve AIs’ readiness for a real clinical environment.

Early-Onset Neonatal Sepsis in Low- and Middle-Income Countries: Current Challenges and Future Opportunities

Neonatal sepsis is defined as a systemic infection within the first 28 days of life, with early-onset sepsis (EOS) occurring within the first 72h, although the definition of EOS varies in literature. Whilst the global incidence has dramatically reduced over the last decade, neonatal sepsis remains an important cause of neonatal mortality, highest in low- and middle-income countries (LMICs). Symptoms at the onset of neonatal sepsis can be subtle, and therefore EOS is often difficult to diagnose from clinical presentation and laboratory testing and blood cultures are not always conclusive or accessible, especially in resource limited countries. Although the World Health Organisation (WHO) currently advocates a ß-lactam, and gentamicin for first line treatment, availability and cost influence the empirical antibiotic therapy administered. Antibiotic treatment of neonatal sepsis in LMICs is highly variable, partially caused by factors such as cost of antibiotics (and who pays for them) and access to certain antibiotics. Antimicrobial resistance (AMR) has increased considerably over the past decade and this review discusses current microbiology data available in the context of the diagnosis, and treatment for EOS. Importantly, this review highlights a large variability in data availability, methodology, availability of diagnostics, and aetiology of sepsis pathogens.

Future of machine learning in paediatrics

Machine learning (ML) is a branch of artificial intelligence (AI) that enables computers to learn without being explicitly programmed, through a combination of statistics and computer science. It encompasses a variety of techniques used to analyse and interpret extremely large amounts of data, which can then be applied to create predictive models. Such applications of this technology are now ubiquitous in our day-to-day lives: predictive text, spam filtering, and recommendation systems in social media, streaming video and e-commerce to name a few examples. It is only more recently that ML has started to be implemented against the vast amount of data generated in healthcare. The emerging role of AI in refining healthcare delivery was recently highlighted in the 'National Health Service Long Term Plan 2019'. In paediatrics, workforce challenges, rising healthcare attendance and increased patient complexity and comorbidity mean that demands on paediatric services are also growing. As healthcare moves into this digital age, this review considers the potential impact ML can have across all aspects of paediatric care from improving workforce efficiency and aiding clinical decision-making to precision medicine and drug development.

Evaluation of the Need for Intensive Care in Children With Pneumonia: Machine Learning Approach

Background

Timely decision-making regarding intensive care unit (ICU) admission for children with pneumonia is crucial for a better prognosis. Despite attempts to establish a guideline or triage system for evaluating ICU care needs, no clinically applicable paradigm is available.

Objective

The aim of this study was to develop machine learning (ML) algorithms to predict ICU care needs for pediatric pneumonia patients within 24 hours of admission, evaluate their performance, and identify clinical indices for making decisions for pediatric pneumonia patients.

Methods

Pneumonia patients admitted to National Taiwan University Hospital from January 2010 to December 2019 aged under 18 years were enrolled. Their underlying diseases, clinical manifestations, and laboratory data at admission were collected. The outcome of interest was ICU transfer within 24 hours of hospitalization. We compared clinically relevant features between early ICU transfer patients and patients without ICU care. ML algorithms were developed to predict ICU admission. The performance of the algorithms was evaluated using sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and average precision. The relative feature importance of the best-performing algorithm was compared with physician-rated feature importance for explainability.

Results

A total of 8464 pediatric hospitalizations due to pneumonia were recorded, and 1166 (1166/8464, 13.8%) hospitalized patients were transferred to the ICU within 24 hours. Early ICU transfer patients were younger (P<.001), had higher rates of underlying diseases (eg, cardiovascular, neuropsychological, and congenital anomaly/genetic disorders; P<.001), had abnormal laboratory data, had higher pulse rates (P<.001), had higher breath rates (P<.001), had lower oxygen saturation (P<.001), and had lower peak body temperature (P<.001) at admission than patients without ICU transfer. The random forest (RF) algorithm achieved the best performance (sensitivity 0.94, 95% CI 0.92-0.95; specificity 0.94, 95% CI 0.92-0.95; AUC 0.99, 95% CI 0.98-0.99; and average precision 0.93, 95% CI 0.90-0.96). The lowest systolic blood pressure and presence of cardiovascular and neuropsychological diseases ranked in the top 10 in both RF relative feature importance and clinician judgment.

Conclusions

The ML approach could provide a clinically applicable triage algorithm and identify important clinical indices, such as age, underlying diseases, abnormal vital signs, and laboratory data for evaluating the need for intensive care in children with pneumonia.

Vital signs as physiomarkers of neonatal sepsis

Neonatal sepsis accounts for significant morbidity and mortality, particularly among premature infants in the Neonatal Intensive Care Unit. Abnormal vital sign patterns serve as physiomarkers of sepsis and provide early warning of illness before overt clinical decompensation. The systemic inflammatory response to pathogens signals the autonomic nervous system, leading to changes in temperature, respiratory rate, heart rate, and blood pressure. In infants with comorbidities of prematurity, vital sign abnormalities often occur in the absence of infection, which confounds sepsis diagnosis. This review will cover the mechanisms of vital sign changes in neonatal sepsis, including the cholinergic anti-inflammatory pathway mediated by the vagus nerve, which is critical to the host response to infectious and inflammatory insults. We will also review the clinical implications of vital sign changes in neonatal sepsis, including their use in early warning scores and systems to direct clinicians to the bedside of infants with physiologic changes that might be due to sepsis. IMPACT: This manuscript summarizes and reviews the relevant literature on the physiological manifestations of neonatal sepsis and how we monitor and analyze these through vital signs and advanced analytics.

Multichannel esophageal signals to monitor respiratory rate in preterm infants

BACKGROUND

Apnea of prematurity cannot be reliably measured with current monitoring techniques. Instead, indirect parameters such as oxygen desaturation or bradycardia are captured. We propose a Kalman filter-based detection of respiration activity and hence apnea using multichannel esophageal signals in neonatal intensive care unit patients.

METHODS

We performed a single-center observational study with moderately preterm infants. Commercially available nasogastric feeding tubes containing multiple electrodes were used to capture signals with customized software. Multichannel esophageal raw signals were manually annotated, processed using extended Kalman filter, and compared with standard monitoring data including chest impedance to measure respiration activity.

RESULTS

Out of a total of 405.4 h captured signals in 13 infants, 100 episodes of drop in oxygen saturation or heart rate were examined. Median (interquartile range) difference in respiratory rate was 0.04 (-2.45 to 1.48)/min between esophageal measurements annotated manually and with Kalman filter and -3.51 (-7.05 to -1.33)/min when compared to standard monitoring, suggesting an underestimation of respiratory rate when using the latter.

CONCLUSIONS

Kalman filter-based estimation of respiratory activity using multichannel esophageal signals is safe and feasible and results in respiratory rate closer to visual annotation than that derived from chest impedance of standard monitoring.

Knowledge gaps in late-onset neonatal sepsis in preterm neonates: a roadmap for future research

Late-onset neonatal sepsis (LONS) remains an important threat to the health of preterm neonates in the neonatal intensive care unit. Strategies to optimize care for preterm neonates with LONS are likely to improve survival and long-term neurocognitive outcomes. However, many important questions on how to improve the prevention, early detection, and therapy for LONS in preterm neonates remain unanswered. This review identifies important knowledge gaps in the management of LONS and describe possible methods and technologies that can be used to resolve these knowledge gaps. The availability of computational medicine and hypothesis-free-omics approaches give way to building bedside feedback tools to guide clinicians in personalized management of LONS. Despite advances in technology, implementation in clinical practice is largely lacking although such tools would help clinicians to optimize many aspects of the management of LONS. We outline which steps are needed to get possible research findings implemented on the neonatal intensive care unit and provide a roadmap for future research initiatives. IMPACT: This review identifies knowledge gaps in prevention, early detection, antibiotic, and additional therapy of late-onset neonatal sepsis in preterm neonates and provides a roadmap for future research efforts. Research opportunities are addressed, which could provide the means to fill knowledge gaps and the steps that need to be made before possible clinical use. Methods to personalize medicine and technologies feasible for bedside clinical use are described.

Artificial Intelligence to Improve Health Outcomes in the NICU and PICU: A Systematic Review

CONTEXT

Artificial intelligence (AI) technologies are increasingly used in pediatrics and have the potential to help inpatient physicians provide high-quality care for critically ill children.

OBJECTIVE

We aimed to describe the use of AI to improve any health outcome(s) in neonatal and pediatric intensive care.

DATA SOURCE

PubMed, IEEE Xplore, Cochrane, and Web of Science databases.

STUDY SELECTION

We used peer-reviewed studies published between June 1, 2010, and May 31, 2020, in which researchers described (1) AI, (2) pediatrics, and (3) intensive care. Studies were included if researchers assessed AI use to improve at least 1 health outcome (eg, mortality).

DATA EXTRACTION

Data extraction was conducted independently by 2 researchers. Articles were categorized by direct or indirect impact of AI, defined by the European Institute of Innovation and Technology Health joint report.

RESULTS

Of the 287 publications screened, 32 met inclusion criteria. Approximately 22% (n = 7) of studies revealed a direct impact and improvement in health outcomes after AI implementation. Majority were in prototype testing, and few were deployed into an ICU setting. Among the remaining 78% (n = 25) AI models outperformed standard clinical modalities and may have indirectly influenced patient outcomes. Quantitative assessment of health outcomes using statistical measures, such as area under the receiver operating curve (56%; n = 18) and specificity (38%; n = 12), revealed marked heterogeneity in metrics and standardization.

CONCLUSIONS

Few studies have revealed that AI has directly improved health outcomes for pediatric critical care patients. Further prospective, experimental studies are needed to assess AI's impact by using established implementation frameworks, standardized metrics, and validated outcome measures.

Neonatal sepsis prediction through clinical decision support algorithms: A systematic review

AIM

To systematically summarise the current evidence of employing clinical decision support algorithms (CDSAs) using non-invasive parameters for sepsis prediction in neonates.

METHODS

A comprehensive search in PubMed, CENTRAL and EMBASE was conducted. Screening, data extraction and risk of bias were performed by two authors. The certainty of the evidence was assessed using GRADE.

PROSPERO ID

CRD42020205143.

RESULTS

After abstract and full-text screening, 36 studies comprising 18,096 infants were included. Most CDSAs evaluated heart rate (HR)-based parameters. Two publications derived from one randomised-controlled trial assessing HR characteristics reported significant reduction in 30-day septicaemia-related mortality. Thirty-four non-randomised studies found promising yet inconclusive results.

CONCLUSION

Heart rate-based parameters are reliable components of CDSAs for sepsis prediction, particularly in combination with additional vital signs and demographics. However, inconclusive evidence and limited standardisation restricts clinical implementation of CDSAs outside of a controlled research environment. Further experimentation and comparison of parameter combinations and testing of new CDSAs are warranted.

A maChine and deep Learning Approach to predict pulmoNary hyperteNsIon in newbornS with congenital diaphragmatic Hernia (CLANNISH): Protocol for a retrospective study

INTRODUCTION

Outcome predictions of patients with congenital diaphragmatic hernia (CDH) still have some limitations in the prenatal estimate of postnatal pulmonary hypertension (PH). We propose applying Machine Learning (ML), and Deep Learning (DL) approaches to fetuses and newborns with CDH to develop forecasting models in prenatal epoch, based on the integrated analysis of clinical data, to provide neonatal PH as the first outcome and, possibly: favorable response to fetal endoscopic tracheal occlusion (FETO), need for Extracorporeal Membrane Oxygenation (ECMO), survival to ECMO, and death. Moreover, we plan to produce a (semi)automatic fetus lung segmentation system in Magnetic Resonance Imaging (MRI), which will be useful during project implementation but will also be an important tool itself to standardize lung volume measures for CDH fetuses.

METHODS AND ANALYTICS

Patients with isolated CDH from singleton pregnancies will be enrolled, whose prenatal checks were performed at the Fetal Surgery Unit of the Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico (Milan, Italy) from the 30th week of gestation. A retrospective data collection of clinical and radiological variables from newborns' and mothers' clinical records will be performed for eligible patients born between 01/01/2012 and 31/12/2020. The native sequences from fetal magnetic resonance imaging (MRI) will be collected. Data from different sources will be integrated and analyzed using ML and DL, and forecasting algorithms will be developed for each outcome. Methods of data augmentation and dimensionality reduction (feature selection and extraction) will be employed to increase sample size and avoid overfitting. A software system for automatic fetal lung volume segmentation in MRI based on the DL 3D U-NET approach will also be developed.

ETHICS AND DISSEMINATION

This retrospective study received approval from the local ethics committee (Milan Area 2, Italy). The development of predictive models in CDH outcomes will provide a key contribution in disease prediction, early targeted interventions, and personalized management, with an overall improvement in care quality, resource allocation, healthcare, and family savings. Our findings will be validated in a future prospective multicenter cohort study.

REGISTRATION

The study was registered at ClinicalTrials.gov with the identifier NCT04609163.

A Risk Prediction Model to Identify Newborns at Risk for Missing Early Childhood Vaccinations

BACKGROUND

Approximately 30% of US children aged 24 months have not received all recommended vaccines. This study aimed to develop a prediction model to identify newborns at high risk for missing early childhood vaccines.

METHODS

A retrospective cohort included 9080 infants born weighing ≥2000 g at an academic medical center between 2008 and 2013. Electronic medical record data were linked to vaccine data from the Washington State Immunization Information System. Risk models were constructed using derivation and validation samples. K-fold cross-validation identified risk factors for model inclusion based on alpha = 0.01. For each patient in the derivation set, the total number of weighted adverse risk factors was calculated and used to establish groups at low, medium, or high risk for undervaccination. Logistic regression evaluated the likelihood of not completing the 7-vaccine series by age 19 months. The final model was tested using the validation sample.

RESULTS

Overall, 53.6% failed to complete the 7-vaccine series by 19 months. Six risk factors were identified: race/ethnicity, maternal language, insurance status, birth hospitalization length of stay, medical service, and hepatitis B vaccine receipt. Likelihood of non-completion was greater in the high (77.1%; adjusted odds ratio [AOR] 5.6; 99% confidence interval [CI]: 4.2, 7.4) and medium (52.7%; AOR 1.9; 99% CI: 1.6, 2.2) vs low (38.7%) risk groups in the derivation sample. Similar results were observed in the validation sample.

CONCLUSIONS

Our prediction model using information readily available in birth hospitalization records consistently identified newborns at high risk for undervaccination. Early identification of high-risk families could be useful for initiating timely, tailored vaccine interventions.

Machine Learning Models for Classification of Cushing's Syndrome Using Retrospective Data

Accurate classification of Cushing's Syndrome (CS) plays a critical role in providing the early and correct diagnosis of CS that may facilitate treatment and improve patient outcomes. Diagnosis of CS is a complex process, which requires careful and concurrent interpretation of signs and symptoms, multiple biochemical test results, and findings of medical imaging by physicians with a high degree of specialty and knowledge to make correct judgments. In this article, we explore the state of the art machine learning algorithms to demonstrate their potential as a clinical decision support system to analyze and classify CS to facilitate the diagnosis, prognosis, and treatment of CS. Prominent algorithms are compared using nested cross-validation and various class comparison strategies including multiclass, one vs. all, and one vs. one binary classification. Our findings show that Random Forest (RF) algorithm is most suitable for the classification of CS. We demonstrate that the proposed approach can classify CS with an average accuracy of 92% and an average F1 score of 91.5%, depending on the class comparison strategy and selected features. RF-based one vs. all binary classification model achieves sensitivity of 97.6%, precision of 91.1%, and specificity of 87.1% to discriminate CS from non-CS on the test dataset. RF-based multiclass classification model achieves average per class sensitivity of 91.8%, average per class specificity of 97.1%, and average per class precision of 92.1% to classify different subtypes of CS on the test dataset. Clinical performance evaluation suggests that the developed models can help improve physicians' judgment in diagnosing CS.