Machine Learning To Predict Serious Bacterial Infections in Young Febrile Infants

Artificial intelligence and prescription of antibiotic therapy: present and future

INTRODUCTION

In the past few years, the use of artificial intelligence in healthcare has grown exponentially. Prescription of antibiotics is not exempt from its rapid diffusion, and various machine learning (ML) techniques, from logistic regression to deep neural networks and large language models, have been explored in the literature to support decisions regarding antibiotic prescription.

AREAS COVERED

In this narrative review, we discuss promises and challenges of the application of ML-based clinical decision support systems (ML-CDSSs) for antibiotic prescription. A search was conducted in PubMed up to April 2024.

EXPERT OPINION

Prescribing antibiotics is a complex process involving various dynamic phases. In each of these phases, the support of ML-CDSSs has shown the potential, and also the actual ability in some studies, to favorably impacting relevant clinical outcomes. Nonetheless, before widely exploiting this massive potential, there are still crucial challenges ahead that are being intensively investigated, pertaining to the transparency of training data, the definition of the sufficient degree of prediction explanations when predictions are obtained through black box models, and the legal and ethical framework for decision responsibility whenever an antibiotic prescription is supported by ML-CDSSs.

Predicting community acquired bloodstream infection in infants using full blood count parameters and C-reactive protein; a machine learning study

Early recognition of bloodstream infection (BSI) in infants can be difficult, as symptoms may be non-specific, and culture can take up to 48 h. As a result, many infants receive unneeded antibiotic treatment while awaiting the culture results. In this study, we aimed to develop a model that can reliably identify infants who do not have positive blood cultures (and, by extension, BSI) based on the full blood count (FBC) and C-reactive protein (CRP) values. Several models (i.e. multivariable logistic regression, linear discriminant analysis, K nearest neighbors, support vector machine, random forest model and decision tree) were trained using FBC and CRP values of 2693 infants aged 7 to 60 days with suspected BSI between 2005 and 2022 in a tertiary paediatric hospital in Dublin, Ireland. All models tested showed similar sensitivities (range 47% - 62%) and specificities (range 85%-95%). A trained decision tree and random forest model were applied to the full dataset and to a dataset containing infants with suspected BSI in 2023 and showed good segregation of a low-risk and high-risk group. Negative predictive values for these two models were high for the full dataset (> 99%) and for the 2023 dataset (> 97%), while positive predictive values were low in both dataset (4%-20%).   Conclusion: We identified several models that can predict positive blood cultures in infants with suspected BSI aged 7 to 60 days. Application of these models could prevent administration of antimicrobial treatment and burdensome diagnostics in infants who do not need them. What is Known: • Bloodstream infection (BSI) in infants cause non-specific symptoms and may be difficult to diagnose. • Results of blood cultures can take up to 48 hours. What is New: • Machine learning models can contribute to clinical decision making on BSI in infants while blood culture results are not yet known.

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.

A machine learning model for the early diagnosis of bloodstream infection in patients admitted to the pediatric intensive care unit

Bloodstream infection (BSI) is associated with increased morbidity and mortality in the pediatric intensive care unit (PICU) and high healthcare costs. Early detection and appropriate treatment of BSI may improve patient's outcome. Data on machine-learning models to predict BSI in pediatric patients are limited and neither study included time series data. We aimed to develop a machine learning model to predict an early diagnosis of BSI in patients admitted to the PICU. This was a retrospective cohort study of patients who had at least one positive blood culture result during stay at a PICU of a tertiary-care university hospital, from January 1st to December 31st 2019. Patients with positive blood culture results with growth of contaminants and those with incomplete data were excluded. Models were developed using demographic, clinical and laboratory data collected from the electronic medical record. Laboratory data (complete blood cell counts with differential and C-reactive protein) and vital signs (heart rate, respiratory rate, blood pressure, temperature, oxygen saturation) were obtained 72 hours before and on the day of blood culture collection. A total of 8816 data from 76 patients were processed by the models. The machine committee was the best-performing model, showing accuracy of 99.33%, precision of 98.89%, sensitivity of 100% and specificity of 98.46%. Hence, we developed a model using demographic, clinical and laboratory data collected on a routine basis that was able to detect BSI with excellent accuracy and precision, and high sensitivity and specificity. The inclusion of vital signs and laboratory data variation over time allowed the model to identify temporal changes that could be suggestive of the diagnosis of BSI. Our model might help the medical team in clinical-decision making by creating an alert in the electronic medical record, which may allow early antimicrobial initiation and better outcomes.

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.

Differentiating viral and bacterial infections: A machine learning model based on routine blood test values

The growing threat of antibiotic resistance necessitates accurate differentiation between bacterial and viral infections for proper antibiotic administration. In this study, a Virus vs. Bacteria machine learning model was developed to distinguish between these infection types using 16 routine blood test results, C-reactive protein concentration (CRP), biological sex, and age. With a dataset of 44,120 cases from a single medical center, the model achieved an accuracy of 82.2 %, a sensitivity of 79.7 %, a specificity of 84.5 %, a Brier score of 0.129, and an area under the ROC curve (AUC) of 0.905, outperforming a CRP-based decision rule. Notably, the machine learning model enhanced accuracy within the CRP range of 10-40 mg/L, a range where CRP alone is less informative. These results highlight the advantage of integrating multiple blood parameters in diagnostics. The "Virus vs. Bacteria" model paves the way for advanced diagnostic tools, leveraging machine learning to optimize infection management.

Leukopenia, neutropenia, and procalcitonin levels in young febrile infants with invasive bacterial infections

BACKGROUND AND OBJECTIVE

Serum procalcitonin (PCT) is a highly accurate biomarker for stratifying the risk of invasive bacterial infections (IBIs) in febrile infants ≤60 days old. However, PCT is unavailable in some settings. We explored the association of leukopenia and neutropenia with IBIs in non-critically ill febrile infants ≤60 days old, with and without PCT.

METHODS

We conducted a secondary analysis of a prospective observational cohort consisting of 7407 non-critically ill infants ≤60 days old with temperatures ≥38°C. We focused on the risk of IBIs in patients with leukopenia (white blood cell [WBC] count <5000 cells/μL) or neutropenia (absolute neutrophil count [ANC] <1000 cells/μL), categorized to extremes of lower values, and the impact of PCT on these associations. Multiple logistic regression was used to identify independent predictors of IBIs.

RESULTS

Final analysis included 6865 infants with complete data; 45% (3098) had PCT data available. Of the 6865, a total of 111 (1.6%) had bacteremia without bacterial meningitis, 18 (0.3%) had bacterial meningitis without bacteremia, and 19 (0.3%) had both bacteremia and bacterial meningitis. IBI was present in four of 20 (20%) infants with WBC counts ≤2500 cells/μL and four of 311 (1.3%) with ANC <1000 cells/μL. In multivariable logistic regression analysis not including PCT, a WBC count <2500 cells/μL was significantly associated with IBI (OR 13.48, 95% CI 2.92-45.35). However, no patients with leukopenia or neutropenia and PCT ≤0.5 ng/mL had IBIs.

CONCLUSIONS

Leukopenia ≤2500 cells/μL in febrile infants ≤60 days old is associated with IBIs. However, in the presence of normal PCT levels, no patients with leukopenia had IBIs. While this suggests leukopenia ≤2500 cells/μL is a risk factor for IBIs in non-critically ill young febrile infants only when PCT is unavailable or elevated, the overall low frequency of leukopenia in this cohort warrants caution in interpretation, with future validation required.

An all-inclusive model for predicting invasive bacterial infection in febrile infants age 7-60 days

BACKGROUND

Invasive bacterial infections (IBIs) in febrile infants are rare but potentially devastating. We aimed to derive and validate a predictive model for IBI among febrile infants age 7-60 days.

METHODS

Data were abstracted retrospectively from electronic records of 37 emergency departments (EDs) for infants with a measured temperature >=100.4 F who underwent an ED evaluation with blood and urine cultures. Models to predict IBI were developed and validated respectively using a random 80/20 dataset split, including 10-fold cross-validation. We used precision recall curves as the classification metric.

RESULTS

Of 4411 eligible infants with a mean age of 37 days, 29% had characteristics that would likely have excluded them from existing risk stratification protocols. There were 196 patients with IBI (4.4%), including 43 (1.0%) with bacterial meningitis. Analytic approaches varied in performance characteristics (precision recall range 0.04-0.29, area under the curve range 0.5-0.84), with the XGBoost model demonstrating the best performance (0.29, 0.84). The five most important variables were serum white blood count, maximum temperature, absolute neutrophil count, absolute band count, and age in days.

CONCLUSION

A machine learning model (XGBoost) demonstrated the best performance in predicting a rare outcome among febrile infants, including those excluded from existing algorithms.

IMPACT

Several models for the risk stratification of febrile infants have been developed. There is a need for a preferred comprehensive model free from limitations and algorithm exclusions that accurately predicts IBIs. This is the first study to derive an all-inclusive predictive model for febrile infants aged 7-60 days in a community ED sample with IBI as a primary outcome. This machine learning model demonstrates potential for clinical utility in predicting IBI.

Early detection of late-onset neonatal sepsis from noninvasive biosignals using deep learning: A multicenter prospective development and validation study

BACKGROUND

Neonatal sepsis is responsible for significant morbidity and mortality worldwide. Its accurate and timely diagnosis is hindered by vague symptoms and the urgent necessity for early antibiotic intervention. The gold standard for diagnosing the condition is the identification of a pathogenic organism from normally sterile sites via laboratory testing. However, this method is resource-intensive and cannot be conducted continuously.

OBJECTIVE

This study aimed to predict the onset of late-onset sepsis (LOS) with good diagnostic value as early as possible using non-invasive biosignal measurements from neonatal intensive care unit (NICU) monitors.

METHODS

In this prospective multicenter study, we developed a multimodal machine learning algorithm based on a convolutional neural network (CNN) structure that uses the power spectral density (PSD) of recorded biosignals to predict the onset of LOS. This approach aimed to discern LOS-related pathogenic spectral signatures without labor-intensive manual artifact removal.

RESULTS

The model achieved an area under the receiver operating characteristic score of 0.810 (95 % CI 0.698-0.922) on the validation dataset. With an optimal operating point, LOS detection had 83 % sensitivity and 73 % specificity. The median early detection was 44 h before clinical suspicion. The results highlighted the additive importance of electrocardiogram and respiratory impedance (RESP) signals in improving predictive accuracy. According to a more detailed analysis, the predictive power arose from the morphology of the electrocardiogram's R-wave and sudden changes in the RESP signal.

CONCLUSION

Raw biosignals from NICU monitors, in conjunction with PSD transformation, as input to the CNN, can provide state-of-the-art prediction performance for LOS without the need for artifact removal. To the knowledge of the authors, this is the first study to highlight the independent and additive predictive potential of electrocardiogram R-wave morphology and concurrent, sudden changes in the RESP waveform in predicting the onset of LOS using non-invasive biosignals.

Artificial intelligence in paediatrics: Current events and challenges

This article examines the use of artificial intelligence (AI) in the field of paediatric care within the framework of the 7P medicine model (Predictive, Preventive, Personalized, Precise, Participatory, Peripheral and Polyprofessional). It highlights various applications of AI in the diagnosis, treatment and management of paediatric diseases as well as the role of AI in prevention and in the efficient management of health care resources and the resulting impact on the sustainability of public health systems. Successful cases of the application of AI in the paediatric care setting are presented, placing emphasis on the need to move towards a 7P health care model. Artificial intelligence is revolutionizing society at large and has a great potential for significantly improving paediatric care.

Artificial intelligence in the neonatal intensive care unit: the time is now

Artificial intelligence (AI) has the potential to revolutionize the neonatal intensive care unit (NICU) care by leveraging the large-scale, high-dimensional data that are generated by NICU patients. There is an emerging recognition that the confluence of technological progress, commercialization pathways, and rich data sets provides a unique opportunity for AI to make a lasting impact on the NICU. In this perspective article, we discuss four broad categories of AI applications in the NICU: imaging interpretation, prediction modeling of electronic health record data, integration of real-time monitoring data, and documentation and billing. By enhancing decision-making, streamlining processes, and improving patient outcomes, AI holds the potential to transform the quality of care for vulnerable newborns, making the excitement surrounding AI advancements well-founded and the potential for significant positive change stronger than ever before.

Clinical Timing-Sequence Warning Models for Serious Bacterial Infections in Adults Based on Machine Learning: Retrospective Study

BACKGROUND

Serious bacterial infections (SBIs) are linked to unplanned hospital admissions and a high mortality rate. The early identification of SBIs is crucial in clinical practice.

OBJECTIVE

This study aims to establish and validate clinically applicable models designed to identify SBIs in patients with infective fever.

METHODS

Clinical data from 945 patients with infective fever, encompassing demographic and laboratory indicators, were retrospectively collected from a 2200-bed teaching hospital between January 2013 and December 2020. The data were randomly divided into training and test sets at a ratio of 7:3. Various machine learning (ML) algorithms, including Boruta, Lasso (least absolute shrinkage and selection operator), and recursive feature elimination, were utilized for feature filtering. The selected features were subsequently used to construct models predicting SBIs using logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) with 5-fold cross-validation. Performance metrics, including the receiver operating characteristic (ROC) curve and area under the ROC curve (AUC), accuracy, sensitivity, and other relevant parameters, were used to assess model performance. Considering both model performance and clinical needs, 2 clinical timing-sequence warning models were ultimately confirmed using LR analysis. The corresponding predictive nomograms were then plotted for clinical use. Moreover, a physician, blinded to the study, collected additional data from the same center involving 164 patients during 2021. The nomograms developed in the study were then applied in clinical practice to further validate their clinical utility.

RESULTS

In total, 69.9% (661/945) of the patients developed SBIs. Age, hemoglobin, neutrophil-to-lymphocyte ratio, fibrinogen, and C-reactive protein levels were identified as important features by at least two ML algorithms. Considering the collection sequence of these indicators and clinical demands, 2 timing-sequence models predicting the SBI risk were constructed accordingly: the early admission model (model 1) and the model within 24 hours of admission (model 2). LR demonstrated better stability than RF and XGBoost in both models and performed the best in model 2, with an AUC, accuracy, and sensitivity of 0.780 (95% CI 0.720-841), 0.754 (95% CI 0.698-804), and 0.776 (95% CI 0.711-832), respectively. XGBoost had an advantage over LR in AUC (0.708, 95% CI 0.641-775 vs 0.686, 95% CI 0.617-754), while RF achieved better accuracy (0.729, 95% CI 0.673-780) and sensitivity (0.790, 95% CI 0.728-844) than the other 2 approaches in model 1. Two SBI-risk prediction nomograms were developed for clinical use based on LR, and they exhibited good performance with an accuracy of 0.707 and 0.750 and a sensitivity of 0.729 and 0.927 in clinical application.

CONCLUSIONS

The clinical timing-sequence warning models demonstrated efficacy in predicting SBIs in patients suspected of having infective fever and in clinical application, suggesting good potential in clinical decision-making. Nevertheless, additional prospective and multicenter studies are necessary to further confirm their clinical utility.

Febrile infants risk score at triage (FIRST) for the early identification of serious bacterial infections

We aimed to derive the Febrile Infants Risk Score at Triage (FIRST) to quantify risk for serious bacterial infections (SBIs), defined as bacteremia, meningitis and urinary tract infections. We performed a prospective observational study on febrile infants < 3 months old at a tertiary hospital in Singapore between 2018 and 2021. We utilized machine learning and logistic regression to derive 2 models: FIRST, based on patient demographics, vital signs and history, and FIRST + , adding laboratory results to the same variables. SBIs were diagnosed in 224/1002 (22.4%) infants. Among 994 children with complete data, age (adjusted odds ratio [aOR] 1.01 95%CI 1.01-1.02, p < 0.001), high temperature (aOR 2.22 95%CI 1.69-2.91, p < 0.001), male sex (aOR 2.62 95%CI 1.86-3.70, p < 0.001) and fever of ≥ 2 days (aOR 1.79 95%CI 1.18-2.74, p = 0.007) were independently associated with SBIs. For FIRST + , abnormal urine leukocyte esterase (aOR 16.46 95%CI 10.00-27.11, p < 0.001) and procalcitonin (aOR 1.05 95%CI 1.01-1.09, p = 0.009) were further identified. A FIRST + threshold of ≥ 15% predicted risk had a sensitivity of 81.8% (95%CI 70.5-91.0%) and specificity of 65.6% (95%CI 57.8-72.7%). In the testing dataset, FIRST + had an area under receiver operating characteristic curve of 0.87 (95%CI 0.81-0.94). These scores can potentially guide triage and prioritization of febrile infants.

Perceptions of Artificial Intelligence-Assisted Care for Children With a Respiratory Complaint

OBJECTIVES

To evaluate caregiver opinions on the use of artificial intelligence (AI)-assisted medical decision-making for children with a respiratory complaint in the emergency department (ED).

METHODS

We surveyed a sample of caregivers of children presenting to a pediatric ED with a respiratory complaint. We assessed caregiver opinions with respect to AI, defined as "specialized computer programs" that "help make decisions about the best way to care for children." We performed multivariable logistic regression to identify factors associated with discomfort with AI-assisted decision-making.

RESULTS

Of 279 caregivers who were approached, 254 (91.0%) participated. Most indicated they would want to know if AI was being used for their child's health care (93.5%) and were extremely or somewhat comfortable with the use of AI in deciding the need for blood (87.9%) and viral testing (87.6%), interpreting chest radiography (84.6%), and determining need for hospitalization (78.9%). In multivariable analysis, caregiver age of 30 to 37 years (adjusted odds ratio [aOR] 3.67, 95% confidence interval [CI] 1.43-9.38; relative to 18-29 years) and a diagnosis of bronchospasm (aOR 5.77, 95% CI 1.24-30.28 relative to asthma) were associated with greater discomfort with AI. Caregivers with children being admitted to the hospital (aOR 0.23, 95% CI 0.09-0.50) had less discomfort with AI.

CONCLUSIONS

Caregivers were receptive toward the use of AI-assisted decision-making. Some subgroups (caregivers aged 30-37 years with children discharged from the ED) demonstrated greater discomfort with AI. Engaging with these subgroups should be considered when developing AI applications for acute care.

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.

Explainable deep learning model to predict invasive bacterial infection in febrile young infants: A retrospective study

BACKGROUND

Machine learning models have demonstrated superior performance in predicting invasive bacterial infection (IBI) in febrile infants compared to commonly used risk stratification criteria in recent studies. However, the black-box nature of these models can make them difficult to apply in clinical practice. In this study, we developed and validated an explainable deep learning model that can predict IBI in febrile infants ≤ 60 days of age visiting the emergency department.

METHODS

We conducted a retrospective study of febrile infants aged ≤ 60 days who presented to the pediatric emergency department of a medical center in Taiwan between January 1, 2011 and December 31, 2019. Patients with uncertain test results and complex chronic health conditions were excluded. IBI was defined as the growth of a pathogen in the blood or cerebrospinal fluid. We used a deep neural network to develop a predictive model for IBI and compared its performance to the IBI score and step-by-step approach. The SHapley Additive Explanations (SHAP) technique was used to explain the model's predictions at different levels.

RESULTS

Our study included 1847 patients, 53 (2.7%) of whom had IBI. The deep learning model performed similarly to the IBI score and step-by-step approach in terms of sensitivity and negative predictive value, but provided better specificity (54%), positive predictive value (5%), and area under the receiver-operating characteristic curve (0.87). SHapley Additive exPlanations identified five influential predictive variables (absolute neutrophil count, body temperature, heart rate, age, and C-reactive protein).

CONCLUSION

We have developed an explainable deep learning model that can predict IBI in febrile infants aged 0-60 days. The model not only performs better than previous scoring systems, but also provides insight into how it arrives at its predictions through individual features and cases.

Artificial Intelligence in Pediatric Nephrology-A Call for Action

Artificial intelligence is playing an increasingly important role in many fields of clinical care to assist health care providers in patient management. In adult-focused nephrology, artificial intelligence is beginning to be used to improve clinical care, hemodialysis prescriptions, and follow-up of transplant recipients. This article provides an overview of medical artificial intelligence applications relevant to pediatric nephrology. We describe the core concepts of artificial intelligence and machine learning and cover the basics of neural networks and deep learning. We also discuss some examples for clinical applications of artificial intelligence in pediatric nephrology, including neonatal kidney function, early recognition of acute kidney injury, renally cleared drug dosing, intrapatient variability, urinary tract infection workup in infancy, and longitudinal disease progression. Furthermore, we consider the future of artificial intelligence in clinical pediatric nephrology and its potential impact on medical practice and address the ethical issues artificial intelligence raises in terms of clinical decision-making, health care provider-patient relationship, patient privacy, and data collection. This article also represents a call for action involving those of us striving to provide optimal services for children, adolescents, and young adults with chronic conditions.

Artificial intelligence-based clinical decision support in pediatrics

Machine learning models may be integrated into clinical decision support (CDS) systems to identify children at risk of specific diagnoses or clinical deterioration to provide evidence-based recommendations. This use of artificial intelligence models in clinical decision support (AI-CDS) may have several advantages over traditional "rule-based" CDS models in pediatric care through increased model accuracy, with fewer false alerts and missed patients. AI-CDS tools must be appropriately developed, provide insight into the rationale behind decisions, be seamlessly integrated into care pathways, be intuitive to use, answer clinically relevant questions, respect the content expertise of the healthcare provider, and be scientifically sound. While numerous machine learning models have been reported in pediatric care, their integration into AI-CDS remains incompletely realized to date. Important challenges in the application of AI models in pediatric care include the relatively lower rates of clinically significant outcomes compared to adults, and the lack of sufficiently large datasets available necessary for the development of machine learning models. In this review article, we summarize key concepts related to AI-CDS, its current application to pediatric care, and its potential benefits and risks. IMPACT: The performance of clinical decision support may be enhanced by the utilization of machine learning-based algorithms to improve the predictive performance of underlying models. Artificial intelligence-based clinical decision support (AI-CDS) uses models that are experientially improved through training and are particularly well suited toward high-dimensional data. The application of AI-CDS toward pediatric care remains limited currently but represents an important area of future research.

Parental Perceptions on Use of Artificial Intelligence in Pediatric Acute Care

BACKGROUND

Family engagement is critical in the implementation of artificial intelligence (AI)-based clinical decision support tools, which will play an increasing role in health care in the future. We sought to understand parental perceptions of computer-assisted health care of children in the emergency department (ED).

METHODS

We conducted a population-weighted household panel survey of parents with minor children in their home in a large US city to evaluate perceptions of the use of computer programs for the care of children with respiratory illness. We identified demographics associated with discomfort with AI using survey-weighted logistic regression.

RESULTS

Surveys were completed by 1620 parents (panel response rate = 49.7%). Most respondents were comfortable with the use of computer programs to determine the need for antibiotics (77.6%) or bloodwork (76.5%), and to interpret radiographs (77.5%). In multivariable analysis, Black non-Hispanic parents reported greater discomfort with AI relative to White non-Hispanic parents (odds ratio [OR] 1.67, 95% confidence interval [CI] 1.03-2.70) as did younger parents (18-25 years) relative to parents ≥46 years (OR 2.48, 95% CI 1.31-4.67). The greatest perceived benefits of computer programs were finding something a human would miss (64.2%, 95% CI 60.9%-67.4%) and obtaining a more rapid diagnosis (59.6%; 56.2%-62.9%). Areas of greatest concern were diagnostic errors (63.0%, 95% CI 59.6%-66.4%), and recommending incorrect treatment (58.9%, 95% CI 55.5%-62.3%).

CONCLUSIONS

Parents were generally receptive to computer-assisted management of children with respiratory illnesses in the ED, though reservations emerged. Black non-Hispanic and younger parents were more likely to express discomfort about AI.

The use of machine learning and artificial intelligence within pediatric critical care

The field of pediatric critical care has been hampered in the era of precision medicine by our inability to accurately define and subclassify disease phenotypes. This has been caused by heterogeneity across age groups that further challenges the ability to perform randomized controlled trials in pediatrics. One approach to overcome these inherent challenges include the use of machine learning algorithms that can assist in generating more meaningful interpretations from clinical data. This review summarizes machine learning and artificial intelligence techniques that are currently in use for clinical data modeling with relevance to pediatric critical care. Focus has been placed on the differences between techniques and the role of each in the clinical arena. The various forms of clinical decision support that utilize machine learning are also described. We review the applications and limitations of machine learning techniques to empower clinicians to make informed decisions at the bedside. IMPACT: Critical care units generate large amounts of under-utilized data that can be processed through artificial intelligence. This review summarizes the machine learning and artificial intelligence techniques currently being used to process clinical data. The review highlights the applications and limitations of these techniques within a clinical context to aid providers in making more informed decisions at the bedside.

Performance Evaluation of Host Biomarker Combinations for the Diagnosis of Serious Bacterial Infection in Young Febrile Children: A Double-Blind, Multicentre, Observational Study

The diagnosis of serious bacterial infection (SBI) in young febrile children remains challenging. This prospective, multicentre, observational study aimed to identify new protein marker combinations that can differentiate a bacterial infection from a viral infection in 983 children, aged 7 days–36 months, presenting with a suspected SBI at three French paediatric emergency departments. The blood levels of seven protein markers (CRP, PCT, IL-6, NGAL, MxA, TRAIL, IP-10) were measured at enrolment. The patients received the standard of care, blinded to the biomarker results. An independent adjudication committee assigned a bacterial vs. viral infection diagnosis based on clinical data, blinded to the biomarker results. Computational modelling was applied to the blood levels of the biomarkers using independent training and validation cohorts. Model performances (area under the curve (AUC), positive and negative likelihood ratios (LR+ and LR–)) were calculated and compared to those of the routine biomarkers CRP and PCT. The targeted performance for added value over CRP or PCT was LR+ ≥ 5.67 and LR− ≤ 0.5. Out of 652 analysed patients, several marker combinations outperformed CRP and PCT, although none achieved the targeted performance criteria in the 7 days–36 months population. The models seemed to perform better in younger (7–91 day-old) patients, with the CRP/MxA/TRAIL combination performing best (AUC 0.895, LR+ 10.46, LR− 0.16). Although computational modelling using combinations of bacterial- and viral-induced host-protein markers is promising, further optimisation is necessary to improve SBI diagnosis in young febrile children.

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.

Application of Machine Learning Approaches to Predict Postnatal Growth Failure in Very Low Birth Weight Infants

PURPOSE

The aims of the study were to develop and evaluate a machine learning model with which to predict postnatal growth failure (PGF) among very low birth weight (VLBW) infants.

MATERIALS AND METHODS

Of 10425 VLBW infants registered in the Korean Neonatal Network between 2013 and 2017, 7954 infants were included. PGF was defined as a decrease in Z score >1.28 at discharge, compared to that at birth. Six metrics [area under the receiver operating characteristic curve (AUROC), accuracy, precision, sensitivity, specificity, and F1 score] were obtained at five time points (at birth, 7 days, 14 days, 28 days after birth, and at discharge). Machine learning models were built using four different techniques [extreme gradient boosting (XGB), random forest, support vector machine, and convolutional neural network] to compare against the conventional multiple logistic regression (MLR) model.

RESULTS

The XGB algorithm showed the best performance with all six metrics across the board. When compared with MLR, XGB showed a significantly higher AUROC (p=0.03) for Day 7, which was the primary performance metric. Using optimal cut-off points, for Day 7, XGB still showed better performances in terms of AUROC (0.74), accuracy (0.68), and F1 score (0.67). AUROC values seemed to increase slightly from birth to 7 days after birth with significance, almost reaching a plateau after 7 days after birth.

CONCLUSION

We have shown the possibility of predicting PGF through machine learning algorithms, especially XGB. Such models may help neonatologists in the early diagnosis of high-risk infants for PGF for early intervention.

Prediction of Lumbar Drainage-Related Meningitis Based on Supervised Machine Learning Algorithms

Background

Lumbar drainage is widely used in the clinic; however, forecasting lumbar drainage-related meningitis (LDRM) is limited. We aimed to establish prediction models using supervised machine learning (ML) algorithms.

Methods

We utilized a cohort of 273 eligible lumbar drainage cases. Data were preprocessed and split into training and testing sets. Optimal hyper-parameters were archived by 10-fold cross-validation and grid search. The support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were adopted for model training. The area under the operating characteristic curve (AUROC) and precision-recall curve (AUPRC), true positive ratio (TPR), true negative ratio (TNR), specificity, sensitivity, accuracy, and kappa coefficient were used for model evaluation. All trained models were internally validated. The importance of features was also analyzed.

Results

In the training set, all the models had AUROC exceeding 0.8. SVM and the RF models had an AUPRC of more than 0.6, but the ANN model had an unexpectedly low AUPRC (0.380). The RF and ANN models revealed similar TPR, whereas the ANN model had a higher TNR and demonstrated better specificity, sensitivity, accuracy, and kappa efficiency. In the testing set, most performance indicators of established models decreased. However, the RF and AVM models maintained adequate AUROC (0.828 vs. 0.719) and AUPRC (0.413 vs. 0.520), and the RF model also had better TPR, specificity, sensitivity, accuracy, and kappa efficiency. Site leakage showed the most considerable mean decrease in accuracy.

Conclusions

The RF and SVM models could predict LDRM, in which the RF model owned the best performance, and site leakage was the most meaningful predictor.

A Novel Algorithm With Paired Predictive Indexes to Stratify the Risk Levels of Neonates With Invasive Bacterial Infections: A Multicenter Cohort Study

BACKGROUND

Our aim was to develop a predictive model comprising clinical and laboratory parameters for early identification of full-term neonates with different risks of invasive bacterial infections (IBIs).

METHODS

We conducted a retrospective study including 1053 neonates presenting in 9 tertiary hospitals in China from January 2010 to August 2019. An algorithm with paired predictive indexes (PPIs) for risk stratification of neonatal IBIs was developed. Predictive performance was validated using k-fold cross-validation.

RESULTS

Overall, 166 neonates were diagnosed with IBIs (15.8%). White blood cell count, C-reactive protein level, procalcitonin level, neutrophil percentage, age at admission, neurologic signs, and ill-appearances showed independent associations with IBIs from stepwise regression analysis and combined into 23 PPIs. Using 10-fold cross-validation, a combination of 7 PPIs with the highest predictive performance was picked out to construct an algorithm. Finally, 58.1% (612/1053) patients were classified as low-risk cases. The sensitivity and negative predictive value of the algorithm were 95.3% (95% confidence interval: 91.7-98.3) and 98.7% (95% confidence interval: 97.8-99.6), respectively. An online calculator based on this algorithm was developed for clinical use.

CONCLUSIONS

The new algorithm constructed for this study was a valuable tool to screen neonates with suspected infection. It stratified risk levels of IBIs and had an excellent predictive performance.

Refinement and Validation of a Clinical-Based Approach to Evaluate Young Febrile Infants

BACKGROUND AND OBJECTIVE

For febrile infants, predictive models to detect bacterial infections are available, but clinical adoption remains limited by implementation barriers. There is a need for predictive models using widely available predictors. Thus, we previously derived 2 novel predictive models (machine learning and regression) by using demographic and clinical factors, plus urine studies. The objective of this study is to refine and externally validate the predictive models.

METHODS

This is a cross-sectional study of infants initially evaluated at one pediatric emergency department from January 2011 to December 2018. Inclusion criteria were age 0 to 90 days, temperature ≥38°C, documented gestational age, and insurance type. To reduce potential biases, we derived models again by using derivation data without insurance status and tested the ability of the refined models to detect bacterial infections (ie, urinary tract infection, bacteremia, and meningitis) in the separate validation sample, calculating areas-under-the-receiver operating characteristic curve, sensitivities, and specificities.

RESULTS

Of 1419 febrile infants (median age 53 days, interquartile range = 32-69), 99 (7%) had a bacterial infection. Areas-under-the-receiver operating characteristic curve of machine learning and regression models were 0.92 (95% confidence interval [CI] 0.89-0.94) and 0.90 (0.86-0.93) compared with 0.95 (0.91-0.98) and 0.96 (0.94-0.98) in the derivation study. Sensitivities and specificities of machine learning and regression models were 98.0% (94.7%-100%) and 54.2% (51.5%-56.9%) and 96.0% (91.5%-99.1%) and 50.0% (47.4%-52.7%).

CONCLUSIONS

Compared with the derivation study, the machine learning and regression models performed similarly. Findings suggest a clinical-based model can estimate bacterial infection risk. Future studies should prospectively test the models and investigate strategies to optimize clinical adoption.

Development and validation of machine learning-driven prediction model for serious bacterial infection among febrile children in emergency departments

Serious bacterial infection (SBI) in children, such as bacterial meningitis or sepsis, is an important condition that can lead to fatal outcomes. Therefore, since it is very important to accurately diagnose SBI, SBI prediction tools such as ‘Refined Lab-score’ or ‘clinical prediction rule’ have been developed and used. However, these tools can predict SBI only when there are values of all factors used in the tool, and if even one of them is missing, the tools become useless. Therefore, the purpose of this study was to develop and validate a machine learning-driven model to predict SBIs among febrile children, even with missing values. This was a multicenter retrospective observational study including febrile children <6 years of age who visited Emergency departments (EDs) of 3 different tertiary hospitals from 2016 to 2018. The SBI prediction model was trained with a derivation cohort (data from two hospitals) and externally tested with a validation cohort (data from a third hospital). A total of 11,973 and 2,858 patient records were included in the derivation and validation cohorts, respectively. In the derivation cohort, the area under the receiver operating characteristic curve (AUROC) of the RF model was 0.964 (95% confidence interval [CI], 0.943–0.986), and the area under the precision-recall curve (AUPRC) was 0.753 (95% CI, 0.681–0.824). The conventional LR (CLR) model showed corresponding values of 0.902 (95% CI, 0.894–0.910) and 0.573 (95% CI, 0.560–0.586), respectively. In the validation cohort, the AUROC (95% CI) of the RF model was 0.950 (95% CI, 0.945–0.956), the AUPRC was 0.605 (95% CI, 0.593–0.616), and the CLR presented corresponding values of 0.815 (95% CI, 0.789–0.841) and 0.586 (95% CI, 0.553–0.619), respectively. We developed a machine learning-driven prediction model for SBI among febrile children, which works robustly despite missing values. And it showed superior performance compared to CLR in both internal validation and external validation.

Machine Learning Used to Compare the Diagnostic Accuracy of Risk Factors, Clinical Signs and Biomarkers and to Develop a New Prediction Model for Neonatal Early-onset Sepsis

BACKGROUND

Current strategies for risk stratification and prediction of neonatal early-onset sepsis (EOS) are inefficient and lack diagnostic performance. The aim of this study was to use machine learning to analyze the diagnostic accuracy of risk factors (RFs), clinical signs and biomarkers and to develop a prediction model for culture-proven EOS. We hypothesized that the contribution to diagnostic accuracy of biomarkers is higher than of RFs or clinical signs.

STUDY DESIGN

Secondary analysis of the prospective international multicenter NeoPInS study. Neonates born after completed 34 weeks of gestation with antibiotic therapy due to suspected EOS within the first 72 hours of life participated. Primary outcome was defined as predictive performance for culture-proven EOS with variables known at the start of antibiotic therapy. Machine learning was used in form of a random forest classifier.

RESULTS

One thousand six hundred eighty-five neonates treated for suspected infection were analyzed. Biomarkers were superior to clinical signs and RFs for prediction of culture-proven EOS. C-reactive protein and white blood cells were most important for the prediction of the culture result. Our full model achieved an area-under-the-receiver-operating-characteristic-curve of 83.41% (±8.8%) and an area-under-the-precision-recall-curve of 28.42% (±11.5%). The predictive performance of the model with RFs alone was comparable with random.

CONCLUSIONS

Biomarkers have to be considered in algorithms for the management of neonates suspected of EOS. A 2-step approach with a screening tool for all neonates in combination with our model in the preselected population with an increased risk for EOS may have the potential to reduce the start of unnecessary antibiotics.

Validation of a Classification Model Using Complete Blood Count to Predict Severe Human Adenovirus Lower Respiratory Tract Infections in Pediatric Cases

BACKGROUND

Human adenovirus (HAdV) lower respiratory tract infections (LRTIs) are prone to severe cases and even cause death in children. Here, we aimed to develop a classification model to predict severity in pediatric patients with HAdV LRTIs using complete blood count (CBC).

METHODS

The CBC parameters from pediatric patients with a diagnosis of HAdV LRTIs from 2013 to 2019 were collected during the disease's course. The data were analyzed as potential predictors for severe cases and were selected using a random forest model.

RESULTS

We enrolled 1,652 CBC specimens from 1,069 pediatric patients with HAdV LRTIs in the present study. Four hundred and seventy-four patients from 2017 to 2019 were used as the discovery cohort, and 470 patients from 2013 to 2016 were used as the validation cohort. The monocyte ratio (MONO%) was the most obvious difference between the mild and severe groups at onset, and could be used as a marker for the early accurate prediction of the severity [area under the subject operating characteristic curve (AUROC): 0.843]. Four risk factors [MONO%, hematocrit (HCT), red blood cell count (RBC), and platelet count (PLT)] were derived to construct a classification model of severe and mild cases using a random forest model (AUROC: 0.931 vs. 0.903).

CONCLUSION

Monocyte ratio can be used as an individual predictor of severe cases in the early stages of HAdV LRTIs. The four risk factors model is a simple and accurate risk assessment tool that can predict severe cases in the early stages of HAdV LRTIs.

Predictor of Early Administration of Antibiotics and a Volume Resuscitation for Young Infants with Septic Shock

(1) Background: It is critical to administer antibiotics and fluid bolus within 1 h of recognizing sepsis in pediatric patients. This study aimed to identify the predictor of the successful completion of a 1-h sepsis bundle for infants with suspected sepsis. (2) Methods: This is an observational study using a prospective registry including febrile young infants (aged < 90 days) who visited a pediatric emergency department with a core body temperature of 38.0 °C or higher and 36.0 °C or lower. Univariate and logistic regression analyses were conducted to determine the predictor (s) of successful sepsis bundle completion. (3) Results: Of the 323 registered patients, 118 patients with suspected sepsis were analyzed, and 38 patients (32.2%) received a bundle-compliant treatment. Among potential variables, such as age, sex, and vital sign parameters, the logistic regression analysis showed that heart rate (odds ratio: OR 1.02; 95% confidence interval: 1.00-1.04) is a significant predictor of the completion of a 1-h sepsis bundle. (4) Conclusions: We found that tachycardia facilitated the sepsis recognition and promoted the successful completion of a 1-h sepsis bundle for young infants with suspected septic shock and a possible indicator for improving the quality of the team-based sepsis management.

Development and Validation of Predictors for the Survival of Patients With COVID-19 Based on Machine Learning

Background: The outbreak of COVID-19 attracted the attention of the whole world. Our study aimed to explore the predictors for the survival of patients with COVID-19 by machine learning. Methods: We conducted a retrospective analysis and used the idea of machine learning to train the data of COVID-19 patients in Leishenshan Hospital through the logical regression algorithm provided by scikit-learn. Results: Of 2010 patients, 42 deaths were recorded until March 29, 2020. The mortality rate was 2.09%. There were 6,812 records after data features combination and data arrangement, 3,025 records with high-quality after deleting incomplete data by manual checking, and 5,738 records after data balancing finally by the method of Borderline-1 Smote. The results of 10 times of data training by logistic regression model showed that albumin, saturation of pulse oxygen at admission, alanine aminotransferase, and percentage of neutrophils were possibly associated with the survival of patients. The results of 10 times of data training including age, sex, and height beyond the laboratory measurements showed that percentage of neutrophils, saturation of pulse oxygen at admission, alanine aminotransferase, sex, and albumin were possibly associated with the survival of patients. The rates of precision, recall, and f1-score of the two training models were all higher than 0.9 and relatively stable. Conclusions: We demonstrated that percentage of neutrophils, saturation of pulse oxygen at admission, alanine aminotransferase, sex, and albumin were possibly associated with the survival of patients with COVID-19.

Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure

BACKGROUND

Early identification of critically ill neonates with poor outcomes can optimize therapeutic strategies. We aimed to examine whether machine learning (ML) methods can improve mortality prediction for neonatal intensive care unit (NICU) patients on intubation for respiratory failure.

METHODS

A total of 1734 neonates with respiratory failure were randomly divided into training (70%, n = 1214) and test (30%, n = 520) sets. The primary outcome was the probability of NICU mortality. The areas under the receiver operating characteristic curves (AUCs) of several ML algorithms were compared with those of the conventional neonatal illness severity scoring systems including the NTISS and SNAPPE-II.

RESULTS

For NICU mortality, the random forest (RF) model showed the highest AUC (0.939 (0.921-0.958)) for the prediction of neonates with respiratory failure, and the bagged classification and regression tree model demonstrated the next best results (0.915 (0.891-0.939)). The AUCs of both models were significantly better than the traditional NTISS (0.836 (0.800-0.871)) and SNAPPE-II scores (0.805 (0.766-0.843)). The superior performances were confirmed by higher accuracy and F1 score and better calibration, and the superior and net benefit was confirmed by decision curve analysis. In addition, Shapley additive explanation (SHAP) values were utilized to explain the RF prediction model.

CONCLUSIONS

Machine learning algorithms increase the accuracy and predictive ability for mortality of neonates with respiratory failure compared with conventional neonatal illness severity scores. The RF model is suitable for clinical use in the NICU, and clinicians can gain insights and have better communication with families in advance.

Neonatal bloodstream infections

PURPOSE OF REVIEW

Neonatal bloodstream infections (BSI) are a major contributor to morbidity and mortality within neonatal intensive care units. BSI, including central line-associated BSI, have decreased over the past 15 years but remain common in extremely preterm infants. The purpose of this review is to highlight recent advances in the causes, diagnosis, management, and prevention of neonatal BSI.

RECENT FINDINGS

Continued quality improvement efforts and bundles have reduced BSI incidence, and novel approaches are highlighted. An update of emerging pathogens as well as traditional pathogens with novel antimicrobial resistance, which are an increasingly common cause of neonatal BSI, is included. Finally, current and future investigations into serum or noninvasive biomarkers for neonatal BSI are reviewed.

SUMMARY

Neonatal BSIs continue to decrease due to enhanced infection control and prevention techniques. However, many challenges remain, including emerging bacterial and fungal resistance and the continued need for novel diagnostics that hasten time to pathogen identification and effective treatment. This review of the past 18 months highlights the rapid changes in this area. Ongoing efforts to reduce the morbidity and mortality caused by neonatal BSI must remain a priority.

Using Machine Learning to Predict Invasive Bacterial Infections in Young Febrile Infants Visiting the Emergency Department

Background: The aim of this study was to develop and evaluate a machine learning (ML) model to predict invasive bacterial infections (IBIs) in young febrile infants visiting the emergency department (ED). Methods: This retrospective study was conducted in the EDs of three medical centers across Taiwan from 2011 to 2018. We included patients age in 0–60 days who were visiting the ED with clinical symptoms of fever. We developed three different ML algorithms, including logistic regression (LR), supportive vector machine (SVM), and extreme gradient boosting (XGboost), comparing their performance at predicting IBIs to a previous validated score system (IBI score). Results: During the study period, 4211 patients were included, where 126 (3.1%) had IBI. A total of eight, five, and seven features were used in the LR, SVM, and XGboost through the feature selection process, respectively. The ML models can achieve a better AUROC value when predicting IBIs in young infants compared with the IBI score (LR: 0.85 vs. SVM: 0.84 vs. XGBoost: 0.85 vs. IBI score: 0.70, p-value < 0.001). Using a cost sensitive learning algorithm, all ML models showed better specificity in predicting IBIs at a 90% sensitivity level compared to an IBI score > 2 (LR: 0.59 vs. SVM: 0.60 vs. XGBoost: 0.57 vs. IBI score >2: 0.43, p-value < 0.001). Conclusions: All ML models developed in this study outperformed the traditional scoring system in stratifying low-risk febrile infants after the standardized sensitivity level.

Machine learning in patient flow: a review

This work is a review of the ways in which machine learning has been used in order to plan, improve or aid the problem of moving patients through healthcare services. We decompose the patient flow problem into four subcategories: prediction of demand on a healthcare institution, prediction of the demand and resource required to transfer patients from the emergency department to the hospital, prediction of potential resource required for the treatment and movement of inpatients and prediction of length-of-stay and discharge timing. We argue that there are benefits to both approaches of considering the healthcare institution as a whole as well as the patient by patient case and that ideally a combination of these would be best for improving patient flow through hospitals. We also argue that it is essential for there to be a shared dataset that will allow researchers to benchmark their algorithms on and thereby allow future researchers to build on that which has already been done. We conclude that machine learning for the improvement of patient flow is still a young field with very few papers tailor-making machine learning methods for the problem being considered. Future works should consider the need to transfer algorithms trained on a dataset to multiple hospitals and allowing for dynamic algorithms which will allow real-time decision-making to help clinical staff on the shop floor.

Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study

Differential diagnosis between bacterial and viral meningitis is crucial. In our study, to differentiate bacterial vs. viral meningitis, three machine learning (ML) algorithms (multiple logistic regression (MLR), random forest (RF), and naïve-Bayes (NB)) were applied for the two age groups (0-14 and >14 years) of patients with meningitis by both conventional (culture) and molecular (PCR) methods. Cerebrospinal fluid (CSF) neutrophils, CSF lymphocytes, neutrophil-to-lymphocyte ratio (NLR), blood albumin, blood C-reactive protein (CRP), glucose, blood soluble urokinase-type plasminogen activator receptor (suPAR), and CSF lymphocytes-to-blood CRP ratio (LCR) were used as predictors for the ML algorithms. The performance of the ML algorithms was evaluated through a cross-validation procedure, and optimal predictions of the type of meningitis were above 95% for viral and 78% for bacterial meningitis. Overall, MLR and RF yielded the best performance when using CSF neutrophils, CSF lymphocytes, NLR, albumin, glucose, gender, and CRP. Also, our results reconfirm the high diagnostic accuracy of NLR in the differential diagnosis between bacterial and viral meningitis.

External Validation of an Invasive Bacterial Infection Score for Young Febrile Infants

OBJECTIVES

The Aronson rule is a point-based clinical decision rule for the identification of febrile infants ≤60 days of age at low risk of invasive bacterial infection (IBI) in the emergency department. This rule uses variables of temperature, age, urinalysis, and absolute neutrophil count. We sought to externally validate this decision rule.

METHODS

We conducted a secondary analysis of a multicenter prospective cohort of febrile infants ≤60 days old presenting to the emergency department between December 2008 and May 2013. Infants were excluded if they had clinical sepsis or chronic conditions or were missing any laboratory components of the Aronson score. Our outcome was IBI (bacteremia and/or bacterial meningitis). We assessed the accuracy of the Aronson rule by reporting metrics of diagnostic accuracy with 95% confidence intervals (CIs) at different point thresholds.

RESULTS

Of 4130 included patients (780 <21 days of age; 2362 boys), 87 (2.1%) had an IBI, including 65 with isolated bacteremia and 22 with meningitis. Using an Aronson cutoff score of 2 resulted in a sensitivity of 93.1% (95% CI 85.6%-97.4%), specificity of 26.6% (95% CI 25.3%-28.0%), and negative predictive value of 99.4% (95% CI 98.8%-99.8%). Six patients with IBI (3 with bacterial meningitis) were misclassified as low risk when using a threshold of 2.

CONCLUSIONS

The Aronson rule demonstrates metrics of diagnostic accuracy that are comparable to the derivation study. Our findings suggest that the rule may be generalizable for the risk stratification of well-appearing febrile infants.