4.6 Review

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

Related references

Note: Only part of the references are listed.
Article Biochemistry & Molecular Biology

Development and validation of a deep-learning-based pediatric early warning system: A single-center study

Seong Jong Park et al.

Summary: The performance of a pediatric early warning system (pDEWS) was evaluated and compared with a modified pediatric early warning score (PEWS) and prediction models using random forest (RF) and logistic regression (LR). The study found that pDEWS outperformed the other methods and integrating it into rapid response teams (RRTs) could improve operational efficiency and clinical outcomes.

BIOMEDICAL JOURNAL (2022)

Article Pediatrics

Pediatric Organ Dysfunction Information Update Mandate (PODIUM) Contemporary Organ Dysfunction Criteria: Executive Summary

Melania M. Bembea et al.

Summary: The prior criteria for organ dysfunction in critically ill children were based on expert opinion. This study summarized data characterizing single and multiple organ dysfunction and derived contemporary criteria for pediatric organ dysfunction through systematic reviews of the literature. A total of 43 criteria for pediatric organ dysfunction were established, providing a foundation for researchers to identify and study organ dysfunction in critically ill children.

PEDIATRICS (2022)

Article Critical Care Medicine

Pediatric severe traumatic brain injury mortality prediction determined with machine learning-based modeling

Mark Daley et al.

Summary: Using machine learning and advanced analytics, we have successfully developed a predictive model that can accurately predict mortality in children with severe traumatic brain injury (sTBI). This model, utilizing several admission variables, demonstrates high classification accuracy and discriminative ability.

INJURY-INTERNATIONAL JOURNAL OF THE CARE OF THE INJURED (2022)

Article Multidisciplinary Sciences

Breaking into the black box of artificial intelligence

Neil Savage

NATURE (2022)

Article Critical Care Medicine

Clinical Decision Support in the PICU: Implications for Design and Evaluation*

Adam C. Dziorny et al.

Summary: The current landscape of clinical decision support (CDS) tools in PICUs was assessed in order to identify priority areas of focus. The survey revealed consensus among providers regarding the importance of evidence-based CDS tools having a proven impact on patient safety. Despite their presence, practitioners still view CDS tools as intrusive and have concerns about diminished critical thinking. Deimplementing ineffective CDS may help alleviate this burden, but postimplementation evaluation of CDS is rare.

PEDIATRIC CRITICAL CARE MEDICINE (2022)

Article Medical Informatics

Al recognition of patient race in medical imaging: a modelling study

Judy Wawira Gichoya et al.

Summary: In this study, we demonstrate that standard AI deep learning models can be trained to accurately predict a person's race from medical images across multiple imaging modalities. This detection is not attributed to proxies or imaging-related surrogate covariates for race, and the model's ability persists over all anatomical regions and frequency spectrums of the images. The findings highlight the risks associated with deploying AI models in medical imaging, as they can accurately predict race even from corrupted or manipulated images that clinical experts may struggle with.

LANCET DIGITAL HEALTH (2022)

Article Emergency Medicine

Deep Learning Algorithm to Predict Need for Critical Care in Pediatric Emergency Departments

Joon-myoung Kwon et al.

Summary: By utilizing data from the Korean National Emergency Department Information System, we developed a deep learning algorithm that accurately predicted the need for critical care in pediatric emergency department patients. This algorithm outperformed traditional early warning scores, triage tools, and machine learning methods in predicting critical care and hospitalization outcomes.

PEDIATRIC EMERGENCY CARE (2021)

Article Public, Environmental & Occupational Health

Designing a Clinical Decision Support Tool That Leverages Machine Learning for Suicide Risk Prediction: Development Study in Partnership With Native American Care Providers

Emily E. Haroz et al.

Summary: Machine learning algorithms for suicide risk prediction have shown promise, but there are challenges in implementing them to guide clinical care. Collaborating with partners to develop and operationalize risk prediction algorithms can enhance clinical care in a community setting. Case managers were willing to accept risk flags based on predictive algorithms, but programming for implementation needed to produce output indicating high versus low risk.

JMIR PUBLIC HEALTH AND SURVEILLANCE (2021)

Article Orthopedics

Application of machine learning to predict the outcome of pediatric traumatic brain injury

Thara Tunthanathip et al.

Summary: This study aimed to assess the predictability of machine learning for functional outcomes of pediatric traumatic brain injury (TBI). The best performing model was found to be the support vector machine model, with high sensitivity. The prognostic factors used in the model included Glasgow coma scale score, hypotension, pupillary light reflex, and subarachnoid hemorrhage.

CHINESE JOURNAL OF TRAUMATOLOGY (2021)

Article Pediatrics

Decision-making in pediatric blunt solid organ injury: deep learning approach to predict massive transfusion, need for operative management, and mortality risk

Niti Shahi et al.

Summary: This study used machine learning algorithms to predict the need for emergent intervention and mortality in pediatric blunt solid organ injury cases with high accuracy and sensitivity.

JOURNAL OF PEDIATRIC SURGERY (2021)

Article Computer Science, Information Systems

Mining tasks and task characteristics from electronic health record audit logs with unsupervised machine learning

Bob Chen et al.

Summary: This study aims to characterize EHR activities as tasks using unsupervised learning methods and define novel data-driven metrics. The results show significant differences in performance time based on task complexity, but no significant differences in clinician prevalence and event types between tasks of different complexities.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION (2021)

Article Multidisciplinary Sciences

External validation of EPIC's Risk of Unplanned Readmission model, the LACE plus index and SQLape as predictors of unplanned hospital readmissions: A monocentric, retrospective, diagnostic cohort study in Switzerland

Aljoscha Benjamin Hwang et al.

Summary: This study aimed to externally validate EPIC's Risk of Unplanned Readmission model and compare it with the internationally used LACE+ index and the Swiss SQLAPE (R) tool. The results showed that EPIC's model had less favorable performance compared to its counterparts, suggesting that its complexity may have hindered its generalizability, warranting model updating.

PLOS ONE (2021)

Article Critical Care Medicine

Continuous Prediction of Mortality in the PICU: A Recurrent Neural Network Model in a Single-Center Dataset*

Melissa D. Aczon et al.

Summary: The study developed a recurrent neural network model that can dynamically integrate patient's electronic medical records for continuous, accurate, and real-time risk assessment in the ICU. Results showed that the model performed well across different diagnostic categories, demonstrating higher discriminative ability and performance.

PEDIATRIC CRITICAL CARE MEDICINE (2021)

Article Multidisciplinary Sciences

Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare

Kim Huat Goh et al.

Summary: Sepsis is a major cause of death in hospitals, and early prediction and diagnosis are challenging. The study develops an artificial intelligence algorithm using both structured data and unstructured clinical notes, demonstrating high predictive accuracy 12 hours before the onset of sepsis.

NATURE COMMUNICATIONS (2021)

Article Multidisciplinary Sciences

Using explainable machine learning to characterise data drift and detect emergent health risks for emergency department admissions during COVID-19

Christopher Duckworth et al.

Summary: The research demonstrates how explainable machine learning can monitor data drift and emerging health risks in healthcare settings. By training and evaluating models, two benefits were discovered that can help improve the accuracy of predicting patient hospital admission risk in emergency departments.

SCIENTIFIC REPORTS (2021)

Article Computer Science, Information Systems

Evaluation of an optimized context-aware clinical decision support system for drug-drug interaction screening

Katoo M. Muylle et al.

Summary: The implementation of six optimization strategies in a clinical decision support system for drug-drug interaction screening resulted in high alert acceptance and clinical pharmacist intervention acceptance, with administration acceptance being significantly higher than prescription acceptance.

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS (2021)

Article Medicine, General & Internal

External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients

Andrew Wong et al.

Summary: The study evaluated the Epic Sepsis Model (ESM) in predicting sepsis and found that it had poor discrimination and calibration. The widespread use of ESM despite its poor performance raises concerns about sepsis management nationally.

JAMA INTERNAL MEDICINE (2021)

Review Computer Science, Interdisciplinary Applications

Applying Self-Supervised Learning to Medicine: Review of the State of the Art and Medical Implementations

Alexander Chowdhury et al.

Summary: Machine learning is widely used in healthcare, with a growing focus on self-supervised learning (SSL) for leveraging unlabeled data. Current research is dedicated to the development of SSL algorithms and their applications in the medical field.

INFORMATICS-BASEL (2021)

Article Critical Care Medicine

Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care

Junzi Dong et al.

Summary: The study successfully predicted creatinine-based AKI in pediatric critical care patients using a machine learning model, providing early alerting and actionable feedback up to 48 hours in advance. The model performed well in predicting moderate to severe AKI, potentially improving outcomes and reducing AKI incidence through early interventions.

CRITICAL CARE (2021)

Article Computer Science, Artificial Intelligence

AI for radiographic COVID-19 detection selects shortcuts over signal

Alex J. DeGrave et al.

Summary: Recent deep learning systems to detect COVID-19 from chest radiographs may rely on confounding factors rather than medical pathology, leading to accuracy issues when tested in new hospitals. The approach to obtain training data for these AI systems introduces a nearly ideal scenario for learning spurious shortcuts, raising concerns in medical-imaging AI. Evaluation of models on external data is insufficient to ensure reliance on medically relevant pathology, highlighting the importance of explainable AI for clinical deployment of machine-learning healthcare models.

NATURE MACHINE INTELLIGENCE (2021)

Article Health Care Sciences & Services

Using machine learning to predict paediatric 30-day unplanned hospital readmissions: a case-control retrospective analysis of medical records, including written discharge documentation

Huaqiong Zhou et al.

Summary: This study found that adding written discharge documentation and clinical information can improve the accuracy of predicting pediatric patient readmissions. Important predictors included patients' social history, language proficiency, completeness of discharge documentation, and timing of issuing discharge summary.

AUSTRALIAN HEALTH REVIEW (2021)

Article Health Care Sciences & Services

Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?

Brett K. Beaulieu-Jones et al.

Summary: Machine learning models trained on clinician-initiated administrative data show performance close to EMR-based benchmarks for inpatient outcomes, but exhibit declines in performance when dealing with specific patient populations, such as myocardial infarction patients. The results highlight the importance of physician diagnosis in the prognostic performance of these models and suggest that models with similar performance may derive their signal from observing clinical behavior to generate predictions. Performance exceeding these benchmarks is necessary for models to guide clinicians in individual decisions.

NPJ DIGITAL MEDICINE (2021)

Article Computer Science, Artificial Intelligence

Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans

Michael Roberts et al.

Summary: Many machine learning-based approaches have been developed for the prognosis and diagnosis of COVID-19 from medical images. However, a systematic review found that current studies have methodological flaws, preventing their potential clinical utility. Recommendations are provided to address these issues for higher-quality model development.

NATURE MACHINE INTELLIGENCE (2021)

Review Critical Care Medicine

Practitioner's Guide to Latent Class Analysis: Methodological Considerations and Common Pitfalls

Pratik Sinha et al.

Summary: Latent class analysis is a probabilistic modeling algorithm that allows clustering of data and statistical inference, which has seen increased application in critical care and respiratory medicine. This review provides an overview of the principles behind latent class analysis and outlines the key processes and challenges in executing this method for investigators seeking to apply it to their data.

CRITICAL CARE MEDICINE (2021)

Review Anesthesiology

A Narrative Review of Analytics in Pediatric Cardiac Anesthesia and Critical Care Medicine

Kelly L. Grogan et al.

JOURNAL OF CARDIOTHORACIC AND VASCULAR ANESTHESIA (2020)

Review Infectious Diseases

Machine learning for clinical decision support in infectious diseases: a narrative review of current applications

N. Peiffer-Smadja et al.

CLINICAL MICROBIOLOGY AND INFECTION (2020)

Review Computer Science, Artificial Intelligence

Clinical Decision Support Systems for Triage in the Emergency Department using Intelligent Systems: a Review

Marta Fernandes et al.

ARTIFICIAL INTELLIGENCE IN MEDICINE (2020)

Article Multidisciplinary Sciences

Machine learning models for identifying preterm infants at risk of cerebral hemorrhage

Varvara Turova et al.

PLOS ONE (2020)

Article Urology & Nephrology

A Time-Updated, Parsimonious Model to Predict AKI in Hospitalized Children

Ibrahim Sandokji et al.

JOURNAL OF THE AMERICAN SOCIETY OF NEPHROLOGY (2020)

Review Allergy

Prediction models for childhood asthma: A systematic review

Dilini M. Kothalawala et al.

PEDIATRIC ALLERGY AND IMMUNOLOGY (2020)

Article Critical Care Medicine

Subphenotypes in critical care: translation into clinical practice

Kiran Reddy et al.

Lancet Respiratory Medicine (2020)

Article Critical Care Medicine

A Vital Sign-Based Model to Predict Clinical Deterioration in Hospitalized Children*

Anoop Mayampurath et al.

PEDIATRIC CRITICAL CARE MEDICINE (2020)

Article Critical Care Medicine

973: Latent Class Analysis of Pediatric Patients With Near-Fatal Asthma

Sneha Kolli et al.

CRITICAL CARE MEDICINE (2020)

Article Multidisciplinary Sciences

Using machine learning tools to predict outcomes for emergency department intensive care unit patients

Qiangrong Zhai et al.

SCIENTIFIC REPORTS (2020)

Review Critical Care Medicine

Artificial Intelligence in the Intensive Care Unit

Guillermo Gutierrez

CRITICAL CARE (2020)

Article Orthopedics

Machine Learning and Artificial Intelligence: Definitions, Applications, and Future Directions

J. Matthew Helm et al.

CURRENT REVIEWS IN MUSCULOSKELETAL MEDICINE (2020)

Article Pediatrics

Machine learning concepts, concerns and opportunities for a pediatric radiologist

Michael M. Moore et al.

PEDIATRIC RADIOLOGY (2019)

Review Medicine, General & Internal

Machine Learning in Medicine

Alvin Rajkomar et al.

NEW ENGLAND JOURNAL OF MEDICINE (2019)

Article Critical Care Medicine

Age-Specific Distribution of Diagnosis and Outcomes of Children Admitted to ICUs: A Population-Based Cohort Study*

Minyoung Jung et al.

PEDIATRIC CRITICAL CARE MEDICINE (2019)

Article Health Care Sciences & Services

Machine learning in medicine: a practical introduction

Jenni A. M. Sidey-Gibbons et al.

BMC MEDICAL RESEARCH METHODOLOGY (2019)

Review Critical Care Medicine

Big Data and Data Science in Critical Care

L. Nelson Sanchez-Pinto et al.

CHEST (2018)

Meeting Abstract Critical Care Medicine

TRENDS IN MORTALITY RATES IN PEDIATRIC INTENSIVE CARE UNITS IN THE UNITED STATES FROM 2004 TO 2015

Punkaj Gupta et al.

CRITICAL CARE MEDICINE (2018)

Article Critical Care Medicine

Applying Machine Learning to Pediatric Critical Care Data

Jon B. Williams et al.

PEDIATRIC CRITICAL CARE MEDICINE (2018)

Review Medicine, General & Internal

eDoctor: machine learning and the future of medicine

G. S. Handelman et al.

JOURNAL OF INTERNAL MEDICINE (2018)

Article Critical Care Medicine

Applying Artificial Intelligence to Identify Physiomarkers Predicting Severe Sepsis in the PICU

Rishikesan Kamaleswaran et al.

PEDIATRIC CRITICAL CARE MEDICINE (2018)

Article Critical Care Medicine

Machine learning for real-time prediction of complications in critical care: a retrospective study

Alexander Meyer et al.

LANCET RESPIRATORY MEDICINE (2018)

Editorial Material Medicine, General & Internal

Clinical Decision Support in the Era of Artificial Intelligence

Edward H. Shortliffe et al.

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION (2018)

Article Critical Care Medicine

Acute Respiratory Distress Syndrome Subphenotypes Respond Differently to Randomized Fluid Management Strategy

Katie R. Famous et al.

AMERICAN JOURNAL OF RESPIRATORY AND CRITICAL CARE MEDICINE (2017)

Article Critical Care Medicine

Epidemiology of Pediatric Critical Illness in a Population-Based Birth Cohort in Olmsted County, MN

Sheri S. Crow et al.

PEDIATRIC CRITICAL CARE MEDICINE (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Comprehensive Review On Supervised Machine Learning Algorithms

Hemant Kumar Gianey et al.

2017 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND DATA SCIENCE (MLDS 2017) (2017)

Article Cardiac & Cardiovascular Systems

Prediction of imminent, severe deterioration of children with parallel circulations using real-time processing of physiologic data

Craig G. Rusin et al.

JOURNAL OF THORACIC AND CARDIOVASCULAR SURGERY (2016)

Article Critical Care Medicine

The Pediatric Risk of Mortality Score: Update 2015

Murray M. Pollack et al.

PEDIATRIC CRITICAL CARE MEDICINE (2016)

Article Critical Care Medicine

PICU Volume and Outcome: A Severity-Adjusted Analysis

Barry P. Markovitz et al.

PEDIATRIC CRITICAL CARE MEDICINE (2016)

Article Critical Care Medicine

Development of a Prediction Model of Early Acute Kidney Injury in Critically Ill Children Using Electronic Health Record Data

L. Nelson Sanchez-Pinto et al.

PEDIATRIC CRITICAL CARE MEDICINE (2016)

Article Computer Science, Interdisciplinary Applications

Clinical Decision Support for Nurses A Fall Risk and Prevention Example

Kathryn S. Lytle et al.

CIN-COMPUTERS INFORMATICS NURSING (2015)

Article Critical Care Medicine

Paediatric Index of Mortality 3: An Updated Model for Predicting Mortality in Pediatric Intensive Care

Lahn Straney et al.

PEDIATRIC CRITICAL CARE MEDICINE (2013)

Review Medicine, General & Internal

Effect of Clinical Decision-Support Systems A Systematic Review

Tiffani J. Bright et al.

ANNALS OF INTERNAL MEDICINE (2012)

Review Pediatrics

A history of pediatric critical care medicine

D Epstein et al.

PEDIATRIC RESEARCH (2005)