Machine Learning and Artificial Intelligence in Pediatric Research: Current State, Future Prospects, and Examples in Perioperative and Critical Care

Lonsdale, Hannah; Jalali, Ali; Ahumada, Luis M.; Matava, Clyde

doi:10.1016/j.jpeds.2020.02.039

Cited by 33 publications

(29 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…93 The standardized collection of international perioperative data may yield data sets which allow for validation of algorithms across institutions providing real-time, personalized and accurate predicted outcomes. 92…”

Section: The Futurementioning

confidence: 99%

“…The use of machine learning and artificial intelligence to diagnose or risk stratify appears promising. Machine learning and artificial intelligence use pattern recognition and computer modeling analysis from information sourced from electronic health record systems, large public health databases, and imaging data 92 . With varying levels of success, event prediction of effects or events (e.g., presence of difficult airway, length of stay, and hypotension) using artificial intelligence has been researched 93 .…”

Section: Main Articlementioning

confidence: 99%

“…Machine learning and artificial intelligence use pattern recognition and computer modeling analysis from information sourced from electronic health record systems, large public health databases, and imaging data. 92 With varying levels of success, event prediction of effects or events (e.g., presence of difficult airway, length of stay, and hypotension) using artificial intelligence has been researched. 93 The standardized collection of international perioperative data may yield data sets which allow for validation of algorithms across institutions providing real-time, personalized and accurate predicted outcomes.…”

Section: The Futurementioning

confidence: 99%

See 2 more Smart Citations

Risk assessment and optimization strategies to reduce perioperative respiratory adverse events in Pediatric Anesthesia—Part 2: Anesthesia‐related risk and treatment options

Templeton

Sommerfield

Hii

et al. 2021

Pediatric Anesthesia

Self Cite

View full text Add to dashboard Cite

Perioperative respiratory adverse events are the most common cause of critical events in children undergoing anesthesia and surgery. While many risk factors remain unmodifiable, there are numerous anesthetic management decisions which can impact the incidence and impact of these events, especially in at-risk children. Ongoing research continues to improve our understanding of both the influence of risk factors and the effect of specific interventions. This review discusses anesthesia risk factors and outlines strategies to reduce the rate and impact of perioperative respiratory adverse events with a chronologic based inquiry into anesthetic management decisions through the perioperative period from premedication to postoperative disposition.

show abstract

Section: The Futurementioning

confidence: 99%

Section: Main Articlementioning

confidence: 99%

Section: The Futurementioning

confidence: 99%

See 1 more Smart Citation

Risk assessment and optimization strategies to reduce perioperative respiratory adverse events in Pediatric Anesthesia—Part 2: Anesthesia‐related risk and treatment options

Templeton

Sommerfield

Hii

et al. 2021

Pediatric Anesthesia

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning is well suited for the scale of the data collected, because it offers an efficient method for statistical analysis of large datasets where complex nonlinear relationships may exist between multiple variables. 25,26 Generating HDTs would likely be an iterative process-the HDT is used by clinicians and patients alongside traditional methods to inform decision-making, then further data are collected while the treatment plan is performed and is used to refine and calibrate the models. 1 end goal of an HDT could be to support clinicians in selecting treatments by their predicted future effect for an individual patient, rather than on what has worked for the average historical presentation of the patient's current condition.…”

Section: Creating a Clinically Useful Hdtmentioning

confidence: 99%

The Perioperative Human Digital Twin

Lonsdale

Gray²,

Ahumada³

et al. 2022

Anesthesia &Amp; Analgesia

Self Cite

View full text Add to dashboard Cite

GLOSSARY BRCA = BReast CAncer gene; ECG = electrocardiogram; EHR = electronic health record; EMR = electronic medical record; GPS = Global Positioning System; HDT = human digital twin; HER-2 = human epidermal growth factor receptor 2; HIPAA = Health Insurance Portability and Accountability Act; IoMT = Internet of Medical Things; IoT = Internet of Things; PGHD = person-generated health data; PWC = physiologic data warehouse; RPM = remote patient monitoring; SARS-CoV-2 = severe acute respiratory syndrome coronavirus 2

show abstract

“…Recently, several studies have reported the use of machine learning approaches with encouraging results (21,(23)(24)(25). To date, the full extent to which machine learning approaches can be applied in pediatric research has not been fully explored, but, as Londsdale et al point out, the opportunities for improving patient care are substantial (26).…”

Section: Introductionmentioning

confidence: 99%

An Artificial Neural Network Model for Pediatric Mortality Prediction in Two Tertiary Pediatric Intensive Care Units in South Africa. A Development Study

et al. 2022

View full text Add to dashboard Cite

ObjectivesThe performance of mortality prediction models remain a challenge in lower- and middle-income countries. We developed an artificial neural network (ANN) model for the prediction of mortality in two tertiary pediatric intensive care units (PICUs) in South Africa using free to download and use software and commercially available computers. These models were compared to a logistic regression model and a recalibrated version of the Pediatric Index of Mortality 3.DesignThis study used data from a retrospective cohort study to develop an artificial neural model and logistic regression model for mortality prediction. The outcome evaluated was death in PICU.SettingTwo tertiary PICUs in South Africa.Patients2,089 patients up to the age of 13 completed years were included in the study.InterventionsNone.Measurements and Main ResultsThe AUROC was higher for the ANN (0.89) than for the logistic regression model (LR) (0.87) and the recalibrated PIM3 model (0.86). The precision recall curve however favors the ANN over logistic regression and recalibrated PIM3 (AUPRC = 0.6 vs. 0.53 and 0.58, respectively. The slope of the calibration curve was 1.12 for the ANN model (intercept 0.01), 1.09 for the logistic regression model (intercept 0.05) and 1.02 (intercept 0.01) for the recalibrated version of PIM3. The calibration curve was however closer to the diagonal for the ANN model.ConclusionsArtificial neural network models are a feasible method for mortality prediction in lower- and middle-income countries but significant challenges exist. There is a need to conduct research directed toward the acquisition of large, complex data sets, the integration of documented clinical care into clinical research and the promotion of the development of electronic health record systems in lower and middle income settings.

show abstract

Machine Learning and Artificial Intelligence in Pediatric Research: Current State, Future Prospects, and Examples in Perioperative and Critical Care

Cited by 33 publications

References 49 publications

Risk assessment and optimization strategies to reduce perioperative respiratory adverse events in Pediatric Anesthesia—Part 2: Anesthesia‐related risk and treatment options

Risk assessment and optimization strategies to reduce perioperative respiratory adverse events in Pediatric Anesthesia—Part 2: Anesthesia‐related risk and treatment options

The Perioperative Human Digital Twin

An Artificial Neural Network Model for Pediatric Mortality Prediction in Two Tertiary Pediatric Intensive Care Units in South Africa. A Development Study

Contact Info

Product

Resources

About