1
|
Brasher M, Virodov A, Raffay TM, Bada HS, Cunningham MD, Bumgardner C, Abu Jawdeh EG. Predicting Extubation Readiness in Preterm Infants Utilizing Machine Learning: A Diagnostic Utility Study. J Pediatr 2024; 271:114043. [PMID: 38561049 DOI: 10.1016/j.jpeds.2024.114043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/06/2023] [Revised: 03/11/2024] [Accepted: 03/26/2024] [Indexed: 04/04/2024]
Abstract
OBJECTIVE The objective of this study was to predict extubation readiness in preterm infants using machine learning analysis of bedside pulse oximeter and ventilator data. STUDY DESIGN This is an observational study with prospective recordings of oxygen saturation (SpO2) and ventilator data from infants <30 weeks of gestation age. Research pulse oximeters collected SpO2 (1 Hz sampling rate) to quantify intermittent hypoxemia (IH). Continuous ventilator metrics were collected (4-5-minute sampling) from bedside ventilators. Data modeling was completed using unbiased machine learning algorithms. Three model sets were created using the following data source combinations: (1) IH and ventilator (IH + SIMV), (2) IH, and (3) ventilator (SIMV). Infants were also analyzed separated by postnatal age (infants <2 or ≥2 weeks of age). Models were compared by area under the receiver operating characteristic curve (AUC). RESULTS A total of 110 extubation events from 110 preterm infants were analyzed. Infants had a median gestation age and birth weight of 26 weeks and 825 g, respectively. Of the 3 models presented, the IH + SIMV model achieved the highest AUC of 0.77 for all infants. Separating infants by postnatal age increased accuracy further achieving AUC of 0.94 for <2 weeks of age group and AUC of 0.83 for ≥2 weeks group. CONCLUSIONS Machine learning analysis has the potential to enhance prediction accuracy of extubation readiness in preterm infants while utilizing readily available data streams from bedside pulse oximeters and ventilators.
Collapse
Affiliation(s)
- Mandy Brasher
- Department of Pediatrics/Neonatology, College of Medicine, University of Kentucky, Lexington, KY
| | - Alexandr Virodov
- Institute of Biomedical Informatics, University of Kentucky, Lexington, KY
| | - Thomas M Raffay
- Department of Pediatrics/Neonatology, College of Medicine, Case Western Reserve University, Cleveland, OH
| | - Henrietta S Bada
- Department of Pediatrics/Neonatology, College of Medicine, University of Kentucky, Lexington, KY
| | - M Douglas Cunningham
- Department of Pediatrics/Neonatology, College of Medicine, University of Kentucky, Lexington, KY
| | - Cody Bumgardner
- Institute of Biomedical Informatics, University of Kentucky, Lexington, KY
| | - Elie G Abu Jawdeh
- Department of Pediatrics/Neonatology, College of Medicine, University of Kentucky, Lexington, KY.
| |
Collapse
|
2
|
Jenkinson AC, Dassios T, Greenough A. Artificial intelligence in the NICU to predict extubation success in prematurely born infants. J Perinat Med 2024; 52:119-125. [PMID: 38059494 DOI: 10.1515/jpm-2023-0454] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/25/2023] [Accepted: 11/11/2023] [Indexed: 12/08/2023]
Abstract
OBJECTIVES Mechanical ventilation in prematurely born infants, particularly if prolonged, can cause long term complications including bronchopulmonary dysplasia. Timely extubation then is essential, yet predicting its success remains challenging. Artificial intelligence (AI) may provide a potential solution. CONTENT A narrative review was undertaken to explore AI's role in predicting extubation success in prematurely born infants. Across the 11 studies analysed, the range of reported area under the receiver operator characteristic curve (AUC) for the selected prediction models was between 0.7 and 0.87. Only two studies implemented an external validation procedure. Comparison to the results of clinical predictors was made in two studies. One group reported a logistic regression model that outperformed clinical predictors on decision tree analysis, while another group reported clinical predictors outperformed their artificial neural network model (AUCs: ANN 0.68 vs. clinical predictors 0.86). Amongst the studies there was an heterogenous selection of variables for inclusion in prediction models, as well as variations in definitions of extubation failure. SUMMARY Although there is potential for AI to enhance extubation success, no model's performance has yet surpassed that of clinical predictors. OUTLOOK Future studies should incorporate external validation to increase the applicability of the models to clinical settings.
Collapse
Affiliation(s)
- Allan C Jenkinson
- Department of Women and Children's Health, School of Life Course Sciences, Faculty of Life Sciences and Medicine, King's College London, London, UK
| | - Theodore Dassios
- Department of Women and Children's Health, School of Life Course Sciences, Faculty of Life Sciences and Medicine, King's College London, London, UK
- Neonatal Intensive Care Centre, King's College Hospital NHS Foundation Trust, London, UK
| | - Anne Greenough
- Department of Women and Children's Health, School of Life Course Sciences, Faculty of Life Sciences and Medicine, King's College London, London, UK
- Neonatal Intensive Care Centre, King's College Hospital NHS Foundation Trust, London, UK
| |
Collapse
|
3
|
Moreira AG, Husain A, Knake LA, Aziz K, Simek K, Valadie CT, Pandillapalli NR, Trivino V, Barry JS. A clinical informatics approach to bronchopulmonary dysplasia: current barriers and future possibilities. Front Pediatr 2024; 12:1221863. [PMID: 38410770 PMCID: PMC10894945 DOI: 10.3389/fped.2024.1221863] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/13/2023] [Accepted: 01/23/2024] [Indexed: 02/28/2024] Open
Abstract
Bronchopulmonary dysplasia (BPD) is a complex, multifactorial lung disease affecting preterm neonates that can result in long-term pulmonary and non-pulmonary complications. Current therapies mainly focus on symptom management after the development of BPD, indicating a need for innovative approaches to predict and identify neonates who would benefit most from targeted or earlier interventions. Clinical informatics, a subfield of biomedical informatics, is transforming healthcare by integrating computational methods with patient data to improve patient outcomes. The application of clinical informatics to develop and enhance clinical therapies for BPD presents opportunities by leveraging electronic health record data, applying machine learning algorithms, and implementing clinical decision support systems. This review highlights the current barriers and the future potential of clinical informatics in identifying clinically relevant BPD phenotypes and developing clinical decision support tools to improve the management of extremely preterm neonates developing or with established BPD. However, the full potential of clinical informatics in advancing our understanding of BPD with the goal of improving patient outcomes cannot be achieved unless we address current challenges such as data collection, storage, privacy, and inherent data bias.
Collapse
Affiliation(s)
- Alvaro G Moreira
- Department of Pediatrics, University of Texas Health San Antonio, San Antonio, TX, United States
| | - Ameena Husain
- Department of Pediatrics, University of Utah, Salt Lake City, UT, United States
| | - Lindsey A Knake
- Department of Pediatrics, University of Iowa, Iowa City, IA, United States
| | - Khyzer Aziz
- Department of Pediatrics, Johns Hopkins University, Baltimore, MD, United States
| | - Kelsey Simek
- Department of Pediatrics, University of Utah, Salt Lake City, UT, United States
| | - Charles T Valadie
- Department of Pediatrics, University of Texas Health San Antonio, San Antonio, TX, United States
| | | | - Vanessa Trivino
- Department of Pediatrics, University of Texas Health San Antonio, San Antonio, TX, United States
| | - James S Barry
- Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, United States
| |
Collapse
|
4
|
Farshid P, Mirnia K, Rezaei-Hachesu P, Maserat E, Samad-Soltani T. Developing a model to predict neonatal respiratory distress syndrome and affecting factors using data mining: A cross-sectional study. Int J Reprod Biomed 2023; 21:909-920. [PMID: 38292513 PMCID: PMC10823121 DOI: 10.18502/ijrm.v21i11.14654] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2022] [Revised: 08/11/2023] [Accepted: 10/26/2023] [Indexed: 02/01/2024] Open
Abstract
Background: One of the major challenges that hospitals and clinicians face is the early identification of newborns at risk for adverse events. One of them is neonatal respiratory distress syndrome (RDS). RDS is the widest spared respiratory disorder in immature newborns and the main source of death among them. Machine learning has been broadly accepted and used in various scopes to analyze medical information and is very useful in the early detection of RDS. Objective: This study aimed to develop a model to predict neonatal RDS and affecting factors using data mining. Materials and Methods: The original dataset in this cross-sectional study was extracted from the medical records of newborns diagnosed with RDS from July 2017-July 2018 in Alzahra hospital, Tabriz, Iran. This data includes information about 1469 neonates, and their mothers information. The data were preprocessed and applied to expand the classification model using machine learning techniques such as support vector machine, Naïve Bayes, classification tree, random forest, CN2 rule induction, and neural network, for prediction of RDS episodes. The study compares models according to their accuracy. Results: Among the obtained results, an accuracy of 0.815, sensitivity of 0.802, specificity of 0.812, and area under the curve of 0.843 was the best output using random forest. Conclusion: The findings of our study proved that new approaches, such as data mining, may support medical decisions, improving diagnosis in neonatal RDS. The feasibility of using a random forest in neonatal RDS prediction would offer the possibility to decrease postpartum complications of neonatal care.
Collapse
Affiliation(s)
- Parisa Farshid
- Department of Health Information Technology, School of Management and Medical Informatics, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Kayvan Mirnia
- Department of Pediatrics, Children's Medical Center, Tehran University of Medical Sciences, Tehran, Iran
| | - Peyman Rezaei-Hachesu
- Department of Health Information Technology, School of Management and Medical Informatics, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Elham Maserat
- Department of Medical Informatics, School of Medical Sciences, Tarbiat Modares University, Tehran, Iran
| | - Taha Samad-Soltani
- Department of Health Information Technology, School of Management and Medical Informatics, Tabriz University of Medical Sciences, Tabriz, Iran
| |
Collapse
|
5
|
Wilson HC, Gunsaulus ME, Owens GE, Goldstein SA, Yu S, Lowery RE, Olive MK. Failed Extubation in Neonates After Cardiac Surgery: A Single-Center, Retrospective Study. Pediatr Crit Care Med 2023; 24:e547-e555. [PMID: 37219966 DOI: 10.1097/pcc.0000000000003283] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 05/25/2023]
Abstract
OBJECTIVES To describe factors associated with failed extubation (FE) in neonates following cardiovascular surgery, and the relationship with clinical outcomes. DESIGN Retrospective cohort study. SETTING Twenty-bed pediatric cardiac ICU (PCICU) in an academic tertiary care children's hospital. PATIENTS Neonates admitted to the PCICU following cardiac surgery between July 2015 and June 2018. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS Patients who experienced FE were compared with patients who were successfully extubated. Variables associated with FE ( p < 0.05) from univariate analysis were considered for inclusion in multivariable logistic regression. Univariate associations of FE with clinical outcomes were also examined. Of 240 patients, 40 (17%) experienced FE. Univariate analyses revealed associations of FE with upper airway (UA) abnormality (25% vs 8%, p = 0.003) and delayed sternal closure (50% vs 24%, p = 0.001). There were weaker associations of FE with hypoplastic left heart syndrome (25% vs 13%, p = 0.04), postoperative ventilation greater than 7 days (33% vs 15%, p = 0.01), Society of Thoracic Surgeons-European Association for Cardio-Thoracic Surgery (STAT) category 5 operations (38% vs 21%, p = 0.02), and respiratory rate during spontaneous breathing trial (median 42 vs 37 breaths/min, p = 0.01). In multivariable analysis, UA abnormalities (adjusted odds ratio [AOR] 3.5; 95% CI, 1.4-9.0), postoperative ventilation greater than 7 days (AOR 2.3; 95% CI, 1.0-5.2), and STAT category 5 operations (AOR 2.4; 95% CI, 1.1-5.2) were independently associated with FE. FE was also associated with unplanned reoperation/reintervention during hospital course (38% vs 22%, p = 0.04), longer hospitalization (median 29 vs 16.5 d, p < 0.0001), and in-hospital mortality (13% vs 3%, p = 0.02). CONCLUSIONS FE in neonates occurs relatively commonly following cardiac surgery and is associated with adverse clinical outcomes. Additional data are needed to further optimize periextubation decision-making in patients with multiple clinical factors associated with FE.
Collapse
Affiliation(s)
- Hunter C Wilson
- Division of Pediatric Cardiology, Department of Pediatrics, C. S. Mott Children's Hospital, University of Michigan, Ann Arbor, MI
| | - Megan E Gunsaulus
- Division of Cardiology, Department of Pediatrics, University of Pittsburgh Medical Center, Pittsburgh, PA
| | - Gabe E Owens
- Division of Pediatric Cardiology, Department of Pediatrics, C. S. Mott Children's Hospital, University of Michigan, Ann Arbor, MI
| | - Stephanie A Goldstein
- Division of Pediatric Critical Care, Department of Pediatrics, University of Utah, Salt Lake City, UT
| | - Sunkyung Yu
- Division of Pediatric Cardiology, Department of Pediatrics, C. S. Mott Children's Hospital, University of Michigan, Ann Arbor, MI
| | - Ray E Lowery
- Division of Pediatric Cardiology, Department of Pediatrics, C. S. Mott Children's Hospital, University of Michigan, Ann Arbor, MI
| | - Mary K Olive
- Division of Pediatric Cardiology, Department of Pediatrics, C. S. Mott Children's Hospital, University of Michigan, Ann Arbor, MI
| |
Collapse
|
6
|
Shalish W, Sant'Anna GM. Optimal timing of extubation in preterm infants. Semin Fetal Neonatal Med 2023; 28:101489. [PMID: 37996367 DOI: 10.1016/j.siny.2023.101489] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2023]
Abstract
In neonatal intensive care, endotracheal intubation is usually performed as an urgent or semi-urgent procedure in infants with critical or unstable conditions related to progressive respiratory failure. Extubation is not. Patients undergoing extubation are typically stable, with improved respiratory function. The key elements to facilitating extubation are to recognize improvement in respiratory status, promote weaning of mechanical ventilation, and accurately identify readiness for removal of the endotracheal tube. Therefore, extubation should be a planned and well-organized procedure. In this review, we will appraise the evidence for existing predictors of extubation readiness and provide patient-specific, pathophysiology-derived strategies to optimize the timing and success of extubation in neonates, with a focus on extremely preterm infants.
Collapse
Affiliation(s)
- Wissam Shalish
- Department of Pediatrics, Division of Neonatology, Montreal Children's Hospital, McGill University Health Center, 1001 Boul. Décarie, Room B05.2714, Montreal, Quebec, H4A 3J1, Canada.
| | - Guilherme M Sant'Anna
- Department of Pediatrics, Division of Neonatology, Montreal Children's Hospital, McGill University Health Center, 1001 Boul. Décarie, Room B05.2714, Montreal, Quebec, H4A 3J1, Canada.
| |
Collapse
|
7
|
Gandhi B, Hagan J, Patil M. EBNEO commentary: Prediction of extubation failure among low birthweight neonates using machine learning. Acta Paediatr 2023; 112:2016-2017. [PMID: 37177905 DOI: 10.1111/apa.16813] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/23/2023] [Revised: 04/24/2023] [Accepted: 05/03/2023] [Indexed: 05/15/2023]
Affiliation(s)
- Bheru Gandhi
- Department of Pediatrics, Baylor College of Medicine/Division of Neonatology, Texas Children's Hospital, Houston, Texas, USA
| | - Joseph Hagan
- Baylor College of Medicine/Division of Neonatology, Texas Children's Hospital, Houston, Texas, USA
| | - Monika Patil
- Department of Pediatrics, Baylor College of Medicine/Division of Neonatology, Texas Children's Hospital, Houston, Texas, USA
| |
Collapse
|