1
|
Qiu J, Di Fiore JM, Krishnamurthi N, Indic P, Carroll JL, Claure N, Kemp JS, Dennery PA, Ambalavanan N, Weese-Mayer DE, Maria Hibbs A, Martin RJ, Bancalari E, Hamvas A, Randall Moorman J, Lake DE. Highly comparative time series analysis of oxygen saturation and heart rate to predict respiratory outcomes in extremely preterm infants. Physiol Meas 2024; 45:055025. [PMID: 38772400 DOI: 10.1088/1361-6579/ad4e91] [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] [Received: 10/30/2023] [Accepted: 05/21/2024] [Indexed: 05/23/2024]
Abstract
Objective.Highly comparative time series analysis (HCTSA) is a novel approach involving massive feature extraction using publicly available code from many disciplines. The Prematurity-Related Ventilatory Control (Pre-Vent) observational multicenter prospective study collected bedside monitor data from>700extremely preterm infants to identify physiologic features that predict respiratory outcomes.Approach. We calculated a subset of 33 HCTSA features on>7 M 10 min windows of oxygen saturation (SPO2) and heart rate (HR) from the Pre-Vent cohort to quantify predictive performance. This subset included representatives previously identified using unsupervised clustering on>3500HCTSA algorithms. We hypothesized that the best HCTSA algorithms would compare favorably to optimal PreVent physiologic predictor IH90_DPE (duration per event of intermittent hypoxemia events below 90%).Main Results.The top HCTSA features were from a cluster of algorithms associated with the autocorrelation of SPO2 time series and identified low frequency patterns of desaturation as high risk. These features had comparable performance to and were highly correlated with IH90_DPE but perhaps measure the physiologic status of an infant in a more robust way that warrants further investigation. The top HR HCTSA features were symbolic transformation measures that had previously been identified as strong predictors of neonatal mortality. HR metrics were only important predictors at early days of life which was likely due to the larger proportion of infants whose outcome was death by any cause. A simple HCTSA model using 3 top features outperformed IH90_DPE at day of life 7 (.778 versus .729) but was essentially equivalent at day of life 28 (.849 versus .850).Significance. These results validated the utility of a representative HCTSA approach but also provides additional evidence supporting IH90_DPE as an optimal predictor of respiratory outcomes.
Collapse
Affiliation(s)
- Jiaxing Qiu
- Department of Medicine, Division of Cardiology, University of Virginia School of Medicine, Charlottesville, VA, United States of America
| | - Juliann M Di Fiore
- Department of Pediatrics, Case Western Reserve University School of Medicine, University Hospitals Rainbow Babies and Children's Hospital, Cleveland, OH, United States of America
| | - Narayanan Krishnamurthi
- Department of Pediatrics, Division of Autonomic Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL, United States of America
| | - Premananda Indic
- Department of Electrical Engineering, University of Texas at Tyler, Tyler, TX, United States of America
| | - John L Carroll
- Department of Pediatrics, University of Arkansas for Medical Sciences and Arkansas Children's Hospital, Little Rock, AR, United States of America
| | - Nelson Claure
- Department of Pediatrics, Division of Neonatology, University of Miami Miller School of Medicine, Miami, FL, United States of America
| | - James S Kemp
- Department of Pediatrics, Division of Pediatric Pulmonology, Washington University School of Medicine, St. Louis, MO, United States of America
| | - Phyllis A Dennery
- Department of Pediatrics, Brown University School of Medicine, Department of Pediatrics, Providence, RI, United States of America
| | - Namasivayam Ambalavanan
- Department of Pediatrics, Division of Neonatology, University of Alabama at Birmingham, Birmingham, AL, United States of America
| | - Debra E Weese-Mayer
- Department of Pediatrics, Division of Autonomic Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL, United States of America
| | - Anna Maria Hibbs
- Department of Pediatrics, Case Western Reserve University School of Medicine, University Hospitals Rainbow Babies and Children's Hospital, Cleveland, OH, United States of America
| | - Richard J Martin
- Department of Pediatrics, Case Western Reserve University School of Medicine, University Hospitals Rainbow Babies and Children's Hospital, Cleveland, OH, United States of America
| | - Eduardo Bancalari
- Department of Pediatrics, Division of Neonatology, University of Miami Miller School of Medicine, Miami, FL, United States of America
| | - Aaron Hamvas
- Ann and Robert H. Lurie Children's Hospital and Northwestern University Department of Pediatrics, Chicago, IL, United States of America
| | - J Randall Moorman
- Department of Medicine, Division of Cardiology, University of Virginia School of Medicine, Charlottesville, VA, United States of America
| | - Douglas E Lake
- Department of Medicine, Division of Cardiology, University of Virginia School of Medicine, Charlottesville, VA, United States of America
| |
Collapse
|
2
|
Beacom MJ, Frasch MG, Lear CA, Gunn AJ. Monitoring chaos at the cot-side. Pediatr Res 2024:10.1038/s41390-024-03151-1. [PMID: 38509228 DOI: 10.1038/s41390-024-03151-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/14/2024] [Accepted: 03/02/2024] [Indexed: 03/22/2024]
Affiliation(s)
- Michael J Beacom
- Department of Physiology, The University of Auckland, Auckland, New Zealand
| | - Martin G Frasch
- Department of Obstetrics and Gynecology and Institute on Human Development and Disability, University of Washington School of Medicine, Seattle, WA, USA
| | - Christopher A Lear
- Department of Physiology, The University of Auckland, Auckland, New Zealand
| | - Alistair J Gunn
- Department of Physiology, The University of Auckland, Auckland, New Zealand.
| |
Collapse
|
3
|
Qiu J, Di Fiore JM, Krishnamurthi N, Indic P, Carroll JL, Claure N, Kemp JS, Dennery PA, Ambalavanan N, Weese-Mayer DE, Hibbs AM, Martin RJ, Bancalari E, Hamvas A, Randall Moorman J, Lake DE. Highly comparative time series analysis of oxygen saturation and heart rate to predict respiratory outcomes in extremely preterm infants. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2024.01.24.24301724. [PMID: 38343830 PMCID: PMC10854343 DOI: 10.1101/2024.01.24.24301724] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 02/18/2024]
Abstract
Objective Highly comparative time series analysis (HCTSA) is a novel approach involving massive feature extraction using publicly available code from many disciplines. The Prematurity-Related Ventilatory Control (Pre-Vent) observational multicenter prospective study collected bedside monitor data from > 700 extremely preterm infants to identify physiologic features that predict respiratory outcomes. We calculated a subset of 33 HCTSA features on > 7M 10-minute windows of oxygen saturation (SPO2) and heart rate (HR) from the Pre-Vent cohort to quantify predictive performance. This subset included representatives previously identified using unsupervised clustering on > 3500 HCTSA algorithms. Performance of each feature was measured by individual area under the receiver operating curve (AUC) at various days of life and binary respiratory outcomes. These were compared to optimal PreVent physiologic predictor IH90 DPE, the duration per event of intermittent hypoxemia events with threshold of 90%. Main Results The top HCTSA features were from a cluster of algorithms associated with the autocorrelation of SPO2 time series and identified low frequency patterns of desaturation as high risk. These features had comparable performance to and were highly correlated with IH90_DPE but perhaps measure the physiologic status of an infant in a more robust way that warrants further investigation. The top HR HCTSA features were symbolic transformation measures that had previously been identified as strong predictors of neonatal mortality. HR metrics were only important predictors at early days of life which was likely due to the larger proportion of infants whose outcome was death by any cause. A simple HCTSA model using 3 top features outperformed IH90_DPE at day of life 7 (.778 versus .729) but was essentially equivalent at day of life 28 (.849 versus .850). These results validated the utility of a representative HCTSA approach but also provides additional evidence supporting IH90_DPE as an optimal predictor of respiratory outcomes.
Collapse
Affiliation(s)
- Jiaxing Qiu
- Department of Medicine, Division of Cardiology, University of Virginia School of Medicine, Charlottesville, VA
| | - Juliann M Di Fiore
- Department of Pediatrics, Case Western Reserve University School of Medicine, University Hospitals Rainbow Babies and Children's Hospital, Cleveland, OH
| | - Narayanan Krishnamurthi
- Department of Pediatrics, Division of Autonomic Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL
| | - Premananda Indic
- Department of Electrical Engineering, University of Texas at Tyler, Tyler, TX
| | - John L Carroll
- Department of Pediatrics, University of Arkansas for Medical Sciences and Arkansas Children's Hospital, Little Rock, AK
| | - Nelson Claure
- Department of Pediatrics, Division of Neonatology, University of Miami Miller School of Medicine, Miami, FL
| | - James S Kemp
- Department of Pediatrics, Division of Pediatric Pulmonology, Washington University School of Medicine, St. Louis, MO
| | - Phyllis A Dennery
- Department of Pediatrics, Division of Newborn Medicine, Washington University School of Medicine, St. Louis, MO
| | - Namasivayam Ambalavanan
- Department of Pediatrics, Division of Neonatology, University of Alabama at Birmingham, Birmingham, AL
| | - Debra E Weese-Mayer
- Department of Pediatrics, Division of Autonomic Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL
| | - Anna Maria Hibbs
- Department of Pediatrics, Case Western Reserve University School of Medicine, University Hospitals Rainbow Babies and Children's Hospital, Cleveland, OH
| | - Richard J Martin
- Department of Pediatrics, Case Western Reserve University School of Medicine, University Hospitals Rainbow Babies and Children's Hospital, Cleveland, OH
| | - Eduardo Bancalari
- Department of Pediatrics, Division of Neonatology, University of Miami Miller School of Medicine, Miami, FL
| | - Aaron Hamvas
- Ann and Robert H. Lurie Children's Hospital and Northwestern University Department of Pediatrics, Chicago, IL
| | - J Randall Moorman
- Department of Medicine, Division of Cardiology, University of Virginia School of Medicine, Charlottesville, VA
| | - Douglas E Lake
- Department of Medicine, Division of Cardiology, University of Virginia School of Medicine, Charlottesville, VA
| |
Collapse
|
4
|
Letzkus L, Picavia R, Lyons G, Brandberg J, Qiu J, Kausch S, Lake D, Fairchild K. Heart rate patterns predicting cerebral palsy in preterm infants. Pediatr Res 2023:10.1038/s41390-023-02853-2. [PMID: 37891365 DOI: 10.1038/s41390-023-02853-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/26/2023] [Revised: 09/26/2023] [Accepted: 09/27/2023] [Indexed: 10/29/2023]
Abstract
BACKGROUND Heart rate (HR) patterns can inform on central nervous system dysfunction. We previously used highly comparative time series analysis (HCTSA) to identify HR patterns predicting mortality among patients in the neonatal intensive care unit (NICU) and now use this methodology to discover patterns predicting cerebral palsy (CP) in preterm infants. METHOD We studied NICU patients <37 weeks' gestation with archived every-2-s HR data throughout the NICU stay and with or without later diagnosis of CP (n = 57 CP and 1119 no CP). We performed HCTSA of >2000 HR metrics and identified 24 metrics analyzed on HR data from two 7-day periods: week 1 and 37 weeks' postmenstrual age (week 1, week 37). Multivariate modeling was used to optimize a parsimonious prediction model. RESULTS Week 1 HR metrics with maximum AUC for CP prediction reflected low variability, including "RobustSD" (AUC 0.826; 0.772-0.870). At week 37, high values of a novel HR metric, "LongSD3," the cubed value of the difference in HR values 100 s apart, were added to week 1 HR metrics for CP prediction. A combined birthweight + early and late HR model had AUC 0.853 (0.805-0.892). CONCLUSIONS Using HCTSA, we discovered novel HR metrics and created a parsimonious model for CP prediction in preterm NICU patients. IMPACT We discovered new heart rate characteristics predicting CP in preterm infants. Using every-2-s HR from two 7-day periods and highly comparative time series analysis, we found a measure of low variability HR week 1 after birth and a pattern of recurrent acceleration in HR at term corrected age that predicted CP. Combined clinical and early and late HR features had AUC 0.853 for CP prediction.
Collapse
Affiliation(s)
- Lisa Letzkus
- Department of Pediatrics, Neurodevelopmental and Behavioral Pediatrics, UVA Children's Hospital, University of Virginia School of Medicine, Charlottesville, VA, USA.
| | - Robin Picavia
- University of Virginia School of Medicine, Charlottesville, VA, USA
| | - Genevieve Lyons
- Department of Public Health Sciences, University of Virginia School of Medicine, Charlottesville, VA, USA
| | | | - Jiaxing Qiu
- University of Virginia School of Medicine, Charlottesville, VA, USA
| | - Sherry Kausch
- University of Virginia School of Medicine, Charlottesville, VA, USA
| | - Doug Lake
- Department of Cardiovascular Medicine, University of Virginia School of Medicine, Charlottesville, VA, USA
| | - Karen Fairchild
- Department of Pediatrics, Neonatology, UVA Children's Hospital, University of Virginia School of Medicine, Charlottesville, VA, USA
| |
Collapse
|
5
|
Monfredi OJ, Moore CC, Sullivan BA, Keim-Malpass J, Fairchild KD, Loftus TJ, Bihorac A, Krahn KN, Dubrawski A, Lake DE, Moorman JR, Clermont G. Continuous ECG monitoring should be the heart of bedside AI-based predictive analytics monitoring for early detection of clinical deterioration. J Electrocardiol 2023; 76:35-38. [PMID: 36434848 PMCID: PMC10061545 DOI: 10.1016/j.jelectrocard.2022.10.011] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2022] [Revised: 10/01/2022] [Accepted: 10/22/2022] [Indexed: 11/24/2022]
Abstract
The idea that we can detect subacute potentially catastrophic illness earlier by using statistical models trained on clinical data is now well-established. We review evidence that supports the role of continuous cardiorespiratory monitoring in these predictive analytics monitoring tools. In particular, we review how continuous ECG monitoring reflects the patient and not the clinician, is less likely to be biased, is unaffected by changes in practice patterns, captures signatures of illnesses that are interpretable by clinicians, and is an underappreciated and underutilized source of detailed information for new mathematical methods to reveal.
Collapse
Affiliation(s)
- Oliver J Monfredi
- Center for Advanced Medical Analytics, University of Virginia, United States of America; Department of Medicine, University of Virginia, United States of America
| | - Christopher C Moore
- Center for Advanced Medical Analytics, University of Virginia, United States of America; Department of Medicine, University of Virginia, United States of America
| | - Brynne A Sullivan
- Center for Advanced Medical Analytics, University of Virginia, United States of America; Department of Pediatrics, University of Virginia, United States of America
| | - Jessica Keim-Malpass
- Center for Advanced Medical Analytics, University of Virginia, United States of America; School of Nursing, University of Virginia, United States of America
| | - Karen D Fairchild
- Center for Advanced Medical Analytics, University of Virginia, United States of America; Department of Pediatrics, University of Virginia, United States of America
| | - Tyler J Loftus
- Department of Surgery, University of Florida, United States of America
| | - Azra Bihorac
- Department of Medicine, University of Florida, United States of America
| | - Katherine N Krahn
- Center for Advanced Medical Analytics, University of Virginia, United States of America; Department of Medicine, University of Virginia, United States of America
| | - Artur Dubrawski
- Robotics Institute, Carnegie Mellon University, United States of America
| | - Douglas E Lake
- Center for Advanced Medical Analytics, University of Virginia, United States of America; Department of Medicine, University of Virginia, United States of America
| | - J Randall Moorman
- Center for Advanced Medical Analytics, University of Virginia, United States of America; Department of Medicine, University of Virginia, United States of America.
| | - Gilles Clermont
- Department of Critical Care, University of Pittsburgh, United States of America
| |
Collapse
|
6
|
The principles of whole-hospital predictive analytics monitoring for clinical medicine originated in the neonatal ICU. NPJ Digit Med 2022; 5:41. [PMID: 35361861 PMCID: PMC8971442 DOI: 10.1038/s41746-022-00584-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Accepted: 02/23/2022] [Indexed: 11/17/2022] Open
Abstract
In 2011, a multicenter group spearheaded at the University of Virginia demonstrated reduced mortality from real-time continuous cardiorespiratory monitoring in the neonatal ICU using what we now call Artificial Intelligence, Big Data, and Machine Learning. The large, randomized heart rate characteristics trial made real, for the first time that we know of, the promise that early detection of illness would allow earlier and more effective intervention and improved patient outcomes. Currently, though, we hear as much of failures as we do of successes in the rapidly growing field of predictive analytics monitoring that has followed. This Perspective aims to describe the principles of how we developed heart rate characteristics monitoring for neonatal sepsis and then applied them throughout adult ICU and hospital medicine. It primarily reflects the work since the 1990s of the University of Virginia group: the theme is that sudden and catastrophic deteriorations can be preceded by subclinical but measurable physiological changes apparent in the continuous cardiorespiratory monitoring and electronic health record.
Collapse
|