4006-776-356 出国就医服务电话

免费获得国外相关药品,最快 1 个工作日回馈药物信息

出境医 / 临床实验 / Machine Learning Modeling of Intraoperative Hemodynamic Predictors of Postoperative Outcomes

Machine Learning Modeling of Intraoperative Hemodynamic Predictors of Postoperative Outcomes

Study Description
Brief Summary:
With population aging and limited resources, strategies to improve outcomes after surgery are ever more important. There is a limited understanding of what ranges of hemodynamic variables under anesthesia are associated with better outcomes. This retrospective cohort study will analyze how hemodynamic variables during surgeries predict mortality, morbidity, Intensive Care Unit admission, length of hospital stay, and hospital readmission. The use of machine learning in a large, broad surgery population dataset could detect new relationships and strategies that may inform current practice, and generate ideas for future research.

Condition or disease Intervention/treatment
Perioperative/Postoperative Complications Morbidity, Multiple Surgery Anesthesia Death Other: Blood pressure Other: Heart rate Other: Use of hemodynamic medications (i.e. special medications for blood pressure) Other: Oxygen saturation by pulse oximetry (SpO2) Other: End-tidal Carbon dioxide (EtCO2)

Detailed Description:

Lay Summary

Introduction: The World Health Organization estimates that 270-360 million operations are performed every year worldwide. Death and complications after surgery are a big challenge. In Canada, out of every 1000 major surgeries, 16 patients die in hospital after surgery. In the United States, for every 1000 operations, 67 patients unexpectedly need life support in the Intensive Care Unit. With population aging and limited resources, strategies to improve health after surgery are ever more important.

Vital signs, such as blood pressure and heart rate, show how the body is doing. Vital signs change during surgery because of patient, surgical, and anesthetic factors. Anesthesiologists can change vital signs with medications. However, medical professionals are only starting to understand which, and what ranges of, vital signs under anesthesia are associated with better health. Machine learning is a tool that can provide new ways to understand data. With better understanding, medical professionals can work to improve outcomes after surgery.

Objective: This study will analyze vital signs during surgeries for their links to death, complications (heart, lung, kidney, brain, infection), Intensive Care Unit admission, length of hospital stay, and hospital readmission. This study will determine which, and what levels of, vital signs may be harmful. The investigators predict that blood pressure, heart rate, oxygen level, carbon dioxide level, and the need for medications to change blood pressure will interact to be associated with death after surgery.

Methods: After obtaining Research Ethics Board approval, the investigators will analyze data from all patients who are at least 45 years old and had an operation (with the exception of heart surgery) with an overnight stay at the Queen Elizabeth II health centre (Halifax, Canada) from January 1, 2013 to December 1, 2017. There are approximately eligible 35,000 patients. The investigators will use machine learning to model the data and test how well our model explains outcomes after surgery.

Significance: The use of machine learning in a large, broad surgery population dataset could detect new relationships and strategies that may inform current practice, and generate ideas for future research. A better understanding of the impact of vital signs during surgeries may unveil methods to improve outcomes and resource allocation after surgery. The results may suggest ways to identify high-risk patients who should be monitored more closely after surgery. If the model performs well, it may motivate other researchers to use machine learning in health data research.

Please see full protocol for details.

May 2020 update (prior to dataset aggregation and analysis)

  1. Added secondary outcome (days alive and out of hospital at 30 days postoperatively)
  2. Improved hemodynamic variable artifact processing algorithm
  3. Added sub-study: machine learning for invasive blood pressure artifact removal algorithm
Study Design
Layout table for study information
Study Type : Observational
Estimated Enrollment : 35000 participants
Observational Model: Cohort
Time Perspective: Retrospective
Official Title: Machine Learning Modeling of Intraoperative Hemodynamic Predictors of 30-day Mortality and Major In-hospital Morbidity After Noncardiac Surgery: a Retrospective Population Cohort Study
Actual Study Start Date : January 1, 2013
Actual Primary Completion Date : December 31, 2017
Actual Study Completion Date : December 31, 2017
Arms and Interventions
Group/Cohort Intervention/treatment
Cohort
Patients ages ≥ 45 receiving their index (i.e. first) non-cardiac surgery with an overnight stay at the Nova Scotia Health Authority Queen Elizabeth II (QEII) hospitals (Victoria General and Halifax Infirmary) Halifax, Canada, from January 1, 2013 to December 1, 2017 will be included. Patients under going cardiac surgery or deceased organ donation will be excluded. Patients without an electronic anesthetic record during surgery will also be excluded. Preliminary analysis of the intraoperative database estimates approximately 35,000 patients in this cohort.
Other: Blood pressure

Systolic Blood Pressure (SBP)

  1. Maximum change from preoperative SBP, in a) absolute change (mmHg), and b) relative change (%)(emergency and elective cases analyzed separately)
  2. Cumulative duration (minutes) >=20% below preoperative SBP
  3. Longest single episode (minutes) below a) 80, b) 90, and c)100 mmHg
  4. Cumulative duration (minutes) below a) 80, b) 90, and c)100 mmHg

Mean Arterial Pressure (MAP)

  1. Maximum change from preoperative MAP, in a) absolute change (mmHg), and b) relative change (%) (emergency and elective cases analyzed separately)
  2. Cumulative duration (minutes) >=20% below preoperative MAP
  3. Longest single episode (minutes) below a) 60, b) 65, c) 70, and d) 80mmHg
  4. Cumulative duration (minutes) below a) 60, b) 65, c) 70, and d) 80mmHg

Other: Heart rate
  1. Maximum change (beats per minute, BPM) from preoperative heart rate (positive and negative)
  2. Relative change (%) from preoperative heart rate (positive and negative)
  3. Maximum pulse variation (maximum heart rate minus minimum heart rate)
  4. Longest single episode (minutes) a) below 60, and b) above 100BPM
  5. Cumulative duration (minutes) a) below 60, and b) above 100BPM

Other: Use of hemodynamic medications (i.e. special medications for blood pressure)
  1. Vasopressor/inotrope use (yes vs. no): phenylephrine, norepinephrine, epinephrine, vasopressin, dobutamine, or milrinone
  2. Infusion of any vasopressor/inotropes above (yes vs. no) (identified by unit of weight over time)
  3. Phenylephrine/ephedrine bolus (yes vs. no) (identified by unit of weight only)
  4. Vasodilator use (yes vs. no): labetalol, esmolol, nitroglycerin, nitroprusside
  5. Infusion of any vasodilator above (yes vs. no) (identified by unit of weight over time)

Other: Oxygen saturation by pulse oximetry (SpO2)
  1. Longest single episode (minutes) below a) 88, and b) 90%
  2. Cumulative duration (minutes) below a) 88, and b) 90%

Other: End-tidal Carbon dioxide (EtCO2)
  1. Longest single episode (minutes) a) below 30, and b) above 45mmHg
  2. Cumulative duration (minutes) a) below 30, and b) above 45mmHg

Outcome Measures
Primary Outcome Measures :
  1. Mortality [ Time Frame: 30 days after date of surgery ]
    All-cause postoperative mortality (yes/no)


Secondary Outcome Measures :
  1. In-hospital Morbidity: Any [ Time Frame: 30 days after date of surgery ]
    Any complications in terms of cardiac, respiratory, renal, cerebrovascular, delirium, or septic shock (yes/no)

  2. In-hospital Morbidity: Cardiac [ Time Frame: 30 days after date of surgery ]
    Composite of acute myocardial infarction, cardiac arrest, ventricular tachycardia, congestive heart failure, pulmonary edema, complete heart block, shock excluding septic shock (yes/no)

  3. In-hospital Morbidity: Respiratory [ Time Frame: 30 days after date of surgery ]
    Composite of pneumonia, pulmonary embolism, acute respiratory failure, respiratory arrest, Mechanical Ventilation >= 96 hours (yes/no)

  4. In-hospital Morbidity: Acute Kidney Injury [ Time Frame: 30 days after date of surgery ]
    Acute Kidney Injury (yes/no)

  5. In-hospital Morbidity: Cerebrovascular [ Time Frame: 30 days after date of surgery ]
    Composite of strokes and transient ischemic attacks (yes/no)

  6. In-hospital Morbidity: Delirium [ Time Frame: 30 days after date of surgery ]
    Delirium (yes/no)

  7. In-hospital Morbidity: Septic Shock [ Time Frame: 30 days after date of surgery ]
    Septic Shock (yes/no)

  8. Postoperative ICU admission [ Time Frame: 30 days after date of surgery ]
    ICU admission (yes/no)

  9. Prolonged Postoperative Length of Stay (LOS) [ Time Frame: 30 days after date of surgery ]
    Greater than vs. less than or equal to Canadian Institute of Health Information Expected Length of Stay (ELOS) as assigned by the Case Mix Grouping

  10. Hospital readmission [ Time Frame: 30 days after date of surgery ]
    Hospital readmission (yes/no)

  11. Intraoperative mortality [ Time Frame: 30 days after date of surgery ]
    Intraoperative mortality (yes/no)

  12. Days alive and out of hospital at 30 days postoperatively [ Time Frame: 30 days after date of surgery ]
    Number of days


Eligibility Criteria
Layout table for eligibility information
Ages Eligible for Study:   45 Years and older   (Adult, Older Adult)
Sexes Eligible for Study:   All
Accepts Healthy Volunteers:   No
Sampling Method:   Non-Probability Sample
Study Population
For data analysis in summer 2019, we have access to mortality data up to December 31, 2017. We chose December 1, 2017, as the last surgery date to be included, to allow for a complete data set 30 days after surgery. January 1, 2013 was chosen to obtain a study period of 5 years.
Criteria

Inclusion Criteria:

  • All patients ages ≥ 45 receiving their index (i.e. first) non-cardiac surgery with an overnight stay at the Nova Scotia Health Authority Queen Elizabeth II (QEII) hospitals (Victoria General and Halifax Infirmary) Halifax, Canada, from January 1, 2013 to December 1, 2017.
  • For patients who had multiple surgeries, only the first non-cardiac surgery with an overnight stay at QEII will be included to avoid confounding from previous surgical admissions (i.e. one surgical admission per patient).

Exclusion Criteria:

  • No intraoperative anesthetic records
  • Cardiac surgery patients
  • Deceased organ donation
Contacts and Locations

No Contacts or Locations Provided

Tracking Information
First Submitted Date July 7, 2019
First Posted Date July 10, 2019
Last Update Posted Date June 30, 2020
Actual Study Start Date January 1, 2013
Actual Primary Completion Date December 31, 2017   (Final data collection date for primary outcome measure)
Current Primary Outcome Measures
 (submitted: July 7, 2019)
Mortality [ Time Frame: 30 days after date of surgery ]
All-cause postoperative mortality (yes/no)
Original Primary Outcome Measures Same as current
Change History
Current Secondary Outcome Measures
 (submitted: June 24, 2020)
  • In-hospital Morbidity: Any [ Time Frame: 30 days after date of surgery ]
    Any complications in terms of cardiac, respiratory, renal, cerebrovascular, delirium, or septic shock (yes/no)
  • In-hospital Morbidity: Cardiac [ Time Frame: 30 days after date of surgery ]
    Composite of acute myocardial infarction, cardiac arrest, ventricular tachycardia, congestive heart failure, pulmonary edema, complete heart block, shock excluding septic shock (yes/no)
  • In-hospital Morbidity: Respiratory [ Time Frame: 30 days after date of surgery ]
    Composite of pneumonia, pulmonary embolism, acute respiratory failure, respiratory arrest, Mechanical Ventilation >= 96 hours (yes/no)
  • In-hospital Morbidity: Acute Kidney Injury [ Time Frame: 30 days after date of surgery ]
    Acute Kidney Injury (yes/no)
  • In-hospital Morbidity: Cerebrovascular [ Time Frame: 30 days after date of surgery ]
    Composite of strokes and transient ischemic attacks (yes/no)
  • In-hospital Morbidity: Delirium [ Time Frame: 30 days after date of surgery ]
    Delirium (yes/no)
  • In-hospital Morbidity: Septic Shock [ Time Frame: 30 days after date of surgery ]
    Septic Shock (yes/no)
  • Postoperative ICU admission [ Time Frame: 30 days after date of surgery ]
    ICU admission (yes/no)
  • Prolonged Postoperative Length of Stay (LOS) [ Time Frame: 30 days after date of surgery ]
    Greater than vs. less than or equal to Canadian Institute of Health Information Expected Length of Stay (ELOS) as assigned by the Case Mix Grouping
  • Hospital readmission [ Time Frame: 30 days after date of surgery ]
    Hospital readmission (yes/no)
  • Intraoperative mortality [ Time Frame: 30 days after date of surgery ]
    Intraoperative mortality (yes/no)
  • Days alive and out of hospital at 30 days postoperatively [ Time Frame: 30 days after date of surgery ]
    Number of days
Original Secondary Outcome Measures
 (submitted: July 7, 2019)
  • In-hospital Morbidity: Any [ Time Frame: 30 days after date of surgery ]
    Any complications in terms of cardiac, respiratory, renal, cerebrovascular, delirium, or septic shock (yes/no)
  • In-hospital Morbidity: Cardiac [ Time Frame: 30 days after date of surgery ]
    Composite of acute myocardial infarction, cardiac arrest, ventricular tachycardia, congestive heart failure, pulmonary edema, complete heart block, shock excluding septic shock (yes/no)
  • In-hospital Morbidity: Respiratory [ Time Frame: 30 days after date of surgery ]
    Composite of pneumonia, pulmonary embolism, acute respiratory failure, respiratory arrest, Mechanical Ventilation >= 96 hours (yes/no)
  • In-hospital Morbidity: Acute Kidney Injury [ Time Frame: 30 days after date of surgery ]
    Acute Kidney Injury (yes/no)
  • In-hospital Morbidity: Cerebrovascular [ Time Frame: 30 days after date of surgery ]
    Composite of strokes and transient ischemic attacks (yes/no)
  • In-hospital Morbidity: Delirium [ Time Frame: 30 days after date of surgery ]
    Delirium (yes/no)
  • In-hospital Morbidity: Septic Shock [ Time Frame: 30 days after date of surgery ]
    Septic Shock (yes/no)
  • Postoperative ICU admission [ Time Frame: 30 days after date of surgery ]
    ICU admission (yes/no)
  • Prolonged Postoperative Length of Stay (LOS) [ Time Frame: 30 days after date of surgery ]
    Greater than vs. less than or equal to Canadian Institute of Health Information Expected Length of Stay (ELOS) as assigned by the Case Mix Grouping
  • Hospital readmission [ Time Frame: 30 days after date of surgery ]
    Hospital readmission (yes/no)
  • Intraoperative mortality [ Time Frame: 30 days after date of surgery ]
    Intraoperative mortality (yes/no)
Current Other Pre-specified Outcome Measures Not Provided
Original Other Pre-specified Outcome Measures Not Provided
 
Descriptive Information
Brief Title Machine Learning Modeling of Intraoperative Hemodynamic Predictors of Postoperative Outcomes
Official Title Machine Learning Modeling of Intraoperative Hemodynamic Predictors of 30-day Mortality and Major In-hospital Morbidity After Noncardiac Surgery: a Retrospective Population Cohort Study
Brief Summary With population aging and limited resources, strategies to improve outcomes after surgery are ever more important. There is a limited understanding of what ranges of hemodynamic variables under anesthesia are associated with better outcomes. This retrospective cohort study will analyze how hemodynamic variables during surgeries predict mortality, morbidity, Intensive Care Unit admission, length of hospital stay, and hospital readmission. The use of machine learning in a large, broad surgery population dataset could detect new relationships and strategies that may inform current practice, and generate ideas for future research.
Detailed Description

Lay Summary

Introduction: The World Health Organization estimates that 270-360 million operations are performed every year worldwide. Death and complications after surgery are a big challenge. In Canada, out of every 1000 major surgeries, 16 patients die in hospital after surgery. In the United States, for every 1000 operations, 67 patients unexpectedly need life support in the Intensive Care Unit. With population aging and limited resources, strategies to improve health after surgery are ever more important.

Vital signs, such as blood pressure and heart rate, show how the body is doing. Vital signs change during surgery because of patient, surgical, and anesthetic factors. Anesthesiologists can change vital signs with medications. However, medical professionals are only starting to understand which, and what ranges of, vital signs under anesthesia are associated with better health. Machine learning is a tool that can provide new ways to understand data. With better understanding, medical professionals can work to improve outcomes after surgery.

Objective: This study will analyze vital signs during surgeries for their links to death, complications (heart, lung, kidney, brain, infection), Intensive Care Unit admission, length of hospital stay, and hospital readmission. This study will determine which, and what levels of, vital signs may be harmful. The investigators predict that blood pressure, heart rate, oxygen level, carbon dioxide level, and the need for medications to change blood pressure will interact to be associated with death after surgery.

Methods: After obtaining Research Ethics Board approval, the investigators will analyze data from all patients who are at least 45 years old and had an operation (with the exception of heart surgery) with an overnight stay at the Queen Elizabeth II health centre (Halifax, Canada) from January 1, 2013 to December 1, 2017. There are approximately eligible 35,000 patients. The investigators will use machine learning to model the data and test how well our model explains outcomes after surgery.

Significance: The use of machine learning in a large, broad surgery population dataset could detect new relationships and strategies that may inform current practice, and generate ideas for future research. A better understanding of the impact of vital signs during surgeries may unveil methods to improve outcomes and resource allocation after surgery. The results may suggest ways to identify high-risk patients who should be monitored more closely after surgery. If the model performs well, it may motivate other researchers to use machine learning in health data research.

Please see full protocol for details.

May 2020 update (prior to dataset aggregation and analysis)

  1. Added secondary outcome (days alive and out of hospital at 30 days postoperatively)
  2. Improved hemodynamic variable artifact processing algorithm
  3. Added sub-study: machine learning for invasive blood pressure artifact removal algorithm
Study Type Observational
Study Design Observational Model: Cohort
Time Perspective: Retrospective
Target Follow-Up Duration Not Provided
Biospecimen Not Provided
Sampling Method Non-Probability Sample
Study Population For data analysis in summer 2019, we have access to mortality data up to December 31, 2017. We chose December 1, 2017, as the last surgery date to be included, to allow for a complete data set 30 days after surgery. January 1, 2013 was chosen to obtain a study period of 5 years.
Condition
  • Perioperative/Postoperative Complications
  • Morbidity, Multiple
  • Surgery
  • Anesthesia
  • Death
Intervention
  • Other: Blood pressure

    Systolic Blood Pressure (SBP)

    1. Maximum change from preoperative SBP, in a) absolute change (mmHg), and b) relative change (%)(emergency and elective cases analyzed separately)
    2. Cumulative duration (minutes) >=20% below preoperative SBP
    3. Longest single episode (minutes) below a) 80, b) 90, and c)100 mmHg
    4. Cumulative duration (minutes) below a) 80, b) 90, and c)100 mmHg

    Mean Arterial Pressure (MAP)

    1. Maximum change from preoperative MAP, in a) absolute change (mmHg), and b) relative change (%) (emergency and elective cases analyzed separately)
    2. Cumulative duration (minutes) >=20% below preoperative MAP
    3. Longest single episode (minutes) below a) 60, b) 65, c) 70, and d) 80mmHg
    4. Cumulative duration (minutes) below a) 60, b) 65, c) 70, and d) 80mmHg
  • Other: Heart rate
    1. Maximum change (beats per minute, BPM) from preoperative heart rate (positive and negative)
    2. Relative change (%) from preoperative heart rate (positive and negative)
    3. Maximum pulse variation (maximum heart rate minus minimum heart rate)
    4. Longest single episode (minutes) a) below 60, and b) above 100BPM
    5. Cumulative duration (minutes) a) below 60, and b) above 100BPM
  • Other: Use of hemodynamic medications (i.e. special medications for blood pressure)
    1. Vasopressor/inotrope use (yes vs. no): phenylephrine, norepinephrine, epinephrine, vasopressin, dobutamine, or milrinone
    2. Infusion of any vasopressor/inotropes above (yes vs. no) (identified by unit of weight over time)
    3. Phenylephrine/ephedrine bolus (yes vs. no) (identified by unit of weight only)
    4. Vasodilator use (yes vs. no): labetalol, esmolol, nitroglycerin, nitroprusside
    5. Infusion of any vasodilator above (yes vs. no) (identified by unit of weight over time)
  • Other: Oxygen saturation by pulse oximetry (SpO2)
    1. Longest single episode (minutes) below a) 88, and b) 90%
    2. Cumulative duration (minutes) below a) 88, and b) 90%
  • Other: End-tidal Carbon dioxide (EtCO2)
    1. Longest single episode (minutes) a) below 30, and b) above 45mmHg
    2. Cumulative duration (minutes) a) below 30, and b) above 45mmHg
Study Groups/Cohorts Cohort
Patients ages ≥ 45 receiving their index (i.e. first) non-cardiac surgery with an overnight stay at the Nova Scotia Health Authority Queen Elizabeth II (QEII) hospitals (Victoria General and Halifax Infirmary) Halifax, Canada, from January 1, 2013 to December 1, 2017 will be included. Patients under going cardiac surgery or deceased organ donation will be excluded. Patients without an electronic anesthetic record during surgery will also be excluded. Preliminary analysis of the intraoperative database estimates approximately 35,000 patients in this cohort.
Interventions:
  • Other: Blood pressure
  • Other: Heart rate
  • Other: Use of hemodynamic medications (i.e. special medications for blood pressure)
  • Other: Oxygen saturation by pulse oximetry (SpO2)
  • Other: End-tidal Carbon dioxide (EtCO2)
Publications * Not Provided

*   Includes publications given by the data provider as well as publications identified by ClinicalTrials.gov Identifier (NCT Number) in Medline.
 
Recruitment Information
Recruitment Status Completed
Estimated Enrollment
 (submitted: July 7, 2019)
35000
Original Estimated Enrollment Same as current
Actual Study Completion Date December 31, 2017
Actual Primary Completion Date December 31, 2017   (Final data collection date for primary outcome measure)
Eligibility Criteria

Inclusion Criteria:

  • All patients ages ≥ 45 receiving their index (i.e. first) non-cardiac surgery with an overnight stay at the Nova Scotia Health Authority Queen Elizabeth II (QEII) hospitals (Victoria General and Halifax Infirmary) Halifax, Canada, from January 1, 2013 to December 1, 2017.
  • For patients who had multiple surgeries, only the first non-cardiac surgery with an overnight stay at QEII will be included to avoid confounding from previous surgical admissions (i.e. one surgical admission per patient).

Exclusion Criteria:

  • No intraoperative anesthetic records
  • Cardiac surgery patients
  • Deceased organ donation
Sex/Gender
Sexes Eligible for Study: All
Ages 45 Years and older   (Adult, Older Adult)
Accepts Healthy Volunteers No
Contacts Contact information is only displayed when the study is recruiting subjects
Listed Location Countries Not Provided
Removed Location Countries  
 
Administrative Information
NCT Number NCT04014010
Other Study ID Numbers 1024251
Has Data Monitoring Committee No
U.S. FDA-regulated Product
Studies a U.S. FDA-regulated Drug Product: No
Studies a U.S. FDA-regulated Device Product: No
IPD Sharing Statement
Plan to Share IPD: No
Responsible Party Janny Xue Chen Ke, Nova Scotia Health Authority
Study Sponsor Janny Xue Chen Ke
Collaborators
  • Dalhousie University
  • Harvard University
  • University of Toronto
  • University of Ottawa
Investigators Not Provided
PRS Account Nova Scotia Health Authority
Verification Date June 2020