Working...
ClinicalTrials.gov
ClinicalTrials.gov Menu

Telemedicine Notifications With Machine Learning for Postoperative Care (ODIN-Report)

The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been evaluated by the U.S. Federal Government. Know the risks and potential benefits of clinical studies and talk to your health care provider before participating. Read our disclaimer for details.
ClinicalTrials.gov Identifier: NCT03974828
Recruitment Status : Not yet recruiting
First Posted : June 5, 2019
Last Update Posted : June 7, 2019
Sponsor:
Information provided by (Responsible Party):
Christopher King, Washington University School of Medicine

Brief Summary:
The ODIN-Report study will be a randomized controlled trial of the effect of providing machine learning risk forecasts to providers caring for patients immediately after surgery on serious complications. The complications studied will be kidney injury, delirium, unplanned or prolonged ventilator use, and 30 day mortality.

Condition or disease Intervention/treatment Phase
Surgery--Complications Perioperative/Postoperative Complications Acute Kidney Injury Postoperative Delirium Respiratory Insufficiency Hospital Mortality Device: Anesthesia Control Tower Notification Not Applicable

Detailed Description:

This will be a single center, randomized, controlled, pragmatic clinical trial. The investigators will screen surgical patients enrolled in TECTONICS (NCT03923699) and randomized to intraoperative contact. Near the end of the operation, the investigators will calculate the same machine learning risk forecasts of major complications as TECTONICS, and enroll patients if any of the following are true:

ICU disposition is intended ML risk forecast is in top 15% of historical PACU patients ML risk forecast has increased by > 50% compared to preoperative.

Patients will be randomized 2:1:1 to no contact, brief contact, and full contact. The postoperative provider (PACU physician, anesthesiologist, ICU fellow or advanced practice nurse) will be notified before arrival of the risk forecast in the contact groups, and in the full contact group an additional set of explanatory ML outputs will be provided. The intention-to-treat principle will be followed for all analyses. All analyses will be fully stratified by ICU / PACU disposition.


Layout table for study information
Study Type : Interventional  (Clinical Trial)
Estimated Enrollment : 10000 participants
Allocation: Randomized
Intervention Model: Parallel Assignment
Intervention Model Description: 2:1:1 randomization between standard of care, postoperative contact (brief), postoperative contact (long).
Masking: Double (Participant, Outcomes Assessor)
Primary Purpose: Other
Official Title: Telemedicine Notifications With Machine Learning for Postoperative Care
Estimated Study Start Date : December 1, 2019
Estimated Primary Completion Date : January 1, 2024
Estimated Study Completion Date : January 1, 2024

Resource links provided by the National Library of Medicine

MedlinePlus related topics: After Surgery

Arm Intervention/treatment
No Intervention: Non-Contact
Participants in the non-contact group will be monitored by anesthesia control tower clinicians who will utilize AlertWatch and integrating machine-learning forecasting algorithms for adverse outcomes predictions, but who will not contact the postoperative provider unless it is clinically necessary for patient safety purposes.
Experimental: Brief contact
PACU providers caring for participants in the brief contact group will be notified by ACT clinicians before arrival if the patient's forecast for MAE is in the top 15% of historical PACU patients. The notification will contain a brief summary of the patient's forecast risk of major adverse events.
Device: Anesthesia Control Tower Notification
Real-time data will be monitored through the AlertWatch system as well as the EHR. Risk forecasts of adverse events (30 day mortality, acute kidney injury, postoperative delirium, respiratory failure), PACU length of stay, and hospital length of stay will be generated by a machine learning algorithm. Additional outputs identifying the most important predictors and their effects will be combined with risk forecasts to form a report card.

Experimental: Full contact
PACU providers caring for participants in the full contact group will be notified by ACT clinicians before arrival if the patient's forecast for MAE is in the top 15% of historical PACU patients. The notification will contain a report card of the patient's forecast risk of major adverse events, explanatory machine-learning outputs, most influential pre- and intraoperative data, and predicted treatments.
Device: Anesthesia Control Tower Notification
Real-time data will be monitored through the AlertWatch system as well as the EHR. Risk forecasts of adverse events (30 day mortality, acute kidney injury, postoperative delirium, respiratory failure), PACU length of stay, and hospital length of stay will be generated by a machine learning algorithm. Additional outputs identifying the most important predictors and their effects will be combined with risk forecasts to form a report card.




Primary Outcome Measures :
  1. Sum of clinically relevant adverse perioperative outcomes [ Time Frame: 30 days post-op ]
    defined and measured in the TECTONICS protocol, acute kidney injury worse than KDIGO grade 1, ventilatory failure > 24 hours, postoperative delirium by CAM-ICU, and mortality in 30 days. Outcomes are derived from the EHR and a local registry of post-discharge mortality. Patients with postoperative death will be marked as having experienced all 4 complications.


Secondary Outcome Measures :
  1. Satisfaction with OR-postoperative handoff: survey [ Time Frame: one hour after patient release from OR ]
    Postoperative providers will be surveyed on their satisfaction with handoff on a 5 point scale with larger values representing more satisfaction. [Very unsatisfied, unsatisfied, neutral, satisfied, very satisfied]

  2. Initial assessment accuracy [ Time Frame: one hour after patient release from OR ]
    Postoperative providers will be surveyed on their estimate of the likelihood for the patient to experience MAE as defined in the primary outcome. PACU providers will be asked their estimate of hospital length of stay, and ICU providers their estimate of ICU length of stay. Providers will be asked the appropriate bed disposition or nursing staff ratio. This will be compared to actual outcomes.

  3. Provider attention [ Time Frame: one hour after patient release from OR ]
    Postoperative providers will be surveyed on the number of times in the first hour that they visited the patient or spoke with their nurse, to a maximum of 5. [ 0 , 1 , 2 , 3 , 4 , 5 or more ] The number of orders changed from order-sets will be extracted from the EHR. This will be compared to calibrated risk forecasts.

  4. Critical care time [ Time Frame: 30 days post-op ]
    The length of stay in PACU (handoff to sign-out) and length of stay in ICU will be extracted from the EHR



Information from the National Library of Medicine

Choosing to participate in a study is an important personal decision. Talk with your doctor and family members or friends about deciding to join a study. To learn more about this study, you or your doctor may contact the study research staff using the contacts provided below. For general information, Learn About Clinical Studies.


Layout table for eligibility information
Ages Eligible for Study:   18 Years and older   (Adult, Older Adult)
Sexes Eligible for Study:   All
Accepts Healthy Volunteers:   No
Criteria

Inclusion Criteria:

  • Enrolled in TECTONICS Study (ID 201903026, NCT03923699), in OR randomized to contact
  • workweek hours
  • preoperative assessment completed
  • estimated risk of major adverse event in top 15% of historical PACU patients or increased by > 50% during surgery or ICU disposition

Exclusion Criteria:

  • Not enrolled in TECTONICS Study
  • Operating room randomized to non-contact in TECTONICS

Information from the National Library of Medicine

To learn more about this study, you or your doctor may contact the study research staff using the contact information provided by the sponsor.

Please refer to this study by its ClinicalTrials.gov identifier (NCT number): NCT03974828


Contacts
Layout table for location contacts
Contact: Sherry McKinnon, BS 314-221-7764 smckinnon@wustl.edu

Sponsors and Collaborators
Washington University School of Medicine
Investigators
Layout table for investigator information
Principal Investigator: Christopher R King, MD, PhD Washington University School of Medicine

Layout table for additonal information
Responsible Party: Christopher King, Principal Investigator, Washington University School of Medicine
ClinicalTrials.gov Identifier: NCT03974828     History of Changes
Other Study ID Numbers: 201905127
First Posted: June 5, 2019    Key Record Dates
Last Update Posted: June 7, 2019
Last Verified: June 2019
Individual Participant Data (IPD) Sharing Statement:
Plan to Share IPD: No
Plan Description: Data are a subset of TECTONICS and will be have the same sharing plan / restrictions.

Layout table for additional information
Studies a U.S. FDA-regulated Drug Product: No
Studies a U.S. FDA-regulated Device Product: Yes
Device Product Not Approved or Cleared by U.S. FDA: No
Pediatric Postmarket Surveillance of a Device Product: No
Product Manufactured in and Exported from the U.S.: Yes

Keywords provided by Christopher King, Washington University School of Medicine:
Telemedicine
Anesthesia Control Tower
Machine Learning
Forecasting Algorithms
Randomized Controlled Trial
PACU

Additional relevant MeSH terms:
Layout table for MeSH terms
Delirium
Acute Kidney Injury
Postoperative Complications
Respiratory Insufficiency
Pulmonary Valve Insufficiency
Confusion
Neurobehavioral Manifestations
Neurologic Manifestations
Nervous System Diseases
Signs and Symptoms
Neurocognitive Disorders
Mental Disorders
Renal Insufficiency
Kidney Diseases
Urologic Diseases
Pathologic Processes
Respiration Disorders
Respiratory Tract Diseases
Heart Valve Diseases
Heart Diseases
Cardiovascular Diseases
Anesthetics
Central Nervous System Depressants
Physiological Effects of Drugs