Impact of Predictive Modeling on Time to Palliative Care in an Outpatient Primary Care Population

• Sponsor: Mayo Clinic (Other)
• Overall Status: Completed
• CT.gov ID: NCT04604457
• Collaborator: (none)
• Enrollment: 127,070
• Location: 1
• Arms: 2
• Actual Duration (Months): 9
• Patients Per Site Per Month: 14167.4

Study Details

Study Description

Brief Summary

A machine learning algorithm will be used to accurately identify patients in certain primary care units who may benefit from palliative care consults.

Condition or Disease	Intervention/Treatment	Phase
Palliative Care	Other: Palliative care contacts primary care	N/A

Detailed Description

A machine learning algorithm will be used to accurately identify patients in certain primary care units who may benefit from palliative care consults. These patients will be presented weekly to a palliative care specialist in a custom user interface. The palliative care specialist will reach out to primary care teams if she determines that the patient would benefit from palliative care. If the primary care provider agrees, he/she would write a palliative care consult order for the patient. The goal is to reduce the time to palliative care for these patients, who may not have been identified as quickly without the algorithm.

Study Design

• Study Type: Interventional
• Actual Enrollment: 127070 participants
• Allocation: Randomized
• Intervention Model: Crossover Assignment
• Intervention Model Description: Step-wedge design with 7 wedges: the first wedge has all primary care teams in the standard of care arm; every six weeks one or two care teams switch to the intervention arm.Step-wedge design with 7 wedges: the first wedge has all primary care teams in the standard of care arm; every six weeks one or two care teams switch to the intervention arm.
• Masking: None (Open Label)
• Primary Purpose: Screening
• Official Title: Impact of Predictive Modeling on Time to Palliative Care in an Outpatient Primary Care Population
• Actual Study Start Date: Aug 31, 2020
• Actual Primary Completion Date: May 31, 2021
• Actual Study Completion Date: May 31, 2021

Arms and Interventions

Arm	Intervention/Treatment
No Intervention: Standard of Care Palliative care specialists would not reach out to primary care providers. Palliative care needs would be met via existing mechanisms.
Experimental: Predictive Model Palliative care specialists review recommendations from the predictive model and contact a patient's primary care provider (PCP) when appropriate to recommend a palliative care consult.	Other: Palliative care contacts primary care; Palliative care specialist reaches out to primary care to recommend a palliative care consult. If the primary care provider agrees, he/she will write an order for a palliative care consult.

Outcome Measures

Primary Outcome Measures

1. Timely identification for need of palliative care [Through study completion, an average of 1 year]

   Time to electronic record of consult by the palliative care team in the outpatient setting

Secondary Outcome Measures

1. Number of palliative care consults [Through study completion, an average of 1 year]

   Number of palliative care consults that occurred on intervention and standard of care arms

2. Number of advanced care planning notes documented in the EHR [Through study completion, an average of 1 year]

   Number of advanced care planning notes documented in the EHR on both arms

3. Number of billing codes for palliative care [Through study completion, an average of 1 year]

   Number of ICD-10 billing codes for palliative care on both arms

4. Positive predictive value of screened patients [Through study completion, an average of 1 year]

   Percentage of screened patients that received palliative care consults

5. Percent of patients who are eligible for ECH based palliative care [Through study completion, an average of 1 year]

   Percent of patients who are eligible for employee/community health (ECH) based palliative care compared to the Palliative Care Clinic.

6. Percent agreement between Palliative Care and Primary Care and average time between Primary Care Contact and Response [Through study completion, an average of 1 year]

   Agreement statistics (percent agreement and Kappa statistics) between Palliative Care and Primary Care and descriptive statistics (mean, etc.) on time between primary care contact and response.

Eligibility Criteria

Criteria

• Ages Eligible for Study: 18 Years and Older
• Sexes Eligible for Study: All
• Accepts Healthy Volunteers: No

Inclusion Criteria:

• Adult patient assigned to a primary care unit from July 2020 to June 2021.

• Weekly the palliative care specialists will select patients by looking at patients in sorted order starting with the highest score and proceeding down the list and evaluating each patient for exclusion criteria.

Exclusion Criteria:

• Patients that have been seen by Palliative care will be excluded for 75 days

• Patients under the age of 18 years.

• Patients currently enrolled with hospice

Contacts and Locations

Locations

	Site	City	State	Country	Postal Code
1	Mayo Clinic in Rochester	Rochester	Minnesota	United States	55905

Sponsors and Collaborators

• Mayo Clinic

Investigators

• Principal Investigator: Rachel Havyer, MD, Mayo Clinic

Study Documents (Full-Text)

None provided.

More Information

Additional Information:

• Mayo Clinic Clinical Trials

Publications

None provided.

• Responsible Party: Rachel D. Havyer, Principal Investigator, Mayo Clinic
• ClinicalTrials.gov Identifier: NCT04604457
• Other Study ID Numbers: 20-005977
• First Posted: Oct 27, 2020
• Last Update Posted: Jun 16, 2021
• Last Verified: Jun 1, 2021

• Individual Participant Data (IPD) Sharing Statement: No
• Plan to Share IPD: No
• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No
• Keywords provided by Rachel D. Havyer, Principal Investigator, Mayo Clinic: machine learning; predictive model; palliative care

Study Results

No Results Posted as of Jun 16, 2021