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

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

Study Overview

• Status: Completed
• Conditions: Palliative Care
• Intervention / Treatment: Other: Palliative care contacts primary care

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 Type: Interventional
• Enrollment (Actual): 127070
• Phase: Not Applicable

Contacts and Locations

Study Locations

• United States
  • Minnesota
    • Rochester, Minnesota, United States, 55905
      • Mayo Clinic in Rochester

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

Description

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

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Screening
• Allocation: Randomized
• Interventional Model: Crossover Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / 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.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Timely identification for need of palliative care	Time to electronic record of consult by the palliative care team in the outpatient setting	Through study completion, an average of 1 year

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Number of palliative care consults	Number of palliative care consults that occurred on intervention and standard of care arms	Through study completion, an average of 1 year
Number of advanced care planning notes documented in the EHR	Number of advanced care planning notes documented in the EHR on both arms	Through study completion, an average of 1 year
Number of billing codes for palliative care	Number of ICD-10 billing codes for palliative care on both arms	Through study completion, an average of 1 year
Positive predictive value of screened patients	Percentage of screened patients that received palliative care consults	Through study completion, an average of 1 year
Percent of patients who are eligible for ECH based palliative care	Percent of patients who are eligible for employee/community health (ECH) based palliative care compared to the Palliative Care Clinic.	Through study completion, an average of 1 year
Percent agreement between Palliative Care and Primary Care and average time between Primary Care Contact and Response	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.	Through study completion, an average of 1 year

Collaborators and Investigators

• Sponsor: Mayo Clinic
• Investigators: Principal Investigator: Rachel Havyer, MD, Mayo Clinic

Publications and helpful links

Helpful Links

• Mayo Clinic Clinical Trials

Study record dates

Study Major Dates

• Study Start (Actual): August 31, 2020
• Primary Completion (Actual): May 31, 2021
• Study Completion (Actual): May 31, 2021

Study Registration Dates

• First Submitted: October 14, 2020
• First Submitted That Met QC Criteria: October 21, 2020
• First Posted (Actual): October 27, 2020

Study Record Updates

• Last Update Posted (Actual): June 16, 2021
• Last Update Submitted That Met QC Criteria: June 14, 2021
• Last Verified: June 1, 2021

More Information

Terms related to this study

• Keywords: palliative care; machine learning; predictive model
• Other Study ID Numbers: 20-005977

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No