Improving Colorectal Cancer Screening in Racially Diverse Zip Codes Using Navigation and Machine Learning (PCSNaP) (PCSNaP)

A Feasibility Study to Improve Colorectal Cancer Screening Among Racially Diverse Zip Codes in a Persistent Poverty County Using Navigation and Machine Learning Predictive Algorithms

The overarching goal of the "PCSNaP" Research Study is to support the Abramson Cancer Center (ACC) of the University of Pennsylvania in carrying out its mission to increase colorectal cancer (CRC) screening completion among high-risk individuals living in a persistent poverty county by designing, conducting, disseminating and evaluating an electronic health record-based automated identification program to target effective, culturally-sensitive CRC screening navigation to individuals who have not completed an ordered colonoscopy or fecal immunochemical test (FIT).

Study Overview

• Status: Completed
• Conditions: Colorectal Cancer
• Intervention / Treatment: Other: Machine Learning Algorithm with Existing Penn Medicine CRC Patient Navigation Program

Detailed Description

Specifically, the goals of this study are to: 1) Adapt a previously validated electronic health record (EHR)-based machine learning algorithm to predict colorectal cancer (CRC) detection by retraining the model using data from patients seen in primary care clinics serving zip codes with a high proportion of racial and ethnic minorities living in Philadelphia County, a persistent poverty county; and 2) Implement and evaluate the feasibility and effectiveness of an algorithm-based CRC navigation program to increase colorectal cancer screening among patients in Philadelphia county who are at high risk of CRC and have uncompleted colonoscopies.

Together, these novel projects aim to be the first to combine use of machine learning algorithms and patient navigation to increase guideline-based cancer screening in order to reduce the burden of CRC among high-risk individuals living in a persistent poverty county through targeted, culturally-sensitive navigation that addresses social factors that prevent CRC screening.

• Study Type: Observational
• Enrollment (Actual): 385

Contacts and Locations

Study Locations

• United States
  • Pennsylvania
    • Philadelphia, Pennsylvania, United States, 19104
      • University of Pennsylvania

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

The cohort will consist of patients residing in 18 zip codes in Western and Southwestern Philadelphia who have primary care providers in 4 Penn Medicine Internal Medicine practices and 3 Penn Medicine Family Medicine Practices. Patients will have had a colonoscopy order placed in the past 6 months and have not scheduled, cancelled, or no-showed to their colonoscopy.

Description

Inclusion Criteria:

• Patients residing in 18 zip codes in Western and Southwestern Philadelphia who have primary care providers in 4 Penn Medicine Internal Medicine practices and 3 Penn Medicine Family Medicine Practices
• Patients who have had a colonoscopy order placed in the past 6 months and have not scheduled, cancelled, or no-showed to their colonoscopy

Exclusion Criteria:

• Not applicable

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Prospective

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

Patients Residing in 18 zip codes in Western and Southwestern Philadelphia; The cohort will consist of patients residing in 18 zip codes in Western and Southwestern Philadelphia who have primary care providers in 4 Penn Medicine Internal Medicine practices and 3 Penn Medicine Family Medicine Practices.

Other: Machine Learning Algorithm with Existing Penn Medicine CRC Patient Navigation Program; This intervention will utilize the existing Penn Medicine CRC patient navigation program. There will be a monthly list of patients with unfilled coloscopies provided, that are risk-stratified according to the machine learning algorithm and select high-risk criteria. The navigation team will prioritize timely outreach and navigation to high-risk patients according to a script that communicates risk.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Enrollment in Navigator Program (Feasibility)	Number of patients that participate in the navigation program	During the three month enrollment period
Completion of Colorectal Cancer Screening	Number of patients that have completed their colonoscopy or Fecal Immunochemical Test (FIT)	Within the three month enrollment period and three month follow-up period
Number of Participants With Adenoma Detection	Rate of adenomas after completion of colonoscopy	Within the three month enrollment period and three month follow-up period

Collaborators and Investigators

• Sponsor: Abramson Cancer Center at Penn Medicine
• Investigators: Principal Investigator: Carmen Guerra, MD, University of Pennsylvania

Study record dates

Study Major Dates

• Study Start (Actual): March 29, 2022
• Primary Completion (Actual): November 1, 2024
• Study Completion (Actual): November 1, 2024

Study Registration Dates

• First Submitted: May 17, 2022
• First Submitted That Met QC Criteria: May 17, 2022
• First Posted (Actual): May 20, 2022

Study Record Updates

• Last Update Posted (Actual): February 11, 2026
• Last Update Submitted That Met QC Criteria: February 10, 2026
• Last Verified: November 1, 2024

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Intestinal Diseases; Gastrointestinal Neoplasms; Digestive System Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Intestinal Neoplasms; Rectal Diseases; Colonic Diseases; Colorectal Neoplasms; Algorithms; Mathematical Concepts; Machine Learning Algorithms
• Other Study ID Numbers: UPCC 09222; 850205 (Other Identifier: IRB)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

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