Prospective Validation of an EHR-based Pancreatic Cancer Risk Model

Prospective Validation of an EHR-based Model to Predict Pancreatic Cancer Risk Using Multicenter US Data

The goal of this prospective observational cohort study is to validate a previously developed pancreatic cancer risk prediction algorith (the PRISM model) using electronic health records from the general population. The main questions it aims to answer are:

• Will a pancreatic cancer risk model, developed on routine EHR data, reliably and accurately predict pancreatic cancer in real-time?
• What is the average time from model deployment and risk prediction, to the date of pancreatic cancer development and what is the stage of pancreatic cancer at diagnosis? The risk model will be deployed on data from individuals eligible for the study. Each individual will be assigned a risk score and tracked over time to assess the model's discriminatory performance and calibration.

Study Overview

• Status: Active, not recruiting
• Conditions: Pancreatic Adenocarcinoma; Predictive Cancer Model
• Intervention / Treatment: Other: Pancreatic Cancer Risk Model (PRISM)

Detailed Description

To prospectively validate, implement in real-time, and assess performance of an EHR- based PDAC risk-prediction model. To test the hypothesis that our model will reliably predict PDAC in a real-time clinical setting, we will conduct a multi-center prospective cohort study, deploying the PDAC risk model within the TriNetX federated network database, and will take the following steps:

i) generate a risk prediction score for each individual under the care of 44 health care organizations (HCOs) in the USA ii) follow all individuals for up to 3 years to assess the primary end-point of PDAC development.

The following metrics will be used to test the discriminative performance and calibration of the EHR-based PDAC risk model in predicting incident PDAC, at the end of the 3-year period:

1. AUROC, sensitivity, specificity, PPV/NPV for assessing discrimination
2. Calibration: for assessing the accuracy of estimates, based on the estimated to observed number of events

• Study Type: Observational
• Enrollment (Actual): 6134060

Contacts and Locations

Study Locations

• United States
  • Massachusetts
    • Boston, Massachusetts, United States, 02115
      • Beth Israel Deaconess Medical Center

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

The cohort will be selected from 44 eligible HCOs comprised of community hospitals, outpatient clinics and academic medical centers from across the US.

Description

Inclusion Criteria:

• Male and females age >= 40 years from 44 US HCOs from the TriNetX platform
• at least 2 clinical encounters to the HCO, within the last year, before the study start date

Exclusion Criteria:

• Personal history of PDAC or current PDAC
• Age below 40

Notes on sampling method: no sampling was performed. All eligible individuals are included in this study.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
prospective general opulation cohort; Males and females age >= 40 years, without a personal history of PDAC or current PDAC, with at least 2 clinical encounters to the HCO within the year prior to the study start date.	Other: Pancreatic Cancer Risk Model (PRISM); A neural network model (PrismNN) and a logistic regression model (PrismLR) that use routinely collected EHR data to stratify individuals from the general population into PDAC risk groups

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Area under the receiver operating characteristic curve (AUROC) of PRISM for all groups stratified	To assess the discriminatory performance of PRISM for prospective identification of high-risk individuals for PDAC development. ROCs and AUROC numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location.	6 months from index date
Area under the receiver operating characteristic curve (AUROC) of PRISM for all groups stratified	To assess the discriminatory performance of PRISM for prospective identification of high-risk individuals for PDAC development. ROCs and AUROC numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location.	at 1 year
Area under the receiver operating characteristic curve (AUROC) of PRISM for all groups stratified	To assess the discriminatory performance of PRISM for prospective identification of high-risk individuals for PDAC development. ROCs and AUROC numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location.	at 2 years
Area under the receiver operating characteristic curve (AUROC) of PRISM for all groups stratified	To assess the discriminatory performance of PRISM for prospective identification of high-risk individuals for PDAC development. ROCs and AUROC numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location.	at 3 years
Calibration of PRISM for all groups stratified	To access how well the risk prediction by PRISM aligns with observed risk without recalibration. Calibration plots will be created for the whole population and groups stratified by age, sex, race, and geographical location.	6 months from index date
Calibration of PRISM for all groups stratified	To access how well the risk prediction by PRISM aligns with observed risk without recalibration. Calibration plots will be created for the whole population and groups stratified by age, sex, race, and geographical location.	at 1 year
Calibration of PRISM for all groups stratified	To access how well the risk prediction by PRISM aligns with observed risk without recalibration. Calibration plots will be created for the whole population and groups stratified by age, sex, race, and geographical location.	at 2 years
Calibration of PRISM for all groups stratified	To access how well the risk prediction by PRISM aligns with observed risk without recalibration. Calibration plots will be created for the whole population and groups stratified by age, sex, race, and geographical location.	at 3 years
PRISM performance metrics of high-risk group for direct screening	To evaluate sensitivity, specificity, PPV, and SIR for patients identified as high-risk by PRISM. Numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location. Risk threshold determined based on Standardized Incidence Ratio of 5 or greater. The absolute one-year risk thresholds are 0.1834% for PrismNN and 0.2048% risk for PrismLR. SIR 5 or greater was chosen because it is comparable to the current screening inclusion threshold for individuals with an inherited predisposition.	6 months from index date
PRISM performance metrics of high-risk group for direct screening	To evaluate sensitivity, specificity, PPV, and SIR for patients identified as high-risk by PRISM. Numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location. Risk threshold determined based on Standardized Incidence Ratio of 5 or greater. The absolute one-year risk thresholds are 0.1834% for PrismNN and 0.2048% risk for PrismLR. SIR 5 or greater was chosen because it is comparable to the current screening inclusion threshold for individuals with an inherited predisposition.	at 1 year
PRISM performance metrics of high-risk group for direct screening	To evaluate sensitivity, specificity, PPV, and SIR for patients identified as high-risk by PRISM. Numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location. Risk threshold determined based on Standardized Incidence Ratio of 5 or greater. The absolute one-year risk thresholds are 0.1834% for PrismNN and 0.2048% risk for PrismLR. SIR 5 or greater was chosen because it is comparable to the current screening inclusion threshold for individuals with an inherited predisposition.	at 2 years
PRISM performance metrics of high-risk group for direct screening	To evaluate sensitivity, specificity, PPV, and SIR for patients identified as high-risk by PRISM. Numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location. Risk threshold determined based on Standardized Incidence Ratio of 5 or greater. The absolute one-year risk thresholds are 0.1834% for PrismNN and 0.2048% risk for PrismLR. SIR 5 or greater was chosen because it is comparable to the current screening inclusion threshold for individuals with an inherited predisposition.	at 3 years
PRISM performance metrics of medium-risk group for biomarker testing	To evaluate sensitivity, specificity, PPV, and SIR for patients identified as medium-risk by PRISM. Numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location. Risk threshold determined by specificity 85%, with sensitivity around 46%. The absolute one-year risk thresholds are 0.0574% for PrismNN and 0.0564% for PrismLR. Prism operates as a tiered system for identifying individuals in need of screening with this lower risk threshold.	6 months from index date
PRISM performance metrics of medium-risk group for biomarker testing	To evaluate sensitivity, specificity, PPV, and SIR for patients identified as medium-risk by PRISM. Numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location. Risk threshold determined by specificity 85%, with sensitivity around 46%. The absolute one-year risk thresholds are 0.0574% for PrismNN and 0.0564% for PrismLR. Prism operates as a tiered system for identifying individuals in need of screening with this lower risk threshold.	at 1 year
PRISM performance metrics of medium-risk group for biomarker testing	To evaluate sensitivity, specificity, PPV, and SIR for patients identified as medium-risk by PRISM. Numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location. Risk threshold determined by specificity 85%, with sensitivity around 46%. The absolute one-year risk thresholds are 0.0574% for PrismNN and 0.0564% for PrismLR. Prism operates as a tiered system for identifying individuals in need of screening with this lower risk threshold.	at 2 years
PRISM performance metrics of medium-risk group for biomarker testing	To evaluate sensitivity, specificity, PPV, and SIR for patients identified as medium-risk by PRISM. Numbers will be calculated for the whole population and groups stratified by age, sex, race, and geographical location. Risk threshold determined by specificity 85%, with sensitivity around 46%. The absolute one-year risk thresholds are 0.0574% for PrismNN and 0.0564% for PrismLR. Prism operates as a tiered system for identifying individuals in need of screening with this lower risk threshold.	at 3 years

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Timing of incident PDAC occurrence	To evaluate how long in advance before PDAC occurrence should be expected for PRISM models to make high-risk predictions. Distribution plots of the date of PDAC incidence for high/medium-risk groups (defined in Outcome 3 and Outcome 4) will be created.	6 months from index date
Timing of incident PDAC occurrence	To evaluate how long in advance before PDAC occurrence should be expected for PRISM models to make high-risk predictions. Distribution plots of the date of PDAC incidence for high/medium-risk groups (defined in Outcome 3 and Outcome 4) will be created.	at 1 year
Timing of incident PDAC occurrence	To evaluate how long in advance before PDAC occurrence should be expected for PRISM models to make high-risk predictions. Distribution plots of the date of PDAC incidence for high/medium-risk groups (defined in Outcome 3 and Outcome 4) will be created.	at 2 years
Timing of incident PDAC occurrence	To evaluate how long in advance before PDAC occurrence should be expected for PRISM models to make high-risk predictions. Distribution plots of the date of PDAC incidence for high/medium-risk groups (defined in Outcome 3 and Outcome 4) will be created.	at 3 years
Tumor stage at PDAC diagnosis	stage at diagnosis per tumor registry/pathology report	6 months from index date
Tumor stage at PDAC diagnosis	stage at diagnosis per tumor registry/pathology report	at 1 year
Tumor stage at PDAC diagnosis	stage at diagnosis per tumor registry/pathology report	at 2 years
Tumor stage at PDAC diagnosis	stage at diagnosis per tumor registry/pathology report	at 3 years

Collaborators and Investigators

• Sponsor: Beth Israel Deaconess Medical Center
• Collaborators: Massachusetts Institute of Technology; TriNetX, LLC
• Investigators: Principal Investigator: Limor Appelbaum, MD, Beth Israel Deaconess Medical Center

Study record dates

Study Major Dates

• Study Start (Actual): July 17, 2023
• Primary Completion (Estimated): July 1, 2026
• Study Completion (Estimated): September 1, 2026

Study Registration Dates

• First Submitted: July 17, 2023
• First Submitted That Met QC Criteria: August 1, 2023
• First Posted (Actual): August 2, 2023

Study Record Updates

• Last Update Posted (Actual): August 2, 2023
• Last Update Submitted That Met QC Criteria: August 1, 2023
• Last Verified: August 1, 2023

More Information

Terms related to this study

• Other Study ID Numbers: 2023Trial

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