A Retrospective Validation Study To Identify Chart-Based Clinical Diagnosis Of Wild-Type Transthyretin Amyloid Cardiomyopathy (Attrwt-CM) And Non-Amyloid Heart Failure Among Patients With Heart Failure (HF).

A Retrospective Chart Validation Study Evaluating the Performance of Machine Learning Algorithm (ML) to Predict the Clinical Diagnosis of Wild-type Transthyretin Amyloid Cardiomyopathy (ATTRwt-CM) and Non-amyloid Heart Failure Among Patients With Heart Failure (HF)

This is an observational, retrospective non-inferiority study with a study sample from a large national database.

A machine learning (ML) model will use a national database to predict the clinical diagnosis of ATTRwt-CM among HF patients. This study will include HF patients ≥50 years old.

Study Overview

• Status: Completed
• Conditions: ATTR-CM
• Intervention / Treatment: Other: Machine learning algorithm

• Study Type: Observational
• Enrollment (Actual): 558

Contacts and Locations

Study Locations

• United States
  • New York
    • New York, New York, United States, 10018
      • Pfizer

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Heart failure patients with clinical diagnosis of ATTRwt-CM or non-amyloid HF

Description

Inclusion Criteria:

• HF patients (defined as having ≥1 claim for HF or HF treatment) ≥50 years old with clinical diagnosis of ATTRwt-CM or non-amyloid HF ascertained by charts. Patients will be required to have ≥12 months of continuous activity in the EHR or claims prior to the Index Date.

Exclusion Criteria:

• Patients with any of the following diagnoses:

  • Light chain (AL) amyloidosis
  • Intracranial hemorrhage
  • Cerebral amyloid angiopathy
  • End stage renal disease
  • Blood cancer

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
ATTRwt-CM and non-amyloid heart failure patients	Other: Machine learning algorithm; Software to calculate the predicted probability of ATTRwt-CM for these heart failure patients based on the presence and absence of certain features

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Number of Participants According to Clinical Diagnosis Predicted Using the Machine Learning (ML) Algorithm	In this outcome measure number of participants were reported according to clinical diagnosis predicted by ML algorithm. True positive (TP) = participants with actual and predicted diagnosis of ATTRwt-CM; False positive (FP) = participants with actual diagnosis of non-amyloid HF and predicted diagnosis of ATTRwt-CM; False negative (FN) = participants with actual diagnosis of ATTRwt-CM and predicted diagnosis of non-amyloid HF; True negative (TN) = participants with actual and predicted diagnosis of non-amyloid HF.	At diagnosis, anytime during retrospective data identification period of approximately 5.4 years; retrospective data observed in this study for approximately 2.5 months

Collaborators and Investigators

• Sponsor: Pfizer
• Investigators: Study Director: Pfizer CT.gov Call Center, Pfizer

Publications and helpful links

Helpful Links

• To obtain contact information for a study center near you, click here.

Study record dates

Study Major Dates

• Study Start (Actual): September 1, 2023
• Primary Completion (Actual): November 14, 2023
• Study Completion (Actual): November 14, 2023

Study Registration Dates

• First Submitted: September 1, 2023
• First Submitted That Met QC Criteria: September 1, 2023
• First Posted (Actual): September 8, 2023

Study Record Updates

• Last Update Posted (Actual): March 25, 2025
• Last Update Submitted That Met QC Criteria: November 7, 2024
• Last Verified: November 1, 2024

More Information

Terms related to this study

• Keywords: Chronic Heart Failure
• Additional Relevant MeSH Terms: Cardiovascular Diseases; Heart Diseases; Heart Failure; Cardiomyopathies
• Other Study ID Numbers: B3461111

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Pfizer will provide access to individual de-identified participant data and related study documents (e.g. protocol, Statistical Analysis Plan (SAP), Clinical Study Report (CSR)) upon request from qualified researchers, and subject to certain criteria, conditions, and exceptions. Further details on Pfizer's data sharing criteria and process for requesting access can be found at: https://www.pfizer.com/science/clinical_trials/trial_data_and_results/data_requests.