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).

ATTR-CM Clinical Trial

Official title:

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)

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT06029452
• Other study ID #: B3461111
• Status: Completed
• Start date: September 1, 2023
• Est. completion date: November 14, 2023

Study information

• Verified date: February 2024
• Source: Pfizer
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

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.

Recruitment information / eligibility

• Status: Completed
• Enrollment: 844
• Est. completion date: November 14, 2023
• Est. primary completion date: November 14, 2023
• Accepts healthy volunteers: No
• Gender: All
• Age group: 50 Years and older

Eligibility

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

Related Conditions & MeSH terms

• ATTR-CM
• Cardiomyopathies
• Heart Failure

Intervention

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

Locations

Country	Name	City	State
United States	Pfizer	New York	New York

Sponsors (1)

Lead Sponsor	Collaborator
Pfizer

Country where clinical trial is conducted

United States, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	The total number of clinically diagnosed patients using the ML algorithm	to evaluate the performance of the ATTRwt-CM ML model to predict the clinical diagnosis of ATTRwt-CM among HF patients against chart-review-based ground truth with a prespecified performance thresholds in sensitivity and specificity.	60 days

External Links

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