ATTR-CM
Conditions
Keywords
Chronic Heart Failure
Brief 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.
Interventions
Software to calculate the predicted probability of ATTRwt-CM for these heart failure patients based on the presence and absence of certain features
Sponsors
Pfizer
Study design
Observational model
COHORT
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
50 Years to No maximum
Healthy volunteers
No
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
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Number of Participants According to Clinical Diagnosis Predicted Using the Machine Learning (ML) Algorithm | At diagnosis, anytime during retrospective data identification period of approximately 5.4 years; retrospective data observed in this study for approximately 2.5 months | 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. |
Countries
United States
Participant flow
Recruitment details
Participants with heart failure (HF) who met the inclusion and exclusion criteria were identified from the Optum electronic healthcare records (EHR) database between 01 January 2018 & 30 April 2023 (approximately 5.4 years). Participants with clinical diagnosis of wild-type transthyretin amyloid cardiomyopathy (ATTRwt-CM) or non-amyloid HF were included in this retrospective study chart validation study. Available data was evaluated from 01 September 2023 to 14 November 2023 (up to 2.5 months).
Participants by arm
| Arm | Count |
|---|---|
| ATTRwt-CM Participants Participants with clinical diagnosis of ATTRwt-CM between 01 January 2018 to 30 April 2023 were observed in this retrospective study. Available data of eligible participants were studied for 2.5 months in this retrospective observational study. | 238 |
| Non-amyloid HF Participants Participants with clinical diagnosis of non-amyloid HF between 01 January 2018 to 30 April 2023 were observed in this retrospective study. Available data of eligible participants were studied for 2.5 months in this retrospective observational study. | 320 |
| Total | 558 |
Baseline characteristics
| Characteristic | ATTRwt-CM Participants | Non-amyloid HF Participants | Total |
|---|---|---|---|
| Age, Customized 50 to 65 Years | 11 Participants | 73 Participants | 84 Participants |
| Age, Customized >=65 years | 227 Participants | 247 Participants | 474 Participants |
| Race and Ethnicity Not Collected | — | — | 0 Participants |
| Sex: Female, Male Female | 0 Participants | 0 Participants | 0 Participants |
| Sex: Female, Male Male | 238 Participants | 320 Participants | 558 Participants |
Adverse events
| Event type | EG000 affected / at risk | EG001 affected / at risk |
|---|---|---|
| deaths Total, all-cause mortality | 0 / 0 | 0 / 0 |
| other Total, other adverse events | 0 / 0 | 0 / 0 |
| serious Total, serious adverse events | 0 / 0 | 0 / 0 |
Outcome results
Primary
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.
Time frame: At diagnosis, anytime during retrospective data identification period of approximately 5.4 years; retrospective data observed in this study for approximately 2.5 months
Population: Study population included all eligible participants with clinical diagnosis of ATTRwt-CM and Non-amyloid HF whose data was retrieved and evaluated in the study. Here, Number of Participants Analyzed signifies number of participants with respective actual clinical diagnosis ascertained by medical charts.
| Arm | Measure | Group | Value (COUNT_OF_PARTICIPANTS) |
|---|---|---|---|
| ATTRwt-CM Participants | Number of Participants According to Clinical Diagnosis Predicted Using the Machine Learning (ML) Algorithm | Predicted for ATTRwt-CM | 203 Participants |
| ATTRwt-CM Participants | Number of Participants According to Clinical Diagnosis Predicted Using the Machine Learning (ML) Algorithm | Predicted for Non-amyloid HF | 35 Participants |
| Non-amyloid HF Participants | Number of Participants According to Clinical Diagnosis Predicted Using the Machine Learning (ML) Algorithm | Predicted for ATTRwt-CM | 133 Participants |
| Non-amyloid HF Participants | Number of Participants According to Clinical Diagnosis Predicted Using the Machine Learning (ML) Algorithm | Predicted for Non-amyloid HF | 187 Participants |