A machine learning model for identifying patients at risk for wild-type transthyretin amyloid cardiomyopathy

Abstract

Transthyretin amyloid cardiomyopathy, an often unrecognized cause of heart failure, is now treatable with a transthyretin stabilizer. It is therefore important to identify at-risk patients who can undergo targeted testing for earlier diagnosis and treatment, prior to the development of irreversible heart failure. Here we show that a random forest machine learning model can identify potential wild-type transthyretin amyloid cardiomyopathy using medical claims data. We derive a machine learning model in 1071 cases and 1071 non-amyloid heart failure controls and validate the model in three nationally representative cohorts (9412 cases, 9412 matched controls), and a large, single-center electronic health record-based cohort (261 cases, 39393 controls). We show that the machine learning model performs well in identifying patients with cardiac amyloidosis in the derivation cohort and all four validation cohorts, thereby providing a systematic framework to increase the suspicion of transthyretin cardiac amyloidosis in patients with heart failure.

Fig. 1. Receiver operating characteristic curves for the Random Forest machine learning model in the four validation cohorts.

a Optum ATTR-CM validation cohort. b IQIVA cardiac amyloidosis validation cohort. c Optum cardiac amyloidosis cohort. d Northwestern Medicine Enterprise Data Warehouse validation cohort. AUROC, area under the receiver operating characteristic curve; ATTR-CM, amyloidogenic transthyretin cardiomyopathy; NMEDW, Northwestern Medicine Enterprise Data Warehouse.

Fig. 2. Odds ratio vs. prevalence for top clinical phenotypes predictive of wild-type ATTR cardiomyopathy.

a Cardiac phenotypes associated with wild-type ATTR cardiomyopathy. b Non-cardiac phenotypes associated with wild-type ATTR cardiomyopathy. All features associated with the diagnosis of ATTR cardiomyopathy at a significance level of P < 10⁻⁴, which had an odds ratio (OR) < 10, were included in the graphs. The three features that had an OR > 10 that met the p-value threshold were: hypertrophic cardiomyopathy (OR 15.8, prevalence 11%); localized adiposity (OR 26.6, prevalence 2%); and organ transplantation (OR 23.4, prevalence 4%). Some diagnoses that were associated with ATTR cardiomyopathy (e.g., hypertrophic cardiomyopathy, multiple myeloma) were likely initial misdiagnoses, as these diagnoses (similar to all diagnoses included here) preceded the ATTR cardiomyopathy diagnosis. Univariate logistic regression was used to calculate odds ratios. *Localized to the connective tissue or soft tissue. AV, atrioventricular; ECG, electrocardiogram; HFrE, heart failure with reduced ejection fraction; HFpEF, heart failure with preserved ejection fraction; SVT, supraventricular tachycardia; VT, ventricular tachycardia.

Fig. 3. Time course of non-cardiac and cardiac phenotypes associated with wild-type ATTR cardiomyopathy vs. non-amyloid heart failure prior to the diagnosis of heart failure.

The proportion of patients at each time point (years before heart failure diagnosis) with a first diagnosis of an associated feature (phenotype). The cumulative proportion of patients with each particular phenotype is equal to the sum of the proportions from each of the years preceding the heart failure diagnosis. ATTR-CM, amyloidogenic transthyretin cardiomyopathy.

Fig. 4. Development and validation of a machine learning model of medical claims data for the systematic identification of wild-type transthyretin amyloid cardiomyopathy.

Nationally representative medical claims data were used to develop a cohort of ATTR-CM and non-amyloid HF controls. ICD codes were extracted and used as features to train a Random Forest machine learning model, which was then internally tested in the derivation cohort. The model was then validated in four external cohorts, one of which was a single health system that is similar to how the model would be used in the clinical setting. The top features (ICD codes) based on variable importance in the Random Forest model were also used to generate phenotypes and phenotype combinations associated with the ATTR-CM diagnosis, which provide clinical insight and clues into the diagnosis. In the future, additional prospective clinical validation with blood tests, echocardiography (with speckle-tracking strain analysis), and bone scintigraphy can be used to verify the ATTR-CM diagnosis with the ultimate goal to automate the identification of ATTR-CM, thereby leading to earlier diagnosis and intervention of these high-risk patients. ATTR-CM, amyloidogenic transthyretin cardiomyopathy.