A machine learning model for identifying patients at risk for wild-type transthyretin amyloid cardiomyopathy
| Autor: | Michelle Stewart, Marianna Bruno, Ahsan Huda, Adam Castaño, Mo Hu, Rahul C. Deo, Sanjiv J. Shah, Jennifer Schumacher, Anindita Niyogi, Faraz S. Ahmad |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Science
General Physics and Astronomy macromolecular substances 030204 cardiovascular system & hematology Cardiovascular Amyloid Neuropathies Machine learning computer.software_genre General Biochemistry Genetics and Molecular Biology Machine Learning 03 medical and health sciences Familial 0302 clinical medicine Clinical Research Electronic health record medicine 2.1 Biological and endogenous factors Electronic Health Records Humans Prealbumin In patient 030212 general & internal medicine Heart Failure Amyloid Neuropathies Familial Multidisciplinary biology business.industry nutritional and metabolic diseases General Chemistry medicine.disease nervous system diseases Brain Disorders 4.1 Discovery and preclinical testing of markers and technologies Transthyretin Amyloid Neuropathy Heart Disease Cardiac amyloidosis Heart failure Cohort biology.protein Artificial intelligence Amyloid cardiomyopathy business Cardiomyopathies computer 4.2 Evaluation of markers and technologies |
| Zdroj: | Nature communications, vol 12, iss 1 Nature Communications, Vol 12, Iss 1, Pp 1-12 (2021) |
| ISSN: | 2041-1723 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|