Abstract
Objective
To develop an artificial intelligence (AI)–based tool to detect cardiac amyloidosis
(CA) from a standard 12-lead electrocardiogram (ECG).
Methods
We collected 12-lead ECG data from 2541 patients with light chain or transthyretin
CA seen at Mayo Clinic between 2000 and 2019. Cases were nearest neighbor matched
for age and sex, with 2454 controls. A subset of 2997 (60%) cases and controls were
used to train a deep neural network to predict the presence of CA with an internal
validation set (n=999; 20%) and a randomly selected holdout testing set (n=999; 20%).
We performed experiments using single-lead and 6-lead ECG subsets.
Results
The area under the receiver operating characteristic curve (AUC) was 0.91 (CI, 0.90
to 0.93), with a positive predictive value for detecting either type of CA of 0.86.
By use of a cutoff probability of 0.485 determined by the Youden index, 426 (84%)
of the holdout patients with CA were detected by the model. Of the patients with CA
and prediagnosis electrocardiographic studies, the AI model successfully predicted
the presence of CA more than 6 months before the clinical diagnosis in 59%. The best
single-lead model was V5 with an AUC of 0.86 and a precision of 0.78, with other single
leads performing similarly. The 6-lead (bipolar leads) model had an AUC of 0.90 and
a precision of 0.85.
Conclusion
An AI-driven ECG model effectively detects CA and may promote early diagnosis of this
life-threatening disease.
Abbreviations and Acronyms:
AI (artificial intelligence), AL (light chain amyloid), ATTR (transthyretin amyloid), ATTRv (variant (hereditary) transthyretin amyloidosis), ATTRwt (wild-type transthyretin amyloidosis), AUC (area under the receiver operating characteristic curve), CA (cardiac amyloidosis), ECG (electrocardiogram), LVH (left ventricular hypertrophy)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Mayo Clinic ProceedingsAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Improved outcomes for newly diagnosed AL amyloidosis between 2000 and 2014: cracking the glass ceiling of early death.Blood. 2017; 129: 2111-2119
- Light chain amyloidosis: patient experience survey from the Amyloidosis Research Consortium.Adv Ther. 2015; 32: 920-928
- Transthyretin amyloid cardiomyopathy: JACC state-of-the-art review.J Am Coll Cardiol. 2019; 73: 2872-2891
- Diagnosis and treatment of cardiac amyloidosis related to plasma cell dyscrasias.Cardiol Clin. 2019; 37: 487-495
- Tafamidis treatment for patients with transthyretin amyloid cardiomyopathy.N Engl J Med. 2018; 379: 1007-1016
- AL (light-chain) cardiac amyloidosis: a review of diagnosis and therapy.J Am Coll Cardiol. 2016; 68: 1323-1341
- Pathophysiology and treatment of cardiac amyloidosis.Nat Rev Cardiol. 2015; 12: 91-102
- Natural history of wild-type transthyretin cardiac amyloidosis and risk stratification using a novel staging system [erratum appears in J Am Coll Cardiol. 2017;69(23):2882].J Am Coll Cardiol. 2016; 68: 1014-1020
- Nonbiopsy diagnosis of cardiac transthyretin amyloidosis.Circulation. 2016; 133: 2404-2412
- Efficacy of chemotherapy for light-chain amyloidosis in patients presenting with symptomatic heart failure.J Am Coll Cardiol. 2016; 67: 2941-2948
- Electrocardiographic findings in primary systemic amyloidosis and biopsy-proven cardiac involvement.Am J Cardiol. 2005; 95: 535-537
- Detection of hypertrophic cardiomyopathy using a convolutional neural network–enabled electrocardiogram.J Am Coll Cardiol. 2020; 75: 722-733
- Classification of amyloidosis by laser microdissection and mass spectrometry–based proteomic analysis in clinical biopsy specimens.Blood. 2009; 114: 4957-4959
- ASNC/AHA/ASE/EANM/HFSA/ISA/SCMR/SNMMI expert consensus recommendations for multimodality imaging in cardiac amyloidosis: part 2 of 2—diagnostic criteria and appropriate utilization.J Card Fail. 2019; 25: 854-865
- Age and sex estimation using artificial intelligence from standard 12-lead ECGs.Circ Arrhythm Electrophysiol. 2019; 12: e007284
- Deep Learning.The MIT Press, Cambridge, MA2016
- Index for rating diagnostic tests.Cancer. 1950; 3: 32-35
- R: a language and environment for statistical computing, version 3.5. 3.R Foundation for Statistical Computing, Vienna, Austria2019
- Tafamidis—a pricey therapy for a not-so-rare condition.JAMA Cardiol. 2020; 5: 247-248
- Unveiling transthyretin cardiac amyloidosis and its predictors among elderly patients with severe aortic stenosis undergoing transcatheter aortic valve replacement.Eur Heart J. 2017; 38: 2879-2887
- Wild-type transthyretin amyloidosis as a cause of heart failure with preserved ejection fraction.Eur Heart J. 2015; 36: 2585-2594
- Transthyretin V122I (pV142I)∗ cardiac amyloidosis: an age-dependent autosomal dominant cardiomyopathy too common to be overlooked as a cause of significant heart disease in elderly African Americans.Genet Med. 2017; 19: 733-742
- Systemic cardiac amyloidoses: disease profiles and clinical courses of the 3 main types.Circulation. 2009; 120: 1203-1212
- Cardiac amyloidosis: pathology, nomenclature, and typing.Cardiovasc Pathol. 2015; 24: 343-350
- Echocardiographic features of cardiac amyloidosis presenting as endomyocardial disease in a 54-year-old male.J Cardiol. 2009; 54: 162-166
- Advanced cardiac amyloidosis associated with normal interventricular septal thickness: an uncommon presentation of infiltrative cardiomyopathy.J Am Soc Echocardiogr. 2014; 27: 440-447
- Automated and interpretable patient ECG profiles for disease detection, tracking, and discovery.Circ Cardiovasc Qual Outcomes. 2019; 12: e005289
Article info
Publication history
Published online: July 02, 2021
Footnotes
Grant Support: This work was funded by Mayo Clinic Department of Cardiovascular Medicine and Mayo Cardiovascular Research Center with no industry support.
Potential Competing Interests: Martha Grogan receives research (clinical trial) grant support from Alnylam, Eidos, Pfizer, and Prothena and consulting fees and honoraria (paid to Mayo Clinic, no personal compensation) from Akcea, Alnylam, Eidos, Pfizer, and Prothena. Zachi Attia has served as an advisor to AliveCor. Angela Dispenzieri receives research support from Celgene, Takeda, Janssen, Pfizer, and Alnylam and is on the advisory board for Janssen. Suraj Kapa has served on an advisory board for Pfizer. Grace Lin receives research funding from Ionis and Pfizer. Omar Abou Ezzedine receives research funding from Pfizer. The remaining authors have nothing to disclose. Drs Grogan, Lopez-Jimenez, Dispenzieri, Attia, Abou Ezzedine, Kapa, Friedman, and Murphree and Mayo Clinic have licensed the algorithm described in this work to Anumana and may benefit from its commercialization.
Identification
Copyright
© 2021 Mayo Foundation for Medical Education and Research
ScienceDirect
Access this article on ScienceDirectLinked Article
- CorrectionMayo Clinic ProceedingsVol. 98Issue 1
