Machine learning to automatically differentiate hypertrophic cardiomyopathy, cardiac light chain, and cardiac transthyretin amyloidosis: a multicenter CMR study
BACKGROUND: - Cardiac amyloidosis is associated with poor outcomes and is caused by the interstitial deposition of misfolded proteins, typically ATTR (transthyretin) or AL (light chains). Although specific therapies during early disease stages exist, the diagnosis is often only established at an adv...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
4 June 2025
|
| In: |
Circulation. Cardiovascular imaging
Year: 2025, Jahrgang: 18, Heft: 7, Pages: 1-12 |
| ISSN: | 1942-0080 |
| DOI: | 10.1161/CIRCIMAGING.124.017761 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1161/CIRCIMAGING.124.017761 Verlag, kostenfrei, Volltext: https://www.ahajournals.org/doi/10.1161/CIRCIMAGING.124.017761 
|
| Verfasserangaben: | Lukas Damian Weberling, MD ; Andreas Ochs, MD;Mitchel Benovoy, PhD; Fabian aus dem Siepen, MD; Janek Salatzki, MD; Evangelos Giannitsis, MD; Chong Duan, PhD; Kevin Maresca,PhD; Yao Zhang, MSc.; Jan Möller, PhD; Silke Friedrich, MD; Stefan Schönland, MD; Benjamin Meder, MD; Matthias G. Friedrich, MD; Norbert Frey, MD; and Florian André, MD |
MARC
| LEADER | 00000naa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1947892770 | ||
| 003 | DE-627 | ||
| 005 | 20260107143902.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 260107s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1161/CIRCIMAGING.124.017761 |2 doi | |
| 035 | |a (DE-627)1947892770 | ||
| 035 | |a (DE-599)KXP1947892770 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Weberling, Lukas D. |e VerfasserIn |0 (DE-588)1142266141 |0 (DE-627)1001438582 |0 (DE-576)494767243 |4 aut | |
| 245 | 1 | 0 | |a Machine learning to automatically differentiate hypertrophic cardiomyopathy, cardiac light chain, and cardiac transthyretin amyloidosis |b a multicenter CMR study |c Lukas Damian Weberling, MD ; Andreas Ochs, MD;Mitchel Benovoy, PhD; Fabian aus dem Siepen, MD; Janek Salatzki, MD; Evangelos Giannitsis, MD; Chong Duan, PhD; Kevin Maresca,PhD; Yao Zhang, MSc.; Jan Möller, PhD; Silke Friedrich, MD; Stefan Schönland, MD; Benjamin Meder, MD; Matthias G. Friedrich, MD; Norbert Frey, MD; and Florian André, MD |
| 264 | 1 | |c 4 June 2025 | |
| 300 | |a 12 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 07.01.2025 | ||
| 520 | |a BACKGROUND: - Cardiac amyloidosis is associated with poor outcomes and is caused by the interstitial deposition of misfolded proteins, typically ATTR (transthyretin) or AL (light chains). Although specific therapies during early disease stages exist, the diagnosis is often only established at an advanced stage. Cardiovascular magnetic resonance (CMR) is the gold standard for imaging suspected myocardial disease. However, differentiating cardiac amyloidosis from hypertrophic cardiomyopathy may be challenging, and a reliable method for an image-based classification of amyloidosis subtypes is lacking. This study sought to investigate a CMR machine learning (ML) algorithm to identify and distinguish cardiac amyloidosis. - METHODS: - This retrospective, multicenter, multivendor feasibility study included consecutive patients diagnosed with hypertrophic cardiomyopathy or AL/ATTR amyloidosis and healthy volunteers. Standard clinical information, semiautomated CMR imaging data, and qualitative CMR features were integrated into a trained ML algorithm. - RESULTS: - Four hundred participants (95 healthy, 94 hypertrophic cardiomyopathy, 95 AL, and 116 ATTR) from 56 institutions were included (269 men aged 58.5 [48.4-69.4] years). A 3-stage ML screening cascade sequentially differentiated healthy volunteers from patients, then hypertrophic cardiomyopathy from amyloidosis, and then AL from ATTR. The ML algorithm resulted in an accurate differentiation at each step (area under the curve, 1.0, 0.99, and 0.92, respectively). After reducing included data to demographics and imaging data alone, the performance remained excellent (area under the curve, 0.99, 0.98, and 0.88, respectively), even after removing late gadolinium enhancement imaging data from the model (area under the curve, 1.0, 0.95, 0.86, respectively). - CONCLUSIONS: - A trained ML model using semiautomated CMR imaging data and patient demographics can accurately identify cardiac amyloidosis and differentiate subtypes. | ||
| 700 | 1 | |a Ochs, Andreas |d 1990- |e VerfasserIn |0 (DE-588)1162141689 |0 (DE-627)1025565177 |0 (DE-576)507197232 |4 aut | |
| 700 | 1 | |a Benovoy, Mitchel |e VerfasserIn |4 aut | |
| 700 | 1 | |a Siepen, Fabian aus dem |d 1984- |e VerfasserIn |0 (DE-588)1066499969 |0 (DE-627)817646469 |0 (DE-576)426014944 |4 aut | |
| 700 | 1 | |a Salatzki, Janek |d 1989- |e VerfasserIn |0 (DE-588)115336624X |0 (DE-627)1014780896 |0 (DE-576)500185492 |4 aut | |
| 700 | 1 | |a Giannitsis, Evangelos |e VerfasserIn |0 (DE-588)113336241 |0 (DE-627)577184091 |0 (DE-576)289759579 |4 aut | |
| 700 | 1 | |a Duan, Chong |e VerfasserIn |4 aut | |
| 700 | 1 | |a Maresca, Kevin |e VerfasserIn |4 aut | |
| 700 | 1 | |a Zhang, Yao |e VerfasserIn |4 aut | |
| 700 | 1 | |a Möller, Jan |e VerfasserIn |4 aut | |
| 700 | 1 | |a Friedrich, Silke |e VerfasserIn |4 aut | |
| 700 | 1 | |a Schönland, Stefan |d 1969- |e VerfasserIn |0 (DE-588)122405226 |0 (DE-627)705896137 |0 (DE-576)293255792 |4 aut | |
| 700 | 1 | |a Meder, Benjamin |e VerfasserIn |0 (DE-588)135821630 |0 (DE-627)571676316 |0 (DE-576)300664745 |4 aut | |
| 700 | 1 | |a Friedrich, Matthias |e VerfasserIn |0 (DE-588)1143606736 |0 (DE-627)100287033X |0 (DE-576)495067881 |4 aut | |
| 700 | 1 | |a Frey, Norbert |e VerfasserIn |0 (DE-588)141244976 |0 (DE-627)625824075 |0 (DE-576)322969514 |4 aut | |
| 700 | 1 | |a André, Florian |d 1983- |e VerfasserIn |0 (DE-588)1051060230 |0 (DE-627)785671714 |0 (DE-576)405733267 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Circulation. Cardiovascular imaging |d Philadelphia, Pa. : Lippincott, Williams & Wilkins, 2008 |g 18(2025), 7, Artikel-ID e017761, Seite 1-12 |h Online-Ressource |w (DE-627)573095884 |w (DE-600)2440475-5 |w (DE-576)299311074 |x 1942-0080 |7 nnas |a Machine learning to automatically differentiate hypertrophic cardiomyopathy, cardiac light chain, and cardiac transthyretin amyloidosis a multicenter CMR study |
| 773 | 1 | 8 | |g volume:18 |g year:2025 |g number:7 |g elocationid:e017761 |g pages:1-12 |g extent:12 |a Machine learning to automatically differentiate hypertrophic cardiomyopathy, cardiac light chain, and cardiac transthyretin amyloidosis a multicenter CMR study |
| 856 | 4 | 0 | |u https://doi.org/10.1161/CIRCIMAGING.124.017761 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |7 0 |
| 856 | 4 | 0 | |u https://www.ahajournals.org/doi/10.1161/CIRCIMAGING.124.017761 |x Verlag |z kostenfrei |3 Volltext |7 0 |
| 951 | |a AR | ||
| 992 | |a 20260107 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 1051060230 |a André, Florian |m 1051060230:André, Florian |d 50000 |e 50000PA1051060230 |k 0/50000/ |p 16 |y j | ||
| 998 | |g 141244976 |a Frey, Norbert |m 141244976:Frey, Norbert |d 910000 |d 910100 |e 910000PF141244976 |e 910100PF141244976 |k 0/910000/ |k 1/910000/910100/ |p 15 | ||
| 998 | |g 1143606736 |a Friedrich, Matthias |m 1143606736:Friedrich, Matthias |d 910000 |d 910100 |e 910000PF1143606736 |e 910100PF1143606736 |k 0/910000/ |k 1/910000/910100/ |p 14 | ||
| 998 | |g 135821630 |a Meder, Benjamin |m 135821630:Meder, Benjamin |d 910000 |d 910100 |e 910000PM135821630 |e 910100PM135821630 |k 0/910000/ |k 1/910000/910100/ |p 13 | ||
| 998 | |g 122405226 |a Schönland, Stefan |m 122405226:Schönland, Stefan |d 910000 |d 910100 |d 50000 |e 910000PS122405226 |e 910100PS122405226 |e 50000PS122405226 |k 0/910000/ |k 1/910000/910100/ |k 0/50000/ |p 12 | ||
| 998 | |g 113336241 |a Giannitsis, Evangelos |m 113336241:Giannitsis, Evangelos |d 910000 |d 910100 |d 50000 |e 910000PG113336241 |e 910100PG113336241 |e 50000PG113336241 |k 0/910000/ |k 1/910000/910100/ |k 0/50000/ |p 6 | ||
| 998 | |g 115336624X |a Salatzki, Janek |m 115336624X:Salatzki, Janek |d 910000 |d 910100 |e 910000PS115336624X |e 910100PS115336624X |k 0/910000/ |k 1/910000/910100/ |p 5 | ||
| 998 | |g 1066499969 |a Siepen, Fabian aus dem |m 1066499969:Siepen, Fabian aus dem |d 910000 |d 910100 |e 910000PS1066499969 |e 910100PS1066499969 |k 0/910000/ |k 1/910000/910100/ |p 4 | ||
| 998 | |g 1162141689 |a Ochs, Andreas |m 1162141689:Ochs, Andreas |d 910000 |d 910100 |e 910000PO1162141689 |e 910100PO1162141689 |k 0/910000/ |k 1/910000/910100/ |p 2 | ||
| 998 | |g 1142266141 |a Weberling, Lukas D. |m 1142266141:Weberling, Lukas D. |d 910000 |d 910100 |e 910000PW1142266141 |e 910100PW1142266141 |k 0/910000/ |k 1/910000/910100/ |p 1 |x j | ||
| 999 | |a KXP-PPN1947892770 |e 4840845859 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"type":{"bibl":"article-journal","media":"Online-Ressource"},"title":[{"title":"Machine learning to automatically differentiate hypertrophic cardiomyopathy, cardiac light chain, and cardiac transthyretin amyloidosis","title_sort":"Machine learning to automatically differentiate hypertrophic cardiomyopathy, cardiac light chain, and cardiac transthyretin amyloidosis","subtitle":"a multicenter CMR study"}],"origin":[{"dateIssuedKey":"2025","dateIssuedDisp":"4 June 2025"}],"note":["Gesehen am 07.01.2025"],"id":{"doi":["10.1161/CIRCIMAGING.124.017761"],"eki":["1947892770"]},"recId":"1947892770","relHost":[{"corporate":[{"role":"isb","display":"American Heart Association"}],"part":{"year":"2025","pages":"1-12","issue":"7","text":"18(2025), 7, Artikel-ID e017761, Seite 1-12","extent":"12","volume":"18"},"titleAlt":[{"title":"Circulation / Cardiovascular imaging"}],"language":["eng"],"disp":"Machine learning to automatically differentiate hypertrophic cardiomyopathy, cardiac light chain, and cardiac transthyretin amyloidosis a multicenter CMR studyCirculation. Cardiovascular imaging","type":{"bibl":"periodical","media":"Online-Ressource"},"pubHistory":["1.2008 -"],"origin":[{"dateIssuedDisp":"2008-","publisher":"Lippincott, Williams & Wilkins","dateIssuedKey":"2008","publisherPlace":"Philadelphia, Pa."}],"note":["Gesehen am 28.11.2016"],"title":[{"title":"Circulation","partname":"Cardiovascular imaging","subtitle":"journal of the American Heart Association","title_sort":"Circulation"}],"id":{"issn":["1942-0080"],"zdb":["2440475-5"],"eki":["573095884"]},"recId":"573095884","physDesc":[{"extent":"Online-Ressource"}]}],"physDesc":[{"extent":"12 S."}],"name":{"displayForm":["Lukas Damian Weberling, MD ; Andreas Ochs, MD;Mitchel Benovoy, PhD; Fabian aus dem Siepen, MD; Janek Salatzki, MD; Evangelos Giannitsis, MD; Chong Duan, PhD; Kevin Maresca,PhD; Yao Zhang, MSc.; Jan Möller, PhD; Silke Friedrich, MD; Stefan Schönland, MD; Benjamin Meder, MD; Matthias G. Friedrich, MD; Norbert Frey, MD; and Florian André, MD"]},"person":[{"family":"Weberling","display":"Weberling, Lukas D.","role":"aut","given":"Lukas D."},{"display":"Ochs, Andreas","family":"Ochs","role":"aut","given":"Andreas"},{"display":"Benovoy, Mitchel","family":"Benovoy","role":"aut","given":"Mitchel"},{"given":"Fabian aus dem","role":"aut","family":"Siepen","display":"Siepen, Fabian aus dem"},{"display":"Salatzki, Janek","family":"Salatzki","given":"Janek","role":"aut"},{"display":"Giannitsis, Evangelos","family":"Giannitsis","given":"Evangelos","role":"aut"},{"family":"Duan","display":"Duan, Chong","role":"aut","given":"Chong"},{"family":"Maresca","display":"Maresca, Kevin","role":"aut","given":"Kevin"},{"family":"Zhang","display":"Zhang, Yao","given":"Yao","role":"aut"},{"given":"Jan","role":"aut","display":"Möller, Jan","family":"Möller"},{"role":"aut","given":"Silke","family":"Friedrich","display":"Friedrich, Silke"},{"display":"Schönland, Stefan","family":"Schönland","role":"aut","given":"Stefan"},{"family":"Meder","display":"Meder, Benjamin","given":"Benjamin","role":"aut"},{"role":"aut","given":"Matthias","display":"Friedrich, Matthias","family":"Friedrich"},{"family":"Frey","display":"Frey, Norbert","role":"aut","given":"Norbert"},{"given":"Florian","role":"aut","family":"André","display":"André, Florian"}],"language":["eng"]} | ||
| SRT | |a WEBERLINGLMACHINELEA4202 | ||