Sub-phenotyping of patients with severe aortic stenosis undergoing transcatheter aortic valve replacement by unsupervised agglomerative clustering of echocardiographic and hemodynamic data
Notice bibliographique
Résumé
Abstract Background Severe aortic stenosis (AS) can trigger a deleterious cascade of impairments including left heart dysfunction, pulmonary hypertension (PH), and eventually right heart failure. Clinical phenotypes therefore appear heterogeneous, depending on disease progression and comorbidities. Purpose This retrospective analysis aims to categorize patients with severe AS according to clinical presentation by applying unsupervised machine learning in combination with an artificial neural network (ANN). Methods Unsupervised agglomerative clustering was applied to pre-procedural data from echocardiography and right heart catheterization from 366 consecutively enrolled patients undergoing transcatheter aortic valve replacement (TAVR) for severe AS at two tertiary centers in Germany between 2014 and 2020. Association between cluster and 2-year all-cause mortality after TAVR was assessed, and an ANN was trained to open the avenue to prospectively predict cluster assignment in future patients. Results Cluster analysis revealed four distinct phenotypes, reflecting various extents of disease severity, and hence differing in mortality. Patients from cluster 1, constituting the majority of cases and hereinafter referred to as reference, presented with regular cardiac function and without PH. Accordingly, estimated 2-year survival was 90.6% (95% CI: 85.8–95.6%). Contrarily, patients from smallest cluster 3 displayed most extensive disease characteristics, i.e. left and right heart dysfunction together with combined pre- and postcapillary PH, and their 2-year mortality was increased (2-year survival: 77.3% (95% CI: 65.2–91.6%), HR for 2-year mortality: 2.6 (95% CI: 1.1–6.2); p-value: 0.025). Clusters 2 and 4 comprised patients suffering from postcapillary PH. Whilst patients from cluster 2 showed similar survival as cluster 1 (2-year survival: 85.8% (95% CI: 76.9–95.6%)), patients from cluster 4 with right atrial enlargement and high prevalence of severe tricuspid regurgitation (TR) deceased more often (2-year survival: 74.9% (95% CI: 65.9–85.2%), HR for 2-year mortality: 2.8 (95% CI: 1.4–5.5); p-value: 0.004). After randomly dividing the study population into derivation and validation cohorts, an ANN could precisely predict cluster assignment (accuracy: 83.5%), significantly outperforming the no information rate (46.8%; p-value: 2.26e-15). Importantly, patients from high-risk clusters 3 and 4 were detected with high sensitivity (100.0% and 85.2%, respectively) and specificity (95.9% and 95.1%, respectively). Conclusion Expanding the analytical armamentarium by machine learning technology aids in capturing complex clinical presentations as observed in patients with severe AS. Assigning patients to clusters can thus facilitate a more sophisticated risk stratification in future clinical practice. Addressing irreversibility of PH and persistence of severe TR after TAVR should obtain paramount priority in order to improve long-term survival. Funding Acknowledgement Type of funding sources: Public Institution(s). Main funding source(s): Mark Lachmann receives funding from Technical University of Munich (Clinician Scientist Grant).
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,001 | 0,002 |
| Méta-épidémiologie (sens strict) | 0,000 | 0,000 |
| Méta-épidémiologie (sens large) | 0,000 | 0,001 |
| Bibliométrie | 0,002 | 0,001 |
| Études des sciences et des technologies | 0,000 | 0,000 |
| Communication savante | 0,001 | 0,000 |
| Science ouverte | 0,000 | 0,001 |
| Intégrité de la recherche | 0,000 | 0,000 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,001 | 0,000 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».