Characterizing patients ineligible for mitral valve intervention: Phenotypic clustering sub-analysis from the CHOICE-MI Registry
Bibliographic record
Abstract
Abstract Background/Introduction Transcatheter mitral valve replacement (TMVR) is emerging as a therapeutic option for surgcal high-risk patients with mitral regurgitation (MR). However, a large proportion of these patients are still rejected due to clinical or anatomical reasons. The majority of these patients remain ineligible for any mitral valve (MV) intervention and continue medical treatment. Phenotypic characterization of these patients may assist in the identification of the anatomical challenges and drive future innovation efforts as well as assist in the risk stratification process of these patients. Purpose To characterize patients ineligible for TMVR and other MV interventions from a large international registry using an unsupervised phenotypic clustering approach integrating clinical, echocardiographic and computed tomography data to unveil differences between phenogroups. Methods Between 2014 and 2022, the CHOICE-MI registry included 984 patients undergoing screening for TMVR at 33 international sites. For this study, only patients with screening failure resulting in medical therapy alone were included. Patients receiving transcatheter or surgical treatment were excluded (Figure 1). A cluster analysis using K-means algorithm was performed on baseline clinical and imaging variables, and predictors of all-cause mortality within these clusters were assessed. Results Among 284 patients (77.4±8.82 years, 56.0% female, EuroSCORE II 6.6±5.8%) considered ineligible for any MV intervention, two clinically distinct phenogroups (PG) were identified using unsupervised hierarchical clustering of principal components (Figure 2): (PG1) Elderly women with primary MR, high left ventricular (LV) ejection fraction, and annular calcification (N=173, 60.9%); (PG2) Patients with secondary or mixed MR, LV and annular dilation, and high prevalence of comorbidities (N=111, 39.1%). There were no differences regarding Kaplan-Meier estimated 1-year all-cause mortality (PG1 vs. PG2, 21.4% vs. 23.4%, p=0.89) and 1-year cardiovascular mortality (10.4% vs. 13.5%, p=0.53). Predictors of mortality were albumin, renal function, extracardiac arteriopathy for PG1, and albumin, coronary artery disease, and prior myocardial infarction for PG2. Conclusions Using cluster analysis, this study identified two major subgroups among patients ineligible for mitral interventions with profound differences in clinical and anatomical profiles, and predictors of outcome. The combination of elderly women with primary MR, preserved LV ejection fraction and annular calcification was the most common phenogroup among patients rejected for mitral intervention. Identifying these factors may drive technological evolution to address unmet clinical and technical needs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".