Abstract 15607: Right Ventricular Diastolic Function: A Machine Learning-Based Echocardiographic Classification Scheme
Bibliographic record
Abstract
Background: Right ventricular (RV) diastolic dysfunction is associated with heart failure and adverse cardiac events. Echocardiography guidelines include a limited assessment of RV diastology based on a scheme borrowed from the left ventricle, which is suboptimal. Hypothesis: An RV-specific classification scheme could be developed using echocardiographic parameters and machine learning to better reflect right-sided physiology and diagnose diastolic dysfunction. Methods: A total of 540 consecutive outpatients undergoing clinically-indicated echocardiograms at the Jewish General Hospital between March and December 2019 were prospectively recruited. Measurements relevant to RV diastology were acquired in triplicate by trained cardiac sonographers and verified by level III echocardiography staff and fellows. A sequential approach of unsupervised and supervised machine learning was used to develop a de novo classification model for RV diastology. Results: First, to prevent the use of redundant echocardiographic parameters within any given model, a feature-level clustering algorithm classified the 35 candidate parameters into mutually exclusive groups (for example, a group containing various size parameters). Second, a patient-level clustering algorithm analyzed all possible combinations of parameters in order to classify patients into three groups: normal, intermediate, and abnormal diastolic function. Third, a decision tree algorithm analyzed the top performing combinations in order to rank the importance of the echocardiographic parameters in predicting the diastology groups. Finally, after selecting the most predictive parameters - Ep, Ep/Ap, and IVC sniff - the final decision tree algorithm was generated. The prevalence of heart failure increased stepwise from 14% in the normal group, to 19% in the intermediate group, and 32% in the abnormal group. Conclusions: Our echocardiographic classification scheme for RV diastology is uniquely tailored to right-sided physiology and identifies patients with increasing rates of heart failure. Further study is warranted to validate this scheme in an independent population and examine its prognostic value for adverse cardiac events.
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 | 0.004 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".