Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1083
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-09-14T06:55:33.127789Z
status: published
lens: g_space
sector: health
headline: Interpretable machine learning-enabled risk stratification for pulmonary arterial hypertension associated with unrepaired congenital heart disease: results from a national prospective registry
dek: Background Standard pulmonary arterial hypertension (PAH) risk models may not fully apply to PAH associated with unrepaired congenital heart disease (PAH-CHD). We aimed to develop and internally validate an interpretable machine learning (ML)-based risk model for adults with unrepaired PAH-CHD, comparing it against the recent European Society of Cardiology (ESC) model. Methods Utilizing a nationwide prospective registry in China, we included adults with unrepaired PAH-CHD. Five survival models were trained and i…
gain_title: Interpretable random survival forest model predicted all-cause mortality in adults with unrepaired PAH-CHD and stratified survival in both Eisenmenger and non-Eisenmenger subgroups where the ESC model did not.
problem_title: (none)
trace_subject: (none)
gain_reading: Interpretable random survival forest model predicted all-cause mortality in adults with unrepaired PAH-CHD and stratified survival in both Eisenmenger and non-Eisenmenger subgroups where the ESC model did not.
gain_evidence: The random survival forest model achieved the highest predictive performance (bootstrapping C-index 0.773) | The novel ML-derived risk model effectively stratified survival in both ES and non-ES cohorts | we developed a novel risk stratification model for unrepaired PAH-CHD, outperforming the ESC model
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers developed and internally validated an interpretable machine learning risk model for adults with unrepaired pulmonary arterial hypertension associated with congenital heart disease using data from 601 patients in a Chinese national prospective registry followed for a median 76 months. A random survival forest achieved a bootstrapping C-index of 0.773, and SHAP analysis highlighted predictors such as hemoglobin, BMI, systolic blood pressure, and diastolic pulmonary artery pressure to build new risk strata.

The work matters because standard ESC risk models classified only 5% as poorer prognosis and did not stratify non-Eisenmenger patients, leaving a gap in individualized management for this high-mortality group. The new model outperformed the ESC model in this cohort, but as of the September 2026 publication it remains internally validated only, with no external or prospective implementation results reported.
limitation: Model was developed and internally validated only within a Chinese nationwide registry of adults with unrepaired PAH-CHD, without external validation reported.
tag: Evidence-backed gain
key_points: Study included 601 adults with unrepaired PAH-CHD from a nationwide prospective registry in China, mean age 34, 56.4% Eisenmenger syndrome. | 108 deaths occurred during median 76-month follow-up; five survival models were trained and internally validated. | SHAP interpretation identified top predictors including hemoglobin, body mass index, systolic blood pressure, and diastolic pulmonary artery pressure.
rundown: The analysis used a nationwide prospective registry in China enrolling adults with unrepaired PAH-CHD. Five survival models were trained to predict all-cause mortality, with the random survival forest selected after bootstrapping validation. SHAP was used to identify the top 15 predictors and clinical cutoffs, leading to novel two-strata and continuous risk models evaluated by C-index and survival curves.

Among 601 patients with mean age 34 and 56.4% Eisenmenger syndrome, 108 died over median 76-month follow-up. The ESC two-strata model classified only 5.0% of patients as "Poorer prognosis" and failed to stratify the non-ES subgroup, while the ML-derived model stratified both ES and non-ES cohorts with log-rank significance.
sources:
- peer_reviewed | International Journal of Cardiology | https://doi.org/10.1016/j.ijcard.2026.134779 | 2026-09-12
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

e6d469a8d7b9ba58518fd93322c4078f5c65e2fd999c411427b5011eb25bd41a

previous

0000000000000000000000000000000000000000000000000000000000000000