+ HEALTH Background Discharge letters are essential for continuity of care, yet patients often misunderstand their con…± HEALTH Hematoxylin and Eosin (H&E) glass slide preparation is fundamental to histopathology. Pathologists' expertise…+ CLIMATE Traditional soil heavy metal risk assessments suffer from fragmented indices and poor logical integration. Co…± HEALTH Background Neonatal pneumothorax can progress rapidly, yet detection on supine chest radiographs remains chal…+ HEALTH T cell exhaustion has widespread implications for the progression and treatment of chronic diseases including…+ HEALTH Background Standard pulmonary arterial hypertension (PAH) risk models may not fully apply to PAH associated w…+ HEALTH Objectives To map and synthesize the scientific evidence regarding the use of Augmented Reality (AR) and Mixe…± HEALTH Objective To examine whether the outputs of machine learning algorithms designed to predict risk of cardiovas…
TruaceTracing the truth around AIMonday, September 14, 2026
Subscribe
Health·G Space·Evidence-backed gain·Published 2026-09-14

Interpretable machine learning-enabled risk stratification for pulmonary arterial hypertension associated with unrepaired congenital heart disease: results from a national prospective registry

Abstract: 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…

TRV-2026-1083Peer-reviewedPermanent record — cite & verify
Interpretable machine learning-enabled risk stratification for pulmonary arterial hypertension associated with unrepaired congenital heart disease: results from a national prospective registry

Shaher8 by Giardello. CC BY-SA 3.0 · https://creativecommons.org/licenses/by-sa/3.0

The 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.

Main 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.
Gain

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.

The 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

Reader signal

How should this claim be treated?

The debate