Four-dimensional left atrial quantification for predicting major adverse cardiovascular events in patients with uremia: an interpretable LASSO-logistic model

Q: What are the key findings of this study?

A LASSO-logistic model integrating 4D-LAQ parameters predicted MACE in uremia patients with an AUC of 0.840 (95% CI: 0.749-0.931), identifying left atrial reservoir strain as the top predictor.

Q: What is the clinical evidence from this study?

Study design: Cohort. Population: Uremia (Chronic Kidney Disease stage 5) (n=223). Intervention: LASSO-logistic regression model integrating four-dimensional left atrial quantification (4D-LAQ) parameters vs. Clinical-only model and conventional echocardiography model. Primary outcome: Major adverse cardiovascular events (MACE: composite of cardiac death, hospitalization for worsening heart failure, non-fatal stroke, and non-fatal myocardial infarction) (AUC 0.840, 95% CI 0.749-0.931, p=<0.05).

Q: What does this research mean for the field?

A LASSO-logistic regression model incorporating four-dimensional left atrial quantification parameters accurately predicts major adverse cardiovascular events in patients with uremia, with left atrial reservoir strain being the most influential predictor. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Q: What question did this study set out to answer?

To develop and validate an interpretable machine learning model incorporating four-dimensional left atrial quantification parameters to predict major adverse cardiovascular events in patients with uremia.

Lina Ma; Mei Jin; Zikang Lin; Ruman Cui; Xuning Huang; Meihua Chen

doi:10.3389/fendo.2026.1970519

October 30, 2026Frontiers in EndocrinologyOpen Access

Four-dimensional left atrial quantification for predicting major adverse cardiovascular events in patients with uremia: an interpretable LASSO-logistic model

View Full Paper

Ask AI

Bookmark

Share

Key result

4D-LAQ model predicts MACE in uremic patients with ~0.84 AUC, led by LA reservoir strain.

AUC 0.840
95% CI 0.749-0.931
P<0.05
n=223

Why the study?

This study was undertaken to develop an interpretable machine learning model using four-dimensional left atrial quantification parameters to predict the risk of MACE in patients with uremia.

Does a LASSO-logistic regression model integrating four-dimensional left atrial quantification (4D-LAQ) parameters improve the prediction of major adverse cardiovascular events (MACE) in patients with uremia?

Key Points

To develop and validate an interpretable machine learning model incorporating four-dimensional left atrial quantification parameters to predict major adverse cardiovascular events in patients with uremia.
Retrospectively enrolled 223 patients with uremia treated at a single center between January 2021 and January 2026, monitoring for the occurrence of major adverse cardiovascular events (MACE).
Applied LASSO regression for feature selection across clinical, laboratory, and echocardiographic variables, constructing eight prediction models and selecting logistic regression via DeLong's test.
Assessed model performance through receiver operating characteristic analysis, five-fold cross-validation, nested 5×5 cross-validation, bootstrap internal validation, calibration plots, decision curve analysis, and SHAP interpretability.
During follow-up, 94 patients (42.1%) experienced MACE, showing significant left ventricular remodeling, increased left atrial volumes, and decreased left atrial strain compared to non-MACE patients.
The logistic regression model achieved an AUC of 0.840 (95% CI: 0.749–0.931) in the validation set, with five-fold cross-validation, nested 5×5 cross-validation, and bootstrap internal validation yielding AUCs of 0.873, 0.856, and 0.869.
SHAP analysis identified left atrial reservoir strain (LASr) as the most influential predictor, while the model demonstrated good calibration (Hosmer-Lemeshow test, P > 0.05) and an AUDC of 0.208 (0.206 - 0.208).

Study Design

Type

Cohort (n=223)

Multicenter

No

Structured PICO

Does a LASSO-logistic regression model integrating four-dimensional left atrial quantification (4D-LAQ) parameters improve the prediction of major adverse cardiovascular events (MACE) in patients with uremia?

P

Population

223 patients with uremia (CKD stage 5, eGFR < 15 mL/min/1.73 m2; median age 47.0 years; 35.9% female) without prior kidney transplantation or moderate-to-severe valvular disease, followed for a median of 20 months.

E

Exposure

Four-dimensional left atrial quantification (4D-LAQ) echocardiography parameters integrated into an interpretable LASSO-penalized logistic regression (LASSO-LR) machine learning model (incorporating LASr, Height, LVMI, LASr-c, LAScd, lnBNP, and LDL)

C

Comparator

Alternative machine learning algorithms (RF, SVM, SGD, KNN, AdaBoost, Bayes, MLP), as well as clinical-only (Model 1) and conventional echocardiography (Model 2) prediction models

O

Outcome

Major adverse cardiovascular events (MACE), defined as a composite of cardiac death, hospitalization for worsening heart failure, non-fatal stroke, and non-fatal myocardial infarction, over a median follow-up of 20 months (IQR 17-48 months; average 30 months), confirmed via electronic medical records and telephone follow-upcomposite

Main Result

Effect estimate: AUC 0.840 (95% CI 0.749-0.931)

p-value: p=<0.05

An interpretable LASSO-logistic regression model incorporating 4D left atrial quantification parameters—particularly left atrial reservoir strain (LASr)—provides incremental predictive value over clinical and conventional echocardiographic models for stratifying MACE risk in patients with uremia.

Limitations

Single-center retrospective study with a relatively small sample size and low event per variable (EPV) ratio of approximately 1.71, lacking external multicenter validation.
Data on the main causes of CKD, renal replacement therapy, blood potassium, HbA1c, and electrocardiogram features were not systematically recorded.
Small sample sizes for individual MACE subtypes prevented evaluation of subtype-specific predictive performance.
Focused only on the occurrence of the first MACE without subsequent follow-up for all-cause mortality or competing risks.
Patients enrolled near the end of the enrollment period (January 2026) had short follow-up before the March 2026 cutoff, potentially underestimating cumulative event rates.

Implication

May support MACE risk stratification in uremia; leaves open external validation before clinical adoption.

Abstract

Background This study aimed to develop a machine learning model using four-dimensional left atrial quantification (4D-LAQ) parameters to the risk of major adverse cardiovascular events (MACE) in patients with uremia. Methods A total of 223 patients with uremia treated at the Second Affiliated Hospital of Hainan Medical University between January 2021 and January 2026 were retrospectively enrolled and followed up for the occurrence of MACE. LASSO regression was utilized for feature selection, followed by the development of eight prediction models. Logistic regression (LR) was identified as the final algorithm based on DeLong’s test. A nomogram was constructed, and Shapley Additive Explanations (SHAP) analysis was performed to enhance model interpretability. Model performance was comprehensively evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA). Intra- and inter-observer reproducibility were assessed using the intraclass correlation coefficient (ICC). Results During the follow-up period, 94 patients (42.1%) developed MACE. The MACE group exhibited left ventricular remodeling, mainly characterized by left atrial volume enlargement and a decrease in strain. The LR model achieved an AUC of 0.840 (95% CI: 0.749–0.931) in the validation set. Multiple validation approaches, including five-fold cross-validation, nested 5×5 cross-validation, and bootstrap internal validation, yielded AUCs of 0.873, 0.856, and 0.869, respectively. The calibration analysis showed good consistency (Hosmer-Lemeshow test, P > 0.05). The AUC of DCA (AUDC) was 0.208 (0.206 - 0.208), and the maximum net benefit was 0.43. The optimal risk stratification threshold, determined by the maximum Youden index in the training set, was 0.41. SHAP analysis identified left atrial reservoir strain (LASr) as the most influential predictive feature in this cohort. Conclusion The LASSO-LR model integrating 4D-LAQ parameters may help MACE risk in patients with uremia, with LASr emerging as an important predictor.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Ma et al. (2026) conducted a cohort in Uremia (Chronic Kidney Disease stage 5) (n=223). LASSO-logistic regression model integrating four-dimensional left atrial quantification (4D-LAQ) parameters vs. Clinical-only model and conventional echocardiography model was evaluated on Major adverse cardiovascular events (MACE: composite of cardiac death, hospitalization for worsening heart failure, non-fatal stroke, and non-fatal myocardial infarction) (AUC 0.840, 95% CI 0.749-0.931, p=<0.05). A LASSO-logistic model integrating 4D-LAQ parameters predicted MACE in uremia patients with an AUC of 0.840 (95% CI: 0.749-0.931), identifying left atrial reservoir strain as the top predictor.

synapsesocial.com/papers/6ae682cae432e7a5c4ef3757 https://doi.org/10.3389/fendo.2026.1970519

View Full Paper

Ask AI

Bookmark

Share

Four-dimensional left atrial quantification for predicting major adverse cardiovascular events in patients with uremia: an interpretable LASSO-logistic model

Key Points

Study Design

Structured PICO

Main Result

Limitations

Implication

Abstract

Discussion

Cite This Study

Four-dimensional left atrial quantification for predicting major adverse cardiovascular events in patients with uremia: an interpretable LASSO-logistic model

Key Points

Study Design

Structured PICO

Main Result

Limitations

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading