Adverse events after repair of tetralogy of Fallot: prediction models by machine learning of a retrospective cohort study in western China

Applying a Combined Model to Evaluate the Risk of Poor Treatment Outcomes in Rifampicin Resistant Tuberculosis Patients: A Multicenter Retrospective Study

Objective

Treating and managing rifampicin resistant tuberculosis (RR-TB) patients in Yunnan, China, are major challenges. This study aims to evaluate the risk of poor treatment outcomes in RR-TB patients, allowing clinical doctors to proactively target patients who would benefit from enhanced patient management.

Methods

Four RR-TB care facilities in different regions of Yunnan province as the data collection points were selected. A total of 524 RR-TB patients were included in this study and randomly assigned into a training set (n=366) and a validation set (n=158). In the training set, four significant factors were screened by using a random forest model and a Lasso regression model, and then included in a logistic regression model to construct a nomogram for internal validation.

Results

The successful treatment rate of RR-TB patients in training set was 42.6% (156/366), and the main poor treatment outcomes were loss to follow-up (66.7%) and death (18.1%). Low hemoglobin (HGB) (OR=0.977, 95% CI: 0.964-0.989), long-regime (OR=2.784, 95% CI: 1.634-4.842), poor culture results at the end of the 6th month (CR6TM) (OR=11.193, 95% CI: 6.507-20.028), pre-extensively drug-resistant tuberculosis (pre-XDR) (OR=3.736, 95% CI: 1.294-12.034) were risk factors for poor treatment outcomes in RR-TB patients. The Area Under Curve (AUC) of this model was 0.829 (95% CI: 0.787-0.870), and there was good consistency between the predicted probability and the actual probability. The DCA curve showed that when the threshold probability was 20-98%, the use of nomogram to predict the net benefit of poor treatment outcomes risk in RR-TB patients was higher.

Conclusion

We combined multiple models to develop a nomogram for predicting poor treatment outcomes in RR-TB patients. This would help clinical doctors identify high-risk populations and enable them to proactively target RR-TB patients who will benefit from strengthened patient management.

Inhibition of the FOXO1-ROCK1 axis mitigates cardiomyocyte injury under chronic hypoxia in Tetralogy of Fallot by maintaining mitochondrial quality control

INTRODUCTION

Persistent chronic myocardial hypoxia causes disturbances in mitochondrial quality control (MQC), ultimately leading to increased cardiomyocyte injury in patients with Tetralogy of Fallot (TOF). The present study aimed to identify the key effector molecules of cardiomyocyte injury under chronic hypoxia in TOF.

METHODS

Clinical data from TOF patients were collected and whole transcriptome sequencing was performed on myocardial samples. Chronic hypoxia models were established in cardiac-specific knockout mice and cardiomyocytes, and a series of molecular experiments were used to determine the specific mechanisms involved.

RESULTS

Clinical cohort data and whole-transcriptome sequencing analysis of myocardial samples from TOF patients revealed that forkhead box O1 (FOXO1) plays an important role in chronic hypoxic cardiomyocyte injury. In a model of chronic hypoxia established in FOXO1 cardiac-specific knockout mice and FOXO1 gene-deficient cardiomyocytes, the AMPK signaling pathway regulates the expression of FOXO1, which in turn disrupts MQC by regulating the transcriptional activation of Rho-associated protein kinase 1 (ROCK1), and increasing the production of mitochondrial ROS, thereby exacerbating damage to cardiomyocytes. Excessive reactive oxygen species (ROS) production during MQC dysfunction further activates Cox7a2L to increase the assembly of the respiratory chain supercomplex. In addition, we found that miR-27b-3p partially binds to the 3' untranslated region of FOXO1 to exert a protective effect.

CONCLUSIONS

Maintenance of MQC under chronic hypoxia is achieved through a series of injury-protection mechanisms, suggesting that FOXO1 inhibition may be crucial for future mitigation of chronic hypoxic cardiomyocyte injury in TOF.

Radiomics with structural magnetic resonance imaging, surface morphometry features, neurology scales, and clinical metrics to evaluate the neurodevelopment of preschool children with corrected tetralogy of Fallot

Background

Despite the improved survival rates of children with tetralogy of Fallot (TOF), various degrees of neurodevelopmental disorders persist. Currently, there is a lack of quantitative and objective imaging markers to assess the neurodevelopment of individuals with TOF. This study aimed to noninvasively examine potential quantitative imaging markers of TOF neurodevelopment by combining radiomics signatures and morphological features and to further clarify the relationship between imaging markers and clinical neurodevelopment metrics.

Methods

This study included 33 preschool children who had undergone surgical correction for TOF and 29 healthy controls (36 in the training cohort and 26 in the testing cohort), all of whom underwent three-dimensional T1-weighted high-resolution (T1-3D) head magnetic resonance imaging (MRI). Radiomics features were extracted by Pyradiomics to construct radiomics models, while surface morphometry (surface and volumetric) features were analyzed to build morphometry models. Merged models integrating radiomics and morphometry features were subsequently developed. The optimal discriminative radiomics signatures were identified via least absolute shrinkage and selection operator (LASSO). Machine learning classification models include support vector machine (SVM) with radial basis function (RBF) and multivariable logistic regression (MLR) models, both of which were used to evaluate the potential imaging biomarkers. Performances of models were evaluated based on their calibration and classification metrics. The area under the receiver operating characteristic curves (AUCs) of the models were evaluated using the Delong test. Neurodevelopmental assessments for children with corrected TOF were conducted with the Wechsler Preschool and Primary Scale of Intelligence-Fourth Edition (WPPSI-IV). Furthermore, the correlation of the significant discriminative indicators with clinical metrics and neurodevelopmental scales was evaluated.

Results

Twelve discriminative radiomics signatures, optimized for classification, were identified. The performance of the merged model (AUCs of 0.922 and 0.917 for the training set and test set with SVM, respectively) was superior to that of the single radiomics model (AUCs of 0.915 and 0.917 for the training set and test set with SVM, respectively) and that of the single morphometric models (AUCs of 0.803 and 0.756 for the training set and test set with SVM, respectively). The radiomics model demonstrated higher significance than did the morphometric models in training set with SVM (AUC: 0.915 vs. 0.803; P<0.001). Additionally, the significant indicators showed a correlation with clinical indicators and neurodevelopmental scales.

Conclusions

MRI-based radiomics features combined with morphometry features can provide complementary information to identify neurodevelopmental abnormalities in children with corrected TOF, which will provide potential evidence for clinical diagnosis and treatment.

The Lifelong Impact of Artificial Intelligence and Clinical Prediction Models on Patients With Tetralogy of Fallot

Medical advancements in the diagnosis, surgical techniques, perioperative care, and continued care throughout childhood have transformed the outlook for individuals with tetralogy of Fallot (TOF), improving survival and shifting the perspective towards lifelong care. However, with a growing population of survivors, longstanding challenges have been accentuated, and new challenges have surfaced, necessitating a re-evaluation of TOF care. Availability of prenatal diagnostics, insufficient information from traditional imaging techniques, previously unforeseen medical complications, and debates surrounding optimal timing and indications for reintervention are among the emerging issues. To address these challenges, the integration of artificial intelligence and machine learning holds great promise as they have the potential to revolutionize patient management and positively impact lifelong outcomes for individuals with TOF. Innovative applications of artificial intelligence and machine learning have spanned across multiple domains of TOF care, including screening and diagnosis, automated image processing and interpretation, clinical risk stratification, and planning and performing cardiac interventions. By embracing these advancements and incorporating them into routine clinical practice, personalized medicine could be delivered, leading to the best possible outcomes for patients. In this review, we provide an overview of these evolving applications and emphasize the challenges, limitations, and future potential for integrating them into clinical care.