BMBradley S. Marino

Bradley S. Marino

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bradley S. Marino has a total of 36 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Hybrid rule-based and on-premises LLM pipeline for extracting CMR and CPET metrics from free-text reports in repaired tetralogy of Fallot

    by Izzet Turkalp Akbasli, Kristen L. Beck, Wilson Liou, Sherry Du, Gabriel Nemer, Orkun Baloglu, Samir Q. Latifi, Bradley S. Marino, Samer Albahra, Animesh Tandon

    Background: Patients with repaired tetralogy of Fallot (rTOF) require lifelong surveillance with cardiovascular magnetic resonance (CMR) and cardiopulmonary exercise testing (CPET). However, results are frequently stored as unstructured free-text reports, hindering large-scale analysis and research. Objectives: This study aimed to develop and evaluate a privacy-preserving hybrid natural language processing pipeline combining regular expressions (regex) and an on-premises large language model (LLM) to accurately extract key CMR and CPET metrics from legacy free-text reports in patients with rTOF. Methods: We retrospectively analyzed 430 CMR and 262 CPET reports (2005–2023) from patients with rTOF. A two-stage hybrid pipeline was implemented: regex rules were applied first, followed by targeted prompting of an on-premises Llama-3.1-8B-Instruct LLM only when regex failed or returned ambiguous results. Performance was compared against regex-only and LLM-only approaches using coverage, precision, recall, and F1-score. Results: In CMR reports, the hybrid pipeline achieved perfect coverage (1.00) and F1-score (1.00) versus 0.98 coverage and 0.93 F1-score with regex alone, while reducing computational cost by ~75% compared with LLM-only. In CPET reports, the hybrid approach improved F1-score from 0.74 (regex alone) to 0.98, with particularly large gains for semantically complex variables (e.g., peak VO □, test termination reason). Conclusions: A hybrid regex–on-premises LLM pipeline provides near-perfect, efficient, and HIPAA-compliant extraction of clinical metrics from unstructured cardiology reports, offering a scalable solution for retrospective research and quality improvement in congenital heart disease.


  • Open Access

    Performance of Supervised Machine Learning Models for Cardiac Surgery-Associated Acute Kidney Injury in Children: Multicenter Retrospective Cohort Study, 2019–2022

    by Orkun Baloglu, Izzet T. Akbasli, Ayse Morca, Samir Q. Latifi, Katja M. Gist, Jamie S. Penk, Bradley S. Marino

    Objectives: To derive and externally validate supervised machine learning (ML) models predictive of cardiac surgery-associated acute kidney injury (CS-AKI). Design: Retrospective cohort analysis. Setting: Multicenter (4), cardiac surgical centers from January 2019 to February 2022. Patients: Seven days to 18 years old who had undergone cardiac surgery. Interventions: None. Measurements and Main Results: CS-AKI was defined using Kidney Disease: Improving Global Outcomes criteria, with stages 2/3 classified as severe, during the first 7 postoperative days. Data analysis followed two approaches: 1) combining three centers for derivation and using a fourth for external validation and 2) randomly dividing the entire dataset into derivation and validation cohorts in a 4:1 ratio. Forty ML models were developed across five derivation-validation pairs using four ML algorithms (light gradient-boosting machine, extreme gradient boosting, categorical boosting, and histogram gradient boosting) to predict two outcomes (any and severe CS-AKI) utilizing preoperative, intraoperative, and immediate postoperative variables. SHapley Additive exPlanations was used for input variable importance analysis. A cohort of 1100 patients was analyzed. Any CS-AKI and severe CS-AKI occurred in 49.1% and 23.1% patients, respectively. Wide range of variations in external validation of model performance were observed among all 40 ML models. For any CS-AKI, the range in metrics were: area under the receiver operating characteristic curve (AUROC) 0.64–0.83, sensitivity 0.29–0.86, specificity 0.46–0.95, positive predictive value (PPV) 0.50–0.85, and negative predictive value (NPV) 0.60–0.86. For severe CS-AKI, we found the range in metrics with AUROC 0.65–0.77, sensitivity 0.04–0.58, specificity 0.77–0.99, PPV 0.32–0.75, and NPV 0.78–0.90. Preoperative serum creatinine, cardiopulmonary bypass, aortic cross-clamp duration, weight, and age at surgery were the most important predictors associated with CS-AKI. Conclusions: This analysis of a retrospective multicenter dataset shows that external performance of ML models vary, highlighting challenges in generalizability, which may be due to center-based differences in practice.


  • Open Access

    Supervised Machine Learning Models Predicting Postoperative Low Cardiac Output Syndrome In Neonates

    by Orkun Baloglu, Xiaofeng Wang, Bradley S. Marino, Ayse Morca, Izzet T. Akbasli, Samir Q. Latifi, Alex Klaben, Animesh Tandon

    OBJECTIVE: To train and test supervised machine learning (ML) models to predict low cardiac output syndrome (LCOS) within the first 48 postoperative hours in neonates undergoing cardiothoracic surgery. DESIGN: Retrospective observational study. An efficient tree-based gradient-boosting algorithm (LightGBM) ML models were developed to predict LCOS occurrence at 2-, 4-, 6-, and 12-hour forecasting horizons, incorporating data from the prediction time and the two preceding hours. SHapley Additive exPlanations (SHAP) analyses were used for feature importance analyses. SETTING: Single center, January 2012 to April 2023. PATIENTS: Neonates 28 days old or younger who underwent cardiothoracic surgery. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: A total of 181 neonates were included, with 14.9% experiencing LCOS. A multivariate time-series dataset was constructed using hourly clinical and laboratory variables recorded during the first 48 postoperative hours. The LightGBM ML models achieved area under the receiver operating characteristic curve values ranging from 0.91 to 0.98 and area under the precision-recall curve values ranging from 0.60 to 0.80 for LCOS prediction across 2-, 4-, 6-, and 12-hour forecasting horizons. SHAP analyses identified higher vasoactive inotrope score, lower urine output, and higher serum lactate as the most influential predictors. CONCLUSIONS: This study demonstrates that the supervised machine learning models can accurately predict LCOS in neonates, offering high interpretability. The findings support further validation in multicenter settings and integration into clinical workflows to enhance postoperative critical cardiac care neonates.


  • Long-Term Quality of Life in Congenital Heart Disease Surgical Survivors: Multicenter Retrospective Study of Surgical and ICU Explanatory Factors

    by Bradley S. Md Marino, Amy Cassedy, Katherine L. Brown, Rodney Franklin, J. William Gaynor, Mirjana Cvetkovic, Simon Rscn Laker, Katherine Levinson, Helen MacGloin, Lynn Mahony, et al.

    OBJECTIVES: Greater congenital heart disease (CHD) complexity is associated with lower health-related quality of life (HRQOL). There are no data on the association between surgical and ICU factors and HRQOL in CHD survivors. This study assess the association between surgical and ICU factors and HRQOL in child and adolescent CHD survivors. DESIGN: This was a corollary study of the Pediatric Cardiac Quality of Life Inventory (PCQLI) Testing Study. SETTING: Eight pediatric hospitals participating in the PCQLI Study. PATIENTS: Patients in the study had the Fontan procedure, surgery for tetralogy of Fallot (TOF), and transposition of the great arteries (TGAs). MEASUREMENTS AND MAIN RESULTS: Surgical/ICU explanatory variables were collected by reviewing the medical records. Primary outcome variables (PCQLI Total patient and parent scores) and covariates were obtained from the Data Registry. General linear modeling was used to create the multivariable models. There were 572 patients included: mean ± sd of age 11.7 ± 2.9 years; CHD Fontan 45%, TOF/TGA 55%; number of cardiac surgeries 2 (1–9); and number of ICU admissions 3 (1–9). In multivariable models, lowest body temperature on cardiopulmonary bypass (CPB) was negatively associated with patient total score (p < 0.05). The total number of CPB runs was negatively associated with parent-reported PCQLI Total score (p < 0.02). Cumulative days on an inotropic/vasoactive drug in the ICU was negatively associated with all patient-/parent-reported PCQLI scores (p < 0.04). Neurological deficit at discharge was negatively associated with parent-reported PCQLI total score (p < 0.02). The variance explained by these factors ranged from 24% to 29%. CONCLUSIONS: Surgical/ICU factors, demographic, and medical care utilization variables explain a low-to-moderate amount of variation in HRQOL. Research is needed to determine whether modification of these surgical and ICU factors improves HRQOL, and to identify other factors that contribute to unexplained variability.