Maryam Pishgar

Dr. Maryam Pishgar


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 August 2024 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
JGJiayi Gao
Jiayi Gao
YLYuying Lu
Yuying Lu
NANegin Ashrafi
Negin Ashrafi
IDIan Domingo
Ian Domingo
KAKamiar Alaei
Kamiar Alaei
MPMaryam Pishgar
Maryam Pishgar
Problem: Sepsis, a life-threatening condition, accounts for the deaths of millions of people worldwide. Accurate prediction of sepsis outcomes is crucial for effective treatment and management. Previous studies have utilized machine learning for prognosis, but have limitations in feature sets and model interpretability. Aim: This study aims to develop a machine learning model that enhances prediction accuracy for sepsis outcomes using a reduced set of features, thereby addressing the limitations of previous studies and enhancing model interpretability. Methods: This study analyzes intensive care patient outcomes using the MIMIC-IV database, focusing on adult sepsis cases. Employing the latest data extraction tools, such as Google BigQuery, and following stringent selection criteria, we selected 38 features in this study. This selection is also informed by a comprehensive literature review and clinical expertise. Data preprocessing included handling missing values, regrouping categorical variables, and using the Synthetic Minority Over-sampling Technique (SMOTE) to balance the data. We evaluated several machine learning models: Decision Trees, Gradient Boosting, XGBoost, LightGBM, Multilayer Perceptrons (MLP), Support Vector Machines (SVM), and Random Forest. The Sequential Halving and Classification (SHAC) algorithm was used for hyperparameter tuning, and both train-test split and cross-validation methodologies were employed for performance and computational efficiency. Results: The Random Forest model was the most effective, achieving an area under the receiver operating characteristic curve (AUROC) of 0.94 with a confidence interval of ±0.01. This significantly outperformed other models and set a new benchmark in the literature. The model also provided detailed insights into the importance of various clinical features, with the Sequential Organ Failure Assessment (SOFA) score and average urine output being highly predictive. SHAP (Shapley Additive Explanations) analysis further enhanced the model’s interpretability, offering a clearer understanding of feature impacts. Conclusion: This study demonstrates significant improvements in predicting sepsis outcomes using a Random Forest model, supported by advanced machine learning techniques and thorough data preprocessing. Our approach provided detailed insights into the key clinical features impacting sepsis mortality, making the model both highly accurate and interpretable. By enhancing the model’s practical utility in clinical settings, we offer a valuable tool for healthcare professionals to make data-driven decisions, ultimately aiming to minimize sepsis-induced fatalities.

8 August 2024 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
ZYZhijiang Yu
Zhijiang Yu
NANegin Ashrafi
Negin Ashrafi
HLHexin Li
Hexin Li
KAKamiar Alaei
Kamiar Alaei
MPMaryam Pishgar
Maryam Pishgar
Background: There is a growing demand for advanced methods to improve the understanding and prediction of illnesses. This study focuses on Sepsis, a critical response to infection, aiming to enhance early detection and mortality prediction for Sepsis-3 patients to improve hospital resource allocation. Methods: In this study, we developed a Machine Learning (ML) framework to predict the 30-day mortality rate of ICU patients with Sepsis-3 using the MIMIC-III database. Advanced big data extraction tools like Snowflake were used to identify eligible patients. Decision tree models and Entropy Analyses helped refine feature selection, resulting in 30 relevant features curated with clinical experts. We employed the Light Gradient Boosting Machine (LightGBM) model for its efficiency and predictive power. Results: The study comprised a cohort of 9118 Sepsis-3 patients. Our preprocessing techniques significantly improved both the AUC and accuracy metrics. The LightGBM model achieved an impressive AUC of 0.983 (95% CI: [0.980–0.990]), an accuracy of 0.966, and an F1-score of 0.910. Notably, LightGBM showed a substantial 6% improvement over our best baseline model and a 14% enhancement over the best existing literature. These advancements are attributed to (I) the inclusion of the novel and pivotal feature Hospital Length of Stay (HOSP_LOS), absent in previous studies, and (II) LightGBM’s gradient boosting architecture, enabling robust predictions with high-dimensional data while maintaining computational efficiency, as demonstrated by its learning curve. Conclusions: Our preprocessing methodology reduced the number of relevant features and identified a crucial feature overlooked in previous studies. The proposed model demonstrated high predictive power and generalization capability, highlighting the potential of ML in ICU settings. This model can streamline ICU resource allocation and provide tailored interventions for Sepsis-3 patients.

2 April 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
NANegin Ashrafi
Negin Ashrafi
AAArmin Abdollahi
Armin Abdollahi
KAKamiar Alaei
Kamiar Alaei
MPMaryam Pishgar
Maryam Pishgar
Ventilator-associated pneumonia significantly increases morbidity, mortality, and healthcare costs among patients with traumatic brain injury. Accurately predicting risk can facilitate earlier interventions and improve patient outcomes. This study leveraged the MIMIC III database, identifying traumatic brain injury cases through standardized clinical criteria. A rigorous data preprocessing workflow included missing value imputation, correlation checks, and expert-driven feature selection, reducing an initial set of features to a subset of critical predictors encompassing demographics, comorbidities, laboratory values, and clinical interventions. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied within a five-fold cross-validation framework, ensuring a balanced training set while maintaining an unbiased validation process. Six machine learning models, including Support Vector Machine, Logistic Regression, Random Forest, XGBoost, Artificial Neural Network, and AdaBoost, were trained using extensive hyperparameter tuning. Comprehensive evaluations were conducted based on multiple metrics, including Area Under the Curve (AUC), accuracy, F1 score, sensitivity, specificity, Positive Predictive Value, and Negative Predictive Value. XGBoost emerged as the top performing algorithm, achieving an AUC of 0.94 and an accuracy of 0.875 on the test set, marking substantial improvements over previously reported best results. An ablation study validated the necessity of each retained feature, indicating that any feature removal led to a decline in model performance. Furthermore, SHAP analysis underscored ICU length of stay, hospital length of stay, serum potassium, and blood urea nitrogen as key contributors to ventilator associated pneumonia risk. Overall, the results demonstrate that advanced ensemble learning, meticulous feature selection, and effective class imbalance handling can significantly enhance early detection in traumatic brain injury cases. These findings have meaningful clinical implications, offering a framework for more timely interventions, optimized resource allocation, and improved patient care in critical settings.

4 September 2024 in PLOS ONE
Verified
Journal Article
Open access
PDF file
HLHexin Li
Hexin Li
NANegin Ashrafi
Negin Ashrafi
CKChris Kang
Chris Kang
GZGuanlan Zhao
Guanlan Zhao
YCYubing Chen
Yubing Chen
MPMaryam Pishgar
Maryam Pishgar
Background: Mechanical ventilation (MV) is vital for critically ill ICU patients but carries significant mortality risks. This study aims to develop a predictive model to estimate hospital mortality among MV patients, utilizing comprehensive health data to assist ICU physicians with early-stage alerts. Methods: We developed a Machine Learning (ML) framework to predict hospital mortality in ICU patients receiving MV. Using the MIMIC-III database, we identified 25,202 eligible patients through ICD-9 codes. We employed backward elimination and the Lasso method, selecting 32 features based on clinical insights and literature. Data preprocessing included eliminating columns with over 90% missing data and using mean imputation for the remaining missing values. To address class imbalance, we used the Synthetic Minority Over-sampling Technique (SMOTE). We evaluated several ML models, including CatBoost, XGBoost, Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Logistic Regression, using a 70/30 train-test split. The CatBoost model was chosen for its superior performance in terms of accuracy, precision, recall, F1-score, AUROC metrics, and calibration plots. Results: The study involved a cohort of 25,202 patients on MV. The CatBoost model attained an AUROC of 0.862, an increase from an initial AUROC of 0.821, which was the best reported in the literature. It also demonstrated an accuracy of 0.789, an F1-score of 0.747, and better calibration, outperforming other models. These improvements are due to systematic feature selection and the robust gradient boosting architecture of CatBoost. Conclusion: The preprocessing methodology significantly reduced the number of relevant features, simplifying computational processes, and identified critical features previously overlooked. Integrating these features and tuning the parameters, our model demonstrated strong generalization to unseen data. This highlights the potential of ML as a crucial tool in ICUs, enhancing resource allocation and providing more personalized interventions for MV patients.

24 July 2025 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
YSYong Si
Yong Si
AAArmin Abdollahi
Armin Abdollahi
NANegin Ashrafi
Negin Ashrafi
GPGreg Placencia
Greg Placencia
EPElham Pishgar
Elham Pishgar
MPMaryam Pishgar
Maryam Pishgar
Background: Coronary artery disease (CAD) remains a leading cause of global mortality, with stroke constituting a significant complication among patients undergoing coronary revascularization procedures, such as percutaneous coronary intervention (PCI) or coronary artery bypass grafting (CABG). Previous research has demonstrated the successful application of machine learning (ML) in predicting various postoperative outcomes, including poor prognosis following cardiac surgery and the risk of postoperative stroke. Despite these advancements, a critical gap persists in studies quantitatively linking the risk of postoperative stroke to revascularization using ML-based approaches. This study aims to address this gap by developing and validating ML models to predict the risk of stroke in CAD patients undergoing coronary revascularization, with the ultimate goal of enhancing clinical decision-making and improving patient outcomes. Methods: We developed an ML framework to predict stroke risk in patients with CAD undergoing revascularization. A total of 5,757 patients were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Feature selection was performed using a combination of Pearson correlation analysis, least absolute shrinkage and selection operator (LASSO), ridge regression, and elastic net. Initially, 35 features were identified based on expert opinion and a comprehensive literature review; the integrated results of the feature selection methods reduced the feature set to 14. The dataset was randomly divided into training, testing, and validation subsets with proportions of 70%, 15%, and 15%, respectively. Several ML models were evaluated, including logistic regression, XGBoost, random forest, AdaBoost, Bernoulli naive Bayes, k-nearest neighbors (KNN), and CatBoost. Model performance was assessed using the area under the receiver operating characteristic curve (AUC-ROC), accuracy, and 500 bootstrapped 95% confidence intervals (CIs) to ensure robust evaluation. Results: The CatBoost model demonstrated superior performance, achieving an AUC of 0.8486 (95% CI: 0.8124–0.8797) on the test set and 0.8511 (95% CI: 0.8203–0.8793) on the validation set. Shapley Additive Explanations (SHAP) analysis identified the Charlson Comorbidity Index (CCI), length of stay (LOS), and treatment types as the most influential predictors. Notably, compared to the best existing literature, which reported an AUC of 0.760 on the test set, our model exhibited a 9% improvement in predictive performance while utilizing a more parsimonious feature set. Conclusion: By integrating four feature selection methods, we significantly streamlined the feature set, resulting in a more efficient and reliable predictive model. We propose the CatBoost model for the prediction of postoperative stroke in patients with CAD undergoing coronary revascularization. With its high accuracy, the proposed model offers valuable insights for medical practitioners, enabling informed decision-making and the implementation of preventive measures to mitigate stroke risk.

13 January 2026 in BioMedInformatics
Verified
Journal Article
Open access
PDF file
YLYupeng Li
Yupeng Li
JFJunyi Fan
Junyi Fan
KAKamiar Alaei
Kamiar Alaei
MPMaryam Pishgar
Maryam Pishgar
Background: Sepsis-associated liver injury (SALI) is a serious complication of sepsis that increases the risk of organ dysfunction and mortality; however, early identification of high-risk patients remains difficult due to nonspecific clinical features and complex pathophysiology. This study aimed to develop machine learning (ML) models to predict 28-day mortality in SALI patients within the first 24 h of intensive care unit (ICU) admission. Methods: A total of 1157 patients were included, comprising 826 from the MIMIC-IV (v2.2) database, 225 from MIMIC-III (v1.4), and 106 from eICU (v2.0). Data from MIMIC-IV were split into training and internal validation sets (7:3), while MIMIC-III and eICU served as external validation cohorts. Thirty clinically relevant features were selected. Eight ML models were evaluated using AUROC, accuracy, precision, recall, F1-score, and specificity. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) enhanced interpretability. Results: XGBoost model achieved the best performance, with an AUROC of 0.8556 (95% CI: 0.807–0.898), accuracy of 0.7702, recall of 0.8469, and specificity of 0.7200. SHAP identified lactate, blood urea nitrogen, heart rate, hemoglobin, and diastolic blood pressure as key predictors, while LIME provided patient-level interpretability. Conclusions: The XGBoost-based model may facilitate early mortality risk stratification and support clinical decision-making for SALI patients in ICU settings.