Ying Daisy Zhuo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ying Daisy Zhuo has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Jack Dunn
Alexandria Health, Cambridge, MA
8 shared publications - Dimitris Bertsimas
Sloan School of Management, Massachusetts Institute of Technology, Cambridge, USA
3 shared publications - Anthony Gebran
University of Pittsburgh Medical Center, USA
2 shared publications Dimitris Bertsimas
Massachusetts Institute of Technology, Cambridge, MA
2 shared publications- Haytham Mohamed Ali Kaafarani
Division of Trauma, Emergency Surgery and Surgical Critical Care, Department of Surgery, Massachusetts General Hospital, Boston, MA 02114, USA
2 shared publications Lydia R. Maurer
Trauma, Emergency Surgery, and Surgical Critical Care, Massachusetts General Hospital, Harvard Medical School, Boston, MA; Center for Outcomes and Patient Safety in Surgery, Massachusetts General Hospital, Boston, MA
2 shared publications
Latest Publications
- 27 July 2022
- Published by Springer Nature in Operations Research Forum
- Vol. 3 (3) , 1-17
Detecting Racial Bias in Jury Selection
- 27 July 2022
- Published by Springer Nature in Operations Research Forum
- Vol. 3 (3) , 1-17
Detecting Racial Bias in Jury Selection
- 9 March 2022
- Published by Springer Nature in Machine Learning
- Vol. 111 (7) , 2741-2768
Optimal policy trees
- 9 March 2022
- Published by Springer Nature in Machine Learning
- Vol. 111 (7) , 2741-2768
Optimal policy trees
- 4 December 2021
- Published by Wiley in Health Services Research
- Vol. 57 (4) , 796-805
Benchmarking cesarean delivery rates using machine learning‐derived optimal classification trees
Objective To establish a case-adjusted hospital-specific performance evaluation tool using machine learning methodology for cesarean delivery. Data Sources Secondary data were collected from patients between 1/1/2015–2/28/2018 using a hospital's “Electronic Data Warehouse” database from Illinois, USA. Study Design The machine learning methodology of Optimal Classification Trees (OCT's) was used to predict cesarean delivery rate by physician group, thereby establishing the case-adjusted benchmarking standards in comparison to the overall hospital cesarean delivery rate. Outcomes of specific patient populations of each participating practice were predicted, as if each were treated in the overall hospital environment. The resulting OCTs estimate physician group expected cesarean delivery outcomes, both aggregate and in specific clinical situations. Data Collection/Extraction methods 12,841 singleton, vertex, term deliveries, cared for by practices with ≥50 births. Principal Findings The overall rate of cesarean delivery was 18.6% (n = 2384), with a range of 13.3%–33.7% amongst 22 physician practices. An optimal decision tree was used to create a prediction model for the overall hospital which defined 23 patient cohorts, divided by 46 nodes. The model's performance for prediction of cesarean delivery is as follows: area under the curve- 0.73, sensitivity- 98.4%, specificity- 16.1%, positive predictive value 83.7%, negative predictive value 70.6%. Comparisons with the overall hospital's specific-case adjusted benchmark groups revealed that several groups outperformed the overall hospital and some practice groups underperformed in comparison to the overall hospital. Conclusions OCT benchmarking can assess physician practice specific case-adjusted performance, both overall and clinical situation specific, and can serve as a valuable tool for hospital self-assessment and quality improvement.
- 4 December 2021
- Published by Wiley in Health Services Research
- Vol. 57 (4) , 796-805
Benchmarking cesarean delivery rates using machine learning‐derived optimal classification trees
Objective To establish a case-adjusted hospital-specific performance evaluation tool using machine learning methodology for cesarean delivery. Data Sources Secondary data were collected from patients between 1/1/2015–2/28/2018 using a hospital's “Electronic Data Warehouse” database from Illinois, USA. Study Design The machine learning methodology of Optimal Classification Trees (OCT's) was used to predict cesarean delivery rate by physician group, thereby establishing the case-adjusted benchmarking standards in comparison to the overall hospital cesarean delivery rate. Outcomes of specific patient populations of each participating practice were predicted, as if each were treated in the overall hospital environment. The resulting OCTs estimate physician group expected cesarean delivery outcomes, both aggregate and in specific clinical situations. Data Collection/Extraction methods 12,841 singleton, vertex, term deliveries, cared for by practices with ≥50 births. Principal Findings The overall rate of cesarean delivery was 18.6% (n = 2384), with a range of 13.3%–33.7% amongst 22 physician practices. An optimal decision tree was used to create a prediction model for the overall hospital which defined 23 patient cohorts, divided by 46 nodes. The model's performance for prediction of cesarean delivery is as follows: area under the curve- 0.73, sensitivity- 98.4%, specificity- 16.1%, positive predictive value 83.7%, negative predictive value 70.6%. Comparisons with the overall hospital's specific-case adjusted benchmark groups revealed that several groups outperformed the overall hospital and some practice groups underperformed in comparison to the overall hospital. Conclusions OCT benchmarking can assess physician practice specific case-adjusted performance, both overall and clinical situation specific, and can serve as a valuable tool for hospital self-assessment and quality improvement.
- Open Access
- 1 September 2021
- Published by Elsevier in Machine Learning with Applications
- Vol. 5, 100042
Interpretable predictive maintenance for hard drives
- 1 September 2021
- Published by Elsevier in Machine Learning with Applications
- Vol. 5, 100042
Open AccessInterpretable predictive maintenance for hard drives
- 28 April 2021
- Published by SAGE Publications in World Journal for Pediatric and Congenital Heart Surgery
- Vol. 12 (4) , 453-460
Adverse Outcomes Prediction for Congenital Heart Surgery: A Machine Learning Approach
Objective: Risk assessment tools typically used in congenital heart surgery (CHS) assume that various possible risk factors interact in a linear and additive fashion, an assumption that may not reflect reality. Using artificial intelligence techniques, we sought to develop nonlinear models for predicting outcomes in CHS. Methods: We built machine learning (ML) models to predict mortality, postoperative mechanical ventilatory support time (MVST), and hospital length of stay (LOS) for patients who underwent CHS, based on data of more than 235,000 patients and 295,000 operations provided by the European Congenital Heart Surgeons Association Congenital Database. We used optimal classification trees (OCTs) methodology for its interpretability and accuracy, and compared to logistic regression and state-of-the-art ML methods (Random Forests, Gradient Boosting), reporting their area under the curve (AUC or c-statistic) for both training and testing data sets. Results: Optimal classification trees achieve outstanding performance across all three models (mortality AUC = 0.86, prolonged MVST AUC = 0.85, prolonged LOS AUC = 0.82), while being intuitively interpretable. The most significant predictors of mortality are procedure, age, and weight, followed by days since previous admission and any general preoperative patient risk factors. Conclusions: The nonlinear ML-based models of OCTs are intuitively interpretable and provide superior predictive power. The associated risk calculator allows easy, accurate, and understandable estimation of individual patient risks, in the theoretical framework of the average performance of all centers represented in the database. This methodology has the potential to facilitate decision-making and resource optimization in CHS, enabling total quality management and precise benchmarking initiatives.
- 28 April 2021
- Published by SAGE Publications in World Journal for Pediatric and Congenital Heart Surgery
- Vol. 12 (4) , 453-460
Adverse Outcomes Prediction for Congenital Heart Surgery: A Machine Learning Approach
Objective: Risk assessment tools typically used in congenital heart surgery (CHS) assume that various possible risk factors interact in a linear and additive fashion, an assumption that may not reflect reality. Using artificial intelligence techniques, we sought to develop nonlinear models for predicting outcomes in CHS. Methods: We built machine learning (ML) models to predict mortality, postoperative mechanical ventilatory support time (MVST), and hospital length of stay (LOS) for patients who underwent CHS, based on data of more than 235,000 patients and 295,000 operations provided by the European Congenital Heart Surgeons Association Congenital Database. We used optimal classification trees (OCTs) methodology for its interpretability and accuracy, and compared to logistic regression and state-of-the-art ML methods (Random Forests, Gradient Boosting), reporting their area under the curve (AUC or c-statistic) for both training and testing data sets. Results: Optimal classification trees achieve outstanding performance across all three models (mortality AUC = 0.86, prolonged MVST AUC = 0.85, prolonged LOS AUC = 0.82), while being intuitively interpretable. The most significant predictors of mortality are procedure, age, and weight, followed by days since previous admission and any general preoperative patient risk factors. Conclusions: The nonlinear ML-based models of OCTs are intuitively interpretable and provide superior predictive power. The associated risk calculator allows easy, accurate, and understandable estimation of individual patient risks, in the theoretical framework of the average performance of all centers represented in the database. This methodology has the potential to facilitate decision-making and resource optimization in CHS, enabling total quality management and precise benchmarking initiatives.
- 1 January 2020
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Optimization
- Vol. 2 (1) , 1-13
Novel Target Discovery of Existing Therapies: Path to Personalized Cancer Therapy
Discovering new drugs involves tremendous effort and financial resources, often at a significant risk of failed trials. Identifying new targets of existing drugs provides a promising direction, especially for molecular targeted cancer therapies. This paper presents a novel, machine learning, and optimization-based method that identifies potential targets of existing drugs to expand the treatable patient population. The method has the following advantages: (1) It is based on clinical and genomic data from a large national cancer hospital; (2) it incorporates state-of-the-art knowledge of cancer molecular biology and signaling pathways; and (3) it models patient heterogeneity explicitly outside genomics. The output is an ordered list of therapy–target pairs that our algorithm identifies as highly promising to be further tested. The results are highly accurate when validated against known mechanisms of action for existing drugs, where relationships such as pertuzumab–ERBB2, cetuximab–EGFR, and erlotinib–EGFR were independently identified. We found similar results in the external The Cancer Genome Atlas data set. The findings suggest that a data-driven optimization approach to precision cancer medicine may lead to breakthroughs in the drug-discovery process and recommend effective personalized cancer treatments given patient-specific genomic and phenotypic information.
- 1 January 2020
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Optimization
- Vol. 2 (1) , 1-13
Novel Target Discovery of Existing Therapies: Path to Personalized Cancer Therapy
Discovering new drugs involves tremendous effort and financial resources, often at a significant risk of failed trials. Identifying new targets of existing drugs provides a promising direction, especially for molecular targeted cancer therapies. This paper presents a novel, machine learning, and optimization-based method that identifies potential targets of existing drugs to expand the treatable patient population. The method has the following advantages: (1) It is based on clinical and genomic data from a large national cancer hospital; (2) it incorporates state-of-the-art knowledge of cancer molecular biology and signaling pathways; and (3) it models patient heterogeneity explicitly outside genomics. The output is an ordered list of therapy–target pairs that our algorithm identifies as highly promising to be further tested. The results are highly accurate when validated against known mechanisms of action for existing drugs, where relationships such as pertuzumab–ERBB2, cetuximab–EGFR, and erlotinib–EGFR were independently identified. We found similar results in the external The Cancer Genome Atlas data set. The findings suggest that a data-driven optimization approach to precision cancer medicine may lead to breakthroughs in the drug-discovery process and recommend effective personalized cancer treatments given patient-specific genomic and phenotypic information.
- 18 July 2019
- Published by The R Foundation
iai: Interface to 'Interpretable AI' Modules
- 1 January 2019
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Optimization
- Vol. 1 (1) , 2-34
Robust Classification
Motivated by the fact that there may be inaccuracies in features and labels of training data, we apply robust optimization techniques to study in a principled way the uncertainty in data features and labels in classification problems and obtain robust formulations for the three most widely used classification methods: support vector machines, logistic regression, and decision trees. We show that adding robustness does not materially change the complexity of the problem and that all robust counterparts can be solved in practical computational times. We demonstrate the advantage of these robust formulations over regularized and nominal methods in synthetic data experiments, and we show that our robust classification methods offer improved out-of-sample accuracy. Furthermore, we run large-scale computational experiments across a sample of 75 data sets from the University of California Irvine Machine Learning Repository and show that adding robustness to any of the three nonregularized classification methods improves the accuracy in the majority of the data sets. We observe the most significant gains for robust classification methods on high-dimensional and difficult classification problems, with an average improvement in out-of-sample accuracy of robust versus nominal problems of 5.3% for support vector machines, 4.0% for logistic regression, and 1.3% for decision trees.
- 1 January 2019
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Optimization
- Vol. 1 (1) , 2-34
Robust Classification
Motivated by the fact that there may be inaccuracies in features and labels of training data, we apply robust optimization techniques to study in a principled way the uncertainty in data features and labels in classification problems and obtain robust formulations for the three most widely used classification methods: support vector machines, logistic regression, and decision trees. We show that adding robustness does not materially change the complexity of the problem and that all robust counterparts can be solved in practical computational times. We demonstrate the advantage of these robust formulations over regularized and nominal methods in synthetic data experiments, and we show that our robust classification methods offer improved out-of-sample accuracy. Furthermore, we run large-scale computational experiments across a sample of 75 data sets from the University of California Irvine Machine Learning Repository and show that adding robustness to any of the three nonregularized classification methods improves the accuracy in the majority of the data sets. We observe the most significant gains for robust classification methods on high-dimensional and difficult classification problems, with an average improvement in out-of-sample accuracy of robust versus nominal problems of 5.3% for support vector machines, 4.0% for logistic regression, and 1.3% for decision trees.