Search

Your search keyword '"Dunn, Jack"' showing total 190 results
Start Over Author "Dunn, Jack"
190 results on '"Dunn, Jack"'

2. Comparing interpretability and explainability for feature selection

Author

Dunn, Jack, Mingardi, Luca, and Zhuo, Ying Daisy

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

A common approach for feature selection is to examine the variable importance scores for a machine learning model, as a way to understand which features are the most relevant for making predictions. Given the significance of feature selection, it is crucial for the calculated importance scores to reflect reality. Falsely overestimating the importance of irrelevant features can lead to false discoveries, while underestimating importance of relevant features may lead us to discard important features, resulting in poor model performance. Additionally, black-box models like XGBoost provide state-of-the art predictive performance, but cannot be easily understood by humans, and thus we rely on variable importance scores or methods for explainability like SHAP to offer insight into their behavior. In this paper, we investigate the performance of variable importance as a feature selection method across various black-box and interpretable machine learning methods. We compare the ability of CART, Optimal Trees, XGBoost and SHAP to correctly identify the relevant subset of variables across a number of experiments. The results show that regardless of whether we use the native variable importance method or SHAP, XGBoost fails to clearly distinguish between relevant and irrelevant features. On the other hand, the interpretable methods are able to correctly and efficiently identify irrelevant features, and thus offer significantly better performance for feature selection.

Published
2021

3. Detecting Racial Bias in Jury Selection

Author

Dunn, Jack and Zhuo, Ying Daisy

Subjects
Computer Science - Machine Learning, Computer Science - Computers and Society
Abstract

To support the 2019 U.S. Supreme Court case "Flowers v. Mississippi", APM Reports collated historical court records to assess whether the State exhibited a racial bias in striking potential jurors. This analysis used backward stepwise logistic regression to conclude that race was a significant factor, however this method for selecting relevant features is only a heuristic, and additionally cannot consider interactions between features. We apply Optimal Feature Selection to identify the globally-optimal subset of features and affirm that there is significant evidence of racial bias in the strike decisions. We also use Optimal Classification Trees to segment the juror population subgroups with similar characteristics and probability of being struck, and find that three of these subgroups exhibit significant racial disparity in strike rate, pinpointing specific areas of bias in the dataset.

Published
2021

4. Interpretable Predictive Maintenance for Hard Drives

Author

Amram, Maxime, Dunn, Jack, Toledano, Jeremy J., and Zhuo, Ying Daisy

Subjects
Computer Science - Machine Learning
Abstract

Existing machine learning approaches for data-driven predictive maintenance are usually black boxes that claim high predictive power yet cannot be understood by humans. This limits the ability of humans to use these models to derive insights and understanding of the underlying failure mechanisms, and also limits the degree of confidence that can be placed in such a system to perform well on future data. We consider the task of predicting hard drive failure in a data center using recent algorithms for interpretable machine learning. We demonstrate that these methods provide meaningful insights about short- and long-term drive health, while also maintaining high predictive performance. We also show that these analyses still deliver useful insights even when limited historical data is available, enabling their use in situations where data collection has only recently begun.

Published
2021

5. Optimal Survival Trees

Author

Bertsimas, Dimitris, Dunn, Jack, Gibson, Emma, and Orfanoudaki, Agni

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

Tree-based models are increasingly popular due to their ability to identify complex relationships that are beyond the scope of parametric models. Survival tree methods adapt these models to allow for the analysis of censored outcomes, which often appear in medical data. We present a new Optimal Survival Trees algorithm that leverages mixed-integer optimization (MIO) and local search techniques to generate globally optimized survival tree models. We demonstrate that the OST algorithm improves on the accuracy of existing survival tree methods, particularly in large datasets.

Published
2020

6. Optimal Policy Trees

Author

Amram, Maxime, Dunn, Jack, and Zhuo, Ying Daisy

Subjects
Computer Science - Machine Learning
Abstract

We propose an approach for learning optimal tree-based prescription policies directly from data, combining methods for counterfactual estimation from the causal inference literature with recent advances in training globally-optimal decision trees. The resulting method, Optimal Policy Trees, yields interpretable prescription policies, is highly scalable, and handles both discrete and continuous treatments. We conduct extensive experiments on both synthetic and real-world datasets and demonstrate that these trees offer best-in-class performance across a wide variety of problems.

Published
2020

12. Benchmarking cesarean delivery rates using machine learning-derived optimal classification trees

Author

Gimovsky, Alexis C., Zhuo, Daisy, Levine, Jordan T., Dunn, Jack, Amarm, Maxime, and Peaceman, Alan M.

Subjects
Cesarean section -- Personalities -- Methods, Benchmarks -- Forecasts and trends, Machine learning -- Usage, Medical care -- Quality management, Benchmark, Market trend/market analysis, Business, Health care industry
Abstract

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 January 1, 2015 and February 28, 2018 using a hospital's 'Electronic Data Warehouse' database from Illinois, USA. Study Design: The machine learning methodology of optimal classification trees (OCTs) 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: Twelve thousand eight hunderd and forty one singleton, vertex, term deliveries, cared for by practices with [greater than or equal to]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 hospital overall, 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 benchmark, and some practice groups underperformed in comparison to the overall hospital benchmark. 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. KEYWORDS cesarean birth, cesarean delivery, cesarean section, database, machine learning, optimal classification trees, risk analysis/modeling, statistics What is known on this topic * The cesarean delivery rate in the United States for low-risk births is higher than the World Health Organization's target rate and associated with increased maternal morbidity and mortality. * Criticisms of prior benchmarking models are the inclusion of limited patient-related factors, reporting of a single summary measure of hospital performance, and outdated analytical methods to predict risk based only on binary risk factors. * Crude comparison of cesarean delivery rates between hospitals or practice groups may not be appropriate given variation in case mix. What this study adds * Optimal classification trees (OCTs) benchmarking analysis is a novel and nonlinear technology that can assess physician practice-specific case-adjusted performance for cesarean delivery with high sensitivity of 98.4% in this study. * OCT benchmarking analysis can be used to compare practice group performance in cesarean delivery with an area under the curve of 0.73. * OCT benchmarking analysis can compare practice groups and reveal differences in performance in comparison to the overall hospital's performance., 1 | INTRODUCTION The current cesarean delivery (CD) rate in the United States for the most recent data from 2018 was 31.9%, with a low-risk CD rate (nulliparous, term, singleton, [...]

Published
2022
Full Text
View/download PDF

23. High Scorers.

Author

Gilchrist, Todd, Dunn, Jack, Buenahora, Andrés, and Drury, Sharareh

Subjects
SOVEREIGN wealth funds, GENDER nonconformity, BUSINESS planning, MULTIPLAYER games, BUSINESS schools, MUSIC videos
Abstract

The article from Variety highlights the top 10 entertainment gaming leaders who are shaping the industry. These leaders are recognized for their contributions to game development, platform building, and multimedia adaptation. Each individual brings a unique perspective and skill set to the industry, emphasizing the importance of storytelling, interactivity, and emotional investment in gaming experiences. [Extracted from the article]

Published
2024

24. Arts and Crafts.

Author

Betancourt, Emiliana, Buenahora, Andres, Tangcay, Jazz, and Dunn, Jack

Subjects
STAR Wars Universe, YOUNG adults, WORKING hours, THEATRICAL scenery, SOUND designers, ENVY
Abstract

Variety's "Arts and Crafts" article highlights 10 artisans in the film industry, including a sound mixer, composer, supervising sound editor, production designer, VFX producer, supervising stunt coordinator, makeup artist, editor, hair department head, and costume designer. Each artisan shares their unique journey and influences in their respective fields, showcasing their impact on recent movies and series. The article celebrates their breakthroughs and contributions to the craft, with Variety set to honor them at the SCAD Savannah Film Festival. [Extracted from the article]

Published
2024

25. power of women.

Author

ANGELIQUE, JACKSON, LITTLETON, CYNTHIA, LONGERETTA, EMILY, STEPHAN, KATCY, BETANCOURT, EMILIANA, DUNN, JACK, GARCIA, THANIA, GILCHRIST, TODD, HENDRICKSON, PAULA, HORST, CAROLE, IDELSON, KAREN, MALONEY, MICHAEL, RILEY, JENELLE, ROSSI, ROSEMARY, and SAPERSTEIN, PAT

Subjects
POOR children, EQUAL pay for equal work, PERFORMING arts, CREATIVE directors, INDIAN women (Asians), SONGWRITING, MENTORING, MUSIC videos, CIGAR smoking
Abstract

The article from Variety delves into Zoe Saldana's career in the entertainment industry, exploring her personal growth, achievements, and philanthropic endeavors. It highlights her roles in major films, struggles with insecurity, and recent projects like "Emilia Pérez." Additionally, the text showcases the accomplishments of various women in the entertainment field, including executives, actors, producers, and agents, who have made significant contributions to content creation, talent representation, marketing, and advocacy. These women are celebrated for their dedication to diversity, empowerment, and innovation within the industry. [Extracted from the article]

Published
2024

26. Depth of Field.

Author

Gilchrist, Todd, Buenahora, Andres, Dunn, Jack, and Betancourt, Emiliana

Subjects
SONY digital cameras, ARTISTIC photography, SHORT films, ART, EMOTIONS, MUSIC videos
Abstract

"Depth of Field" from Variety magazine profiles 10 up-and-coming cinematographers in 2024, including Ayana Baraka, Lauren Guiteras, Ryoma Kohari, Veronica Bouza, and Xiaolong Liu. The article highlights their diverse backgrounds and creative visions in the film industry, emphasizing the importance of adaptability, collaboration, and capturing emotional moments on screen. Each cinematographer aims to tell impactful stories and elevate voices through their work, showcasing a range of perspectives and experiences in cinematography. [Extracted from the article]

Published
2024

27. Comparative Compositions of Grain of Bread Wheat, Emmer and Spelt Grown with Different Levels of Nitrogen Fertilisation

Author

Lovegrove, Alison, primary, Dunn, Jack, additional, Pellny, Till K., additional, Hood, Jessica, additional, Burridge, Amanda J., additional, America, Antoine H. P., additional, Gilissen, Luud, additional, Timmer, Ruud, additional, Proos-Huijsmans, Zsuzsan A. M., additional, van Straaten, Jan Philip, additional, Jonkers, Daisy, additional, Ward, Jane L., additional, Brouns, Fred, additional, and Shewry, Peter R., additional

Published
2023
Full Text
View/download PDF

30. Benchmarking in Congenital Heart Surgery Using Machine Learning-Derived Optimal Classification Trees

Author

Massachusetts Institute of Technology. Operations Research Center, Sloan School of Management, Bertsimas, Dimitris, Zhuo, Daisy, Levine, Jordan, Dunn, Jack, Tobota, Zdzislaw, Maruszewski, Bohdan, Fragata, Jose, Sarris, George E, Massachusetts Institute of Technology. Operations Research Center, Sloan School of Management, Bertsimas, Dimitris, Zhuo, Daisy, Levine, Jordan, Dunn, Jack, Tobota, Zdzislaw, Maruszewski, Bohdan, Fragata, Jose, and Sarris, George E

Abstract

Background: We have previously shown that the machine learning methodology of optimal classification trees (OCTs) can accurately predict risk after congenital heart surgery (CHS). We have now applied this methodology to define benchmarking standards after CHS, permitting case-adjusted hospital-specific performance evaluation. Methods: The European Congenital Heart Surgeons Association Congenital Database data subset (31 792 patients) who had undergone any of the 10 “benchmark procedure group” primary procedures were analyzed. OCT models were built predicting hospital mortality (HM), and prolonged postoperative mechanical ventilatory support time (MVST) or length of hospital stay (LOS), thereby establishing case-adjusted benchmarking standards reflecting the overall performance of all participating hospitals, designated as the “virtual hospital.” These models were then used to predict individual hospitals’ expected outcomes (both aggregate and, importantly, for risk-matched patient cohorts) for their own specific cases and case-mix, based on OCT analysis of aggregate data from the “virtual hospital.” Results: The raw average rates were HM = 4.4%, MVST = 15.3%, and LOS = 15.5%. Of 64 participating centers, in comparison with each hospital's specific case-adjusted benchmark, 17.0% statistically (under 90% confidence intervals) overperformed and 26.4% underperformed with respect to the predicted outcomes for their own specific cases and case-mix. For MVST and LOS, overperformers were 34.0% and 26.4%, and underperformers were 28.3% and 43.4%, respectively. OCT analyses reveal hospital-specific patient cohorts of either overperformance or underperformance. Conclusions: OCT benchmarking analysis can assess hospital-specific case-adjusted performance after CHS, both overall and patient cohort-specific, serving as a tool for hospital self-assessment and quality improvement.

Published
2022

31. Sparse regression over clusters: SparClur

Author

Sloan School of Management, Massachusetts Institute of Technology. Operations Research Center, Bertsimas, Dimitris, Dunn, Jack, Kapelevich, Lea, Zhang, Rebecca, Sloan School of Management, Massachusetts Institute of Technology. Operations Research Center, Bertsimas, Dimitris, Dunn, Jack, Kapelevich, Lea, and Zhang, Rebecca

Abstract

Prediction tasks in personalized medicine require models that combine accuracy and interpretability. We propose an integer optimization approach for building sparse regression models with enforced coordination, using data partitioned among leaves in a prediction tree. We show that the method recovers the true underlying relationship between observations and target variables in large-scale synthetic data in seconds. We apply our method to several real-world medical prediction problems and observe that the additional structure imposed provides a substantial gain in interpretability, at a low cost to accuracy.

Published
2022

32. Adverse Outcomes Prediction for Congenital Heart Surgery: A Machine Learning Approach

Author

Massachusetts Institute of Technology. Operations Research Center, Sloan School of Management, Bertsimas, Dimitris, Zhuo, Daisy, Dunn, Jack, Levine, Jordan, Zuccarelli, Eugenio, Smyrnakis, Nikos, Tobota, Zdzislaw, Maruszewski, Bohdan, Fragata, Jose, Sarris, George E, Massachusetts Institute of Technology. Operations Research Center, Sloan School of Management, Bertsimas, Dimitris, Zhuo, Daisy, Dunn, Jack, Levine, Jordan, Zuccarelli, Eugenio, Smyrnakis, Nikos, Tobota, Zdzislaw, Maruszewski, Bohdan, Fragata, Jose, and Sarris, George E

Abstract

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 optimizatio

Published
2022

34. Leaders of the Pack.

Author

Dunn, Jack, Kuznikov, Selena, and Thompson, Jaden

Subjects
ACADEMY Awards, MUSIC videos, SCREEN Actors Guild Awards, CHIEF legal officers
Abstract

The Gold House A100 list recognizes Asian American and Pacific Islander (AAPI) leaders in a range of industries. The list includes prominent figures like Shou Chew, CEO of TikTok, Carla Hassan and Sanoke Viswanathan, executives at JPMorgan Chase, Tariq Hassan, Chief Marketing & Customer Experience Officer at McDonald's, Shailesh Jejurikar, Chief Operating Officer at Procter & Gamble, and Thomas Kurian, CEO of Google Cloud. The list also features individuals from the entertainment and media industry, such as Steve Aoki, Alia Bhatt, and Luciane Buchanan. The A100 honorees will be celebrated at the Gold Gala on May 11. This document provides a comprehensive list of individuals and organizations in various fields, including film, music, television, and fashion, highlighting their achievements and roles within their respective industries. Notable figures mentioned include Alex Norström, co-president and chief business officer of Spotify, and Mackenyu, an actor known for his roles in "One Piece" and "Knights of the Zodiac." The document also showcases the accomplishments of various artists, writers, directors, chefs, and more, emphasizing their contributions to their respective fields. It offers brief biographical information about these individuals, who encompass a diverse range of professionals, including makeup artists, CEOs, authors, activists, journalists, and athletes. [Extracted from the article]

Published
2024

35. Film Studies.

Author

Drury, Sharareh, Dunn, Jack, Gilchrist, Todd, Horst, Carole, Kuznikov, Selena, Idelson, Karen, and Thompson, Jaden

Subjects
FILM studies, SCHOLARSHIPS, INTERNSHIP programs, SOUND studios, SHORT films, EDUCATION & training services industry, FILMMAKING
Abstract

Variety has compiled a list of top film school programs in North America, highlighting their strengths and offerings. The schools on the list have experienced alumni who have made significant contributions to the industry. Some notable programs include Belmont University, Biola University, and Boston University. Other schools mentioned include California State University, Northridge; Chapman University; Columbia College Chicago; Columbia University; Community College of Aurora; Emerson College; Feirstein Graduate School of Cinema; Florida State University; Hofstra University; and Ithaca College. Each school offers unique opportunities and resources for aspiring filmmakers. This article provides a brief overview of several universities and film schools in the United States and Canada, emphasizing their programs and resources for students interested in pursuing careers in the entertainment industry. [Extracted from the article]

Published
2024

37. A Machine Learning Approach

Author

Bertsimas, Dimitris, Zhuo, Daisy, Dunn, Jack, Levine, Jordan, Zuccarelli, Eugenio, Smyrnakis, Nikos, Tobota, Zdzislaw, Maruszewski, Bohdan, Fragata, Jose, Sarris, George E., and NOVA Medical School|Faculdade de Ciências Médicas (NMS|FCM)

Subjects
congenital heart surgery, statistics-survival analysis, Surgery, statistics-risk analysis/modeling, Pediatrics, Perinatology, and Child Health, artificial intelligence, outcomes, Cardiology and Cardiovascular Medicine
Abstract

Funding Information: The authors wish to gratefully acknowledge the contributions of all ECDB participating surgeons and centers, as the contributions of the data concerning their patients who had surgery with CHD over the years have made this study possible. The author(s) received no financial support for the research, authorship, and/or publication of this article. Publisher Copyright: © The Author(s) 2021. 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. publishersversion published

Published
2021

43. sj-docx-1-pch-10.1177_21501351211051227 - Supplemental material for Benchmarking in Congenital Heart Surgery Using Machine Learning-Derived Optimal Classification Trees

Author

Bertsimas, Dimitris, Zhuo, Daisy, Levine, Jordan, Dunn, Jack, Tobota, Zdzislaw, Maruszewski, Bohdan, Fragata, Jose, and Sarris, George E

Subjects
FOS: Clinical medicine, Cardiology, 110323 Surgery, 111403 Paediatrics
Abstract

Supplemental material, sj-docx-1-pch-10.1177_21501351211051227 for Benchmarking in Congenital Heart Surgery Using Machine Learning-Derived Optimal Classification Trees by Dimitris Bertsimas, Daisy Zhuo, Jordan Levine, Jack Dunn, Zdzislaw Tobota, Bohdan Maruszewski, Jose Fragata and George E Sarris in World Journal for Pediatric and Congenital Heart Surgery

Published
2021
Full Text
View/download PDF

44. Supplemental Material, sj-docx-1-pch-10.1177_21501351211007106 - Adverse Outcomes Prediction for Congenital Heart Surgery: A Machine Learning Approach

Author

Bertsimas, Dimitris, Zhuo, Daisy, Dunn, Jack, Levine, Jordan, Zuccarelli, Eugenio, Smyrnakis, Nikos, Tobota, Zdzislaw, Maruszewski, Bohdan, Fragata, Jose, and Sarris, George E.

Subjects
FOS: Clinical medicine, Cardiology, 110323 Surgery, 111403 Paediatrics
Abstract

Supplemental Material, sj-docx-1-pch-10.1177_21501351211007106 for Adverse Outcomes Prediction for Congenital Heart Surgery: A Machine Learning Approach by Dimitris Bertsimas, Daisy Zhuo, Jack Dunn, Jordan Levine, Eugenio Zuccarelli, Nikos Smyrnakis, Zdzislaw Tobota, Bohdan Maruszewski, Jose Fragata and George E. Sarris in World Journal for Pediatric and Congenital Heart Surgery

Published
2021
Full Text
View/download PDF

45. Supplemental Material, sj-pptx-1-pch-10.1177_21501351211007106 - Adverse Outcomes Prediction for Congenital Heart Surgery: A Machine Learning Approach

Author

Bertsimas, Dimitris, Zhuo, Daisy, Dunn, Jack, Levine, Jordan, Zuccarelli, Eugenio, Smyrnakis, Nikos, Tobota, Zdzislaw, Maruszewski, Bohdan, Fragata, Jose, and Sarris, George E.

Subjects
FOS: Clinical medicine, Cardiology, 110323 Surgery, 111403 Paediatrics
Abstract

Supplemental Material, sj-pptx-1-pch-10.1177_21501351211007106 for Adverse Outcomes Prediction for Congenital Heart Surgery: A Machine Learning Approach by Dimitris Bertsimas, Daisy Zhuo, Jack Dunn, Jordan Levine, Eugenio Zuccarelli, Nikos Smyrnakis, Zdzislaw Tobota, Bohdan Maruszewski, Jose Fragata and George E. Sarris in World Journal for Pediatric and Congenital Heart Surgery

Published
2021
Full Text
View/download PDF

46. Targeted Workup after Initial Febrile Urinary Tract Infection: Using a Novel Machine Learning Model to Identify Children Most Likely to Benefit from Voiding Cystourethrogram

Author

Massachusetts Institute of Technology. Operations Research Center, Estrada, CR, Nelson, CP, Wang, HH, Bertsimas, Dimitris J, Dunn, Jack William, Li, Michael, Zhuo, Ying Daisy, MIT ORC Personalized Medicine Group, Advanced Analytics Group of Pediatric Urology, Massachusetts Institute of Technology. Operations Research Center, Estrada, CR, Nelson, CP, Wang, HH, Bertsimas, Dimitris J, Dunn, Jack William, Li, Michael, Zhuo, Ying Daisy, MIT ORC Personalized Medicine Group, and Advanced Analytics Group of Pediatric Urology

Abstract

Purpose:Significant debate persists regarding the appropriate workup in children with an initial urinary tract infection. Greatly preferable to all or none approaches in the current guideline would be a model to identify children at highest risk for a recurrent urinary tract infection plus vesicoureteral reflux to allow for targeted voiding cystourethrogram while children at low risk could be observed. We sought to develop a model to predict the probability of recurrent urinary tract infection associated vesicoureteral reflux in children after an initial urinary tract infection.Materials and Methods:We included subjects from the RIVUR (Randomized Intervention for Children with Vesico-Ureteral Reflux) and CUTIE (Careful Urinary Tract Infection Evaluation) trials in our study, excluding the prophylaxis treatment arm of the RIVUR. The main outcome was defined as recurrent urinary tract infection associated vesicoureteral reflux. Missing data were imputed using optimal tree imputation. Data were split into training, validation and testing sets. Machine learning algorithm hyperparameters were tuned by the validation set with fivefold cross-validation.Results:A total of 500 subjects, including 305 from the RIVUR and 195 from the CUTIE trials, were included in study. Of the subjects 90% were female and mean ± SD age was 21 ± 19 months. A recurrent urinary tract infection developed in 72 patients, of whom 53 also had vesicoureteral reflux (10.6% of the total). The final model included age, sex, race, weight, the systolic blood pressure percentile, dysuria, the urine albumin-to-creatinine ratio, prior antibiotic exposure and current medication. The model predicted recurrent urinary tract infection associated vesicoureteral reflux with an AUC of 0.761 (95% CI 0.714-0.808) in the testing set.Conclusions:Our predictive model using a novel machine learning algorithm provided promising performance to facilitate individualized treatment of children with an initial urinary tract in

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results