1
|
Assis de Souza A, Stubbs AP, Hesselink DA, Baan CC, Boer K. Cherry on Top or Real Need? A Review of Explainable Machine Learning in Kidney Transplantation. Transplantation 2024:00007890-990000000-00768. [PMID: 38773859 DOI: 10.1097/tp.0000000000005063] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/24/2024]
Abstract
Research on solid organ transplantation has taken advantage of the substantial acquisition of medical data and the use of artificial intelligence (AI) and machine learning (ML) to answer diagnostic, prognostic, and therapeutic questions for many years. Nevertheless, despite the question of whether AI models add value to traditional modeling approaches, such as regression models, their "black box" nature is one of the factors that have hindered the translation from research to clinical practice. Several techniques that make such models understandable to humans were developed with the promise of increasing transparency in the support of medical decision-making. These techniques should help AI to close the gap between theory and practice by yielding trust in the model by doctors and patients, allowing model auditing, and facilitating compliance with emergent AI regulations. But is this also happening in the field of kidney transplantation? This review reports the use and explanation of "black box" models to diagnose and predict kidney allograft rejection, delayed graft function, graft failure, and other related outcomes after kidney transplantation. In particular, we emphasize the discussion on the need (or not) to explain ML models for biological discovery and clinical implementation in kidney transplantation. We also discuss promising future research paths for these computational tools.
Collapse
Affiliation(s)
- Alvaro Assis de Souza
- Department of Internal Medicine, Erasmus MC Transplant Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands
| | - Andrew P Stubbs
- Department of Pathology and Clinical Bioinformatics, Erasmus MC Stubbs Group, University Medical Center Rotterdam, Rotterdam, the Netherlands
| | - Dennis A Hesselink
- Department of Internal Medicine, Erasmus MC Transplant Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands
| | - Carla C Baan
- Department of Internal Medicine, Erasmus MC Transplant Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands
| | - Karin Boer
- Department of Internal Medicine, Erasmus MC Transplant Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands
| |
Collapse
|
2
|
Wu Y, Xiang C, Wang Z, Fang Y. Interpretable prediction models for disability in older adults with hypertension: the Chinese Longitudinal Healthy Longevity and Happy Family Study. Psychogeriatrics 2024; 24:645-654. [PMID: 38514389 DOI: 10.1111/psyg.13112] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/01/2023] [Revised: 02/14/2024] [Accepted: 03/05/2024] [Indexed: 03/23/2024]
Abstract
BACKGROUND Older adults with hypertension have a high risk of disability, while an accurate risk prediction model is still lacking. This study aimed to construct interpretable disability prediction models for older Chinese with hypertension based on multiple time intervals. METHODS Data were collected from the Chinese Longitudinal Healthy Longevity and Happy Family Study for 2008-2018. A total of 1602, 1108, and 537 older adults were included for the periods of 2008-2012, 2008-2014, and 2008-2018, respectively. Disability was measured by basic activities of daily living. Least absolute shrinkage and selection operator (LASSO) was applied for feature selection. Five machine learning algorithms combined with LASSO set and full-variable set were used to predict 4-, 6-, and 10-year disability risk, respectively. Area under the receiver operating characteristic curve was used as the main metric for selection of the optimal model. SHapley Additive exPlanations (SHAP) was used to explore important predictors of the optimal model. RESULTS Random forest in full-variable set and XGBoost in LASSO set were the optimal models for 4-year prediction. Support vector machine was the optimal model for 6-year prediction on both sets. For 10-year prediction, deep neural network in full variable set and logistic regression in LASSO set were optimal models. Age ranked the most important predictor. Marital status, body mass index, score of Mini-Mental State Examination, and psychological well-being score were also important predictors. CONCLUSIONS Machine learning shows promise in screening out older adults at high risk of disability. Disability prevention strategies should specifically focus on older patients with unfortunate marriage, high BMI, and poor cognitive and psychological conditions.
Collapse
Affiliation(s)
- Yafei Wu
- School of Public Health, Xiamen University, Xiamen, China
- Key Laboratory of Health Technology Assessment of Fujian Province, Xiamen, China
| | - Chaoyi Xiang
- School of Public Health, Xiamen University, Xiamen, China
- Key Laboratory of Health Technology Assessment of Fujian Province, Xiamen, China
| | - Zongjie Wang
- School of Public Health, Xiamen University, Xiamen, China
- Key Laboratory of Health Technology Assessment of Fujian Province, Xiamen, China
| | - Ya Fang
- School of Public Health, Xiamen University, Xiamen, China
- Key Laboratory of Health Technology Assessment of Fujian Province, Xiamen, China
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China
| |
Collapse
|
3
|
Rieckmann A, Nielsen S, Dworzynski P, Amini H, Mogensen SW, Silva IB, Chang AY, Arah OA, Samek W, Rod NH, Ekstrøm CT, Benn CS, Aaby P, Fisker AB. Discovering Subgroups of Children With High Mortality in Urban Guinea-Bissau: Exploratory and Validation Cohort Study. JMIR Public Health Surveill 2024; 10:e48060. [PMID: 38592761 DOI: 10.2196/48060] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2023] [Revised: 12/22/2023] [Accepted: 01/23/2024] [Indexed: 04/10/2024] Open
Abstract
BACKGROUND The decline in global child mortality is an important public health achievement, yet child mortality remains disproportionally high in many low-income countries like Guinea-Bissau. The persisting high mortality rates necessitate targeted research to identify vulnerable subgroups of children and formulate effective interventions. OBJECTIVE This study aimed to discover subgroups of children at an elevated risk of mortality in the urban setting of Bissau, Guinea-Bissau, West Africa. By identifying these groups, we intend to provide a foundation for developing targeted health interventions and inform public health policy. METHODS We used data from the health and demographic surveillance site, Bandim Health Project, covering 2003 to 2019. We identified baseline variables recorded before children reached the age of 6 weeks. The focus was on determining factors consistently linked with increased mortality up to the age of 3 years. Our multifaceted methodological approach incorporated spatial analysis for visualizing geographical variations in mortality risk, causally adjusted regression analysis to single out specific risk factors, and machine learning techniques for identifying clusters of multifactorial risk factors. To ensure robustness and validity, we divided the data set temporally, assessing the persistence of identified subgroups over different periods. The reassessment of mortality risk used the targeted maximum likelihood estimation (TMLE) method to achieve more robust causal modeling. RESULTS We analyzed data from 21,005 children. The mortality risk (6 weeks to 3 years of age) was 5.2% (95% CI 4.8%-5.6%) for children born between 2003 and 2011, and 2.9% (95% CI 2.5%-3.3%) for children born between 2012 and 2016. Our findings revealed 3 distinct high-risk subgroups with notably higher mortality rates, children residing in a specific urban area (adjusted mortality risk difference of 3.4%, 95% CI 0.3%-6.5%), children born to mothers with no prenatal consultations (adjusted mortality risk difference of 5.8%, 95% CI 2.6%-8.9%), and children from polygamous families born during the dry season (adjusted mortality risk difference of 1.7%, 95% CI 0.4%-2.9%). These subgroups, though small, showed a consistent pattern of higher mortality risk over time. Common social and economic factors were linked to a larger share of the total child deaths. CONCLUSIONS The study's results underscore the need for targeted interventions to address the specific risks faced by these identified high-risk subgroups. These interventions should be designed to work to complement broader public health strategies, creating a comprehensive approach to reducing child mortality. We suggest future research that focuses on developing, testing, and comparing targeted intervention strategies unraveling the proposed hypotheses found in this study. The ultimate aim is to optimize health outcomes for all children in high-mortality settings, leveraging a strategic mix of targeted and general health interventions to address the varied needs of different child subgroups.
Collapse
Affiliation(s)
- Andreas Rieckmann
- Section of Epidemiology, Department of Public Health, University of Copenhagen, Copenhagen, Denmark
| | - Sebastian Nielsen
- Bandim Health Project, INDEPTH Network, Bissau, Guinea-Bissau
- Bandim Health Project, Research unit Odense Patient Data Explorative Network (OPEN), Department of Clinical Research, Odense University Hospital and University of Southern Denmark, Odense, Denmark
| | - Piotr Dworzynski
- Novo Nordisk Foundation Center for Basic Metabolic Research, University of Copenhagen, Copenhagen, Denmark
| | - Heresh Amini
- Department of Environmental Medicine and Climate Science, Icahn School of Medicine at Mount Sinai, New York, NY, United States
- Institute for Climate Change, Environmental Health, and Exposomics, Icahn School of Medicine at Mount Sinai, New York, NY, United States
| | | | - Isaquel Bartolomeu Silva
- Bandim Health Project, INDEPTH Network, Bissau, Guinea-Bissau
- Bandim Health Project, Research unit Odense Patient Data Explorative Network (OPEN), Department of Clinical Research, Odense University Hospital and University of Southern Denmark, Odense, Denmark
| | - Angela Y Chang
- Danish Institute for Advanced Study, University of Southern Denmark, Odense, Denmark
- The Interdisciplinary Centre on Population Dynamics, University of Southern Denmark, Odense, Denmark
| | - Onyebuchi A Arah
- Department of Epidemiology, Fielding School of Public Health, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Statistics and Data Science, College of Letters and Science, University of California, Los Angeles, Los Angeles, CA, United States
- Research Unit for Epidemiology, Department of Public Health, University of Aarhus, Aarhus, Denmark
| | - Wojciech Samek
- Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, Berlin, Germany
- Department of Electrical Engineering and Computer Science, Technical University of Berlin, Berlin, Germany
- Berlin Institute for the Foundations of Learning and Data, Berlin, Germany
| | - Naja Hulvej Rod
- Section of Epidemiology, Department of Public Health, University of Copenhagen, Copenhagen, Denmark
| | - Claus Thorn Ekstrøm
- Section of Biostatistics, Department of Public Health, University of Copenhagen, Copenhagen, Denmark
| | - Christine Stabell Benn
- Bandim Health Project, INDEPTH Network, Bissau, Guinea-Bissau
- Bandim Health Project, Research unit Odense Patient Data Explorative Network (OPEN), Department of Clinical Research, Odense University Hospital and University of Southern Denmark, Odense, Denmark
- Danish Institute for Advanced Study, University of Southern Denmark, Odense, Denmark
| | - Peter Aaby
- Bandim Health Project, INDEPTH Network, Bissau, Guinea-Bissau
- Bandim Health Project, Research unit Odense Patient Data Explorative Network (OPEN), Department of Clinical Research, Odense University Hospital and University of Southern Denmark, Odense, Denmark
| | - Ane Bærent Fisker
- Bandim Health Project, INDEPTH Network, Bissau, Guinea-Bissau
- Bandim Health Project, Research unit Odense Patient Data Explorative Network (OPEN), Department of Clinical Research, Odense University Hospital and University of Southern Denmark, Odense, Denmark
| |
Collapse
|
4
|
Wang S, Zhang T, Li Z, Hong J. Exploring pollutant joint effects in disease through interpretable machine learning. JOURNAL OF HAZARDOUS MATERIALS 2024; 467:133707. [PMID: 38335621 DOI: 10.1016/j.jhazmat.2024.133707] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/25/2023] [Revised: 01/16/2024] [Accepted: 02/01/2024] [Indexed: 02/12/2024]
Abstract
Identifying the impact of pollutants on diseases is crucial. However, assessing the health risks posed by the interplay of multiple pollutants is challenging. This study introduces the concept of Pollutants Outcome Disease, integrating multidisciplinary knowledge and employing explainable artificial intelligence (AI) to explore the joint effects of industrial pollutants on diseases. Using lung cancer as a representative case study, an extreme gradient boosting predictive model that integrates meteorological, socio-economic, pollutants, and lung cancer statistical data is developed. The joint effects of industrial pollutants on lung cancer are identified and analyzed by employing the SHAP (Shapley Additive exPlanations) interpretable machine learning technique. Results reveal substantial spatial heterogeneity in emissions from CPG and ILC, highlighting pronounced nonlinear relationships among variables. The model yielded strong predictions (an R of 0.954, an RMSE of 4283, and an R2 of 0.911) and emphasized the impact of pollutant emission amounts on lung cancer responses. Diverse joint effects patterns were observed, varying in terms of patterns, regions (frequency), and the extent of antagonistic and synergistic effects among pollutants. The study provides a new perspective for exploring the joint effects of pollutants on diseases and demonstrates the potential of AI technology to assist scientific discovery.
Collapse
Affiliation(s)
- Shuo Wang
- Shandong Key Laboratory of Environmental Processes and Health, School of Environmental Science and Engineering, Shandong University, Qingdao 266237, China
| | - Tianzhuo Zhang
- Shandong Key Laboratory of Environmental Processes and Health, School of Environmental Science and Engineering, Shandong University, Qingdao 266237, China
| | - Ziheng Li
- Shandong Key Laboratory of Environmental Processes and Health, School of Environmental Science and Engineering, Shandong University, Qingdao 266237, China
| | - Jinglan Hong
- Shandong Key Laboratory of Environmental Processes and Health, School of Environmental Science and Engineering, Shandong University, Qingdao 266237, China; Shandong University Climate Change and Health Center, Public Health School, Shandong University, Jinan 250012, China.
| |
Collapse
|
5
|
Samadi ME, Guzman-Maldonado J, Nikulina K, Mirzaieazar H, Sharafutdinov K, Fritsch SJ, Schuppert A. A hybrid modeling framework for generalizable and interpretable predictions of ICU mortality across multiple hospitals. Sci Rep 2024; 14:5725. [PMID: 38459085 PMCID: PMC10923850 DOI: 10.1038/s41598-024-55577-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2023] [Accepted: 02/26/2024] [Indexed: 03/10/2024] Open
Abstract
The development of reliable mortality risk stratification models is an active research area in computational healthcare. Mortality risk stratification provides a standard to assist physicians in evaluating a patient's condition or prognosis objectively. Particular interest lies in methods that are transparent to clinical interpretation and that retain predictive power once validated across diverse datasets they were not trained on. This study addresses the challenge of consolidating numerous ICD codes for predictive modeling of ICU mortality, employing a hybrid modeling approach that integrates mechanistic, clinical knowledge with mathematical and machine learning models . A tree-structured network connecting independent modules that carry clinical meaning is implemented for interpretability. Our training strategy utilizes graph-theoretic methods for data analysis, aiming to identify the functions of individual black-box modules within the tree-structured network by harnessing solutions from specific max-cut problems. The trained model is then validated on external datasets from different hospitals, demonstrating successful generalization capabilities, particularly in binary-feature datasets where label assessment involves extrapolation.
Collapse
Affiliation(s)
- Moein E Samadi
- Institute for Computational Biomedicine, RWTH Aachen University, Aachen, Germany.
| | | | - Kateryna Nikulina
- Institute for Computational Biomedicine, RWTH Aachen University, Aachen, Germany
| | - Hedieh Mirzaieazar
- Institute for Computational Biomedicine, RWTH Aachen University, Aachen, Germany
| | | | - Sebastian Johannes Fritsch
- Department of Intensive Care Medicine, University Hospital RWTH Aachen, Aachen, Germany
- Jülich Supercomputing Centre, Forschungszentrum Jülich, Jülich, Germany
- Center for Advanced Simulation and Analytics (CASA), Forschungszentrum Jülich, Jülich, Germany
| | - Andreas Schuppert
- Institute for Computational Biomedicine, RWTH Aachen University, Aachen, Germany
| |
Collapse
|
6
|
Huber M, Bello C, Schober P, Filipovic MG, Luedi MM. Decision Curve Analysis of In-Hospital Mortality Prediction Models: The Relative Value of Pre- and Intraoperative Data For Decision-Making. Anesth Analg 2024:00000539-990000000-00733. [PMID: 38315623 DOI: 10.1213/ane.0000000000006874] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2024]
Abstract
BACKGROUND Clinical prediction modeling plays a pivotal part in modern clinical care, particularly in predicting the risk of in-hospital mortality. Recent modeling efforts have focused on leveraging intraoperative data sources to improve model performance. However, the individual and collective benefit of pre- and intraoperative data for clinical decision-making remains unknown. We hypothesized that pre- and intraoperative predictors contribute equally to the net benefit in a decision curve analysis (DCA) of in-hospital mortality prediction models that include pre- and intraoperative predictors. METHODS Data from the VitalDB database featuring a subcohort of 6043 patients were used. A total of 141 predictors for in-hospital mortality were grouped into preoperative (demographics, intervention characteristics, and laboratory measurements) and intraoperative (laboratory and monitor data, drugs, and fluids) data. Prediction models using either preoperative, intraoperative, or all data were developed with multiple methods (logistic regression, neural network, random forest, gradient boosting machine, and a stacked learner). Predictive performance was evaluated by the area under the receiver-operating characteristic curve (AUROC) and under the precision-recall curve (AUPRC). Clinical utility was examined with a DCA in the predefined risk preference range (denoted by so-called treatment threshold probabilities) between 0% and 20%. RESULTS AUROC performance of the prediction models ranged from 0.53 to 0.78. AUPRC values ranged from 0.02 to 0.25 (compared to the incidence of 0.09 in our dataset) and high AUPRC values resulted from prediction models based on preoperative laboratory values. A DCA of pre- and intraoperative prediction models highlighted that preoperative data provide the largest overall benefit for decision-making, whereas intraoperative values provide only limited benefit for decision-making compared to preoperative data. While preoperative demographics, comorbidities, and surgery-related data provide the largest benefit for low treatment thresholds up to 5% to 10%, preoperative laboratory measurements become the dominant source for decision support for higher thresholds. CONCLUSIONS When it comes to predicting in-hospital mortality and subsequent decision-making, preoperative demographics, comorbidities, and surgery-related data provide the largest benefit for clinicians with risk-averse preferences, whereas preoperative laboratory values provide the largest benefit for decision-makers with more moderate risk preferences. Our decision-analytic investigation of different predictor categories moves beyond the question of whether certain predictors provide a benefit in traditional performance metrics (eg, AUROC). It offers a nuanced perspective on for whom these predictors might be beneficial in clinical decision-making. Follow-up studies requiring larger datasets and dedicated deep-learning models to handle continuous intraoperative data are essential to examine the robustness of our results.
Collapse
Affiliation(s)
- Markus Huber
- From the Department of Anaesthesiology and Pain Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Corina Bello
- From the Department of Anaesthesiology and Pain Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Patrick Schober
- Department of Anesthesiology, Amsterdam University Medical Centres, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
| | - Mark G Filipovic
- From the Department of Anaesthesiology and Pain Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Markus M Luedi
- From the Department of Anaesthesiology and Pain Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| |
Collapse
|
7
|
Lu W, Tong Y, Zhao X, Feng Y, Zhong Y, Fang Z, Chen C, Huang K, Si Y, Zou J. Machine learning-based risk prediction of hypoxemia for outpatients undergoing sedation colonoscopy: a practical clinical tool. Postgrad Med 2024; 136:84-94. [PMID: 38314753 DOI: 10.1080/00325481.2024.2313448] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Accepted: 01/16/2024] [Indexed: 02/07/2024]
Abstract
OBJECTIVES Hypoxemia as a common complication in colonoscopy under sedation and may result in serious consequences. Unfortunately, a hypoxemia prediction model for outpatient colonoscopy has not been developed. Consequently, the objective of our study was to develop a practical and accurate model to predict the risk of hypoxemia in outpatient colonoscopy under sedation. METHODS In this study, we included patients who received colonoscopy with anesthesia in Nanjing First Hospital from July to September 2021. Risk factors were selected through the least absolute shrinkage and selection operator (LASSO). Prediction models based on logistic regression (LR), random forest classifier (RFC), extreme gradient boosting (XGBoost), support vector machine (SVM), and stacking classifier (SCLF) model were implemented and assessed by standard metrics such as the area under the receiver operating characteristic curve (AUROC), sensitivity and specificity. Then choose the best model to develop an online tool for clinical use. RESULTS We ultimately included 839 patients. After LASSO, body mass index (BMI) (coefficient = 0.36), obstructive sleep apnea-hypopnea syndrome (OSAHS) (coefficient = 1.32), basal oxygen saturation (coefficient = -0.14), and remifentanil dosage (coefficient = 0.04) were independent risk factors for hypoxemia. The XGBoost model with an AUROC of 0.913 showed the best performance among the five models. CONCLUSION Our study selected the XGBoost as the first model especially for colonoscopy, with over 95% accuracy and excellent specificity. The XGBoost includes four variables that can be quickly obtained. Moreover, an online prediction practical tool has been provided, which helps screen high-risk outpatients with hypoxemia swiftly and conveniently.
Collapse
Affiliation(s)
- Wei Lu
- School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, Nanjing, China
- Department of Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Yulan Tong
- School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, Nanjing, China
- Department of Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Xiuxiu Zhao
- Department of Anesthesiology, Periodic and Pain Medicine (APPM), Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Yue Feng
- Department of Anesthesiology, Periodic and Pain Medicine (APPM), Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Yi Zhong
- Department of Anesthesiology, Periodic and Pain Medicine (APPM), Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Zhaojing Fang
- Department of Anesthesiology, Periodic and Pain Medicine (APPM), Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Chen Chen
- Department of Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
- Department of Pharmacy, Nanjing First Hospital, China Pharmaceutical University, Nanjing, China
| | - Kaizong Huang
- Department of Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
- Department of Pharmacy, Nanjing First Hospital, China Pharmaceutical University, Nanjing, China
| | - Yanna Si
- Department of Anesthesiology, Periodic and Pain Medicine (APPM), Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Jianjun Zou
- Department of Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
- Department of Pharmacy, Nanjing First Hospital, China Pharmaceutical University, Nanjing, China
| |
Collapse
|
8
|
Kalyakulina A, Yusipov I, Moskalev A, Franceschi C, Ivanchenko M. eXplainable Artificial Intelligence (XAI) in aging clock models. Ageing Res Rev 2024; 93:102144. [PMID: 38030090 DOI: 10.1016/j.arr.2023.102144] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2023] [Revised: 11/07/2023] [Accepted: 11/23/2023] [Indexed: 12/01/2023]
Abstract
XAI is a rapidly progressing field of machine learning, aiming to unravel the predictions of complex models. XAI is especially required in sensitive applications, e.g. in health care, when diagnosis, recommendations and treatment choices might rely on the decisions made by artificial intelligence systems. AI approaches have become widely used in aging research as well, in particular, in developing biological clock models and identifying biomarkers of aging and age-related diseases. However, the potential of XAI here awaits to be fully appreciated. We discuss the application of XAI for developing the "aging clocks" and present a comprehensive analysis of the literature categorized by the focus on particular physiological systems.
Collapse
Affiliation(s)
- Alena Kalyakulina
- Institute of Biogerontology, Lobachevsky State University, Nizhny Novgorod 603022, Russia; Research Center for Trusted Artificial Intelligence, The Ivannikov Institute for System Programming of the Russian Academy of Sciences, Moscow 109004, Russia; Department of Applied Mathematics, Institute of Information Technologies, Mathematics and Mechanics, Lobachevsky State University, Nizhny Novgorod 603022, Russia.
| | - Igor Yusipov
- Institute of Biogerontology, Lobachevsky State University, Nizhny Novgorod 603022, Russia; Research Center for Trusted Artificial Intelligence, The Ivannikov Institute for System Programming of the Russian Academy of Sciences, Moscow 109004, Russia; Department of Applied Mathematics, Institute of Information Technologies, Mathematics and Mechanics, Lobachevsky State University, Nizhny Novgorod 603022, Russia
| | - Alexey Moskalev
- Institute of Biogerontology, Lobachevsky State University, Nizhny Novgorod 603022, Russia
| | - Claudio Franceschi
- Institute of Biogerontology, Lobachevsky State University, Nizhny Novgorod 603022, Russia
| | - Mikhail Ivanchenko
- Institute of Biogerontology, Lobachevsky State University, Nizhny Novgorod 603022, Russia; Department of Applied Mathematics, Institute of Information Technologies, Mathematics and Mechanics, Lobachevsky State University, Nizhny Novgorod 603022, Russia
| |
Collapse
|
9
|
Qiu W, Chen H, Kaeberlein M, Lee SI. ExplaiNAble BioLogical Age (ENABL Age): an artificial intelligence framework for interpretable biological age. THE LANCET. HEALTHY LONGEVITY 2023; 4:e711-e723. [PMID: 37944549 DOI: 10.1016/s2666-7568(23)00189-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2022] [Revised: 08/10/2023] [Accepted: 08/30/2023] [Indexed: 11/12/2023] Open
Abstract
BACKGROUND Biological age is a measure of health that offers insights into ageing. The existing age clocks, although valuable, often trade off accuracy and interpretability. We introduce ExplaiNAble BioLogical Age (ENABL Age), a computational framework that combines machine-learning models with explainable artificial intelligence (XAI) methods to accurately estimate biological age with individualised explanations. METHODS To construct the ENABL Age clock, we first predicted an age-related outcome (eg, all-cause or cause-specific mortality), and then rescaled these predictions to estimate biological age, using UK Biobank and National Health and Nutrition Examination Survey (NHANES) datasets. We adapted existing XAI methods to decompose individual ENABL Ages into contributing risk factors. For broad accessibility, we developed two versions: ENABL Age-L, based on blood tests, and ENABL Age-Q, based on questionnaire characteristics. Finally, we validated diverse ageing mechanisms captured by each ENABL Age clock through genome-wide association studies (GWAS) association analyses. FINDINGS Our ENABL Age clock was significantly correlated with chronological age (r=0·7867, p<0·0001 for UK Biobank; r=0·7126, p<0·0001 for NHANES). These clocks distinguish individuals who are healthy (ie, their ENABL Age is lower than their chronological age) from those who are unhealthy (ie, their ENABL Age is higher than their chronological age), predicting mortality more effectively than existing clocks. Groups of individuals who were unhealthy showed approximately three to 12 times higher log hazard ratio than healthy groups, as per ENABL Age. The clocks achieved high mortality prediction power with an area under the receiver operating characteristic curve of 0·8179 for 5-year mortality and 0·8115 for 10-year mortality on the UK Biobank dataset, and 0·8935 for 5-year mortality and 0·9107 for 10-year mortality on the NHANES dataset. The individualised explanations that revealed the contribution of specific characteristics to ENABL Age provided insights into the important characteristics for ageing. An association analysis with risk factors and ageing-related morbidities and GWAS results on ENABL Age clocks trained on different mortality causes showed that each clock captures distinct ageing mechanisms. INTERPRETATION ENABL Age brings an important leap forward in the application of XAI for interpreting biological age clocks. ENABL Age also carries substantial potential in practical settings, assisting medical professionals in untangling the complexity of ageing mechanisms, and potentially becoming a valuable tool in informed clinical decision-making processes. FUNDING National Science Foundation and National Institutes of Health.
Collapse
Affiliation(s)
- Wei Qiu
- Paul G Allen School of Computer Science and Engineering, University of Washington, Washington, DC, USA
| | - Hugh Chen
- Paul G Allen School of Computer Science and Engineering, University of Washington, Washington, DC, USA
| | - Matt Kaeberlein
- Department of Laboratory Medicine and Pathology, University of Washington, Washington, DC, USA
| | - Su-In Lee
- Paul G Allen School of Computer Science and Engineering, University of Washington, Washington, DC, USA.
| |
Collapse
|
10
|
Fernández-Sarmiento J, Hernández-Sarmiento R, Salazar MP, Barrera S, Castilla V, Duque C. The association between hypoalbuminemia and microcirculation, endothelium, and glycocalyx disorders in children with sepsis. Microcirculation 2023; 30:e12829. [PMID: 37639384 DOI: 10.1111/micc.12829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2023] [Revised: 08/05/2023] [Accepted: 08/20/2023] [Indexed: 08/31/2023]
Abstract
OBJECTIVE The objective of this study was to evaluate the association between serum albumin levels and microcirculation changes, glycocalyx degradation, and the clinical outcomes of interest. METHODS Observational, prospective study in children with sepsis. The primary outcome was the association between hypoalbuminemia and microcirculation disorders, endothelial activation and glycocalyx degradation using a perfused boundary region (PBR) (abnormal >2.0 μm on sublingual video microscopy) or plasma biomarkers (syndecan-1, angiopoietin-2). RESULTS A total of 125 patients with sepsis were included. The median age was 2.0 years (IQR 0.5-12.5). Children with hypoalbuminemia had more abnormal microcirculation with a higher PBR (2.16 μm [IQR 2.03-2.47] vs. 1.92 [1.76-2.28]; p = .01) and more 4-6 μm capillaries recruited (60% vs. 40%; p = .04). The low albumin group that had the worst PBR had the most 4-6 μm capillaries recruited (rho 0.29; p < .01), 48% higher Ang-2 (p = .04), worse annexin A5 (p = 0.03) and no syndecan-1 abnormalities (p = .21). Children with hypoalbuminemia and a greater percentage of blood volume in their capillaries needed mechanical ventilation more often (56.3% vs. 43.7%; aOR 2.01 95% CI 1.38-3.10: p < .01). CONCLUSIONS In children with sepsis, an association was found between hypoalbuminemia and microcirculation changes, vascular permeability, and greater endothelial glycocalyx degradation.
Collapse
Affiliation(s)
- Jaime Fernández-Sarmiento
- Department of Critical Care Medicine and Pediatrics, Universidad de La Sabana Fundación Cardioinfantil-Instituto de Cardiología, Bogotá, Colombia
| | - Ricardo Hernández-Sarmiento
- Department of Critical Care Medicine and Pediatrics, Universidad de La Sabana Fundación Cardioinfantil-Instituto de Cardiología, Bogotá, Colombia
| | - María Paula Salazar
- Department of Critical Care Medicine and Pediatrics, Universidad de La Sabana Fundación Cardioinfantil-Instituto de Cardiología, Bogotá, Colombia
| | - Sofia Barrera
- Department of Critical Care Medicine and Pediatrics, Universidad de La Sabana Fundación Cardioinfantil-Instituto de Cardiología, Bogotá, Colombia
| | - Valeria Castilla
- Department of Pediatrics Fundación Cardioinfantil-Instituo de Cardiología, Universidad del Rosario, Bogotá, Colombia
| | - Catalina Duque
- Department of Critical Care Medicine and Pediatrics, Universidad de La Sabana Fundación Cardioinfantil-Instituto de Cardiología, Bogotá, Colombia
| |
Collapse
|
11
|
Lee JY, Lee W, Cho SI. Characteristics of fatal occupational injuries in migrant workers in South Korea: A machine learning study. Heliyon 2023; 9:e20138. [PMID: 37810039 PMCID: PMC10559917 DOI: 10.1016/j.heliyon.2023.e20138] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2023] [Revised: 09/09/2023] [Accepted: 09/12/2023] [Indexed: 10/10/2023] Open
Abstract
Objective Analysis of occupational injuries is essential for developing preventive strategies. However, few studies have evaluated severe occupational injuries in migrant workers from the perspective of gender. Therefore, using a new analytical method, this study was performed to identify gender-specific characteristics associated with fatal occupational injuries among migrant workers; the interactions between these factors, were also analyzed. In addition, we compared the utility of explainable artificial intelligence (XAI) using SHapley Additive exPlanations (SHAP) with logistic regression (LR) and discuss caveats regarding its use. Materials and methods We analyzed national statistics for occupational injuries among migrant workers (n = 67,576) in South Korea between January 1, 2007, and September 30, 2018. We applied an extreme gradient boosting model and developed SHAP and LR models for comparison. Results We found clear gender differences in fatal occupational injuries among migrant workers, with males in the same occupation having a higher risk of death than females. These gender differences suggest the need for gender-specific occupational injury prevention interventions for migrant workers to reduce the mortality rate. Occupation was a significant predictor of death among female migrant workers only, with care jobs having the highest fatality risk. The occupational fatality risk of female workers would not have been identified without the performance of detailed job-specific analyses stratified by gender. The major advantages of SHAP identified in the present study were the automatic identification and analysis of interactions, ability to determine the relative contributions of each feature, and high overall performance. The major caveat when using SHAP is that causality cannot be established. Conclusion Detailed job-specific analyses stratified by gender, and interventions considering the gender of migrant workers, are necessary to reduce occupational fatality rates. The XAI approach should be considered as a complementary analytical method for epidemiological studies, as it overcomes the limitations of traditional statistical analyses.
Collapse
Affiliation(s)
- Ju-Yeun Lee
- The Department of Public Health, Graduate School of Public Health, Seoul National University, Seoul, Republic of Korea
| | - Woojoo Lee
- The Department of Public Health, Graduate School of Public Health, Seoul National University, Seoul, Republic of Korea
| | - Sung-il Cho
- The Department of Public Health, Graduate School of Public Health, Seoul National University, Seoul, Republic of Korea
- Institute of Health and Environment, Graduate School of Public Health, Seoul National University, Seoul, Republic of Korea
| |
Collapse
|
12
|
Chen RJ, Wang JJ, Williamson DFK, Chen TY, Lipkova J, Lu MY, Sahai S, Mahmood F. Algorithmic fairness in artificial intelligence for medicine and healthcare. Nat Biomed Eng 2023; 7:719-742. [PMID: 37380750 PMCID: PMC10632090 DOI: 10.1038/s41551-023-01056-8] [Citation(s) in RCA: 14] [Impact Index Per Article: 14.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2021] [Accepted: 04/13/2023] [Indexed: 06/30/2023]
Abstract
In healthcare, the development and deployment of insufficiently fair systems of artificial intelligence (AI) can undermine the delivery of equitable care. Assessments of AI models stratified across subpopulations have revealed inequalities in how patients are diagnosed, treated and billed. In this Perspective, we outline fairness in machine learning through the lens of healthcare, and discuss how algorithmic biases (in data acquisition, genetic variation and intra-observer labelling variability, in particular) arise in clinical workflows and the resulting healthcare disparities. We also review emerging technology for mitigating biases via disentanglement, federated learning and model explainability, and their role in the development of AI-based software as a medical device.
Collapse
Affiliation(s)
- Richard J Chen
- Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
- Cancer Program, Broad Institute of Harvard and Massachusetts Institute of Technology, Cambridge, MA, USA
- Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA, USA
| | - Judy J Wang
- Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
- Boston University School of Medicine, Boston, MA, USA
| | - Drew F K Williamson
- Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
- Cancer Program, Broad Institute of Harvard and Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Tiffany Y Chen
- Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
- Cancer Program, Broad Institute of Harvard and Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Jana Lipkova
- Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
- Cancer Program, Broad Institute of Harvard and Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Ming Y Lu
- Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
- Cancer Program, Broad Institute of Harvard and Massachusetts Institute of Technology, Cambridge, MA, USA
- Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA, USA
- Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Sharifa Sahai
- Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
- Cancer Program, Broad Institute of Harvard and Massachusetts Institute of Technology, Cambridge, MA, USA
- Department of Systems Biology, Harvard Medical School, Boston, MA, USA
| | - Faisal Mahmood
- Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
- Cancer Program, Broad Institute of Harvard and Massachusetts Institute of Technology, Cambridge, MA, USA.
- Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA, USA.
- Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
- Harvard Data Science Initiative, Harvard University, Cambridge, MA, USA.
| |
Collapse
|
13
|
Atuegwu NC, Mortensen EM, Krishnan-Sarin S, Laubenbacher RC, Litt MD. Prospective predictors of electronic nicotine delivery system initiation in tobacco naive young adults: A machine learning approach. Prev Med Rep 2023; 32:102148. [PMID: 36865398 PMCID: PMC9971268 DOI: 10.1016/j.pmedr.2023.102148] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2022] [Revised: 01/11/2023] [Accepted: 02/10/2023] [Indexed: 02/15/2023] Open
Abstract
The use of electronic nicotine delivery systems (ENDS) is increasing among young adults. However, there are few studies regarding predictors of ENDS initiation in tobacco-naive young adults. Identifying the risk and protective factors of ENDS initiation that are specific to tobacco-naive young adults will enable the creation of targeted policies and prevention programs. This study used machine learning (ML) to create predictive models, identify risk and protective factors for ENDS initiation for tobacco-naive young adults, and the relationship between these predictors and the prediction of ENDS initiation. We used nationally representative data of tobacco-naive young adults in the U.S drawn from the Population Assessment of Tobacco and Health (PATH) longitudinal cohort survey. Respondents were young adults (18-24 years) who had never used any tobacco products in Wave 4 and who completed Waves 4 and 5 interviews. ML techniques were used to create models and determine predictors at 1-year follow-up from Wave 4 data. Among the 2,746 tobacco-naive young adults at baseline, 309 initiated ENDS use at 1-year follow-up. The top five prospective predictors of ENDS initiation were susceptibility to ENDS, increased days of physical exercise specifically designed to strengthen muscles, frequency of social media use, marijuana use and susceptibility to cigarettes. This study identified previously unreported and emerging predictors of ENDS initiation that warrant further investigation and provided comprehensive information on the predictors of ENDS initiation. Furthermore, this study showed that ML is a promising technique that can aid ENDS monitoring and prevention programs.
Collapse
Affiliation(s)
- Nkiruka C. Atuegwu
- Department of Medicine, University of Connecticut School of Medicine, Farmington, CT 06030, USA
- Corresponding author at: University of Connecticut, Department of Medicine, 263 Farmington Avenue, Farmington, CT 06030, USA.
| | - Eric M. Mortensen
- Department of Medicine, University of Connecticut School of Medicine, Farmington, CT 06030, USA
| | - Suchitra Krishnan-Sarin
- Department of Psychiatry, Yale University School of Medicine, Connecticut Mental Health Center, 34 Park Street, New Haven, CT 06519, USA
| | - Reinhard C. Laubenbacher
- Laboratory for Systems Medicine, Department of Medicine, University of Florida, Gainesville, FL 32610, USA
| | - Mark D. Litt
- Division of Behavioral Sciences and Community Health, University of Connecticut Health Center, Farmington, CT 06030, USA
| |
Collapse
|
14
|
Settouti N, Saidi M. Preliminary analysis of explainable machine learning methods for multiple myeloma chemotherapy treatment recognition. EVOLUTIONARY INTELLIGENCE 2023. [DOI: 10.1007/s12065-023-00833-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/18/2023]
|
15
|
Sheu RK, Pardeshi MS. A Survey on Medical Explainable AI (XAI): Recent Progress, Explainability Approach, Human Interaction and Scoring System. SENSORS (BASEL, SWITZERLAND) 2022; 22:8068. [PMID: 36298417 PMCID: PMC9609212 DOI: 10.3390/s22208068] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/23/2022] [Revised: 10/18/2022] [Accepted: 10/18/2022] [Indexed: 06/16/2023]
Abstract
The emerging field of eXplainable AI (XAI) in the medical domain is considered to be of utmost importance. Meanwhile, incorporating explanations in the medical domain with respect to legal and ethical AI is necessary to understand detailed decisions, results, and current status of the patient's conditions. Successively, we will be presenting a detailed survey for the medical XAI with the model enhancements, evaluation methods, significant overview of case studies with open box architecture, medical open datasets, and future improvements. Potential differences in AI and XAI methods are provided with the recent XAI methods stated as (i) local and global methods for preprocessing, (ii) knowledge base and distillation algorithms, and (iii) interpretable machine learning. XAI characteristics details with future healthcare explainability is included prominently, whereas the pre-requisite provides insights for the brainstorming sessions before beginning a medical XAI project. Practical case study determines the recent XAI progress leading to the advance developments within the medical field. Ultimately, this survey proposes critical ideas surrounding a user-in-the-loop approach, with an emphasis on human-machine collaboration, to better produce explainable solutions. The surrounding details of the XAI feedback system for human rating-based evaluation provides intelligible insights into a constructive method to produce human enforced explanation feedback. For a long time, XAI limitations of the ratings, scores and grading are present. Therefore, a novel XAI recommendation system and XAI scoring system are designed and approached from this work. Additionally, this paper encourages the importance of implementing explainable solutions into the high impact medical field.
Collapse
Affiliation(s)
- Ruey-Kai Sheu
- Department of Computer Science, Tunghai University, No. 1727, Section 4, Taiwan Blvd, Xitun District, Taichung 407224, Taiwan
| | - Mayuresh Sunil Pardeshi
- AI Center, Tunghai University, No. 1727, Section 4, Taiwan Blvd, Xitun District, Taichung 407224, Taiwan
| |
Collapse
|
16
|
Qiu W, Chen H, Dincer AB, Lundberg S, Kaeberlein M, Lee SI. Interpretable machine learning prediction of all-cause mortality. COMMUNICATIONS MEDICINE 2022; 2:125. [PMID: 36204043 PMCID: PMC9530124 DOI: 10.1038/s43856-022-00180-x] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2022] [Accepted: 08/31/2022] [Indexed: 11/06/2022] Open
Abstract
Background Unlike linear models which are traditionally used to study all-cause mortality, complex machine learning models can capture non-linear interrelations and provide opportunities to identify unexplored risk factors. Explainable artificial intelligence can improve prediction accuracy over linear models and reveal great insights into outcomes like mortality. This paper comprehensively analyzes all-cause mortality by explaining complex machine learning models. Methods We propose the IMPACT framework that uses XAI technique to explain a state-of-the-art tree ensemble mortality prediction model. We apply IMPACT to understand all-cause mortality for 1-, 3-, 5-, and 10-year follow-up times within the NHANES dataset, which contains 47,261 samples and 151 features. Results We show that IMPACT models achieve higher accuracy than linear models and neural networks. Using IMPACT, we identify several overlooked risk factors and interaction effects. Furthermore, we identify relationships between laboratory features and mortality that may suggest adjusting established reference intervals. Finally, we develop highly accurate, efficient and interpretable mortality risk scores that can be used by medical professionals and individuals without medical expertise. We ensure generalizability by performing temporal validation of the mortality risk scores and external validation of important findings with the UK Biobank dataset. Conclusions IMPACT's unique strength is the explainable prediction, which provides insights into the complex, non-linear relationships between mortality and features, while maintaining high accuracy. Our explainable risk scores could help individuals improve self-awareness of their health status and help clinicians identify patients with high risk. IMPACT takes a consequential step towards bringing contemporary developments in XAI to epidemiology.
Collapse
Affiliation(s)
- Wei Qiu
- Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA USA
| | - Hugh Chen
- Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA USA
| | - Ayse Berceste Dincer
- Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA USA
| | | | - Matt Kaeberlein
- Department of Laboratory Medicine and Pathology, University of Washington, Seattle, WA USA
| | - Su-In Lee
- Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA USA
| |
Collapse
|