A5061359226- Machine Learning in Healthcare
- Data Management and Algorithms
- Artificial Intelligence in Healthcare
- Data Mining Algorithms and Applications
- Recommender Systems and Techniques
- Shoulder Injury and Treatment
- Data Visualization and Analytics
- Explainable Artificial Intelligence (XAI)
- Sepsis Diagnosis and Treatment
- Heart Failure Treatment and Management
- Complex Network Analysis Techniques
- Evolutionary Algorithms and Applications
- Artificial Intelligence in Healthcare and Education
- Mobile Health and mHealth Applications
- Video Analysis and Summarization
- Caching and Content Delivery
- Geographic Information Systems Studies
- Spam and Phishing Detection
- Anomaly Detection Techniques and Applications
- Data Stream Mining Techniques
- Human Mobility and Location-Based Analysis
- Cloud Computing and Resource Management
- Advanced Image and Video Retrieval Techniques
- Traffic Prediction and Management Techniques
- Ethics and Social Impacts of AI
University of Washington
2013-2024
University of Washington Tacoma
2013-2023
Seattle University
2009-2023
Behavioral Tech Research, Inc.
2018-2021
Clinical Orthopaedics and Related Research
2020
Exactech (France)
2020
Committee on Publication Ethics
2020
Washington Center
2018
University of Luxembourg
2013
Microsoft Research (United Kingdom)
2013
This tutorial extensively covers the definitions, nuances, challenges, and requirements for design of interpretable explainable machine learning models systems in healthcare. We discuss many uses which are needed healthcare how they should be deployed. Additionally, we explore landscape recent advances to address challenges model interpretability also describe one would go about choosing right learnig algorithm a given problem
This tutorial extensively covers the definitions, nuances, challenges, and requirements for design of interpretable explainable machine learning models systems in healthcare. We discuss many uses which are needed healthcare how they should be deployed. Additionally, we explore landscape recent advances to address challenges model interpretability also describe one would go about choosing right learnig algorithm a given problem
Ranking microblogs, such as tweets, search results for a query is challenging, among other things because of the sheer amount microblogs that are being generated in real time, well short length each individual microblog.In this paper, we describe several new strategies ranking real-time engine.Evaluating these non-trivial due to lack publicly available ground truth validation dataset.We have therefore developed framework obtain data, evaluation measures assess accuracy proposed...
By comparing and extending several well-known trust-enhanced techniques for recommending controversial reviews from Epinions.com, the authors provide first experimental study of using distrust in recommendation process.
Developing holistic predictive modeling solutions for risk prediction is extremely challenging in healthcare informatics. Risk involves integration of clinical factors with socio-demographic factors, health conditions, disease parameters, hospital care quality and a variety variables specific to each provider making the task increasingly complex. Unsurprisingly, many such need be extracted independently from different sources, integrated back improve modeling. Such sources are typically...
Abstract Background Machine learning techniques can identify complex relationships in large healthcare datasets and build prediction models that better inform physicians ways assist patient treatment decision-making. In the domain of shoulder arthroplasty, machine appears to have potential anticipate patients’ results after surgery, but this has not been well explored. Questions/purposes (1) What is accuracy predict American Shoulder Elbow Surgery (ASES), University California Los Angeles...
The issue of bias and fairness in healthcare has been around for centuries. With the integration AI potential to discriminate perpetuate unfair biased practices increases many folds tutorial focuses on challenges, requirements opportunities area various nuances associated with it. problem as a multi-faceted systems level that necessitates careful different notions corresponding concepts machine learning is elucidated via real world examples.
The increasing availability of digital health records should ideally improve accountability in healthcare. In this context, the study predictive modeling healthcare costs forms a foundation for accountable care, at both population and individual patient-level care. research we use machine learning algorithms accurate predictions on publicly available claims survey data. Specifically, investigate regression trees, M5 model trees random forest, to predict patients given their prior medical...
Congestive Heart Failure (CHF) is a serious chronic condition often leading to 50% mortality within 5 years. Improper treatment and post-discharge care of CHF patients leads repeat frequent hospitalizations (i.e., readmissions). Accurately predicting patient's risk-of-readmission enables care-providers plan resources, perform factor analysis, improve patient quality life. In this paper, we describe supervised learning framework, Dynamic Hierarchical Classification (DHC) for prediction....
Effectiveness of MapReduce as a big data processing framework depends on efficiencies scale for both map and reduce phases. While most tasks are preemptive parallelizable, the typically not easily decomposed often become bottleneck due to constraints locality task complexity. By assuming that non-parallelizable, we study offline scheduling minimizing makespan total completion time, respectively. Both non-preemptive considered. On minimization, version design an algorithm prove its...
Machine Learning (ML) techniques now impact a wide variety of domains. Highly regulated industries such as healthcare and finance have stringent compliance data governance policies around sharing. Advances in secure multiparty computation (SMC) for privacy-preserving machine learning (PPML) can help transform these by allowing ML computations over encrypted with personally identifiable information (PII). Yet very little SMC-based PPML has been put into practice so far. In this paper we...
Collaborative filtering recommender systems are typically unable to generate adequate recommendations for newcomers. Empirical evidence suggests that the incorporation of a trust network among users system can significantly help alleviate this problem. Hence, highly encouraged connect other expand network, but choosing whom is often difficult task. Given impact choice has on delivered recommendations, it critical guide newcomers through early stage connection process. In paper, we identify...
Generating adequate recommendations for newcomers is a hard problem recommender system (RS) due to lack of detailed user profiles and social preference data. Empirical evidence suggests that the incorporation trust network among users RS can leverage such 'cold start' (CS) recommendations. Hence, new should be encouraged connect as soon possible. But whom to? Given impact this choice has on delivered recommendations, it critical guide through early stage connection process. In paper, we...
A particularly challenging task for recommender systems (RSs) is deciding whether to recommend an item that received a variety of high and low scores from its users. RSs incorporate trust network among their users have the potential make more personalized recommendations such controversial items (CIs) compared collaborative filtering (CF) based systems, provided they succeed in utilizing information advantage. In this paper, we formalize concept CIs RSs. We then compare performance several...
The 20th ACM SIGSPATIAL Conference on Advances in Geographic Information Systems (GIS) was held November of 2012. In conjunction with this conference, we organized the conference's first competition, called GIS Cup subject competition map matching, which is problem correctly matching a sequence noisy GPS points to roads. We describe details contest, results and lessons learned running contest like this.
Electronic sensors and various digital devices have been quite successful in improving collection of physical activity data a pervasive manner, we believe that advances dietary assessment can be achieved using similar strategies. Dietary is critical yet understudied component within the domain recent electronic health records management. The design system for real-time recording food intake requires considerable research to optimize both characteristics procedures, rigorous validation...