Author: doyubkim

Personalized Risk Prediction for 30-Day Readmissions With Venous Thromboembolism Using Machine Learning

doyubkim

Jung In Park1, Doyub Kim2, Jung-Ah Lee3, 
Kai Zheng4, Alpesh Amin5

  1. Assistant Professor, Sue & Bill Gross School of Nursing, University of California, Irvine, CA.
  2. Principal Software Engineer, NVIDIA, Santa Clara, CA.
  3. Associate Professor, Sue & Bill Gross School of Nursing, University of California, Irvine, CA.
  4. Professor, Donald Bren School of Information & Computer Sciences, University of California, Irvine, CA.
  5. Professor, School of Medicine, University of California, Irvine, CA.

Journal of Nursing Scholarship 2021 Feb 22

Abstract

Purpose: The aim of the study was to develop and validate machine learning models to predict the personalized risk for 30-day readmission with venous thromboembolism (VTE).

Design: This study was a retrospective, observational study.

Methods: We extracted and preprocessed the structured electronic health records (EHRs) from a single academic hospital. Then we developed and evaluated three prediction models using logistic regression, the balanced random forest model, and the multilayer perceptron.

Results: The study sample included 158,804 total admissions; VTE-positive cases accounted for 2,080 admissions from among 1,695 patients (1.31%). Based on the evaluation results, the balanced random forest model outperformed the other two risk prediction models.

Conclusions: This study delivered a high-performing, validated risk prediction tool using machine learning and EHRs to identify patients at high risk for VTE after discharge.

Clinical relevance: The risk prediction model developed in this study can potentially guide treatment decisions for discharged patients for better patient outcomes.

Keywords: 30-day readmission; Risk Prediction Model; electronic health records; machine learning; venous thromboembolism.

Fluid Engine Development

doyubkim

 

From the splash of breaking waves to turbulent swirling smoke, the mathematical dynamics of fluids are varied and continue to be one of the most challenging aspects of animation. Fluid Engine Development demonstrates how to create a working fluid engine through the use of particles and grids, and even a combination of the two. Core algorithms are explained from a developer’s perspective in a practical, approachable way that will not overwhelm readers. The Code Repository offers further opportunity for growth and discussion with continuously changing content and source codes. This book helps to serve as the ultimate guide to navigating complex fluid animation and development.

Project Site

Source Code from Github

Publisher’s Site

Amazon Page

Maps app and SDK for Windows 10

doyubkim

streetside

Microsoft released newly refreshed Maps app together with its SDK (which is part of Windows SDK) featuring 3D cities and Streetside experience. I led a team developing Streetside feature together with many talented people from Bing Maps and Windows (KJ Sethi, Mike Ammerlaan, Pablo Candelas Gonzalez, Roberto Bojorquez Alfaro, Seung Woo Lee, Teemu Laakso, and many others). Using the feature we released, users can explore street-level experience natively from Windows by default. Also, any developers can utilize our SDK to embed Streetside to their awesome apps.

Near-exhaustive Precomputation of Secondary Cloth Effects

doyubkim

Near-exhaustive Precomputation of Secondary Cloth Effects from Doyub Kim on Vimeo.

Doyub Kim1, Woojong Koh2, Rahul Narain2, Kayvon Fatahalian 1, Adrien Treuille1, and James F. O’Brien2

1Carnegie Mellon University
2UC Berkeley

ACM Transactions on Graphics (Proc. SIGGRAPH 2013) Vol. 32, No. 4, 87.

The central argument against data-driven methods in computer graphics rests on the curse of dimensionality: it is intractable to precompute “everything” about a complex space. In this paper, we challenge that assumption by using several thousand CPU-hours to perform a massive exploration of the space of secondary clothing effects on a character animated through a large motion graph. Our system continually explores the phase space of cloth dynamics, incrementally constructing a secondary cloth motion graph that captures the dynamics of the system. We find that it is possible to sample the dynamical space to a low visual error tolerance and that secondary motion graphs containing tens of gigabytes of raw mesh data can be compressed down to only tens of megabytes. These results allow us to capture the effect of high-resolution, off-line cloth simulation for a rich space of character motion and deliver it efficiently as part of an interactive application.

Resources

acm ACM TOG Page

bibtex Bibtex

download Download Paper (5.5 MB)

slide Download Presentation Slides

download Video

Near-exhaustive Precomputation of Secondary Cloth Effects

Press

TechCrunch – Researchers Create “Near-Exhaustive,” Ultra-Realistic Cloth Simulation
CNET – Computers sweat for 4,554 hours to simulate cloth movement

Baroclinic Turbulence with Varying Density and Temperature

doyubkim

Baroclinic Turbulence with Varying Density and Temperature from Doyub Kim on Vimeo.

Doyub Kim1, Seung Woo Lee2, Oh-young Song3, and Hyeong-Seok Ko4

1Carnegie Mellon University
2Youngwoo CNI
3Sejong University
4Seoul National University

IEEE Transactions on Visualization and Computer Graphics, Sept. 2012 (Vol. 18, No. 9) pp. 1488-1495.

The explosive or volcanic scenes in motion pictures involve complex turbulent flow as its temperature and density vary in space. To simulate this turbulent flow of an inhomogeneous fluid, we propose a simple and efficient framework. Instead of explicitly computing the complex motion of this fluid dynamical instability, we first approximate the average motion of the fluid. Then, the high-resolution dynamics is computed using our new extended version of the vortex particle method with baroclinity. This baroclinity term makes turbulent effects by generating new vortex particles according to temperature/density distributions. Using our method, we efficiently simulated a complex scene with varying density and temperature.

Resources

ieee IEEE TVCG Page

bibtex Bibtex

download Download Paper (15.5MB)

A Practical Simulation of Dispersed Bubble Flow

doyubkim

A Practical Simulation of Dispersed Bubble Flow from Doyub Kim on Vimeo.

Doyub Kim1, Oh-young Song2, and Hyeong-Seok Ko1

1Seoul National University
2Sejong University

ACM Transactions on Graphics (Proc. SIGGRAPH 2010) Vol. 29, No. 4, 70.

In this paper, we propose a simple and efficient framework for simulating dispersed bubble flow. Instead of modeling the complex hydrodynamics of numerous small bubbles explicitly, our method approximates the average motion of these bubbles using a continuum multiphase solver. Then, the subgrid interactions among bubbles are computed using our new stochastic solver. Using the proposed scheme, we can efficiently simulate complex scenes with millions of bubbles.

Resources

acm ACM TOG Page / ACM SIGGRAPH Page

bibtex Bibtex

download Download Paper (7.27MB)

slide Download Presentation Slides

youtube YouTube

download Video (Xvid codec required)

A Practical Simulation of Dispersed Bubble Flow

download Images

agentbunny

Stretching and Wiggling Liquids

doyubkim

Stretching and Wiggling Liquids from Doyub Kim on Vimeo.

Doyub Kim1, Oh-young Song2, and Hyeong-Seok Ko1

1Seoul National University
2Sejong University

ACM Transactions on Graphics (Proc. SIGGRAPH Asia 2009) Vol. 28, No. 5, 120.

This paper presents a novel framework for simulating the stretching and wiggling of liquids. We demonstrate that complex phase-interface dynamics can be effectively simulated by introducing the Eulerian vortex sheet method, which focuses on the vorticity at the interface (rather than the whole domain). We extend this model to provide user control for the production of visual effects. Then, the generated fluid flow creates complex surface details, such as thin and wiggling fluid sheets. To capture such high-frequency features efficiently, this work employs a denser grid for surface tracking in addition to the (coarser) simulation grid. In this context, the paper proposes a filter, called the liquid-biased filter, which is able to downsample the surface in the high-resolution grid into the coarse grid without unrealistic volume loss resulting from aliasing error. The proposed method, which runs on a single PC, realistically reproduces complex fluid scenes.

Resources

bibtex Bibtex

download Download Paper (High Res) (21.74MB)

download Download Paper (Low Res) (4.33MB)

slide Download Presentation Slides

youtube YouTube

download Video (Xvid codec required)

Stretching and Wiggling Liquid

download Images

splashshower

Press

New Scientist – Triple Shadows and Fake Reflections: Future Graphics

A Semi-Lagrangian CIP Fluid Solver without Dimensional Splitting

doyubkim

A Semi-Lagrangian CIP Fluid Solver without Dimensional Splitting

Doyub Kim1, Oh-young Song2, and Hyeong-Seok Ko1

1Seoul National University
2Sejong University

Computer Graphics Forum (Proc. Eurographics), April 2008 (Vol. 27, No. 2) pp. 467-475.

In this paper, we propose a new constrained interpolation profile (CIP) method that is stable and accurate but requires less amount of computation compared to existing CIP-based solvers. CIP is a high-order fluid advection solver that can reproduce rich details of fluids. It has third-order accuracy but its computation is performed over a compact stencil. These advantageous features of CIP are, however, diluted by the following two shortcomings: (1) CIP contains a defect in the utilization of the grid data, which makes the method suitable only for simulations with a tight CFL restriction; and (2) CIP does not guarantee unconditional stability. There have been several attempts to fix these problems in CIP, but they have been only partially successful. The solutions that fixed both problems ended up introducing other undesirable features, namely increased computation time and/or reduced accuracy. This paper proposes a novel modification of the original CIP method that fixes all of the above problems without increasing the computational load or reducing the accuracy. Both quantitative and visual experiments were performed to test the performance of the new CIP in comparison to existing fluid solvers. The results show that the proposed method brings significant improvements in both accuracy and speed.

Resources

download Download Paper (3.37MB)

download Download Interpolation Codes (2D/3D)

download Videos

venusrising smokebunny dropbreaking dam

Eulerian Motion Blur

doyubkim

Eulerian Motion Blur

Doyub Kim and Hyeong-Seok Ko

Seoul National University

In Eurographics Workshop on Natural Phenomena, 2007,
Poster at ACM SIGGRAPH / Eurographics Symposium on Computer Animation, 2007.

This paper describes a motion blur technique which can be applied to rendering fluid simulations that are carried out in the Eulerian framework. Existing motion blur techniques can be applied to rigid bodies, deformable solids, clothes, and several other kinds of objects, and produce satisfactory results. As there is no specific reason to discriminate fluids from the above objects, one may consider applying an existing motion blur technique to render fluids. However, here we show that existing motion blur techniques are intended for simulations carried out in the Lagrangian framework, and are not suited to Eulerian simulations. Then, we propose a new motion blur technique that is suitable for rendering Eulerian simulations.

Resources

download Download Paper (430KB)

download Download Poster (815KB)

video Video

water drop