Predictive Analysis of Diabetes Dedicated Social Networks

Summary

According to the National Diabetes Statistics Report by the Center for Disease Control and Prevention released in 2017, 30.3 million people in the United States have diabetes mellitus (diabetes for short), a number that makes up 9.4% of the country’s population. Diabetes remains one of the leading causes of death in the United States and has incurred hundreds of billion dollars of economic loss (estimated to be $245 billion). In the face of such alarming statistics, the American Diabetes Association is treating diabetes as an epidemic that is projected to affect one in three Americans by 2050.

As the population of people with diabetes continues to grow, various online social networks dedicated to this disease have been emerging. The popularity of these networks can be attributed to the positive effects that they could have on patients in terms of forming support groups, exchanging personal experience, seeking help from one another, sharing news pertinent to diabetes, etc. To date, the state of practice of these diabetes dedicated social networks has been essentially devoted to such exploratory tasks, with each social network operating on its own. Despite the success of such practice, the predictive connection between a patient’s social activities on these networks and his/her measurements of biomarkers largely remains unknown.

The PI proposes a paradigm shift for diabetes dedicated social networks, from exploration to prediction. The overall goal of this project is to harness diabetes patients’ online social behaviors from multiple networks to predict their biomarker measurements. It consists of four complementary research thrusts, including (1) comprehensive social behavior feature extraction, (2) diabetes biomarker measurements extraction and densification, (3) connection between social behaviors and diabetes biomarkers, and (4) algorithmic and clinical evaluations.

Publications

Book

A. Nelakurthi, J. He. Social Media Analytics for User Behavior Modeling: A Task Heterogeneity Perspective. CRC Taylor and Francis Group, February 2020

Journals

X. Liu, J. He, W Min, and H. Yang. Missing Information Imputation for Disease-dedicated Social Networks with Heterogeneous Auxiliary Data. IISE Transactions on Healthcare Systems Engineering

Conferences

Y. Qi, Y. Ban, and J. He. Neural Bandit with Arm Group Graph. KDD 2022
Y. Ban, Y. Zhang, H. Tong, A. Banerjee, and J. He. Improved Algorithms for Neural Active Learning. NeurIPS 2022 [NeurIPS Scholar Award]
Z. Wu, and J. He. Fairness-aware Model-agnostic Positive and Unlabeled Learning. ACM FAccT 2022 Distinguished Paper Award
Y. Ban, Y. Yan, A. Banerjee, and J. He. EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits. ICLR 2022
Y. Zhou, J. Xu, J. Wu, Z. Taghavi, E. Korpeoglu, K. Achan, and J. He. PURE: Positive-Unlabeled Recommendation with Generative Adversarial Network. KDD 2021
J. Wu, and J. He. Indirect Invisible Poisoning Attacks on Domain Adaptation. KDD 2021
Y. Ban, J. He, and C.B. Cook. Multi-facet Contextual Bandits: A Neural Network Perspective. KDD 2021
L. Zheng, Y. Cheng, H. Yang, N. Cao, and J. He. Deep Co-Attention Network for Multi-View Subspace Learning. WWW 2021
Y. Ban, and J. He. Local Clustering in Contextual Multi-Armed Bandits. WWW 2021
H. Wang, C. Zhou, C. Yang, H. Yang, and J. He. Controllable Gradient Item Retrieval. WWW 2021
D. Fu, and J. He. SDG: A Simplified and Dynamic Graph Neural Network. SIGIR 2021
J. Li, L. Zheng, Y. Zhou, and J. He. Outlier Impact Characterization for Time Series Data. AAAI 2021
D. Zhou, L. Zheng, J. Han, and J. He. A Data Driven Graph Generative Model for Temporal Interaction Networks. KDD 2020
Y. Ban, and J. He. Generic Outlier Detection in Multi-Armed Bandit. KDD 2020
D. Fu, D. Zhou, and J. He. Local Motif Clustering on Time-Evolving Graphs. KDD 2020
D. Fu, Z. Xu, B. Li, H. Tong, and J. He. A View-Adversarial Framework for Multi-View Network Embedding. CIKM 2020
Y. Zhou, A. Nelakurthi, R. Maciejewski, W. Fan, and J. He. Crowd Teaching with Imperfect Labels. WWW 2020
D. Zhou, L. Zheng, Y. Zhu, J. Li, and J. He. Domain Adaptive Multi-Modality Neural Attention Network for Financial Forecasting. WWW 2020
Z. Liu, D. Zhou, Y. Zhu, J. Gu, and J. He. Towards Fine-Grained Temporal Network Representation via Time-Reinforced Random Walk. AAAI 2020
J. Wu, and J. He. Scalable Manifold-Regularized Attributed Network Embedding via Maximum Mean Discrepancy. CIKM 2019
Z. Liu, D. Zhou, and J. He. Towards Explainable Representation of Time-Evolving Graphs via Spatial-Temporal Graph Attention Networks. CIKM 2019
X. Liu, J. He, S. Duddy, and L. O’Sullivan. Convolution-Consistent Collective Matrix Completion. CIKM 2019

Tutorials

Source Code

Ban et al., NeurIPS'22: https://github.com/matouk98/I-NeurAL
Qi et al., KDD'22: https://github.com/yunzhe0306/AGG-UCB
Wu et al., FAccT'22: https://github.com/hhhiddleston/fairpul
Ban et al., ICLR'22: https://github.com/banyikun/EE-Net-ICLR-2022
Zhou et al., KDD'21: https://drive.google.com/file/d/1f82giul6W1nAtposWdVy9z1G6lXwkHxT/view
Ban et al., KDD'21: https://github.com/banyikun/KDD2021_MuFasa
Wu et al., KDD'21: https://github.com/jwu4sml/I2Attack
Ban et al., WWW'21: https://github.com/banyikun/LOCB
Zheng et al., WWW'21: https://github.com/Leo02016/ANTS
Wang et al., WWW'21: https://github.com/haonan3/CGIR
Fu et al., SIGIR'21: https://github.com/DongqiFu/SDG
Fu et al., KDD'20: https://github.com/DongqiFu/L-MEGA
Ban et al., KDD'20: https://anonymous.4open.science/r/8f096b64-734d-4718-b96b-c3f8ec6d338d/
Zhou et al., KDD'20: https://github.com/davidchouzdw/TagGen
Fu et al., CIKM'20: https://github.com/DongqiFu/VANE
Zhou et al., WWW'20: https://github.com/arunreddy/vader
Liu et al., AAAI'20 paper: http://publish.illinois.edu/daweizhou/files/2020/02/FiGTNE.zip
Wu et al., CIKM'19: https://github.com/jwu4sml/MARINE
Liu et al., CIKM'19: http://publish.illinois.edu/daweizhou/files/2019/11/STANE.zip