Joon Lee

SODA Conference 2022 Conference Paper

The Sparse Parity Matrix

• Amin Coja-Oghlan
• Oliver Cooley
• Mihyun Kang
• Joon Lee
• Jean Bernoulli Ravelomanana

The last decade witnessed several pivotal results on random inference problems where the aim is to learn a hidden ground truth from indirect randomised observations; much of this research has been guided by statistical physics intuition. Prominent examples include the stochastic block model, low-density parity check codes or compressed sensing. In all random inference problems studied so far the posterior distribution of the ground truth given the observations appears to enjoy a key property called “strong replica symmetry”. This means that the overlap of the posterior distribution with the ground truth (basically the number of bits that can be learned correctly) concentrates on a deterministic value. Whether this is generally true has been an open question. In this paper we discover an example of an inference problem based on a very simple random matrix over that fails to exhibit strong replica symmetry. Beyond its impact on random inference problems, the random matrix model, reminiscent of the binomial Erdős-Rényi random graph, gives rise to a natural random constraint satisfaction problem related to the intensely studied random k -XORSAT problem.

JBHI Journal 2021 Journal Article

Predicting Discharge Destination of Critically Ill Patients Using Machine Learning

• Zahra Shakeri Hossein Abad
• David M. Maslove
• Joon Lee

Decision making about discharge destination for critically ill patients is a highly subjective and multidisciplinary process, heavily reliant on the ICU care team, patients and their caregivers’ preferences, resource demand, staffing, and bed capacity. Timely identification of discharge disposition can be useful in care planning, and as a surrogate for functional status outcomes following critical illness. Although prior research has proposed methods to predict discharge destination in a critical care setting, they are limited in scope and in the generalizability of their findings. We proposed and implemented different machine learning architectures to determine the efficacy of the Acute Physiology and Chronic Health Evaluation (APACHE) IV score as well as the patient characteristics that comprise it to predict the discharge destination for critically ill patients within 24 hours of ICU admission. We conducted a retrospective study of ICU admissions within the eICU Collaborative Research Database (eICU-CRD) populated with de-identified clinical data from adult patients admitted to an ICU between 2014 and 2015. Machine learning models were developed to predict four discharge categories: death, home, nursing facility, and rehabilitation. These models were trained and tested on 115, 248 unique ICU admissions. To mitigate class imbalance, we used synthetic minority over-sampling techniques. Hierarchical and ensemble classifiers were used to further study the impact of imbalanced testing set on the performance of our predictive models. Amongst all of the tested models, XGBoost provided the best discrimination performance with an area under the receiver operating characteristic curve of 90% (recall: 71%, F1: 70%). Our findings indicate that the variables used in the APACHE IV model for estimating patient severity of illness are better predictors of hospital discharge destination than the APACHE IV score alone. Incorporating these models into clinical decision support systems may assist patients, caregivers, and the ICU team to begin disposition planning as early as possible during the hospitalization.

AIIM Journal 2011 Journal Article

Classification of healthy and abnormal swallows based on accelerometry and nasal airflow signals

• Joon Lee
• Catriona M. Steele
• Tom Chau

JMLR Journal 2010 Journal Article

Continuous Time Bayesian Network Reasoning and Learning Engine

• Christian R. Shelton
• Yu Fan
• William Lam
• Joon Lee
• Jing Xu

We present a continuous time Bayesian network reasoning and learning engine (CTBN-RLE). A continuous time Bayesian network (CTBN) provides a compact (factored) description of a continuous-time Markov process. This software provides libraries and programs for most of the algorithms developed for CTBNs. For learning, CTBN-RLE implements structure and parameter learning for both complete and partial data. For inference, it implements exact inference and Gibbs and importance sampling approximate inference for any type of evidence pattern. Additionally, the library supplies visualization methods for graphically displaying CTBNs or trajectories of evidence. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2010. ( edit, beta )