@article{li_agor_ozaltin_2024, title={Temporal pattern mining for knowledge discovery in the early prediction of septic shock}, volume={151}, ISSN={["1873-5142"]}, DOI={10.1016/j.patcog.2024.110436}, abstractNote={Temporal pattern mining can be employed to detect patterns and trends in a patient's health status as it evolves over time. However, these methods often produce an overwhelming number of patterns, impeding knowledge discovery and practical implementation in acute care settings. To address this, we propose a framework that focuses on identifying a concise set of relevant temporal patterns and static variables from electronic health records for the early prediction of septic shock. Sepsis is caused by an adverse immune response to infection that triggers widespread inflammation throughout the body, which can progress to septic shock and ultimately result in death if not treated promptly. The analysis of health state patterns in sepsis patients over time offers the potential to predict septic shock prior to its onset, enabling proactive healthcare interventions. Our framework incorporates a temporal pattern mining method and four feature selection techniques. We discover that selecting features based on a model-based wrapper approach yields the highest prediction performance among these techniques. On the other hand, the use of information value identifies more multi-state patterns with abnormal health states, providing healthcare providers with valuable indicators of patient deterioration.}, journal={PATTERN RECOGNITION}, author={Li, Ruoting and Agor, Joseph K. and Ozaltin, Osman Y.}, year={2024}, month={Jul} }
 @article{li_tobey_mayorga_caltagirone_ozaltin_2023, title={Detecting Human Trafficking: Automated Classification of Online Customer Reviews of Massage Businesses}, volume={2}, ISSN={["1526-5498"]}, DOI={10.1287/msom.2023.1196}, abstractNote={ Problem definition: Approximately 11,000 alleged illicit massage businesses (IMBs) exist across the United States hidden in plain sight among legitimate businesses. These illicit businesses frequently exploit workers, many of whom are victims of human trafficking, forced or coerced to provide commercial sex. Academic/practical relevance: Although IMB review boards like Rubmaps.ch can provide first-hand information to identify IMBs, these sites are likely to be closed by law enforcement. Open websites like Yelp.com provide more accessible and detailed information about a larger set of massage businesses. Reviews from these sites can be screened for risk factors of trafficking. Methodology: We develop a natural language processing approach to detect online customer reviews that indicate a massage business is likely engaged in human trafficking. We label data sets of Yelp reviews using knowledge of known IMBs. We develop a lexicon of key words/phrases related to human trafficking and commercial sex acts. We then build two classification models based on this lexicon. We also train two classification models using embeddings from the bidirectional encoder representations from transformers (BERT) model and the Doc2Vec model. Results: We evaluate the performance of these classification models and various ensemble models. The lexicon-based models achieve high precision, whereas the embedding-based models have relatively high recall. The ensemble models provide a compromise and achieve the best performance on the out-of-sample test. Our results verify the usefulness of ensemble methods for building robust models to detect risk factors of human trafficking in reviews on open websites like Yelp. Managerial implications: The proposed models can save countless hours in IMB investigations by automatically sorting through large quantities of data to flag potential illicit activity, eliminating the need for manual screening of these reviews by law enforcement and other stakeholders.  Funding: This work was supported by the National Science Foundation [Grant 1936331].  Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2023.1196 . }, journal={M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT}, author={Li, Ruoting and Tobey, Margaret and Mayorga, Maria E. and Caltagirone, Sherrie and Ozaltin, Osman Y.}, year={2023}, month={Feb} }
 @article{tobey_li_ozaltin_mayorga_caltagirone_2022, title={Interpretable models for the automated detection of human trafficking in illicit massage businesses}, volume={8}, ISSN={["2472-5862"]}, DOI={10.1080/24725854.2022.2113187}, abstractNote={Abstract Sexually oriented establishments across the United States often pose as massage businesses and force victim workers into a hybrid of sex and labor trafficking, simultaneously harming the legitimate massage industry. Stakeholders with varied goals and approaches to dismantling the illicit massage industry all report the need for multi-source data to clearly and transparently identify the worst offenders and highlight patterns in behaviors. We utilize findings from primary stakeholder interviews with law enforcement, regulatory bodies, legitimate massage practitioners, and subject-matter experts from nonprofit organizations to identify data sources and potential indicators of illicit massage businesses (IMBs). We focus our analysis on data from open sources in Texas and Florida including customer reviews and business data from Yelp.com, the U.S. Census, and GIS files such as truck stop, highway, and military base locations. We build two interpretable prediction models, risk scores and optimal decision trees, to determine the risk that a given massage establishment is an IMB. The proposed multi-source data-based approach and interpretable models can be used by stakeholders at all levels to save time and resources, serve victim-workers, and support well informed regulatory efforts.}, journal={IISE TRANSACTIONS}, author={Tobey, Margaret and Li, Ruoting and Ozaltin, Osman Y. and Mayorga, Maria E. and Caltagirone, Sherrie}, year={2022}, month={Aug} }
 @article{agor_li_ozaltin_2022, title={Septic shock prediction and knowledge discovery through temporal pattern mining}, volume={132}, ISSN={["1873-2860"]}, DOI={10.1016/j.artmed.2022.102406}, abstractNote={Sepsis is the body's adverse response to infection which can lead to septic shock and eventually death if not treated in a timely manner. Analyzing patterns in sepsis patients' health status over time can help predict septic shock before its onset allowing healthcare providers to be more proactive. Temporal pattern mining methods can be used to identify trends in a patient's health status over time. If these methods return too many patterns, however, this can hinder knowledge discovery and practical implementation at the bedside in acute care settings. We propose a framework to find a small number of relevant temporal patterns in electronic health records for the early prediction of septic shock. Our framework consists of a temporal pattern mining method and three pattern selection techniques based on non-contrasted group support (PST1), contrasted group support (PST2), and model predictive power (PST3, PST4). We find that model-based feature selection approaches PST3 and PST4 yield the best prediction performance among these techniques. However, PST2 identifies more multi-state patterns with abnormal health states, which can give healthcare providers indicators of patient deterioration towards septic shock. Hence, from a knowledge discovery perspective, it may be worthwhile to sacrifice a small amount of prediction power for actionable patient health information through the implementation of PST2.}, journal={ARTIFICIAL INTELLIGENCE IN MEDICINE}, author={Agor, Joseph K. and Li, Ruoting and Ozaltin, Osman Y.}, year={2022}, month={Oct} }