Browse
Recent Submissions
Item Examining mental illness trends in the United States from 2006 to 2019(IEEE, 2021-12-09) Olson, Thomas; Vodenska, Irena; Zhang, Guanglan; Nishijima, Marislei; Chitkushev, LouWe investigate the characteristics of medical expenditures associated with mental illness hospitalizations using the Truven Health MarketScan Database. We focus on the inpatient admissions due to mental illness of adults aged 1S to 64 between 2006 to 2019. We aim to answer the following questions: (1) Did the financial crisis of 2008 impact mental health in the U.S.?(2) What are the other macro-level (socioeconomic and regulartory) and micro-level (individualpatient related) factors that affect the cost of inpatient care due to mental illness; (3) Did mental illness affect men and women differently? (4) How were different regions within the U.S. affected by mental illness?Item TANTIGEN 2.0: a knowledge base of tumor T cell antigens and epitopes(BioMed Central, 2021) Zhang, Guanglan; Chitkushev, Lou; Olsen, Lars Rønn; Keskin, Derin B.; Brusic, VladimirWe previously developed TANTIGEN, a comprehensive online database cataloging more than 1,000 T cell epitopes and HLA ligands from 292 tumor antigens. In TANTIGEN 2.0, we significantly expanded coverage in both immune response targets (T cell epitopes and HLA ligands) and tumor antigens. It catalogs 4,296 antigen variants from 403 unique tumor antigens and more than 1,500 T cell epitopes and HLA ligands. We also included neoantigens, a class of tumor antigens generated through mutations resulting in new amino acid sequences in tumor antigens. TANTIGEN 2.0 contains validated TCR sequences specific for cognate T cell epitopes and tumor antigen gene/mRNA/protein expression information in major human cancers extracted by Human Pathology Atlas. TANTIGEN 2.0 is a rich data resource for tumor antigens and their associated epitopes and neoepitopes. It hosts a set of tailored data analytics tools tightly integrated with the data to form meaningful analysis workflows. It is freely available at http://projects.met-hilab.org/tadb.Item How do consumers choose offline shops on online platforms? An investigation of interactive consumer decision processing in diagnosis-and-cure markets(Emerald, 2022-05-10) Lee, Jennifer Joo; Ma, ZecongPURPOSE: The purpose of this paper is twofold: (1) to understand the process and consequences of the two-way communication between consumers and businesses on online-to-offline (O2O) diagnosis-and-cure services platforms and (2) to examine how consumer request-specific factors and service quote-specific factors influence consumer decisions in the interactive marketing context. DESIGN/METHODOLOGY/APPROACH: The study analyzes a dataset of 17,878 service requests and 57,867 price quotes obtained from an O2O platform bridging consumers and automotive repair shops. On the platform, consumers request service quotes by uploading the description of automotive damage and multiple service providers suggest price quotes. The authors formulated a logit model to examine consumer decisions of responding service quotes. FINDINGS: This paper finds that (1) consumers receiving more severe diagnostic results are more likely to respond to the price quotes, and (2) diagnostic severity and inconsistency moderate the impacts of geographic distance, shop size, and quote price on consumers' responses to the service quotes. RESEARCH LIMITATIONS/IMPLICATIONS: This paper fills the gap in the literature by advancing the consumer decision processing model to address the interactive shopping experience on O2O diagnosis-and-cure services platforms. The findings are limited by the data and the research context. PRACTICAL IMPLICATIONS: For marketing practitioners, the empirical results imply specific positioning and targeting strategies for markets with informational and geographic barriers to expand the market scope and customer base. ORIGINALITY/VALUE: The present work is the first to examine the consumer decision process on O2O diagnosis-and-cure service platforms. It adds value to the literature by investigating how consumers update their problem awareness through the service request-specific factors (i.e. diagnostic severity and diagnostic inconsistency) and how the request-specific factors moderate the impacts of the quote-specific factors (i.e. shop distance, shop size and quote price) on consumers' responses to price quote. The conceptual model and empirical findings provide theoretical and practical values for e-commerce researchers and practitioners.Item CovidCTNet: an open-source deep learning approach to diagnose Covid-19 using small cohort of CT images(Nature Research (part of Springer Nature), 2021-02-17) Javaheri, T.; Homayounfar, M.; Amoozgar, Z.; Reiazi, R.; Homayounieh, F.; Abbas, E.; Laali, A.; Radmard, A.R.; Gharib, M.H.; Mousavi, S.A.J.; Ghaemi, O.; Babaei, R.; Mobin, H.K.; Hosseinzadeh, M.; Jahanban-Esfahlan, R.; Seidi, K.; Kalra, M.K.; Zhang, G.; Chitkushev, Lubomir T.; Haibe-Kains, B.; Malekzadeh, R.; Rawassizadeh, R.Coronavirus disease 2019 (Covid-19) is highly contagious with limited treatment options. Early and accurate diagnosis of Covid-19 is crucial in reducing the spread of the disease and its accompanied mortality. Currently, detection by reverse transcriptasepolymerase chain reaction (RT-PCR) is the gold standard of outpatient and inpatient detection of Covid-19. RT-PCR is a rapid method; however, its accuracy in detection is only ~70–75%. Another approved strategy is computed tomography (CT) imaging. CT imaging has a much higher sensitivity of ~80–98%, but similar accuracy of 70%. To enhance the accuracy of CT imaging detection, we developed an open-source framework, CovidCTNet, composed of a set of deep learning algorithms that accurately differentiates Covid-19 from community-acquired pneumonia (CAP) and other lung diseases. CovidCTNet increases the accuracy of CT imaging detection to 95% compared to radiologists (70%). CovidCTNet is designed to work with heterogeneous and small sample sizes independent of the CT imaging hardware. To facilitate the detection of Covid-19 globally and assist radiologists and physicians in the screening process, we are releasing all algorithms and model parameter details as open-source. Open-source sharing of CovidCTNet enables developers to rapidly improve and optimize services while preserving user privacy and data ownership.Item “Rafiki Kahawa Shamba”: Developing “coffee tourism” in organic coffee farm to support local economic development in Tanzania(2017) Hajarrahmah, Dini; Patrucco, Fiorella; Suwimol, Natnicha (Annie)