A Signal Detection Theory Approach for Predicting Immunity to Pandemic Vaccine Fake News

2023 | HICSS | Citations: 0

Authors: Barajas, J.; John, R.

Abstract: Managing a contagious disease pandemic, such as , requires that the public unde ... Expand

Abstract: Managing a contagious disease pandemic, such as , requires that the public understand and cooperate with behavioral guidelines to reduce viral transmission. This research uses Signal Detection Theory (SDT) to explore how U.S. adults distinguish between true and false information related to COVID-19 vaccines. A total of 372 U.S. adults categorized 17 true and 17 false COVID-19 vaccine headlines. Item Response Theory analyses suggest that the ability to identify true information about the pandemic is a construct that can be reliably measured with our novel methodology. Signal Detection Theory analyses indicate high accuracy (AUC = 0.861), with no bias favoring either true or false responses. Overall, U.S. adults correctly classified 7 of 10 true and 8 of 10 false headlines. Multiple regression analyses on individual performance metrics reveal substantially lower accuracy among conservatives and those with lower scores on a measure of Actively Open-minded Thinking. Implications and limitations of these findings within the pandemic news context are discussed. Collapse

Topics: misinformation fake news pandemic social media covid 19

Methods: machine learning survey multiple linear regression survey design regression analysis method

Theories: signal detection theory

Optimizing Substance Use Treatment Selection Using Reinforcement Learning

2023 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Baucum, Matt; Khojandi, Anahita; Myers, Carole; Kessler, Larry

Abstract: Substance use disorder (SUD) exacts a substantial economic and social cost in th ... Expand

Abstract: Substance use disorder (SUD) exacts a substantial economic and social cost in the United States, and it is crucial for SUD treatment providers to match patients with feasible, effective, and affordable treatment plans. The availability of large SUD patient datasets allows for machine learning techniques to predict patient-level SUD outcomes, yet there has been almost no research on whether machine learning can be used to optimize or personalize which treatment plans SUD patients receive. We use contextual bandits (a reinforcement learning technique) to optimally map patients to SUD treatment plans, based on dozens of patient-level and geographic covariates. We also use near-optimal policies to incorporate treatments’ time-intensiveness and cost into our recommendations, to aid treatment providers and policymakers in allocating treatment resources. Our personalized treatment recommendation policies are estimated to yield higher remission rates than observed in our original dataset, and they suggest clinical insights to inform future research on data-driven SUD treatment matching. Collapse

Topics: electronic health record individual characteristic healthcare data missing data

Methods: hazard function machine learning random forest classification descriptive statistic propensity score method

Expl(AI)ned: The Impact of Explainable Artificial Intelligence on Users’ Information Processing

2023 | Information Systems Research | Citations: 0

Authors: Bauer, Kevin; von Zahn, Moritz; Hinz, Oliver

Abstract: Because of a growing number of initiatives and regulations, predictions of moder ... Expand

Abstract: Because of a growing number of initiatives and regulations, predictions of modern artificial intelligence (AI) systems increasingly come with explanations about why they behave the way they do. In this paper, we explore the impact of feature-based explanations on users’ information processing. We designed two complementary empirical studies where participants either made incentivized decisions on their own, with the aid of opaque predictions, or with explained predictions. In Study 1, laypeople engaged in the deliberately abstract investment game task. In Study 2, experts from the real estate industry estimated listing prices for real German apartments. Our results indicate that the provision of feature-based explanations paves the way for AI systems to reshape users’ sense making of information and understanding of the world around them. Specifically, explanations change users’ situational weighting of available information and evoke mental model adjustments. Crucially, mental model adjustments are subject to the confirmation bias so that misconceptions can persist and even accumulate, possibly leading to suboptimal or biased decisions. Additionally, mental model adjustments create spillover effects that alter user behavior in related yet disparate domains. Overall, this paper provides important insights into potential downstream consequences of the broad employment of modern explainable AI methods. In particular, side effects of mental model adjustments present a potential risk of manipulating user behavior, promoting discriminatory inclinations, and increasing noise in decision making. Our findings may inform the refinement of current efforts of companies building AI systems and regulators that aim to mitigate problems associated with the black-box nature of many modern AI systems. History: Alessandro Acquisti, senior editor; Jason Chan, associate editor. Funding: This work was supported by the Deutsche Forschungsgemeinschaft (DFG) (Projek 449023539), Volkswagen Foundation (ML2MT), and LeibnizInstitute for Financial Research SAFE. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2023.1199. Collapse

Topics: explainable artificial intelligence artificial intelligence shapley additive explanation local interpretable model agnostic explanation decision making

Methods: F-test regression analysis method experiment field study robustness check

Human-machine collaboration for feature selection and integration to improve congestive Heart failure risk prediction

2023 | Decision Support Systems | Citations: 0

Authors: Ben-Assuli, Ofir; Heart, Tsipi; Klempfner, Robert; Padman, Rema

Abstract: The issue of harnessing machine learning (ML) algorithms for the prediction of a ... Expand

Abstract: The issue of harnessing machine learning (ML) algorithms for the prediction of adverse medical events is important considering the prevalence of vast repositories of patient-level medical data, and the quest to reduce healthcare costs while elevating the quality of care. Of particular interest is identifying a set of features that can better predict the risk of unplanned readmissions of chronically ill patients within 30 days post discharge, among them patients with Congestive Heart Failure (CHF). While numerous studies have employed ML algorithms to identify sets of significant features, only a handful have compared features extracted by various methods, and even fewer have compared the predictive power of feature sets selected by human experts to those selected by ML. Hence, this research aimed to elicit a comprehensive feature set selected by four ML algorithms and compare its predictive performance to that of a feature set selected by experts. We then evaluated a merged list of the two feature sets, constructing a human-machine collaborative set to predict the likelihood of 30-day unplanned readmission of CHF patients using data on 10,763 CHF patients hospitalized during the years 2010–2017. Our models achieved Area under the ROC Curve (AUC) above 0.8 and an Accuracy of ~0.89, comparable to the best models in the extant literature. Moreover, the Human-Machine Collaborative model significantly outperformed (best AUC 0.836) other human-only selected models as well as the machine-selected set. This study contributes to a better understanding of the power of using ML for patient risk stratification with special attention to the benefits of human-machine collaboration, even when these two entities work separately or in parallel, for improved clinical decision making. Collapse

Topics: healthcare data decision making big data missing data data warehouse

Methods: machine learning computational algorithm XGBoost descriptive statistic random forest classification

Business Inferences and Risk Modeling with Machine Learning; The case of Aviation Incidents

2023 | HICSS | Citations: 0

Authors: Cankaya, B.; Topuz, K.; Glassman, A.

Abstract: Machine learning becomes truly valuable only when decision-makers begin to depe ... Expand

Abstract: Machine learning becomes truly valuable only when decision-makers begin to depend on it to optimize decisions. Instilling trust in machine learning is critical for businesses in their efforts to interpret and get insights into data, and to make their analytical choices accessible and subject to accountability. In the field of aviation, the innovative application of machine learning and analytics can facilitate an understanding of the risk of accidents and other incidents. These occur infrequently, generally in an irregular, unpredictable manner, and cause significant disruptions, and hence, they are classified as "highimpact, low-probability" (HILP) events. Aviation incident reports are inspected by experts, but it is also important to have a comprehensive overview of incidents and their holistic effects. This study provides an interpretable machine-learning framework for predicting aircraft damage. In addition, it describes patterns of flight specifications detected through the use of a simulation tool and illuminates the underlying reasons for specific aviation accidents. As a result, we can predict the aircraft damage with 85% accuracy and 84% in-class accuracy. Most important, we simulate a combination of possible flight-type, aircraft-type, and pilot-expertise combinations to arrive at insights, and we recommend actions that can be taken by aviation stakeholders, such as airport managers, airlines, flight training companies, and aviation policy makers. In short, we combine predictive results with simulations to interpret findings and prescribe actions.A machine-learning (ML) algorithm was chosen for its fast performance, short run-time, and interpretability. The ML algorithms were compared and evaluated on a confusion matrix for their mean receiver operating characteristic curve (ROC), Collapse

Topics: decision making decision support system graphical user interface usability missing data

Methods: simulation machine learning multinomial logistic regression computational algorithm support vector machine

A privacy-preserving decentralized credit scoring method based on multi-party information

2023 | Decision Support Systems | Citations: 0

Authors: He, Haoran; Wang, Zhao; Jain, Hemant; Jiang, Cuiqing; Yang, Shanlin

Abstract: With society's wide-scale adoption of information technology, significant inform ... Expand

Abstract: With society's wide-scale adoption of information technology, significant information about borrowers is distributed across various parties, information that can be jointly used to improve credit scoring. However, use of such information faces many challenges, such as the problems of preserving privacy and information redun­ dancy. To address these challenges in leveraging multi-source information for credit scoring, we propose a decentralized multi-party method based on logistic regression. Specifically, we formulate a logistic regression model using the vertical federated learning paradigm. To preserve data privacy during multi-party collaborative model training, we use additively homomorphic encryption based on the second-order Taylor series expansion of the loss function and its gradient. To address information redundancy and to improve the performance of the credit scoring model, we use the proposed HE-DPGD algorithm to estimate the distributed coefficients in a privacy-preserving setting. Empirical evaluation shows that the proposed method can leverage information from multiple parties securely and effectively. Collapse

Topics: privacy homomorphic encryption logistics management online lending missing data

Methods: computational algorithm machine learning federated learning logistic regression experiment

ARTIFICIAL INTELLIGENCE-AUGMENTED DECISION MAKING IN SUPPLY CHAIN MONITORING: AN ACTION DESIGN RESEARCH STUDY

2023 | European Conference On Information Systems | Citations: 0

Authors: Herath Pathirannehelage, Savindu; Jóhannsson, Jóhann; Shrestha, Yash; Krogh, Georg von

Abstract: Organizations are progressively adopting hybrid human-artificial intelligence ( ... Expand

Abstract: Organizations are progressively adopting hybrid human-artificial intelligence (AI) systems in decisionmaking processes, with human decisions being augmented by AI insights. Among the promising AI applications in supply chain monitoring (SCMo) are predictive maintenance systems that predict potential device failures and augment maintenance decisions, allowing for timely and efficient interventions. Despite the growing proliferation of such systems, prescriptive knowledge encompassing technical, business, and organizational aspects on how to design, develop, and deploy them in actual operational environments remains limited. To address this shortcoming of evidence-based design principles in practice, our action design research developed a predictive maintenance system that predicts SCMo device failures and augments the maintenance decisions about those devices. By doing so, we outline generalizable design principles to guide prospective predictive maintenance systems in SCMo. Collapse

Topics: artificial intelligence predictive maintenance organizational context decision making systems evaluation

Methods: machine learning design principle design artifact artificial neural network random forest classification

Theories: evidence-based design

Maximizing Online Revisiting and Purchasing: A Clickstream-Based Approach to Enhancing Customer Lifetime Value

2023 | Journal of Management Information Systems | Citations: 0

Authors: Jabr, Wael; Ghoshal, Abhijeet; Cheng, Yichen; Pavlou, Paul

Abstract: Online retailers are increasingly focused on maintaining a long-term relationshi ... Expand

Abstract: Online retailers are increasingly focused on maintaining a long-term relationship with customers, encouraging repeat visits rather than single-time purchases to increase customer lifetime value. To help retailers maximize the probabilities of customers' revisiting and purchasing, we develop a two-stage model to better characterize and predict these two fundamental customer activities. In the first stage, we characterize the propensity of a customer revisiting the retailer's website. In the second stage, we develop a stochastic model that predicts revisits while also incorporating individual customer heterogeneity in exerted search effort during repeated visits. This heterogeneity is based on individual customer preferences in the choice of consideration sets, product information, pricing, and the search environment. Using customer level clickstream data, we show that our approach is not only better at predicting repeat customer visits, compared to existing methods, but also explainable and managerially interpretable. Most importantly, using computationally efficient simulation-based prescriptive analytics, we leverage our modeling approach to propose practical intervention strategies that maximize the joint likelihoods of customers revisiting and purchasing at the individual customer level. Collapse

Topics: website price management mobile system accounting logistics management

Methods: simulation logistic regression proportional hazards model cluster analysis machine learning

Responsible Artificial Intelligence in Healthcare: Predicting and Preventing Insurance Claim Denials for Economic and Social Wellbeing

2023 | Information Systems Frontiers | Citations: 1

Authors: Johnson, Marina; Albizri, Abdullah; Harfouche, Antoine

Abstract: It is estimated that one out of seven health insurance claims is rejected in the ... Expand

Abstract: It is estimated that one out of seven health insurance claims is rejected in the US; hospitals across the country lose approximately $262 billion annually due to denied claims. This widespread problem causes huge cash-flow issues and overburdens patients. Thus, preventing claim denials before claims are submitted to insurers improves profitability, accelerates the revenue cycle, and supports patients’ wellbeing. This study utilizes Design Science Research (DSR) paradigm and develops a Responsible Artificial Intelligence (RAI) solution helping hospital administrators identify potentially denied claims. Guided by five principles, this framework utilizes six AI algorithms – classified as white-box and glass-box – and employs cross-validation to tune hyperparameters and determine the best model. The results show that a white-box algorithm (AdaBoost) model yields an AUC rate of 0.83, outperforming all other models. This research’s primary implications are to (1) help providers reduce operational costs and increase the efficiency of insurance claim processes (2) help patients focus on their recovery instead of dealing with appealing claims. Collapse

Topics: artificial intelligence ADA missing data partial dependence plot responsible artificial intelligence

Methods: machine learning computational algorithm experiment support vector machine design artifact

Information System Articulation Development - Managing Veracity Attributes and Quantifying Relationship with Readability of Textual Data

2023 | International Conference on Information Systems | Citations: 0

Authors: Naik, Neelam; Nimmagadda, Shastri; Purohit, Seema; Reiners, Torsten; Mani, Dr Neel

Abstract: Often the textual data are either disorganized or misinterpreted because of uns ... Expand

Abstract: Often the textual data are either disorganized or misinterpreted because of unstructured Big Data in multiple dimensions. Managing readable textual alphanumeric data and its analytics is challenging. In spatial dimensions, the facts can be ambiguous and inconsistent, posing interpretation and new knowledge discovery challenges. The information can be wordy, erratic, and noisy. The research aims to assimilate the data characteristics through Information System (IS) artefacts that are appropriate to data analytics, especially in application domains that involve big data sources. Data heterogeneity and multidimensionality can make and preclude IS-guided veracity models in the data integration process, including customer analytics services. The veracity of big data thus can impact visualization and value, including knowledge enhancement in the vast amount of textual data qualitatively. The manner the veracity features construed in each schematic, semantic and syntactic attribute dimension in several IS artefacts and relevant documents can enhance the readability of textual data robustly. 2Modelling Veracity Attributes of Textual Data concepts and contexts (Lacasta et al. 2010). We have proposed a holistic methodology to build relationships between veracity attributes and instances and ease the readability of textual data. We can ontologically structure textual facts to explore connections between wordy readable, erratic, and noisy data. For example, ontologically structured alphanumeric data can logically and physically be integrated into unified textual metadata in a repository system. The metadata can be cost-effective for explicitly exploring new knowledge in a textual form (Vasarhelyi et al. 2015).The rest of the research paper is structured in various sections. The research objectives are highlighted, along with the motivation and significance of the research. The literature review identifies the research gaps in textual data mining. Various issues and challenges of Big textual Data mining are discussed in the next section. IS guided data mapping and modelling methods are described, including how the veracity attribute instances are mappable qualitatively with textual data mining artefacts that are construed with readability attributes and their occurrences, which are the highlights of the framework development. The value of information systems in various business contexts is highlighted in Rainer and Prince (2022). Several IS artefacts are articulated in the framework development. The integrated methodological framework adapts the ontology-based alphanumeric metadata with various mining artefacts, all accommodated in a repository. Results and discussions are analyzed, along with contributions and the intended research audience. The research is concluded with future scopes and limitations. Collapse

Topics: Python big data website Twitter decision making

Methods: experiment machine learning data modeling design artifact product review