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

ROLEX: A Novel Method for Interpretable Machine Learning Using Robust Local Explanations

2023 | Management Information Systems Quarterly | Citations: 2

Authors: Kim, Buomsoo (Raymond); Srinivasan, Karthik; Kong, Sung Hye; Kim, Jung Hee; Shin, Chan Soo; Ram, Sudha

Abstract: Recent developments in big data technologies are revolutionizing the field of h ... Expand

Abstract: Recent developments in big data technologies are revolutionizing the field of healthcare predictive analytics (HPA), enabling researchers to explore challenging problems using complex prediction models. Nevertheless, healthcare practitioners are reluctant to adopt those models as they are less transparent and accountable due to their black-box structure. We believe that instance-level, or local, explanations enhance patient safety and foster trust by enabling patient-level interpretations and medical knowledge discovery. Therefore, we propose the RObust Local EXplanations (ROLEX) method to develop robust, instance-level explanations for HPA models in this study. ROLEX adapts state-of-the-art methods and ameliorates their shortcomings in explaining individual-level predictions made by black-box machine learning models. Our analysis with a large real-world dataset related to a prevalent medical condition called fragility fracture and two publicly available healthcare datasets reveals that ROLEX outperforms widely accepted benchmark methods in terms of local faithfulness of explanations. In addition, ROLEX is more robust since it does not rely on extensive hyperparameter tuning or heuristic algorithms. Explanations generated by ROLEX, along with the prototype user interface presented in this study, have the potential to promote personalized care and precision medicine by providing patient-level interpretations and novel insights. We discuss the theoretical implications of our study in healthcare, big data, and design science. Collapse

Topics: explainable artificial intelligence usability user interface local interpretable model agnostic explanation problem solving

Methods: machine learning design artifact computational algorithm longitudinal research ablation analysis

Theories: lemon market theory

The optimal asset trading settlement based on Proof-of-Stake blockchains

2023 | Decision Support Systems | Citations: 0

Authors: Li, Chao; Wang, Li; Yang, Haijun

Abstract: The Proof-of-Stake (PoS) protocol is booming in blockchain networks because of e ... Expand

Abstract: The Proof-of-Stake (PoS) protocol is booming in blockchain networks because of excessive energy consumption and slow block generation associated with the Proof-of-Work (PoW) protocol. In terms of transaction settlement, does the PoS protocol perform better than PoW? We build a transaction settlement model based on the PoS blockchain, describing how the staking income and costs affect settlement performance, and put forward a Successful Settlement Factor (SSF) to determine whether the settlement will be successful given the block size and block time. In addition, the system developers can adjust block size and block time according to SSF to achieve the best settlement performance. Finally, using historical data for a real-world blockchain network, our model demonstrates that the optimal block time, average settlement time, average settlement fees, and total settlement lag of the PoS blockchain are 23.41%, 23.29%, 23.23%, 23.31%, respectively, less than that of the PoW blockchain. Collapse

Topics: blockchain systems design ADA cryptocurrency decentralized finance

Methods: robustness check theoretical contribution experiment sensitivity analysis economic model

ICT for Good: Digital Accessibility in Local Government

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Rosenbaum, Howard; Shermis, Michael

Abstract: This paper describes a case study of a local government in the United States th ... Expand

Abstract: This paper describes a case study of a local government in the United States that is in the process of developing an inclusive and accessible ICT infrastructure for the delivery of e-government resources and services to its citizens with specific attention paid to people with disabilities. Developing such an inclusive infrastructure has proven to be difficult for many municipalities. Attempts to comply with the legal requirements to improve the possibilities for civic engagement for people with disabilities have met with mixed results. The research reported here focuses on a municipality engaged in a complex, user-driven initiative intended to transition its existing ICT infrastructure to one that is more inclusive and accessible to all. KeywordsDigital inclusion, access, local government, disabilities federally funded programs from discriminating against people with disabilities" (Loftus, 2021; 4). The ADA extends this prohibition to state and local government through Title II (ADA.gov, 2023). According to Grisham, the ADA uses the following definition of "disability:" (A) a physical or mental impairment that substantially limits one or more major life activities of [an] individual; (B) a record of such an impairment; or (C) being regarded as having such an impairment."The ADA "guarantee[s] equal opportunity for people with disabilities in employment, state and local government services, public accommodations, commercial facilities, and transportation" and "prohibits disability discrimination by all public entities at the state and local level." (Loftus, 2021; 2). The burden is therefore placed on municipalities to accommodate people with disabilities, providing access to all services, programs, and activities and making available reasonable means by which people can engage in effective communication and participation in their local governments. This latter requirement is generally interpreted as applying to digital content, web sites, and other channels of digital communications in which governments routinely engage. Examples of reasonable accommodations can include live on-camera sign language interpreters, assistive listening devices, and closed captioning, Among the specific requirements that municipalities must meet include the following (ADA.gov, 2023):• Communicate with people with disabilities as effectively as you communicate with others.• Make reasonable modifications to policies, practices, and procedures where needed to make sure that a person with a disability can access the state/local government's programs, services, or activities • Provide program access by ensuring that individuals with disabilities are not excluded from programs because existing buildings or facilities are inaccessible to them. Collapse

Topics: information technology infrastructure web application ADA pandemic government system

Methods: case study survey qualitative interview

Theories: theory of affordance

Trust Recipes for Enhancing the Intention to Adopt Conversational Agents for Disease Diagnosis: An fsQCA Approach

2022 | HICSS | Citations: 0

Authors: Anton, Eduard; Oesterreich, Thuy Duong; Fitte, Christian; Teuteberg, Frank

Abstract: In this study, we examine the configurations of trust-enhancing factors that det ... Expand

Abstract: In this study, we examine the configurations of trust-enhancing factors that determine the intention to adopt conversational agents (CAs) for disease diagnosis. After identifying trust factors influencing the behavioral intent to adopt CAs based on the information systems acceptance research field, we assigned 201 participants to use the mobile Ada application and surveyed them about their experience. Ada is a medical diagnostic CA that combines patients’ symptoms with their medical history and provides diagnostic suggestions. The collected data was analyzed using a fuzzy set qualitative comparative analysis to capture the causal complexity of trust. We identified several configurations of trust-enhancing factors affecting the intention to adopt the CA. In particular, our results show that the adoption intentions are strongly determined by trust factors associated with the performance dimension. Furthermore, we derived two propositions for the development of CAs for healthcare purposes and elaborated implications for research and practice. Collapse

Topics: artificial intelligence technology adoption behavioral intention mobile application fuzzy logic

Methods: survey fuzzy set qualitative comparative analysis literature study structural equation modeling case study

Theories: fuzzy set theory set theory

Examining Power Relationships in the Use of Information Systems to Comply with Laws and Enable Social Inclusion

2022 | HICSS | Citations: 0

Authors: Cao, Shiya; Strong, Diane; Loiacono, Eleanor

Abstract: This study employs the circuits of power framework to analyze how power relation ... Expand

Abstract: This study employs the circuits of power framework to analyze how power relationships affect the use of Information Systems (IS) in the social inclusion context. This research majorly contributes to social inclusion research in IS by examining how the power relationships influence the use of IS and how IS design can address complex power relationships and enable social inclusion. Collapse

Topics: information system use systems design organizational change evaluation criteria electronic mail

Methods: case study qualitative interview design principle personal interview qualitative coding

Theories: socio technical theory

ADA-CMM: A Capability Maturity Model for Advanced Data Analytics

2022 | HICSS | Citations: 0

Authors: Korsten, Ginger; Aysolmaz, Banu; Turetken, Oktay; Edel, Diederick; Ozkan, Baris

Abstract: Despite the rising importance of advanced data analytics, there is limited guida ... Expand

Abstract: Despite the rising importance of advanced data analytics, there is limited guidance on how organizations should leverage it. The benefits that an organization can gain through advanced data analytics depends on the organization’s ability to gain and use relevant capabilities. This study introduces a capability maturity model (ADA-CMM) for advanced data analytics to help organizations assess their current state of capabilities for managing advanced data analytics. We used the Delphi method to develop the maturity model and performed a survey to evaluate its validity. The results confirm that the maturity level of the advanced data analytics capabilities of organizations is positively related to the business value that they can capture from their use, which in turn found positively related to organizational performance. ADA-CMM can be used by organizations as a self-assessment tool and to create a roadmap for improving their relevant capabilities. Collapse

Topics: ADA organizational productivity analytical information system value creation big data

Methods: survey design science maturity model partial least squares path modeling capability maturity model

Introduction to the Business Intelligence & Big Data for Innovative and Sustainable Development of Organizations Mini-track

2022 | HICSS | Citations: 0

Authors: Olszak, Celina M; Zurada, Jozef; Kozanoglu, Dilek Cetindamar

Abstract: This mini-track sought papers that provide a theoretical, conceptual, and/or ap ... Expand

Abstract: This mini-track sought papers that provide a theoretical, conceptual, and/or applied grounded discussion of Business Intelligence (BI) and Big Data (BD) to (1) aid organizations in innovative and sustainable development, (2) provide the added value to the development of organizations and their decisionmaking process, (3) support organizational creativity, (4) design intelligent information systems and build decision support systems in organizations, and (5) use tools and solutions to achieve innovative and sustainable development of organizations.The mini-track includes five papers. The first paper, titled Toward a unified model of mobile Business Intelligence (m-BI) acceptance and use, focuses on factors affecting m-BI. After conducting a systematic literature review, Weichbroth, Kowal, and Kalinowski identify five factors: Perceived Value, Perceived Ease of Use, Managerial Attitudes, Facilitating Conditions and Quality of Information, and specified their interrelationships. Then, they introduce an acceptance and use model (m-BIAM). The paper invites researchers to test and evaluate their m-BIAM model to confirm its validity and predictive power. Collapse

Topics: supply chain management procurement management ADA analytical information system business intelligence

Methods: design science capability maturity model

Dynamic Composition of Cyber-Physical Systems

2019 | HICSS | Citations: 0

Authors: Jakobs, Christine; Werner, Matthias; Troger, Peter

Abstract: Future cyber-physical systems must fulfill strong demands on timeliness and relia ... Expand

Abstract: Future cyber-physical systems must fulfill strong demands on timeliness and reliability, so that the safety of their operational environment is never violated. At the same time, such systems are networked computers with the typical demand for reconfigurability and software modification. The combination of both expectations makes established modeling and analysis techniques difficult to apply, since they cannot scale with the number of possible operational constellations resulting from the dynamics. The problem increases when components with different non-functional demands are combined to one cyber-physical system and updated independent from each other. Collapse

Topics: enterprise architecture cyber-physical system operating system ADA system deployment

Methods: computational algorithm design process

Theories: set theory

Digitization of Music: Consumer Adoption Amidst Piracy, Unbundling, and Rebundling

2019 | Management Information Systems Quarterly | Citations: 5

Authors: Koh, Byungwan; Hann, Il-Horn; Raghunathan, Srinivasan

Abstract: Digital music formats and the Internet as a distribution mechanism have fundamen ... Expand

Abstract: Digital music formats and the Internet as a distribution mechanism have fundamentally disrupted the music industry by altering the way music is packaged, distributed, and consumed. This disruptive innovation has come in two stages. First, it enabled music to be purchased as an individual song (digital single) or as an album (digital album) or to be enjoyed without paying for it (unlicensed digital music). More recently, music has become available as a streaming service (streaming music). Prior to these innovations, music was primarily distributed as an album using a physical medium such as the CD. Building on multi-generation diffusion models, we identify and quantify different types of concurrent demand migration in the music industry such as generational substitution, unbundling, and piracy effects in the first stage and streaming effects in the subsequent stage. Measuring the relative contributions of factors that drive each of these different migration types, we find that the introduction of licensed digital downloads (digital single and digital album) has weakened the piracy effect. Since the introduction of licensed digital downloads, the piracy effect on the demand for CDs has decreased about 15 percent every year. At the same time, unbundling, rather than piracy, has become the dominant factor in the decline of industry revenue. More recently, streaming music services such as Pandora have moved demand from digital albums to streaming music. However, demand has not yet migrated from digital singles to streaming music. The introduction of streaming music has further weakened the piracy effect by about 7 percent every year. Collapse

Topics: digital service music streaming service internet technology innovation management computer crime

Methods: robustness check hazard function accelerated failure time model simulation descriptive statistic