Does Analytics Help Resolve Equivocality in the Healthcare Context? Contrasting the Effects of Analyzability and Differentiation

2023 | Journal of the Association for Information Systems | Citations: 0

Authors: Adjerid, Idris; Angst, Corey; Devaraj, Sarv; Berente, Nicholas

Abstract: Organizations are increasingly using data analytics to help make decisions and ... Expand

Abstract: Organizations are increasingly using data analytics to help make decisions and drive positive outcomes. But organizational scholarship has warned us that the sort of information processing associated with analytic capabilities, while effective for uncertainty reduction, may be less effective in equivocal contexts. Equivocality is evident when tasks are not easily analyzable (task analyzability) or when organizational departments are highly differentiated (differentiation). We hypothesize that analytics will be less effective in driving positive outcomes when equivocality is high because of low task analyzability. However, when an organization is more differentiated, resulting in high equivocality, we anticipate that analytics will be more effective in driving positive outcomes. To test this theory, we studied how clinical healthcare analytics influenced experiential quality (akin to patient satisfaction) in over 3,000 hospitals across nine years. Our results show that analytics capabilities, on average, do improve outcomes in terms of patient experiential quality, suggesting that analytics can reduce uncertainty, but we also found evidence for the moderating role of equivocality. Specifically, as task analyzability decreases (i.e., increasing equivocality), clinical healthcare analytics becomes less effective in improving experiential quality. However, when equivocality is high because of differentiation, there is a positive relationship between clinical healthcare analytics and experiential quality but only in larger hospitals. From a managerial perspective, this study has implications for boundary conditions of data analytics in organizations. Collapse

Topics: healthcare analytics technology adoption electronic health record health information system artificial intelligence

Methods: theory development post-hoc analysis experimental group longitudinal research machine learning

Theories: organizational information processing theory

What Symptoms and How Long? An Interpretable AI Approach for Depression Detection in Social Media

2023 | International Conference on Information Systems | Citations: 0

Authors: Kuang, Junwei; Xie, Jiaheng; Yan, Zhijun

Abstract: Depression is the most prevalent and serious mental illness, which induces grav ... Expand

Abstract: Depression is the most prevalent and serious mental illness, which induces grave financial and societal ramifications. Depression detection is key for early intervention to mitigate those consequences. Such a high-stake decision inherently necessitates interpretability. Although a few depression detection studies attempt to explain the decision, these explanations misalign with the clinical depression diagnosis criterion that is based on depressive symptoms. To fill this gap, we develop a novel Multi-Scale Temporal Prototype Network (MSTPNet). MSTPNet innovatively detects and interprets depressive symptoms as well as how long they last. Extensive empirical analyses show that MSTPNet outperforms state-of-the-art depression detection methods. This result also reveals new symptoms that are unnoted in the survey approach. We further conduct a user study to demonstrate its superiority over the benchmarks in interpretability. This study contributes to IS literature with a novel interpretable deep learning model for depression detection in social media. Collapse

Topics: social media healthcare analytics

Methods: design artifact deep learning computational algorithm machine learning ablation analysis

Responsible Artificial Intelligence (AI) for Digital Health and Medical Analytics

2023 | Information Systems Frontiers | Citations: 0

Authors: Sivarajah, Uthayasankar; Wang, Yichuan; Olya, Hossein; Mathew, Sherin

Abstract: ... Expand

Abstract: Collapse

Topics: artificial intelligence health information system responsible artificial intelligence healthcare analytics usage intention

Methods: survey personal interview literature sample structured literature research bibliometric analysis

Examining Disease Multimorbidity in U.S. Hospital Visits Before and During COVID-19 Pandemic: A Graph Analytics Approach

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

Authors: Srinivasan, Karthik; Jiang, Jinhang

Abstract: Enduring effects of the COVID-19 pandemic on healthcare systems can be preempted ... Expand

Abstract: Enduring effects of the COVID-19 pandemic on healthcare systems can be preempted by identifying patterns in diseases recorded in hospital visits over time. Disease multimorbidity or simultaneous occurrence of multiple diseases is a growing global public health challenge as populations age and long-term conditions become more prevalent. We propose a graph analytics framework for analyzing disease multimorbidity in hospital visits. Within the framework, we propose a graph model to explain multimorbidity as a function of prevalence, category, and chronic nature of the underlying disease. We apply our model to examine and compare multimorbidity patterns in public hospitals in Arizona, U.S., during five six-month time periods before and during the pandemic. We observe that while multimorbidity increased by 34.26% and 41.04% during peak pandemic for mental disorders and respiratory disorders respectively, the gradients for endocrine diseases and circulatory disorders were not significant. Multimorbidity for acute conditions is observed to be decreasing during the pandemic while multimorbidity for chronic conditions remains unchanged. Our graph analytics framework provides guidelines for empirical analysis of disease multimorbidity using electronic health records. The patterns identified using our proposed graph model informs future research and healthcare policy makers for pre-emptive decision making. Collapse

Topics: pandemic electronic health record decision making programming language database system

Methods: longitudinal survey longitudinal research deep learning machine learning ablation analysis

Deep Learning-Based Imputation Method to Enhance Crowdsourced Data on Online Business Directory Platforms for Improved Services

2023 | Journal of Management Information Systems | Citations: 0

Authors: Xu, Da; Hu, Paul Jen-Hwa; Fang, Xiao

Abstract: Popular online business directory (OBD) platforms, such as Yelp and TripAdvisor, ... Expand

Abstract: Popular online business directory (OBD) platforms, such as Yelp and TripAdvisor, depend on voluntarily user-submitted data about various businesses to assist consumers in finding appropriate options for transactions. Yet the crowdsourced nature of such data restricts the availability of attribute values for many businesses on the platform. Crowdsourced data often suffer serious completeness and timeliness constraints, with negative implications for key stakeholders such as users, businesses, and the platform. We thus develop a novel, deep learning–based imputation method, premised in institutional theory, to estimate missing attribute values of individual businesses on an OBD platform. The proposed method leverages a deep model architecture and considers both inter-business and inter-attribute relationships for imputations. An application to a Yelp data set reveals our method's greater imputation effectiveness relative to prevalent methods. To illustrate the method's practical utilities and values, we further examine the efficacy of business recommendations empowered by its imputed business attribute values, in comparison with those enabled by data imputed by benchmark methods. The results affirm that the proposed method substantially outperforms benchmarks for imputing missing attribute values and empowers more effective business recommendations. This study addresses crucial, prominent completeness and timeliness constraints in crowdsourced data on OBD platforms and offers insights for downstream applications that can improve user experiences, firm performance, and platform services. Collapse

Topics: missing data crowdsourcing data completeness wireless LAN healthcare data

Methods: data imputation autoencoder data transformation deep learning multivariate imputation with chained equations

Theories: institutional theory social learning theory

Exploring health-analytics adoption in indian private healthcare organizations: An institutional-theoretic perspective

2022 | Information and Organization | Citations: 0

Authors: Venkatraman, Sathyanarayanan; Sundarraj, Rangaraja P.; Seethamraju, Ravi

Abstract: In India, private hospitals are at the cusp of adopting health-analytics (HA) te ... Expand

Abstract: In India, private hospitals are at the cusp of adopting health-analytics (HA) technology to manage their organizational performance through data-driven decision-making. Past studies have analyzed the applications and benefits of HA. Our study builds on this descriptive base to investigate the patterns of HA adoption and the institutional factors which impact adoption. We conducted a cross-sectional field study that involved ten Indian private healthcare organizations and four health-ecosystem partners and analyzed the case study data using an institutional theory lens. Our cases reveal that the breadth and depth of HA adoption varies and falls into three distinct patterns: far-sighted, conservative, and niche. We assess how these patterns are influ­ enced by the two key dimensions of institutional environments (material-resource environment and institutional environment). We highlight distinctive factors (management support for building organizational trust on data-driven decisions and IT-Medical practitioner collaboration) that exert important contextual influences on HA adoption. Our study identifies areas of commonalty for HA adoption across national healthcare settings as well as contextual aspects representative of the burgeoning Indian healthcare field. Collapse

Topics: healthcare data innovation management technology adoption business model top management support

Methods: case study qualitative interview cross sectional research field study maturity model

Theories: institutional theory information systems theory

Historical profile will tell? A deep learning-based multi-level embedding framework for adverse drug event detection and extraction

2022 | Decision Support Systems | Citations: 0

Authors: Xia, Long

Abstract: Analyzing adverse drug events (ADEs) is an integral part of drug safety monitori ... Expand

Abstract: Analyzing adverse drug events (ADEs) is an integral part of drug safety monitoring, which plays a significant role in medication decision-making. The increasing prevalence of health-related social media may provide an avenue for drug safety profiling using patients' online posts. Recent advances in machine learning, especially in deep learning, have dramatically benefited ADE detection and extraction. However, despite the wide use of state-ofthe-art deep learning models, prior research has predominantly analyzed each post independently instead of treating the relevant posts holistically. In this study, guided by the theories of transfer of learning, we adopted the design science research methodology and developed a deep learning-based approach by innovatively inte­ grating historical profiles for ADE detection and extraction. Our framework—the Historical Awareness MultiLevel Embedding (HAMLE) model—outperformed existing state-of-the-art benchmarks by large margins. We also validated its real-world safety monitoring application using the Food and Drug Administration's drug safety warnings, and it showed promising performance in identifying previously unknown ADEs. This confirmed its potential for use as an early warning system for postmarketing surveillance. Furthermore, to evaluate the generalizability of HAMLE, we further tested it on a formal medical dataset extracted from PubMed, and it demonstrated robustness and achieved new state-of-the-art results. Our strategy of building a historical aware­ ness deep learning model, inspired by extant theories, could create a new way to integrate historical profiles and characteristics to support various business tasks in different domains. Collapse

Topics: social media artificial intelligence knowledge sharing decision making database system

Methods: deep learning machine learning design science experiment BERT

Theories: learning theory cognitive theory

Readmission Prediction for Patients with Heterogeneous Medical History: A Trajectory-Based Deep Learning Approach

2022 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Xie, Jiaheng; Zhang, Bin; Ma, Jian; Zeng, Daniel; Lo-Ciganic, Jenny

Abstract: Hospital readmission refers to the situation where a patient is re-hospitalized ... Expand

Abstract: Hospital readmission refers to the situation where a patient is re-hospitalized with the same primary diagnosis within a specific time interval after discharge. Hospital readmission causes $26 billion preventable expenses to the U.S. health systems annually and often indicates suboptimal patient care. To alleviate those severe financial and health consequences, it is crucial to proactively predict patients’ readmission risk. Such prediction is challenging because the evolution of patients’ medical history is dynamic and complex. The state-of-the-art studies apply statistical models which use static predictors in a period, failing to consider patients’ heterogeneous medical history. Our approach – Trajectory-BAsed DEep Learning (TADEL) – is motivated to tackle the deficiencies of the existing approaches by capturing dynamic medical history. We evaluate TADEL on a five-year national Medicare claims dataset including 3.6 million patients per year over all hospitals in the United States, reaching an F1 score of 87.3% and an AUC of 88.4%. Our approach significantly outperforms all the state-of-the-art methods. Our findings suggest that health status factors and insurance coverage are important predictors for readmission. This study contributes to IS literature and analytical methodology by formulating the trajectory-based readmission prediction problem and developing a novel deep-learning-based readmission risk prediction framework. From a health IT perspective, this research delivers implementable methods to assess patients’ readmission risk and take early interventions to avoid potential negative consequences. Collapse

Topics: health information system healthcare data online learning system crowdsourcing crowdfunding

Methods: machine learning deep learning logistic regression support vector machine experimental group

Wearable Sensor-Based Chronic Condition Severity Assessment: An Adversarial Attention-Based Deep Multisource Multitask Learning Approach

2022 | Management Information Systems Quarterly | Citations: 0

Authors: Yu, Shuo; Chai, Yidong; Chen, Hsinchun; Sherman, Scott; Brown, Randall

Abstract: Advancing the quality of healthcare for senior citizens with chronic conditions ... Expand

Abstract: Advancing the quality of healthcare for senior citizens with chronic conditions is of great social relevance. To better manage chronic conditions, objective, convenient, and inexpensive wearable sensorbased information systems (IS) have been increasingly used by researchers and practitioners. However, existing models often focus on a single aspect of chronic conditions and are often "black boxes" with limited interpretability. In this research, we adopt the computational design science paradigm and propose a novel adversarial attention-based deep multisource multitask learning (AADMML) framework. Drawing upon deep learning, multitask learning, multisource learning, attention mechanism, and adversarial learning, AADMML addresses limitations with existing wearable sensor-based chronic condition severity assessment methods. Choosing Parkinson's disease (PD) as our test case because of its prevalence and societal significance, we conduct benchmark experiments to evaluate AADMML against state-of-the-art models on a large-scale dataset containing thousands of instances. We present three case studies to demonstrate the practical utility and economic benefits of AADMML and by applying it to detect early-stage PD. We discuss how our work is related to the IS knowledge base and its practical implications. This work can contribute to improved life quality for senior citizens and advance IS research in mobile health analytics. Collapse

Topics: smart wearable device knowledge base decision making healthcare analytics Python

Methods: deep learning wearables based research experiment case study machine learning

Data analytics for the sustainable use of resources in hospitals: Predicting the length of stay for patients with chronic diseases

2022 | Information & Management | Citations: 0

Authors: Zolbanin, Hamed M.; Davazdahemami, Behrooz; Delen, Dursun; Zadeh, Amir Hassan

Abstract: Various factors are behind the forces that drive hospitals toward more sustainab ... Expand

Abstract: Various factors are behind the forces that drive hospitals toward more sustainable operations. Hospitals con­ tracting with Medicare, for instance, are reimbursed for the procedures performed, regardless of the number of days that patients stay in the hospital. This reimbursement structure has incentivized hospitals to use their re­ sources (such as their beds) more efficiently to maximize revenues. One way hospitals can improve bed utili­ zation is by predicting patients’ length of stay (LOS) at the time of admission, the benefits of which extend to employees, communities, and the patients themselves. In this paper, we employ a data analytics approach to develop and test a deep learning neural network to predict LOS for patients with chronic obstructive pulmonary disease (COPD) and pneumonia. The theoretical contribution of our effort is that it identifies variables related to patients’ prior admissions as important factors in the prediction of LOS in hospitals, thereby revising the current paradigm in which patients’ medical histories are rarely considered for the prediction of LOS. The methodo­ logical contributions of our work include the development of a data engineering methodology to augment the data sets, prediction of LOS as a numerical (rather than a binary) variable, temporal evaluation of the training and validation data sets, and a significant improvement in the accuracy of predicting LOS for COPD and pneumonia inpatients. Our evaluations show that variables related to patients’ previous admissions are the main driver of the deep network’s superior performance in predicting the LOS as a numerical variable. Using the assessment criteria introduced in prior studies (i.e., ±2 days and ±3 days tolerance), our models are able to predict the length of hospital stay with 86 % and 91 % accuracy for the COPD data set, and with 74 % and 85 % accuracy for the pneumonia data set. Hence, our effort could help hospitals serve a larger number of patients with a fixed amount of resources, thereby reducing their environmental footprint while increasing their revenue, as well as their patients’ satisfaction. Collapse

Topics: analytical information system missing data electronic health record healthcare data data warehouse

Methods: deep learning decision tree classification Keras experiment convolutional neural network