Corey Angst ([email protected]) is the Jack and Joan McGraw Family Collegiate Professor of IT, Analytics, and Operations at the Mendoza College of Business, University of Notre Dame. His research interest is in the transformational effect that technology has on society. Dr. Angst has published academic papers in top journals in the information systems, operations, and management fields. His publications use a variety of methods, including empirical (primary and secondary data analysis), experimental, and qualitative. Prior to pursuing graduate education, he worked for 10 years as an engineer and project manager with Flowserve Corporation and E. I. du Pont de Nemours and Company.
Alan R. Dennis ([email protected]; corresponding author) is a Professor of Information Systems and holds the John T. Chambers Chair of Internet Systems in the Kelley School of Business at Indiana University. His research focuses on four main themes: artificial intelligence; team collaboration; fake news on social media; and cybersecurity. Dr. Dennis has written more than 150 research papers, and has won numerous awards for his theoretical and applied research. A 2020 analysis of citation data since 1990 placed him in the top 1% of the most influential researchers in the world, across all scientific disciplines. His research has been reported in the popular press almost 1000 times, including the Wall Street Journal, Forbes, USA Today, The Atlantic, CBS, Fox Business Network, PBS, Canada’s CBC and CTV, and the UK’s Daily Mail and the Telegraph. He also has written four books (two on data communications and networking, and two on systems analysis and design). He is a Past President of the Association for Information Systems, an AIS Fellow, and has received the LEO Award.
Elena Karahanna ([email protected]) is Distinguished Research Professor and C. Herman and Mary Virginia Terry Distinguished Chair at the Terry College of Business, University of Georgia. She has published in top journals such as Information Systems Research, Journal of Management Information Systems, Management Science, MIS Quarterly, Organization Science, and Academy of Management Review, among others. She has served as senior editor at MIS Quarterly, Information Systems Research, and the Journal of the Association for Information Systems and serves as associate editor at Management Science. She is a Fellow of the Association for Information Systems, an INFORMS Information Systems Society Distinguished Fellow, and has received the AIS LEO award for lifetime exceptional achievement in the Information Systems discipline.
Gondy Leroy ([email protected]) is Professor of MIS, Research Director of the Center for Management Innovations in Healthcare, and Associate Dean for Research at the University of Arizona’s Eller College of Management. She earned her PhD in Management Information Systems from the University of Arizona. Dr. Leroy’s research focuses on natural language processing and machine learning. She has won grants from the National Institutes of Health (NIH) (National Library of Medicine [NLM], National Institute of Mental Health [NIMH]), Agency for Healthcare Research and Quality (AHRQ), National Science Foundation (NSF), Microsoft Research, and several foundations. She serves on the editorial board of various journals, serves as an ad hoc member for several NIH study sections, is a standing member of the NIH Clinical Data Management and Analysis Study Section, and chairs and co-chairs several special issues, sessions, tracks, workshops, and conferences focusing on design science and healthcare IT. Dr. Leroy is the author of the book Designing User Studies in Informatics (Springer, 2011).
Mental health issues are a growing epidemic facing modern society. The Mental Health America Society estimated that nearly a fifth of the adult U.S. population suffered a mental illness in 2019-2020 and that 94% of these individuals did not receive any treatment [7]. While many different treatment choices exist, the National Institute of Mental Health recognizes Digital Health Technology as an opportunity to “improve access, availability, utilization, and quality of mental health care services.”1 Information technology (IT) such as wearables, digital pills, tracking devices, apps, and electronic health records combined using artificial intelligence (AI), Virtual Reality (VR), and new systems and products have been designed, developed, and used to help address the growing mental health crisis. However, understanding the creation, adoption, use, and impact of such technologies for alleviating mental health illnesses remains nascent. Information systems (IS) scholars are starting to study various aspects of mental health, including occupational stress [1, 3, 6, 10], distress [2, 8], and diagnosable mental health disorders [4, 11]. Significant areas of opportunity remain for developing and evaluating digital technologies that could tackle a variety of disorders (e.g., anxiety disorder, mood disorders, and addictions [e.g., substance abuse, chemical dependence]), but also support and help with lifestyle choices, social determinants of health, as well as community building. Potential users range from medical specialists to laypersons and policymakers.
This special section highlights two papers that focus on the use of IT to address mental health issues. The first paper, “Digital Phenotyping-based Depression Detection in the Presence of Comorbidity: An Uncertainty Reasoning Approach” [5], explores digital phenotyping as a method for automatically detecting depression from user-behavior data collected by sensors. They point out that current digital phenotyping-based approaches to depression detection have not adequately accounted for the uncertainty arising from similar symptoms shared between depression and its comorbidities. They introduce an innovative deep learning model that integrates data from multiple sensors through a novel symptom-specific two-step approach, addressing diagnostic uncertainty using evidence theory. The model is compared with state-of-the-art models using sensor data from patients with Parkinson’s disease and depression, as these conditions frequently co-occur. Their method demonstrates improved accuracy in detecting depression compared to existing methods, particularly in patients with comorbidities.
The second paper, “Explainable Artificial Intelligence for Mental Disorder Screening: A Computational Design Science Approach” [9] introduces readers to MDScan, an explainable AI (XAI) artifact that assists clinicians in the screening process for ten different mental disorders. Using data from the mental disorder screening instrument SCL-90-R, and the authors’ proprietary ShapRadiation approach, MDscan transforms 90 mental health indicators for each patient into an easily interpretable diagnostic image, similar to a radiological image. With increasing demands on clinicians’ time, this study shows that AI is a welcome addition to the clinical toolkit from a time-saving perspective, but more importantly, MDscan has higher classification accuracy than clinician-labeled data.
Both studies, and the scores of manuscripts we reviewed, show the tremendous potential that advanced IT can have on mental health and the progress that has already been made in addressing the epidemic of deteriorating mental health. Advances in AI, including Large Language Models, create novel opportunities to complement current mental health professionals. By strategically integrating AI-powered tools and systems, we can enhance the expertise of mental health practitioners and offer additional support to improve overall mental health
AI can play a multifaceted role in bolstering mental healthcare. It can enhance early detection and diagnosis of mental health conditions by analyzing large datasets to identify early warning signs and patterns. AI algorithms can develop personalized treatment plans by considering individual factors such as medical history, genetics, and lifestyle data. AI-powered systems can also continuously monitor individuals’ behavior, speech, and physiological indicators to provide real-time feedback, predict potential relapse, and promptly direct users to appropriate resources or professional help when needed. AI-driven chatbots can offer round-the-clock mental health support, engaging users in empathetic conversations and providing coping strategies that complement the care delivered by mental health professionals, ensuring individuals have access to mental health when human providers are unavailable.
However, the integration of AI in mental healthcare also raises important ethical considerations. It is crucial to establish robust frameworks to guide the development and deployment of AI systems, ensuring privacy, confidentiality, and informed consent are upheld. Research is also needed to understand best practices for integrating AI tools into existing mental health practices and workflows, and to evaluate the comparative outcomes of AI-assisted interventions versus traditional approaches. Designing AI-based mental health applications that enhance user acceptance and trust is another critical area of exploration. Factors such as user interface, interaction design, and transparency around the capabilities and limitations of AI systems can significantly impact their adoption and long-term effectiveness.
By addressing these research priorities and implementing evidence-based strategies, we can harness the transformative potential of AI to complement and empower mental health professionals, ultimately improving mental health outcomes for individuals and communities. This collaborative approach, grounded in ethical principles and rigorous evaluation, will be essential in ensuring that AI-based mental health applications are developed and deployed in a responsible and impactful manner.
Notes
1.https://www.nimh.nih.gov/about/strategic-planning-reports/challenges-and-opportunities
References
1.Califf, C.B.; Sarker, S.; and Sarker, S. The bright and dark sides of technostress: A mixed-methods study involving healthcare IT. MIS Quarterly, 44, 2 (June 2020), 809–856.
2.Chau, M.; Li, T.M.H.; Wong, P.W.C.; Xu, J.J.; Yip, P.S.F.; and Chen, H. Finding people with emotional distress in online social media: A design combining machine learning and rule-based classification. MIS Quarterly, 44, 2 (June 2020), 933–955.
3.Cram, W.A.; Wiener, M.; Tarafdar, M.; and Benlian, A. Examining the impact of algorithmic control on Uber drivers’ technostress. Journal of Management Information Systems, 39, 2 (April 2022), 426–453.
4.James, T.L.; Lowry, P.B.; Wallace, L.; and Warkentin, M. The effect of belongingness on obsessive-compulsive disorder in the use of online social networks. Journal of Management Information Systems, 34, 2 (April 2017), 560–596.
5.Peng, F.; Zhang, D., and Yan, Z.I Digital Phenotyping-based depression detection in the presence of comorbidity: An uncertainty reasoning approach, Journal of Management Information Systems.
6.Pirkkalainen, H.; Salo, M.; Tarafdar, M.; and Makkonen, M. Deliberate or instinctive? Proactive and reactive coping for technostress. Journal of Management Information Systems, 36, 4 (October 2019), 1179–1212.
7.Reinert, M.; Fritze, D., and Nguyen, T. The State of Mental Health in America 2023. Mental Health America, 2022. https://mhanational.org/sites/default/files/2022%20State%20of%20Mental%20Health%20in%20America.pdf
8.Spohrer, K.; Fallon, M.; Hoehle, H.; and Heinzl, A. Designing effective mobile health apps: Does combining behavior change techniques really create synergies? Journal of Management Information Systems, 38, 2 (April 2021), 517–545.
9.Tutun, S.; Topuz, K.; Tosyali, A.; Bhattacherjee, A.; and Li, K. Explainable artificial intelligence for mental disorder screening: A computational design science approach. Journal of Management Information Systems, this issue
10Windeler, J.B.; Maruping, L.; and Venkatesh, V. Technical systems development risk factors: The role of empowering leadership in lowering developers’ stress. Information Systems Research, 28, 4 (December 2017), 775–796.
11.Xie, J.; Zhang, Z.; Liu, X.; and Zeng, D. Unveiling the hidden truth of drug addiction: A social media approach using similarity network-based deep learning. Journal of Management Information Systems, 38, 1 (January 2021), 166–195.