To highlight the often overlooked role of user interface (UI) design in mitigating bias in artificial intelligence (AI)-based clinical decision support (CDS). This perspective paper discusses the interdependency between AI-based algorithm development and UI design and proposes strategies for increasing the safety and efficacy of CDS. The role of design in biasing user behavior is well documented in behavioral economics and other disciplines. We offer an example of how UI designs play a role in how bias manifests in our machine learning-based CDS development. Much discussion on bias in AI revolves around data quality and algorithm design; less attention is given to how UI design can exacerbate or mitigate limitations of AI-based applications. This work highlights important considerations including the role of UI design in reinforcing/mitigating bias, human factors methods for identifying issues before an application is released, and risk communication strategies.
Background. Safe opioid prescribing and effective pain care are particularly important issues in the United States, where decades of widespread opioid prescribing have contributed to high rates of opioid use disorder. Because of the importance of clinician-patient communication in effective pain care and recent initiatives to curb rising opioid overdose deaths, this study sought to understand how clinicians and patients communicate about the risks, benefits, and goals of opioid therapy during primary care visits. Methods. We recruited clinicians and patients from six primary care clinics across three health systems in the Midwest United States. We audio-recorded 30 unique patients currently receiving opioids for chronic noncancer pain from 12 clinicians. We systematically analyzed transcribed, clinic visits to identify emergent themes. Results. Twenty of the 30 patient participants were females. Several patients had multiple pain diagnoses, with the most common diagnoses being osteoarthritis ( n = 10), spondylosis ( n = 6), and low back pain ( n = 5). We identified five themes: 1) communication about individual-level and population-level risks, 2) communication about policies or clinical guidelines related to opioids, 3) communication about the limited effectiveness of opioids for chronic pain conditions, 4) communication about nonopioid therapies for chronic pain, and 5) communication about the goal of the opioid tapering. Conclusions. Clinicians discuss opioid-related risks in varying ways during patient visits, which may differentially affect patient experiences. Our findings may inform the development and use of more standardized approaches to discussing opioids during primary care visits.
This paper presents a tradespace framework designed to analyze tradeoffs associated with different crewing configuration options. It was created in support of the United States Army’s Future Vertical Lift (FVL) program whose goal is to develop future Army rotorcraft that incorporate advanced automation and can be flexibly crewed depending on mission context. The tradespace framework provides an analytic tool that can help Army decision makers evaluate the tradeoffs associated with different crewing configurations and compare crewing options for different mission contexts. While the framework was developed to assess crew configurations for military rotorcraft, the use of tradeoffs as an organizing framework to analyze crewing alternatives can be applied to a variety of domains.
Background: There is a need for health information technology evaluation that goes beyond randomized controlled trials to include consideration of usability, cognition, feedback from representative users, and impact on efficiency, data quality, and clinical workflow. This article presents an evaluation illustrating one approach to this need using the Decision-Centered Design framework. Objective: To evaluate, through a Decision-Centered Design framework, the ability of the Screening and Surveillance App to support primary care clinicians in tracking and managing colorectal cancer testing. Methods: We leveraged two evaluation formats, online and in-person, to obtain feedback from a range primary care clinicians and obtain comparative data. Both the online and in-person evaluations used mock patient data to simulate challenging patient scenarios. Primary care clinicians responded to a series of colorectal cancer-related questions about each patient and made recommendations for screening. We collected data on performance, perceived workload, and usability. Key elements of Decision-Centered Design include evaluation in the context of realistic, challenging scenarios and measures designed to explore impact on cognitive performance. Results: Comparison of means revealed increases in accuracy, efficiency, and usability and decreases in perceived mental effort and workload when using the Screening and Surveillance App. Conclusion: The results speak to the benefits of using the Decision-Centered Design approach in the analysis, design, and evaluation of Health Information Technology. Furthermore, the Screening and Surveillance App shows promise for filling decision support gaps in current electronic health records.
Abstract Background For complex patients with chronic conditions, electronic health records (EHRs) contain large amounts of relevant historical patient data. To use this information effectively, clinicians may benefit from visual information displays that organize and help them make sense of information on past and current treatments, outcomes, and new treatment options. Unfortunately, few clinical decision support tools are designed to support clinical sensemaking. Objective The objective of this study was to describe a decision-centered design process, and resultant interactive patient information displays, to support key clinical decision requirements in chronic noncancer pain care. Methods To identify key clinical decision requirements, we conducted critical decision method interviews with 10 adult primary care clinicians. Next, to identify key information needs and decision support design seeds, we conducted a half-day multidisciplinary design workshop. Finally, we designed an interactive prototype to support the key clinical decision requirements and information needs uncovered during the previous research activities. Results The resulting Chronic Pain Treatment Tracker prototype summarizes the current treatment plan, past treatment history, potential future treatments, and treatment options to be cautious about. Clinicians can access additional details about each treatment, current or past, through modal views. Additional decision support for potential future treatments and treatments to be cautious about is also provided through modal views. Conclusion This study designed the Chronic Pain Treatment Tracker, a novel approach to decision support that presents clinicians with the information they need in a structure that promotes quick uptake, understanding, and action.
There is increasing demand to operate unmanned aircraft systems (UAS) in congested terminal environments, such as busy commercial airports. With this demand comes challenges to pilots. To identify these challenges, we conducted critical decision method (CDM) interviews with pilots. CDM is a cognitive task analysis method aimed at uncovering tacit cognitive challenges. Eight pilots from the U.S. were interviewed including four UAS pilots and four commercial pilots. Interviews were analyzed using thematic analysis, resulting in the identification of four categories of cognitive challenges: (i) noticing anomalies, (ii) diagnosing automation behavior, (iii) understanding when and how to intervene, and (iv) coordinating with air traffic control. In this paper, we describe each challenge, highlight real-world examples from our interviews, and provide some recommendations for addressing the implications of integrating UAS in congested terminal airspace.
