OBJECTIVE: Clinical practice guidelines (CPGs) provide evidence-based recommendations for patient care; however, integrating them into artificial intelligence (AI) remains challenging. Previous approaches, such as rule-based systems or black-box AI models, face significant limitations, including poor interpretability, inconsistent adherence to guidelines, and narrow domain applicability. To address this, we develop and validate CPGPrompt, an auto-prompting system that converts narrative clinical guidelines into large language models (LLMs). MATERIALS AND METHODS: Our framework translates CPGs into structured decision trees and utilizes an LLM to dynamically navigate them for patient case evaluation. Synthetic vignettes were generated across 3 domains-headache, lower back pain, and prostate cancer-and distributed into 4 categories to test different decision scenarios. System performance was assessed on both binary specialty referral decisions and fine-grained pathway classification tasks. RESULTS: The binary specialty referral classification achieved consistently strong performance across all domains (F1: 0.85-1.00), with high recall (1.00 ± 0.00). In contrast, multiclass pathway assignment showed reduced performance, with domain-specific variations: headache (F1: 0.47), lower back pain (F1: 0.72), and prostate cancer (F1: 0.77). DISCUSSION: Domain-specific performance differences reflected the structure of each guideline. The headache guideline highlighted challenges with negation handling. The lower back pain guideline required temporal reasoning. In contrast, prostate cancer pathways benefited from quantifiable laboratory tests, resulting in more reliable decision-making. CONCLUSION: CPGPrompt demonstrates generalizability across diverse clinical domains while maintaining high sensitivity for referral decisions. Its transparent, auditable framework enables the systematic identification of failure modes and provides advantages over black-box AI approaches. However, persistent challenges with subjective clinical assessments indicate a need for targeted improvements and greater clinical robustness.

What challenges do volunteers providing peer support in online mental health platforms (OMHPs) face in operating and growing their communities? How could the HCI community develop human-AI systems to help? Recent work on online peer counseling has led to the development of novel AI tools for conversational interaction, but it remains unknown how such technology can fit into broader practices that include extratherapeutic tasks. In this research, we conducted interviews and design exercises with seventeen peer counselors from 7 Cups of Tea, a large online therapy and counseling platform, to design tools --- AI or not --- that resolve challenges that arise from day-to-day community practices. Participant responses suggest three classes of tools that could improve online peer counseling: real-time decision support, productivity, and management and training. Investigation of design motivations surfaced four practice-based challenges including chat interface limitations, difficulties in support seeker management, fragmented contexts of practice, and lack of visibility due to privacy concerns. Based on counselors' discussion of benefits and risks associated with AI features in the tools they designed, we offer suggestions for research on AI tools embedded within peer counseling practices, and connect our findings with broader implications about online peer counseling as a form of volunteer-based mental health practice.

Extensive research has been published on the conversational factors of effective volunteer peer counseling on online mental health platforms (OMHPs). However, studies differ in how they define and measure success outcomes, with most prior work examining only a single success metric. In this work, we model the relationship between previously reported linguistic predictors of effective counseling with four outcomes following a peer-to-peer session on a single OMHP: retention in the community, following up on a previous session with a counselor, users’ evaluation of a counselor, and changes in users’ mood. Results show that predictors correlate negatively with community retention but positively with users following up with and giving higher evaluations to individual counselors. We suggest actionable insights for therapy platform design and outcome measurement based on findings that the relationship between predictors and outcomes of successful conversations depends on differences in measurement construct and operationalization.

Despite the advances and ubiquity of digital communication media such as videoconferencing and virtual reality, they remain oblivious to the rich intentions expressed by users. Beyond transmitting audio, videos, and messages, we envision digital communication media as proactive facilitators that can provide unobtrusive assistance to enhance communication and collaboration. Informed by the results of a formative study, we propose three key design concepts to explore the systematic integration of intelligence into communication and collaboration, including the panel substrate, language-based intent recognition, and lightweight interaction techniques. We developed CrossTalk, a videoconferencing system that instantiates these concepts, which was found to enable a more fluid and flexible communication and collaboration experience.

We generalize the information bottleneck (IB) and privacy funnel (PF) problems by introducing the notion of a sensitive attribute, which arises in a growing number of applications. In this generalization, we seek to construct representations of observations that are maximally (or minimally) informative about a target variable, while also satisfying constraints with respect to a variable corresponding to the sensitive attribute. In the Gaussian and discrete settings, we show that by suitably approximating the Kullback-Liebler (KL) divergence defining traditional Shannon mutual information, the generalized IB and PF problems can be formulated as semi-definite programs (SDPs), and thus efficiently solved, which is important in applications of high-dimensional inference. We validate our algorithms on synthetic data and demonstrate their use in imposing fairness in machine learning on real data as an illustrative application.

Habituation is a biological behavior allowing non-critical information to be disregarded enabling more processing resources for critical tasks. We have implemented habituation adaptation in VLSI. Our simulations and experimental results illustrate the habituation response.