Yufen Lin

BACKGROUND Chronic disease management increasingly depends on monitoring symptoms and health behaviors outside clinical settings, yet most mobile health (mHealth) systems treat behavioral data capture and intervention delivery as separate functions. Platforms that collect high-resolution sensor or ecological momentary assessment (EMA) data often provide limited tools for clinician-authored intervention content, whereas intervention applications commonly embed content and decision logic directly in application code. This coupling slows iteration, limits personalization, and creates dependence on software developers. OBJECTIVE This paper presents CanBeWell, a disease-agnostic telehealth platform that integrates multimodal behavioral data collection with a clinician-operated, code-free intervention authoring and delivery workflow. CanBeWell consists of a patient-facing mobile application, a backend application programming interface (API) and data layer, and a clinician-facing dashboard. We describe the platform's system architecture, design rationale, implementation for cancer survivorship care, and formative stakeholder evaluation. METHODS CanBeWell was developed as a platform-oriented system informed by prior work in remote patient monitoring, mHealth sensing, and adaptive intervention theory. The platform was evaluated through formative semi-structured interviews with cancer patients (n=12) and their caregivers (n=9). [CX3.1]All study participants reviewed the mobile application prototype and provided feedback during in-person interviews on its usability, perceived value, and suggested improvements. Participants also rated the platform's overall usability on a 10-point scale. Additionally, clinicians (n = 6) were provided access to both the patient-facing mobile application and the clinician dashboard to evaluate the platform's usability, functionality, clinical relevance, and intervention workflow. Qualitative data were analyzed using thematic analysis by two independent coders RESULTS Twenty-one participants (patients and caregivers) completed the demographic survey (mean age 49.4 years; 61.9% female; 57.1% non-Hispanic White). Four themes emerged based on patient and caregiver interviews: ease of use, interest in the application, valued features, and overall user-friendliness[CX4.1]. The mean usability rating across patients and caregivers was 9 out of 10. Patients and caregivers valued the phased intervention structure, baseline activity tracking, and incremental goal progression. Clinicians responded positively to the no-code authoring workflow, noting that the ability to review behavioral data, draft content, and deploy approved phases without developer involvement could reduce technical barriers and accelerate intervention refinement[CX5.1]. The most common requested improvement by clinicians was stronger notification support to sustain engagement over longer deployments. CONCLUSIONS CanBeWell extends remote patient monitoring infrastructure by adding a clinician-governed intervention authoring and delivery layer that closes the loop between behavioral sensing and patient-facing support. Formative validation in a cancer survivorship context suggests that the platform is usable and clinically meaningful to patients, caregivers, and clinicians. By separating intervention content from application code, the platform enables clinicians to create and update personalized interventions without extensive programming support, reducing engineering bottlenecks and facilitating scalable implementation across chronic disease settings.

Black transgender women in the United States (US) report a significant burden of minority stress contributing to high post‐traumatic stress disorder (PTSD) and depressive symptom severity and suicidality. Literature suggests Black Americans are less likely than White peers to report suicidal ideation (SI) but more likely to attempt suicide in the last year. Limited research exists to identify specific symptoms that may indicate increased risk of suicidality among Black transgender women who do not disclose SI—limiting clinicians' ability to identify those at risk of suicidality. Our study aimed to compare the prevalence and severity of PTSD and depressive symptoms among Black transgender women who endorse or do not endorse SI. We analyzed cross‐sectional online survey data from a convenience sample of Black transgender women in the US ( N  = 153). Symptoms were measured using the PTSD Symptom Checklist – DSM‐V version and the Beck Depression Inventory‐II. Statistical analyses included Wilcoxon Rank Sum Tests, Fischer's Exact Tests, and logistic regression. Worthlessness, changes in appetite, and severity of total Beck Depression Inventory II (BDI‐II) scores were consistently significantly higher or more prominent in those endorsing SI compared to those who did not. Findings highlight those two symptoms and the total depressive symptom score as potential indicators of suicidality, which highlights opportunities for providers to further assess for SI and consider safety planning even in the absence of SI disclosure. More research is needed with larger samples of gender‐expansive people to further explore these findings.

Purpose: Survivorship in colorectal cancer (CRC) is often accompanied by co-occurring psychoneurological symptoms (PNS, e.g., fatigue, depression, pain), which negatively affect quality of life. Caregivers of individuals with CRC also experience PNS due to caregiving burdens, amplifying distress across the dyad. PNS may be influenced by the activity of the gut microbes. The purpose of this pilot study was to examine gut microbiome diversity and composition, and their association with PNS in CRC patients and their caregivers. Methods: Baseline data from a technology-based dyadic intervention were included in this analysis. Eleven patients and eight caregivers provided stool samples and completed PROMIS measures of PNS at baseline. Gut microbiome profiles were assessed using 16S rRNA gene sequencing. Alpha and beta diversity metrics and differential abundance analyses were used to characterize the gut microbiome and examine its associations with PNS. Results: Patients exhibited significantly lower microbial alpha diversity than caregivers in the full sample ( p = 0.033). Dyadic comparisons identified 92 differentially abundant taxa, with patients showing depletion of short-chain fatty acid-producing taxa and enrichment of opportunistic taxa. Microbiome-symptom models revealed significant interactions by group (patient vs. caregiver) and taxa-level effects, with patients showing stronger positive associations between microbial alterations and higher PNS severity. Conclusions: CRC patients actively on chemotherapy demonstrated reduced diversity and depletion of beneficial taxa that may contribute to heightened PNS. Caregivers, despite healthier profiles, reported substantial symptom burden that were linked to gut microbiome features, highlighting dyadic interdependence and the potential for microbiome-targeted, dyadic interventions in survivorship care.

Probiotics have been increasingly evaluated for their potential effect on anxiety and depression through the modulation of the gut–brain axis. Individuals with cancer experience a high prevalence of these symptoms. However, the effects of probiotics and their underlying mechanisms in this population have not been systematically evaluated. This review synthesizes current evidence regarding probiotic interventions for anxiety and depression in cancer and examines the associated mechanistic pathways. A systematic search for original trials in PubMed, Embase, CINAHL, Web of Science, and PsycINFO was conducted in May 2025. Eligible studies included animal models or adults with cancer who received probiotics alone or in combination with other treatments, with outcomes related to anxiety, depressive symptoms, or depression. Search terms included animal model, cancer, probiotics, anxiety, depressive symptoms, depression, gastrointestinal microbiome, gut microbiome, and microbiota. The review followed PRISMA guidelines. Risk of bias in trials was assessed using the SYRCLE and Cochrane RoB2 tool. Nine studies met the inclusion criteria, including seven human studies, one animal study, and one mixed human–animal study, with human sample sizes ranging from 24 to 266. The animal study reported reductions in depressive and anxiety-like behaviors, paralleled by modulation of the hypothalamic–pituitary–adrenal (HPA) axis, reduced inflammation, rebalancing of the gut microbiota, and improvements in neurotransmitter pathways. Findings from human studies were more variable. Some trials reported improvements in anxiety, and depressive symptoms, while others showed no significant differences compared with control groups. Studies that combined probiotics with antidepressants or exercise demonstrated the most pronounced reductions in anxiety and depression. Mechanistic insights from human studies partially aligned with animal evidence, with several trials showing reductions in inflammatory markers (IL-6, TNF-α), improvements in neuroendocrine measures (serotonin, dopamine, cortisol), stabilization of metabolic markers, and favorable shifts in gut microbiota, although these effects were not consistent across all studies. Probiotics appear to be safe within the intervention periods of the reviewed studies (<24 weeks), as no serious adverse effects were reported. Substantial heterogeneity across studies, including variations in cancer type, intervention duration, probiotic strains, formulations, dosages, and study design combined with small sample sizes, restricts the ability to draw definitive conclusions. Rigorously designed randomized controlled trials with larger sample sizes and mechanistic biomarkers are required to confirm the efficacy of probiotics for relieving anxiety and depression in the cancer population.

Digital health interventions offer promise for scalable and accessible health care, but access is still limited by some participatory challenges, especially for disadvantaged families facing limited health literacy, language barriers, low income, or living in marginalized areas. These issues are particularly pronounced for patients with colorectal cancer (CRC), who often experience distressing symptoms and struggle with educational materials due to complex jargon, fatigue, or reading level mismatches. To address these issues, we developed and assessed the feasibility of a digital health platform, CRCWeb, to improve the accessibility of educational resources on symptom management for disadvantaged patients with CRC and their caregivers facing limited health literacy or low income. CRCWeb was developed through a stakeholder-centered participatory design approach. Two-phase semistructured interviews with patients, caregivers, and oncology experts informed the iterative design process. From the interviews, we developed the following 5 key design principles: user-friendly navigation, multimedia integration, concise and clear content, enhanced accessibility for individuals with vision and reading disabilities, and scalability for future content expansion. Initial feedback from iterative stakeholder engagements confirmed high user satisfaction, with participants rating CRCWeb an average of 3.98 out of 5 on the postintervention survey. Additionally, using generative artificial intelligence tools, including large language models like ChatGPT and multimedia generation tools such as Pictory, complex health care guidelines were transformed into concise, easily comprehensible multimedia content, and made accessible through CRCWeb. User engagement was notably higher among disadvantaged participants with limited health literacy or low income, who logged into the platform 2.52 times more frequently than nondisadvantaged participants. The structured development approach of CRCWeb demonstrates that generative artificial intelligence–powered multimedia interventions can effectively address health care accessibility barriers faced by disadvantaged patients with CRC and caregivers with limited health literacy or low income. This structured approach highlights how digital innovations can enhance health care.

Background: Cancer survivors and their caregivers, particularly those from disadvantaged backgrounds with limited health literacy or racial and ethnic minorities facing language barriers, are at a disproportionately higher risk of experiencing symptom burdens from cancer and its treatments. Large language models (LLMs) offer a promising avenue for generating concise, linguistically appropriate, and accessible educational materials tailored to these populations. However, there is limited research evaluating how effectively LLMs perform in creating targeted content for individuals with diverse literacy and language needs. Objective: This study aimed to evaluate the overall performance of LLMs in generating tailored educational content for cancer survivors and their caregivers with limited health literacy or language barriers, compare the performances of 3 Generative Pretrained Transformer (GPT) models (ie, GPT-3.5 Turbo, GPT-4, and GPT-4 Turbo; OpenAI), and examine how different prompting approaches influence the quality of the generated content. Methods: We selected 30 topics from national guidelines on cancer care and education. GPT-3.5 Turbo, GPT-4, and GPT-4 Turbo were used to generate tailored content of up to 250 words at a 6th-grade reading level, with translations into Spanish and Chinese for each topic. Two distinct prompting approaches (textual and bulleted) were applied and evaluated. Nine oncology experts evaluated 360 generated responses based on predetermined criteria: word limit, reading level, and quality assessment (ie, clarity, accuracy, relevance, completeness, and comprehensibility). ANOVA (analysis of variance) or chi-square analyses were used to compare differences among the various GPT models and prompts. Results: Overall, LLMs showed excellent performance in tailoring educational content, with 74.2% (267/360) adhering to the specified word limit and achieving an average quality assessment score of 8.933 out of 10. However, LLMs showed moderate performance in reading level, with 41.1% (148/360) of content failing to meet the sixth-grade reading level. LLMs demonstrated strong translation capabilities, achieving an accuracy of 96.7% (87/90) for Spanish and 81.1% (73/90) for Chinese translations. Common errors included imprecise scopes, inaccuracies in definitions, and content that lacked actionable recommendations. The more advanced GPT-4 family models showed better overall performance compared to GPT-3.5 Turbo. Prompting GPTs to produce bulleted-format content was likely to result in better educational content compared with textual-format content. Conclusions: All 3 LLMs demonstrated high potential for delivering multilingual, concise, and low health literacy educational content for cancer survivors and caregivers who face limited literacy or language barriers. GPT-4 family models were notably more robust. While further refinement is required to ensure simpler reading levels and fully comprehensive information, these findings highlight LLMs as an emerging tool for bridging gaps in cancer education and advancing health equity. Future research should integrate expert feedback, additional prompt engineering strategies, and specialized training data to optimize content accuracy and accessibility.

Large language models (LLMs) are transforming healthcare by advancing clinical decision support, patient care, and administrative efficiency. However, effectively and sustainably integrating LLMs into healthcare systems requires addressing participatory gaps that may hinder alignment with stakeholders' practical and ethical needs. This paper explores how participatory methods can be applied throughout the development lifecycle of LLM-enhanced health systems (LLMHS), arguing that: 1) participatory approaches are critical for engaging stakeholders in LLMHS development, and 2) LLM techniques can create novel participatory opportunities that reinforce stakeholder engagement while driving technical innovation in LLMHS. This dual perspective highlights the potential of LLMHS to align technical sophistication with real-world healthcare demands, paving the way for next-generation health systems.

Background: Colorectal cancer (CRC) patients and their caregivers often experience multiple co-occurring symptoms (eg, fatigue, depression, anxiety, and sleep disturbance). There is a noticeable gap in research regarding symptom management for patient-caregiver dyads, particularly using technology-based tools. Objective: This study aimed to describe the needs and perceptions of patient-caregiver dyads regarding a technology-based tool to manage their multiple symptoms. Methods: This study utilized a qualitative descriptive design with purposive sampling. Semistructured interviews were conducted with CRC patients undergoing chemotherapy and their caregivers. Thematic analysis was performed to identify key themes. Results: The study included 11 patients and 8 caregivers (8 patient-caregiver dyads and 3 patients without dyads). Four main themes emerged: (1) high symptom burden experienced by CRC patients and their caregivers; (2) symptom self-management strategies, including information seeking and self-education, family and social support, and coping strategies; (3) input and suggestions for technology use, covering aspects such as content, format, and specific technology features; and (4) concerns about barriers to healthcare access, including technological literacy, geographical distance, and time constraints. Conclusions: Our findings provide novel insights into experiences, needs, and suggestions of CRC patient-caregiver dyads for managing multiple symptoms. Participants emphasized the importance of developing a tailored, technology-based tool that includes personalized, evidence-based content; accessible and intuitive design features; and interactive social support capabilities. Implications for Practice: Leveraging these findings, we aim to develop a technology-based dyadic intervention tool that addresses the psychosocial needs of CRC patient-caregiver dyads. This approach can also enhance health equity by making care more accessible.

BACKGROUND Digital health interventions offer promise for scalable and accessible healthcare, but access is still limited by some participatory challenges, especially for disadvantaged families facing limited health literacy, language barriers, low income, or living in marginalized areas. These issues are particularly pronounced for colorectal cancer (CRC) patients, who often experience distressing symptoms and struggle with educational materials due to complex jargon, fatigue, or reading level mismatches. OBJECTIVE This study aimed to address health disparities by improving the accessibility of educational resources on symptom management for disadvantaged CRC patients and their caregivers. METHODS To address these health disparities, we proposed a generative AI (GenAI)-powered system to customize CRC educational materials into accessible multimedia content, delivered by a mobile platform, CRCWeb. We conducted an 8-week single-arm prospective study with 40 participants (20 patients and 20 caregivers) with both disadvantaged and non-disadvantaged backgrounds. RESULTS Analysis of user login activity showed that the login frequency of the disadvantaged group is 2.52 times higher than that of the non-disadvantaged group. Post-intervention ratings from both groups demonstrated significant equivalence (P ≤ .001) in overall satisfaction with CRCWeb. The pre- and post-intervention symptom data showed reductions in symptom scores for both the disadvantaged group (a difference of 0.108, P = .123) and the non-disadvantaged group (a difference of 0.211, P = .002). CONCLUSIONS Our findings highlight the potential of GenAI-powered digital solutions to address gaps in healthcare access, offering support that promotes cancer care and health equity for disadvantaged populations. CLINICALTRIAL ClinicalTrials.gov NCT05663203. INTERNATIONAL REGISTERED REPORT RR2-10.2196/48499