Distinct profiles of multiple co-occurring symptoms in patients with gastrointestinal cancers receiving chemotherapy

Leveraging Artificial Intelligence for Digital Symptom Management in Oncology: The Development of CRCWeb

UNSTRUCTURED

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. 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 CRC patients and their caregivers facing limited health literacy or low income. CRCWeb was developed through a stakeholder-centered participatory design approach. Two-phase semi-structured interviews with patients, caregivers, and oncology experts informed the iterative design process. From the interviews, we developed the following five 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 post-intervention survey. Additionally, using GenAI tools, including large language models (LLMs) like ChatGPT and multimedia generation tools such as Pictory, complex healthcare 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 non-disadvantaged participants. The structured development approach of CRCWeb demonstrates that GenAI-powered multimedia interventions can effectively address healthcare accessibility barriers faced by disadvantaged CRC patients and caregivers with limited health literacy or low income. This structured approach highlights how digital innovations can enhance healthcare.

INTERNATIONAL REGISTERED REPORT

RR2-10.2196/48499.

Evaluation of Large Language Models in Tailoring Educational Content for Cancer Survivors and Their Caregivers: Quality Analysis

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.

Identification of postpartum symptom informedness and preparedness typologies and their associations with psychological health: A latent class analysis

BACKGROUND

Birthing parents, defined as postpartum women and people with various gender identities who give birth, commonly experience challenging postpartum symptoms. However, many report feeling uninformed and unprepared to navigate their postpartum health.

OBJECTIVE

To identify typologies of postpartum symptom informedness and preparedness using latent class analysis (LCA) and to examine the associated patient and healthcare characteristics.

METHODS

We used survey data from a large, multi-method, longitudinal research project Postnatal Safety Learning Lab. Participants were recruited using convenience sampling and enrolled between November 2020 and June 2021. LCA was used to identify subgroups of birthing parents with different symptom informedness and preparedness using 10 binary variables (N = 148). Bivariate analysis was conducted to examine the association between characteristics and each typology.

FINDINGS

The 3-class models had better fit indices and interpretability for both informedness and preparedness typologies: High, High-moderate, and Moderate-low. The sample characteristics were different by typologies. In the modified discrimination in medical settings assessment, we found higher discrimination scores in the moderate-low informedness and preparedness typologies. The moderate-low preparedness typology had a higher percentage of birthing parents who did not have private insurance, underwent cesarean section, and planned for formula or mixed infant feeding. The median PHQ-4 scores at 4 weeks postpartum were lower among those in high informedness and preparedness typologies.

CONCLUSION

In our sample, 18 to 21 % of birthing parents were in the moderate-low informedness or preparedness typologies. Future research and practice should consider providing tailored information and anticipatory guidance as a part of more equitable and supportive care.

Subgroups of ICU patients identified by self-reported symptoms - A prospective multicenter study

BACKGROUND

Intensive care unit (ICU) patients experience several symptoms, yet patterns of symptoms and their relationship with demographic and clinical characteristics have not previously been investigated.

OBJECTIVES

To identify and compare subgroups (i.e. latent symptom classes) of intensive ICU patients based on prevalence of co-occurring symptoms over seven days.

RESEARCH METHODOLOGY

Prospective cohort study of adult ICU patients' self-reports of five symptoms during seven days in ICU. Latent class analysis was applied to identify subgroups of ICU patients.

SETTING

Multicenter study with patients from six mixed ICUs in Norway.

MAIN OUTCOME MEASURES

Patient Symptom Survey was used to assess five symptoms (i.e., thirst, pain, anxiousness, tiredness, shortness of breath).

RESULTS

Among 353 included patients, median age was 63 years and 60.3 % were male. Subgroups of patients were identified in a Low class (n = 126, 35.7 %), Middle Class (n = 177, 50.1 %) and High Class (n = 50, 14.2 %) based on reporting of the prevalence of five symptoms. Patients in the Low class had a low prevalence of all symptoms. Middle Class patients had a high prevalence of thirst and tiredness and a low prevalence of pain, anxiousness and shortness of breath. The High class patients had a high prevalence of all symptoms. Symptom prevalence remained stable in the Low and Middle class over time and increased over time in the High class. There were significant differences among symptom classes in use of mechanical ventilation (p = 0.012), analgesics (p < 0.001), alpha-2 agonists (p = 0.004) and fluid restriction (p = 0.006). Patients in the High class received more of these ICU-treatments.

CONCLUSIONS

Findings suggest that subgroups of ICU patients with distinct symptom experiences can be identified. The High prevalence class patients had consistently high levels of all symptoms across seven ICU days and received more ICU-related interventions.

IMPLICATION FOR CLINICAL PRACTICE

Some ICU patients experience a consistently high prevalence of co-occurring symptoms. Clinicians should be aware of treatment factors that could be linked to a high burden of symptoms.

Identification of subgroups of patients with gastrointestinal cancers based on symptom severity and frequency: A latent profile and latent class analysis

PURPOSE

Identify subgroups of patients with gastrointestinal cancer with different frequency and severity of symptoms and assess differences in demographics, clinical characteristics, and degree of interference with daily life.

METHODS

This was a cross-sectional study. A total of 202 patients with gastrointestinal cancers completed the Chinese version of the MD Anderson Symptom Inventory for Gastrointestinal Cancer Module by convenience sampling. Subgroups of patients were identified using latent profile analysis and latent class analysis. Chi-squared, Mann-Whitney-U, and Kruskal-Wallis tests assessed differences among subgroups.

RESULTS

In terms of symptom severity, low (70.3%), Moderate (13.4%), and high (16.3%) classes were identified. Compared with the other two classes, the Moderate group had a higher proportion of patients with a history of tobacco and alcohol, esophageal cancer, and gastric cancer (P < 0.05). In terms of symptom frequency, all -high (57.9%), high physical symptoms (9.9%), and all-low (32.2%) classes were identified. All-high groups had a younger age and a higher proportion of patients with cancer stage IV (P < 0.05). The high group had the most interference with daily life in both perspectives (P < 0.001), and psycho-emotional symptoms were frequent and severe.

CONCLUSIONS

The two perspectives of symptom severity and frequency can play a complementary role in identifying high-risk groups. Clinical practitioners should strengthen psychological interventions in young and advanced cancer patients and provide pharmaceutical and non-pharmaceutical interventions for dysphagia symptoms in esophageal and gastric cancer patients with a history of tobacco and alcohol.

Associations of differentially expressed genes with psychoneurological symptoms in patients with head and neck cancer: A longitudinal study

OBJECTIVE

Patients with head and neck cancer (HNC) experience psychoneurological symptoms (PNS, i.e., depression, fatigue, sleep disturbance, pain, and cognitive dysfunction) during intensity-modulated radiotherapy (IMRT) that negatively impact their functional status, quality of life, and overall survival. The underlying mechanisms for PNS are still not fully understood. This study aimed to examine differentially expressed genes and pathways related to PNS for patients undergoing IMRT (i.e., before, end of, 6 months, and 12 months after IMRT).

METHODS

Participants included 142 patients with HNC (mean age 58.9 ± 10.3 years, 72.5% male, 83.1% White). Total RNA extracted from blood leukocytes were used for genome-wide gene expression assays. Linear mixed effects model was used to examine the association between PNS and gene expression across time. Gene Ontology (GO) enrichment analysis was employed to identify pathways related to PNS.

RESULTS

A total of 1352 genes (162 upregulated, 1190 downregulated) were significantly associated with PNS across time (false discovery rate (FDR) < 0.05). Among these genes, 112 GO terms were identified (FDR < 0.05). The top 20 GO terms among the significant upregulated genes were related to immune and inflammatory responses, while the top 20 GO terms among the significant downregulated genes were associated with telomere maintenance.

CONCLUSION

This study is the first to identify genes and pathways linked to immune and inflammatory responses and telomere maintenance that are associated with PNS in patients with HNC receiving IMRT. Inflammation and aging markers may be candidate biomarkers for PNS. Understanding biological markers may produce targets for novel interventions.

Patient-Reported Outcomes Measurement Information System in patients with gastrointestinal cancer: a scoping review

PURPOSE

The purpose of this study was to identify and evaluate the use of the Patient-Reported Outcomes Measurement Information System in patients with gastrointestinal cancer, as well as provide references for analyzing treatment outcomes, gauging prognostic risk, and assessing clinical symptoms and function in gastrointestinal cancer patients.

METHODS

PubMed, Web of Science, ProQuest, Embase, and CINAHL were systematically searched using keywords and controlled vocabulary through January 2023.

RESULTS

The scoping review collected 30 studies published from 2012 to 2022, including observational studies (n = 21), interventional studies (n = 4), and mixed studies (n = 5). Outcome indicators included mood, pain, fatigue, sleep, the ability to perform activities of daily living, social functioning, and other health problems.

CONCLUSION

Being a self-report questionnaire, the Patient-Reported Outcomes Measurement Information System offers a full assessment of patient's symptoms and quality of life, and accurately captures their actual thoughts, feelings, and experiences. Individuals with gastrointestinal cancer made frequent use of the Patient-Reported Outcomes Measurement Information System to provide an accurate measure of their health status.

A Web-Based Dyadic Intervention to Manage Psychoneurological Symptoms for Patients With Colorectal Cancer and Their Caregivers: Protocol for a Mixed Methods Study

BACKGROUND

Patients with colorectal cancer (CRC) receiving chemotherapy often experience psychoneurological symptoms (PNS; ie, fatigue, depression, anxiety, sleep disturbance, pain, and cognitive dysfunction) that negatively impact both patients' and their caregivers' health outcomes. Limited information is available on PNS management for CRC patient and caregiver dyads.

OBJECTIVE

The purposes of this study are to (1) develop a web-based dyadic intervention for patients with CRC receiving chemotherapy and their caregivers (CRCweb) and (2) evaluate the feasibility, acceptability, and preliminary effects of CRCweb among patient-caregiver dyads in a cancer clinic.

METHODS

A mixed methods approach will be used. Semistructured interviews among 8 dyads will be conducted to develop CRCweb. A single-group pre- and posttest clinical trial will be used to examine the feasibility, acceptability, and preliminary effects of the intervention (CRCweb) among 20 dyads. Study assessments will be conducted before (T1) and after intervention (T2). Content analysis will be performed for semistructured interviews. Descriptive statistics will be calculated separately for patients and caregivers, and pre-post paired t tests will be used to evaluate treatment effects.

RESULTS

This study was funded in November 2022. As of April 2023, we have obtained institutional review board approval and completed clinical trial registration and are currently recruiting patient-caregiver dyads in a cancer clinic. The study is expected to be completed in October 2024.

CONCLUSIONS

Developing a web-based dyadic intervention holds great promise to reduce the PNS burden in patients with CRC receiving chemotherapy and their caregivers. The findings from this study will advance intervention development and implementation of symptom management and palliative care for patients with cancer and their caregivers.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05663203; https://clinicaltrials.gov/ct2/show/NCT05663203.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/48499.