Search

Background: Hospital call centers play a critical role in providing support and information to patients with cancer, making it crucial to effectively identify and understand patient intent during consultations. However, operational efficiency and standardization of telephone consultations, particularly when categorizing diverse patient inquiries, remain significant challenges. While traditional deep learning models like long short-term memory (LSTM) and bidirectional encoder representations from transformers (BERT) have been used to address these issues, they heavily depend on annotated datasets, which are labor-intensive and time-consuming to generate. Large language models (LLMs) like GPT-4, with their in-context learning capabilities, offer a promising alternative for classifying patient intent without requiring extensive retraining. Objective: This study evaluates the performance of GPT-4 in classifying the purpose of telephone consultations of patients with cancer. In addition, it compares the performance of GPT-4 to that of discriminative models, such as LSTM and BERT, with a particular focus on their ability to manage ambiguous and complex queries. Methods: We used a dataset of 430,355 sentences from telephone consultations with patients with cancer between 2016 and 2020. LSTM and BERT models were trained on 300,000 sentences using supervised learning, while GPT-4 was applied using zero-shot and few-shot approaches without explicit retraining. The accuracy of each model was compared using 1,000 randomly selected sentences from 2020 onward, with special attention paid to how each model handled ambiguous or uncertain queries. Results: GPT-4, which uses only a few examples (a few shots), attained a remarkable accuracy of 85.2%, considerably outperforming the LSTM and BERT models, which achieved accuracies of 73.7% and 71.3%, respectively. Notably, categories such as "Treatment," "Rescheduling," and "Symptoms" involve multiple contexts and exhibit significant complexity. GPT-4 demonstrated more than 15% superior performance in handling ambiguous queries in these categories. In addition, GPT-4 excelled in categories like "Records" and "Routine," where contextual clues were clear, outperforming the discriminative models. These findings emphasize the potential of LLMs, particularly GPT-4, for interpreting complicated patient interactions during cancer-related telephone consultations. Conclusions: This study shows the potential of GPT-4 to significantly improve the classification of patient intent in cancer-related telephone oncological consultations. GPT-4's ability to handle complex and ambiguous queries without extensive retraining provides a substantial advantage over discriminative models like LSTM and BERT. While GPT-4 demonstrates strong performance in various areas, further refinement of prompt design and category definitions is necessary to fully leverage its capabilities in practical health care applications. Future research will explore the integration of LLMs like GPT-4 into hybrid systems that combine human oversight with artificial intelligence–driven technologies. [ABSTRACT FROM AUTHOR]

Objective: This study aims to identify factors associated with divorce following breast cancer diagnosis and measures the impact of divorce on the quality of life (QoL) of patients. Methods: We used cross-sectional survey data collected at breast cancer outpatient clinics in South Korea from November 2018 to April 2019. Adult breast cancer survivors who completed active treatment without any cancer recurrence at the time of the survey (N = 4,366) were included. The participants were classified into two groups: "maintaining marriage" and "being divorced," between at the survey and at the cancer diagnosis. We performed logistic regression and linear regression to identify the factors associated with divorce after cancer diagnosis and to compare the QoL of divorced and nondivorced survivors. Results: Approximately 11.1/1,000 of married breast cancer survivors experienced divorce after cancer diagnosis. Younger age, lower education, and being employed at diagnosis were associated with divorce. Being divorced survivors had significantly lower QoL (Coefficient [Coef] = −7.50; 95% CI = −13.63, −1.36), social functioning (Coef = −9.47; 95% CI = −16.36, −2.57), and body image (Coef = −8.34; 95% CI = −6.29, −0.39) than survivors who remained married. They also experienced more symptoms including pain, insomnia, financial difficulties, and distress due to hair loss. Conclusion: Identifying risk factors of divorce will ultimately help ascertain the resources necessary for early intervention. [ABSTRACT FROM AUTHOR]

Objective: To map how social, commercial, political and digital determinants of health have changed or emerged during the recent digital transformation of society and to identify priority areas for policy action., Methods: We systematically searched MEDLINE, Embase and Web of Science on 24 September 2023, to identify eligible reviews published in 2018 and later. To ensure we included the most recent literature, we supplemented our review with non-systematic searches in PubMed® and Google Scholar, along with records identified by subject matter experts. Using thematic analysis, we clustered the extracted data into five societal domains affected by digitalization. The clustering also informed a novel framework, which the authors and contributors reviewed for comprehensiveness and accuracy. Using a two-round consensus process, we rated the identified determinants into high, moderate and low urgency for policy actions., Findings: We identified 13 804 records, of which 204 met the inclusion criteria. A total of 127 health determinants were found to have emerged or changed during the digital transformation of society (37 digital, 33 social, 33 commercial and economic and 24 political determinants). Of these, 30 determinants (23.6%) were considered particularly urgent for policy action., Conclusion: This review offers a comprehensive overview of health determinants across digital, social, commercial and economic, and political domains, highlighting how policy decisions, individual behaviours and broader factors influence health by digitalization. The findings deepen our understanding of how health outcomes manifest within a digital ecosystem and inform strategies for addressing the complex and evolving networks of health determinants., ((c) 2025 The authors; licensee World Health Organization.)

Purpose: This cross-sectional study aimed to examine which chemotherapy (CTx) terms were most difficult to understand for cancer patients and identify vulnerable patient populations who might need extra support to understand the terms., Materials and Methods: We listed 56 CTx-related terms based on the experts' review, then 300 cancer patients and their caregivers completed a questionnaire that assessed literacy in CTx terms (LCT), functional health literacy, and empowerment. Descriptive analysis was performed to examine which CTx-related terms were most difficult for them. Logistic regression analyses were performed to identify factors associated with LCT level., Results: Of the total 300 people, 162 (54.0%) were in the low-scoring (LS) group in LCT. LS group had a higher proportion of males, lower monthly income, and lived at the province, compared to the high scoring (HS) group. The participants tended to have difficulties in understanding terms related to blood count, risk of infection, and symptoms written in Sino-Korean. In the multivariable logistic regression, male participants (Adjusted Odds Ratio [aOR] = 2.59, 95% confidence interval [CI]: 1.48-4.62), those with no cancer-related information-seeking (aOR = 4.32, 95% CI: 1.75-12.33), and those with low empowerment (aOR = 3.07, 95% CI: 1.83-5.23) were more likely to have a low level of LCT., Conclusion: There were still linguistic health literacy challenges faced by cancer patients and their caregivers, specifically in understanding chemotherapy-related terms. Minimizing medical jargon and Sino-Korean terms and empowering patients to be ready for treatment are necessary.

Introduction: Symptoms due to chemotherapy are common in patients with cancer. Cancer-related symptoms are closely associated with the deterioration of physical function which can be associated with decreased quality of life and increased mortality. Thus, timely symptom identification is critical for improving cancer prognosis and survival. Recently, remote symptom monitoring system using digital technology has demonstrated its effects on symptom control or survival. However, few studies examined whether remote monitoring would contribute to retaining physical function among patients with cancer. Therefore, this study aimed to evaluate the effectiveness of mobile-based symptom monitoring in improving physical function among patients with cancer under chemotherapy., Methods and Analysis: This study is a multicentre, open-label, parallel-group, randomised controlled trial. We will recruit 372 patients at three tertiary hospitals located in Seoul, South Korea. Study participants will be randomly assigned to either an intervention group receiving the ePRO-CTCAE app and a control group receiving routine clinical practice only. The primary outcome is changes in physical function from commencement to completion of planned chemotherapy. A linear mixed model will be performed under the intention-to-treat principle. The secondary outcomes include physical activity level; changes in pain interference; changes in depressive symptom; unplanned clinical visits; additional medical expenditure for symptom management; completion rate of planned chemotherapy; changes in symptom burden and health-related quality of life; and 1-year overall mortality., Ethics and Dissemination: The study has been approved by the institutional review board and ethics committee at the three university hospitals involved in this trial. Written informed consent will be obtained from all the participants. The results of the trial will be submitted for publication in peer-reviewed academic journals and disseminated through relevant literatures., Trial Registration Number: KCT0007220., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Objectives: We developed and validated the Health Literacy Index for the Community (HLIC) to assess the health literacy of the Korean population within the framework of the Korean National Health and Nutrition and Examination Survey., Methods: The HLIC was developed through (1) defining the conceptual framework and generating the item pool and (2) finalizing the items and identifying the cut-off value. Interviews were conducted to examine items' face validity, and a cross-sectional survey was performed to analyze the item-response theory and Rasch models to investigate the instrument's psychometric properties., Results: In this study of 1,041 participants, most had no difficulty understanding health information; however, 67.9% struggled to assess the reliability of health information from the Internet or media. A 4-factor structure was identified through factor analysis, leading to the exclusion of some items. This resulted in 10 items across 4 domains: (1) disease prevention, (2) health promotion, (3) health care, and (4) technology and resources. The HLIC demonstrated good internal consistency, with a Cronbach's α of 0.87. It also showed high test-retest reliability and correlations with other health literacy instruments. A socio-demographic analysis of the HLIC revealed disparities in health literacy across various age groups, education levels, and income brackets., Conclusions: The HLIC was developed to systematically measure health literacy in Korea's general population. Its simplicity and conciseness ensure reliability and validity and improve its accessibility, making it particularly suitable for the broader Korean population, including those with lower literacy levels.

Purpose: The purpose of the study was to validate the Korean version of Patient-Reported Outcomes Measurement Information System 29 Profile v2.1 (K-PROMIS-29 V2.1) among cancer survivors., Materials and Methods: Participants were recruited from outpatient clinics of the Comprehensive Cancer Center at the Samsung Medical Center in Seoul, South Korea, from September to October 2018. Participants completed a survey questionnaire that included the K-PROMIS-29 V2.1 and the European Organisation for Research and Treatment of Cancer Quality of Life Core Questionnaire (EORTC QLQ-C30). Principal component analysis and confirmatory factor analysis (CFA) and Pearson's correlations were used to evaluate the reliability and validity of the K-PROMIS-29 V2.1., Results: The mean age of the study participants was 54.4 years, the mean time since diagnosis was 1.2 (±2.4) years, and 349 (87.3%) completed the entire questionnaire. The Cronbach's alpha coefficients of the seven domains in the K-PROMIS-29 V2.1 ranged from 0.81 to 0.96, indicating satisfactory internal consistency. In the CFA, the goodness-of-fit indices for the K-PROMIS-29 V2.1 were high (comparative fit index, 0.91 and standardized root-mean-squared residual, 0.06). High to moderate correlations were found between comparable subscales of the K-PROMIS-29 V2.1 and subscales of the EORTC QLQ-C30 (r=0.52-0.73)., Conclusion: The K-PROMIS-29 V2.1 is a reliable and valid measure for assessing the health-related quality of life domains in a cancer population, thus supporting their use in studies and oncology trials.