Cancer-related Information Research Articles

Measuring what really matters: Advocacy-led co-creation and accrual of a pan-cancer QoL survey.

240 Background: Implementing co-creation methods in research may provide vital input to improve accrual, retention, and research value. Advocates for Collaborative Education (ACE), a global coalition of patient, community, research, and policy advocates, used co-creation methodology with patients, survivors, and metavivors to Design, Develop , and Deploy a survey to define and quantify QoL impacts across a large sample of individuals with a diagnosis or history of cancer. Methods: With a defined primary objective to “gain insight into challenges faced by individuals with a history or diagnosis of cancer and how these challenges impact their life and quality of life,” a co-creation team of individuals with lived experience in early stage or metastatic cancers was established. In the Design phase, co-creation team members were interviewed and engaged in discussions on side effect measurement and impact. They were asked a variety of questions, including what side effects they believed were most impactful to QoL, what elements they felt were missing in conversations around QoL, and how accurately they felt QoL was measured in the clinical setting. In the Develop phase, survey questions were developed and vetted with the co-creation team. In the Deploy phase, co-creation team members, advocate members of the ACE community, and aligned advocacy groups, were key to recruiting a broad audience via electronic distribution and social media platforms. Results: Efforts resulted in the co-creation of a six-section, 93 question, IRB-exempt survey. The co-creation team identified 17 treatment-related side effects that were incorporated into the survey. Survey questions asked respondents about perceived severity of side effects, how well informed they felt about possibilities of experiencing these side effects, access to supportive care, side effects of supportive care therapies, and personal preferences for receiving cancer-related information. A unique measurement scale was shaped by the co-creation team to be more reflective of side effect impact on QoL. In five weeks, the survey accrued over 500 responses across a variety of cancer types (15+), stages (0 - IV), ages, statuses, and racial groups. Conclusions: Co-creation methods were used in Design to identify side effect experiences in cancer treatment and validate what matters most to individuals with cancer; in Develop to validate a pan-cancer survey examining what mattered to the audience of interest; and in Deploy to rapidly accrue a large and diverse set of responses through advocacy partnerships. Co-creation also identified layers of side effect management challenges that cannot be reflected in current rubrics for QoL measurement. While co-creation may seem daunting, this study provides a template for effective, quality partnerships between study teams, advocates, and advocacy groups for implementing co-creation methods in the cancer setting.

The Digital Health Revolution: Exploring the Impact of Online Cancer Information on Self-Reported Preventive Behaviors.

Cancer, one of the leading causes of death worldwide, is a disease characterized by uncontrolled cell growth within the body. While there have been many improvements in the treatment of cancer clinically, there is now an urgent need to improve cancer-related communication. This study explores the impact of online health information, specifically cancer-related information and prevention, among members of the general public. Through a randomized survey, we examined what information leads people to take action to minimize their cancer risk and communicate with their providers. Through evaluation of the various modes of communication, we were able to provide insight into which are more effective and better received by members of the general public. Through this, ways of bettering these avenues of communication and strengthening the bond between them will be highlighted and more easily elaborated on by future studies. The results of our study indicated that 60% of participants asserted that they are motivated by online preventive information to take steps to limit their cancer risk, while only roughly 44% of participants overall agreed that their doctor has communicated with them about when proper cancer screenings should be scheduled for the future. Although patients may be turning to the Internet now more than ever due to various reasons, when comparing self-reported rates of comprehension among the study participants, 35% agreed that the cancer-related information they can access online is confusing, while fewer than 22% of participants agreed that the cancer-related information they receive directly from their doctor is confusing. This is indicative of the limitations the Internet may have when undertaking the role of being a medical resource, especially when acting as a replacement for in-person medical appointments where patients can communicate directly with their physicians. Ultimately, these results provide a unique perspective into how people receive, evaluate, and implement cancer-preventive steps and general health-related information in a post-COVID-19 world, where the Internet is now strongly embedded in healthcare.

Family-centered care for child cancer treatment in Ethiopia—A qualitative descriptive study

BackgroundFamilies are the primary source of support and strength in the care process of children with cancer. Family-centered care (FCC) is a healthcare delivery approach that considers parents as both partners and care recipients, characterized by providing care based on dignity and respect, information sharing, participation, and collaboration or partnership. AimThis study aimed to describe the delivery of care based on the family-centered care approach at the Tikur Anbessa Specialized Hospital pediatric cancer unit. MethodAn exploratory, descriptive qualitative study was conducted from March 2023 to August 2023. Eighteen participants (thirteen parents and five health care providers) were interviewed using a semi-structured interview guide. All interviews were audio-recorded, transcribed verbatim, and translated into English. The translated transcripts were used for inductive, data-driven thematic analysis. ATLAS.ti 9 software was used to assist the analysis process. ResultTwo themes have emerged during the analysis. These are (1) Information sharing, and (2) Enabling and partnership. Under the information sharing theme, we described parents' understanding of child cancer, parents' information-related expectations, the process of obtaining information, adequacy of information received, and factors inhibiting information sharing. Under the enabling and partnership theme, we presented family participation in childcare, discussion among parents, parents' communication with healthcare providers and psychosocial support. ConclusionSuboptimal implementation of family-centered care practice was identified at the pediatric oncology unit. Practice implicationsThe findings from this study indicate the need to strengthen the provision of child cancer-related information, improve communication, and strengthen family participation in childcare.

Prioritising Key Concepts for informed health choices in cancer: An evidence-based online educational programme

ObjectiveThe overabundance of health misinformation has undermined people's capacity to make evidence-based, informed choices about their health. Using the Informed Health Choices (IHC) Key Concepts (KCs), we are developing a two-stage education programme, Informed Health Choices-Cancer (IHC-C), to provide those impacted by cancer with the knowledge and skills necessary to think critically about the reliability of health information and claims and make well-informed choices. Stage 1 seeks to prioritise the most relevant Key Concepts. MethodsA project group and a patient and carer participation group completed a two-round prioritisation process. The process involved disseminating pre-reading materials, training sessions, and a structured judgement form to evaluate concepts for inclusion. Data from each round were analysed to reach a consensus on the concepts to include. ResultsFourteen participants were recruited and completed the first-round prioritisation. Fifteen participants undertook the second-round prioritisation. Nine Key Concepts were selected for the programme across five training sessions and two consensus meetings. ConclusionThe prioritised concepts identified represent the most pertinent aspects of cancer-related information for those impacted by the disease. By incorporating these concepts into educational materials and communication strategies, healthcare providers and organisations can potentially help cancer patients, survivors, and their loved ones to recognise and combat cancer-related misinformation more effectively. InnovationThis study introduces a participatory prioritisation process, which integrates the expertise of healthcare professionals with the insights of patients and carers, thereby enhancing the programme's relevance and applicability.

Influenza Vaccine Hesitancy among Cancer Survivors in China: A Multicenter Survey.

Cancer survivors are at higher risk of developing severe complications from influenza due to their compromised immune systems. Despite their increased vulnerability to influenza and the availability of vaccines, vaccine hesitancy among cancer survivors remains a significant public health concern in China. A multicenter, cross-sectional study was conducted among cancer survivors in China from January to December 2023. A total of 500 participants were recruited from the oncology departments of five tertiary hospitals. A structured, self-administered questionnaire was used to collect data on socio-demographic characteristics, cancer-related information, medical history, lifestyle factors, and influenza vaccine hesitancy. Univariate and multivariate logistic regression analyses were performed to identify factors associated with influenza vaccine hesitancy. The response rate was 97.0% (485/500). Among all participants, 204 (42.06%) reported vaccine hesitancy. The results of multiple logistic regression showed that the longer the end of anti-cancer treatment, without a history of adverse vaccine reactions, and the level of family support played a protective role in vaccine hesitancy. Current rehabilitation status, frequent colds, not being informed by doctors about vaccination, exercising, lack of community vaccination education programs, and concerns about vaccine safety were risk factors that increase vaccine hesitancy. A high proportion of cancer survivors in our study reported influenza vaccine hesitancy. Addressing concerns about vaccine safety, improving access to vaccination services, and enhancing doctor-patient communication are crucial for increasing influenza vaccine uptake in this vulnerable population.

Natural language processing pipeline to extract prostate cancer-related information from clinical notes.

To develop an automated pipeline for extracting prostate cancer-related information from clinical notes. This retrospective study included 23,225 patients who underwent prostate MRI between 2017 and 2022. Cancer risk factors (family history of cancer and digital rectal exam findings), pre-MRI prostate pathology, and treatment history of prostate cancer were extracted from free-text clinical notes in English as binary or multi-class classification tasks. Any sentence containing pre-defined keywords was extracted from clinical notes within one year before the MRI. After manually creating sentence-level datasets with ground truth, Bidirectional Encoder Representations from Transformers (BERT)-based sentence-level models were fine-tuned using the extracted sentence as input and the category as output. The patient-level output was determined by compilation of multiple sentence-level outputs using tree-based models. Sentence-level classification performance was evaluated using the area under the receiver operating characteristic curve (AUC) on 15% of the sentence-level dataset (sentence-level test set). The patient-level classification performance was evaluated on the patient-level test set created by radiologists by reviewing the clinical notes of 603 patients. Accuracy and sensitivity were compared between the pipeline and radiologists. Sentence-level AUCs were ≥ 0.94. The pipeline showed higher patient-level sensitivity for extracting cancer risk factors (e.g., family history of prostate cancer, 96.5% vs. 77.9%, p < 0.001), but lower accuracy in classifying pre-MRI prostate pathology (92.5% vs. 95.9%, p = 0.002) and treatment history of prostate cancer (95.5% vs. 97.7%, p = 0.03) than radiologists, respectively. The proposed pipeline showed promising performance, especially for extracting cancer risk factors from patient's clinical notes. The natural language processing pipeline showed a higher sensitivity for extracting prostate cancer risk factors than radiologists and may help efficiently gather relevant text information when interpreting prostate MRI. When interpreting prostate MRI, it is necessary to extract prostate cancer-related information from clinical notes. This pipeline extracted the presence of prostate cancer risk factors with higher sensitivity than radiologists. Natural language processing may help radiologists efficiently gather relevant prostate cancer-related text information.

Hidden advertisements included in cancer information posts: Insights from social listening.

e21017 Background: Access to cancer information on the Internet has proliferated, yet ensuring the accuracy and reliability of such information remains a challenge. The abundance of online content necessitates a comprehensive understanding of the prevailing landscape of cancer information dissemination. Methods: Cancer-related information was retrieved from search engine results pages of NAVER and Google, the most frequently used websites for information search in South Korea, during September and October 2023. Promoted posts and overt advertisements were excluded from the dataset. Posts featuring more than 50% of advertising content were categorized as fully hidden advertisements (HA), while those with lesser proportions were classified as partially HA. In cases where there was no advertising content but the hospital name or contact information was indicated for promotional purposes, it was classified as a simple HA. Topic modeling techniques were employed to analyze the content of HA posts, identifying prevalent themes and keywords indicative of promotional intent. Results: Of the collected posts, 48.6% were classified as HA. The publisher of the HA was 26.8% of oriental medicine/care hospitals, followed by general hospitals (25.3%), non-professional (21.3%), and small and medium-sized private hospitals (17.4%). In HA, 40.3% were full advertisements, 36.75% were partial advertisements, and the remainder were simple displays. By cancer type, 65.3% of posts about breast cancer were advertising posts, 55.2% were about colon cancer, and 53.7% were about stomach cancer. In the topic modeling analysis of HA, despite containing basic and theoretical information about cancer, HA subtly directs users towards advertising content, featuring terms related to private insurance and complementary medicine. Conclusions: The study elucidates the prevalence and characteristics of HA within cancer-related information available online, highlighting the need for heightened awareness. While it may not be inherently wrong, HA can impact user perception and decision-making processes. Additional research is underway to determine whether information classified as HA can be trusted. Addressing issues such as HA within cancer information will likely require cooperation between search engine platforms and government agencies.

Access to cancer center information for patients with limited English proficiency from NCI Cancer Center websites.

e23124 Background: Patients with Limited English Proficiency (LEP) can experience health disparities in cancer care and clinical trial participation. This study sought to assess the availability of information on interpreter services, clinical trials, and second opinions from National Cancer Institute – Designated Cancer Center (NCI-DCC) websites for patients with LEP. Methods: The public facing websites of all 65 adult NCI-DCCs were reviewed from January 1, 2023 to May 15, 2023 to assess availability of English and translated, non-English information on interpreter services, second opinion programs, and clinical trials. Data abstraction was conducted through predefined criteria for website inspection and search bars. Three authors independently abstracted websites for content, with constant comparison until consensus was achieved. Chi-square tests were used to ascertain any significant association between the proportion of LEP populations served by the centers ( &gt; 5%) and their likelihood to provide translated information. Results: 92.3% of NCI-DCCs and their affiliated flagships hospitals provide information on interpreter services for patients with LEP. This information was translated into a non-English language approximately half of the time. All NCI-DCC center webpages provide information on clinical trials and 38.5% provide information regarding second opinions. There was no difference in the availability of translated information on interpreter services or second opinion programs based on percentage of LEP population. However, there was an association between higher LEP population and the provision of translated clinical trial pages. Conclusions: The majority of NCI-DCCs provide information on their webpages related to interpreter services and clinical trials. Half of these centers provide this information in a non-English language and there was an association between higher percentage of LEP populations in the NCI-DCC state and translated clinical trial pages. Future work should identify optimal methods to provide cancer related information to patients with LEP with the goal of improving clinical trial participation for LEP populations. [Table: see text]

Unveiling impacts: A quality of life survey for individuals with a history or diagnosis of cancer.

e23179 Background: Cancer treatments, despite increasing effectiveness, involve significant short and long-term side effects profoundly impacting a person's quality of life (QoL). In response, Advocates for Collaborative Education, a global coalition of patient advocates, initiated an exempt, online survey to gather insights on the perceived QoL impact of cancer diagnosis and treatment. The effort sought to identify community priorities and hopes to guide improvements in supportive care. Methods: A comprehensive survey, developed by patients, survivors, and advocates, comprised six sections and 93 questions. Co-creation played a vital role in determining relevant categories, questions, and measurement scales to assess severity and impact of QoL challenges. The study requested demographic and cancer diagnosis data before inquiring about 17 treatment-related side effects, their perceived severity, preparation, unintended side effects of supportive care, and personal preferences for cancer-related information. Recruitment was conducted via social media. Results: The survey garnered responses from 515 individuals with a history of cancer and a wide range of demographic subsets, including age, race, stage of cancer, and treatment modalities. Survey respondents reported an average pre-diagnosis QoL score of 8.87 out of 10, which declined to a mean score of 6.41 post-diagnosis. Across all cancer types, physical well-being was a top priority for most respondents (51.5%), followed by emotional well-being (25.4%). Across a variety of side effects, unintended consequences of side effect treatments were highlighted, revealing complexities in supportive care. Detailed results for all categories and stratification by subsets of age, race, metastatic vs. early stage, treatment type, and others are available for presentation and publication purposes. Conclusions: This study highlights the significant negative impact of cancer treatment on an individual's QoL, addressing an underexplored area of cancer research. While managing treatment side effects is crucial, supportive therapies may introduce additional side effects, exacerbating an overall burden on patients. The collaborative survey development with patients and survivors represents a pivotal step, offering valuable insights for enhancing the well-being of individuals affected by cancer. [Table: see text]

Exploring Health Information-Seeking Behavior and Information Source Preferences Among a Diverse Sample of Cancer Survivors: Implications for Patient Education.

This study examined health information-seeking behavior among cancer survivors, including informational sources used and the factors correlated with information-seeking across different racial/ethnic groups. We used data from the Health Information National Trends Survey (2017-2022). Adjusted logistic regression was conducted to identify the predictors of information-seeking by race/ethnicity. Predicting variables were organized into demographic (age, education, race, income, and comorbidity), enabling (having health insurance, having a regular provider, and frequency of care visits), predisposing (quality of care, self-efficacy, and confidence in one's ability to get information), and reinforcing (patient-centered communication, ease of getting information, and confusing information available) factors based on the PRECEDE-PROCEED Model. We included 4723 cancer survivors, of which 15.41% have breast cancer, 17.50% have skin cancer, and 11.11% have prostate cancer. A majority (75.08%) had sought health information. Healthcare providers were the most preferred sources of information across demographic groups, followed by the Internet. Health insurance, a regular provider, and frequent visits were enabling factors that positively influenced information-seeking behavior. Confidence in getting information when needed and self-efficacy were predisposing factors positively associated with the information-seeking behavior. Finally, reinforcing factors (ease of getting information and non-confusion of the information available) were also positively associated with information-seeking. Study findings suggest that one-fourth of cancer survivors had not sought cancer-related information. The results have implications for identifying patients at increased risk for unmet information needs. They also contribute to our understanding of critical racial differences and similarities. Further, findings can help guide interventions to assist in information seeking based on patient preferences.

Abstract PO3-28-01: More Than a Diagnosis: An Untold Story of Quality of Life

Abstract Background Advocates for Collaborative Education, a global coalition of patient, community, research, and policy advocates, initiated an anonymous, online survey to assess Quality of Life (QoL) impacts of cancer diagnosis and treatment to inform research, clinical care, and the broader cancer community. Identifying what matters most to individuals can potentially guide improvements in supportive care to effectively address QoL impacts. Methods A six-section, 93 question survey was co-created by patients, survivors, and advocates. Co-creation was instrumental in determining categories, specific questions, and measurement scales used to assess severity and impact of QoL challenges. Beyond demographic, treatment, and cancer diagnosis data, co-creation participants identified seventeen (17) treatment-related side effects. Survey questions asked about these side effects, their perceived severity, how well informed they felt about possibilities of experiencing these side effects, supportive care access, side effects of supportive care therapies, and personal preferences for receiving cancer-related information. Recruitment efforts for this online survey were conducted through advocacy groups and social media platforms. Results Across a wide range of demographic subsets, including age, race, stage of cancer, and treatment modalities, 334 respondents with a history of breast cancer reported a decline in QoL scores pre cancer vs post cancer according to the co-created measurement tool. Physical and emotional well-being emerged as top priorities for most respondents, 47.9% and 27.5% respectively. Of 17 listed side effects, respondents cited fatigue (49%), muscle/joint pain (36%), and emotional distress (35%) as primary concerns, with sexual dysfunction and cognitive impairment ranking prominently. Forty-six percent reported severe (frequent &amp; highly disruptive) to very severe (constant &amp; severely impacting quality of life) emotional distress, but only 55% of those felt informed or well informed about the possibility of emotional distress. Among respondents, only 41% received a plan to address emotional distress. Many felt unprepared for physical side effects as well. While 54% of individuals experienced diarrhea or fecal incontinence as a treatment side effect, 22% of affected individuals did not feel informed about the possibility of such side effects. Survey findings also highlight consequences of treatments to manage side effects. For example, 37% of respondents were prescribed treatment to address diarrhea and 100% of these patients reported additional side effects stemming from this supportive care including nausea, constipation, and fatigue. Detailed results for all categories as well as stratification by subsets of age, race, metastatic vs. early stage, treatment type, and others will be available for presentation and publication. Conclusion This study sheds light on an underexplored area of cancer research. Management of treatment side effects is integral to supportive care, yet supportive medications can introduce a cascade of their own side effects, exacerbating the overall burden on patients. Information and education are critical to bridge the gap. The collaboration with patients and survivors in developing this survey represents a pivotal step in determining areas that demand attention for improving QoL and offers valuable insights aimed at enhancing the well-being of individuals affected by cancer and additional research will pursue collaborative solutions. Demographic and High Level QoL Responses from MTAD (Breast) Detailed data on perceived severity, impact to QoL, perceived preparation for, and relevant supportive care is available for each side effect Citation Format: Stacey Tinianov, Kelly Shanahan, Catherine Thomsen, Ginny Mason, Laura Carfang, Joanne Mika Hayashi, Laurie Hutcheson. More Than a Diagnosis: An Untold Story of Quality of Life [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO3-28-01.

The Role of Social Determinants of Health in Seeking Cancer-Related Information and Influencing Cancer Screening Behaviors Among U.S. Adult Women Aged 40–65 Years [ID 2683457

INTRODUCTION: Social determinants of health (SDOH) influence patients’ breast health and their decision and ability to screen for breast cancer. Our study aims to provide a general overview of SDOH acting as significant predictors of mammogram completion across different timeline categories (1–5 years ago, &gt;5 years ago, and never had a mammogram) compared to having a mammogram a year ago or less. METHODS: The data were obtained from the 2020 Health Information National Trends Survey 5 (HINTS 5) Cycle 4, which was administered from February through June 2020 to a total of 2,204 females. Multinomial logistic regression was carried out to identify SDOH acting as predictors of mammogram completion for three different timeline categories (1–5 years ago, &gt;5 years ago, and never had a mammogram) compared to having a mammogram a year ago or less. RESULTS: The SDOH predictor variables varied as predictors of mammogram completion across the three timeline categories. For the “mammogram 1–5 years ago” category, being Black, not having a full-time job, being single, and not having health insurance were seen as significant predictors of the screening behavior. For the “mammogram &gt;5 years ago” category, identifying as widowed and not having health insurance showed significance as predictors of breast cancer screening. For the “never had a mammogram” category, all age categories &gt;25 years of age, identifying as Black, being single, and not having health insurance were recorded as significant predictors of mammography. Health insurance was consistently seen as a significant predictor of mammogram completion across the different timeline categories. CONCLUSION: Future interventions should consider insurance status as an important factor influencing a woman’s decision to seek breast cancer screening. However, a holistic approach integrating the diverse aspects of the SDOH will be more effective in understanding the different barriers hindering at-risk women from seeking annual mammography.

Shared decision-making needs, barriers, and facilitators of patients with newly diagnosed advanced cancer in the hospital: a multi-level, mixed-methods study

PurposeLittle is known about the shared decision-making (SDM) needs, barriers, and facilitators of patients with newly diagnosed advanced cancer in the hospital. Understanding this may improve SDM and cancer care quality in this vulnerable population.MethodsA single-site, mixed-methods study of hospitalized patients with newly diagnosed advanced cancer, caregivers, and oncologists was conducted. After discharge, patient ± caregiver semi-structured interviews exploring SDM needs, barriers, and facilitators regarding their most important upcoming cancer-related decision were conducted. Oncologists were surveyed about patient knowledge and SDM needs using closed- and open-ended questions, respectively. Thematic analysis was performed for qualitative data with a focus on themes unique to or amplified by hospitalization. Descriptive statistics and the Chi-squared test were performed for quantitative data.ResultsPatients and caregivers reported high SDM needs surrounding treatment and prognostic information, leading to decisional conflict. Eight themes emerged: anticipated cancer treatment decisions, variable control preferences in decision-making, high cancer-related information needs and uncertainty, barriers and facilitators to information gathering during and post hospitalization, and decision-making facilitators. Among 32 oncologists, most (56%) reported patients were poorly informed about treatment and prognosis. Oncologists reported variable expectations about patient knowledge after hospitalization, facilitators to patient decision-making, and patient uncertainty while awaiting an outpatient oncologist appointment.ConclusionPatients newly diagnosed with advanced cancer in the hospital have high SDM needs and experience decisional conflict. This may be due to barriers unique to or exacerbated by hospitalization. Further research is needed to develop strategies to address these barriers and enhance the facilitators identified in this study.

Internet-based eHealth technology for emotional well-being among the older adults with a family cancer history: full mediation effects of health information self-efficacy and cancer fatalism

BackgroundOlder adults with a family cancer history (FCH) face an increased cancer risk, which may adversely impact their emotional well-being. Internet-based eHealth technologies (IETs) provide a potential solution to this challenge. This study examines the influence of using IETs on the emotional well-being of older adults with FCH. It also delves into the mediating pathways through health information self-efficacy and cancer fatalism.MethodsThis study conducted a mediation analysis using data from the Health Information National Trends Survey (HINTS 6) collected from March 2022 to November 2022, focusing on older adults with FCH who had previously searched for cancer-related information (N = 1,280).ResultsIn the mediation model, no positive direct associations between IETs usage and emotional well-being were found. Only health information self-efficacy and cancer fatalism were found to mediate the relationship between IETs usage and emotional well-being serially (β = 0.007, 95% CI [0.003, 0.012]).ConclusionsThe findings inform health information professionals and healthcare practitioners on enhancing the impact of IETs usage on individual health information self-efficacy, which mitigates cancer fatalism, contributing to better emotional well-being in the digital era.

Integrating predictive coding and a user-centric interface for enhanced auditing and quality in cancer registry data

Data curation for a hospital-based cancer registry heavily relies on the labor-intensive manual abstraction process by cancer registrars to identify cancer-related information from free-text electronic health records. To streamline this process, a natural language processing system incorporating a hybrid of deep learning-based and rule-based approaches for identifying lung cancer registry-related concepts, along with a symbolic expert system that generates registry coding based on weighted rules, was developed. The system is integrated with the hospital information system at a medical center to provide cancer registrars with a patient journey visualization platform. The embedded system offers a comprehensive view of patient reports annotated with significant registry concepts to facilitate the manual coding process and elevate overall quality. Extensive evaluations, including comparisons with state-of-the-art methods, were conducted using a lung cancer dataset comprising 1428 patients from the medical center. The experimental results illustrate the effectiveness of the developed system, consistently achieving F1-scores of 0.85 and 1.00 across 30 coding items. Registrar feedback highlights the system’s reliability as a tool for assisting and auditing the abstraction. By presenting key registry items along the timeline of a patient’s reports with accurate code predictions, the system improves the quality of registrar outcomes and reduces the labor resources and time required for data abstraction. Our study highlights advancements in cancer registry coding practices, demonstrating that the proposed hybrid weighted neural-symbolic cancer registry system is reliable and efficient for assisting cancer registrars in the coding workflow and contributing to clinical outcomes.

Examining the role of ChatGPT in promoting health behaviors and lifestyle changes among cancer patients.

Purpose: This study aims to investigate the role of ChatGPT in promoting health behavioral changes among cancer patients. Methods: A quasi-experiment design with qualitative approach was adopted in this study, as the ChatGPT technology is novel, and many people are unaware of it. The participants included outpatients at a public hospital. An experiment was carried out, where the participants used ChatGPT for seeking cancer related information for two weeks, which is then followed by focus group (FG) discussions. A total of 72 outpatients participated in ten focus groups. Results: Three main themes with 14 sub-themes were identified reflecting the role of ChatGPT in promoting health behavior changes. Its prominent role was observed in developing health literacy, promoting self-management of conditions through emotional, informational, motivational support. Three challenges including privacy, lack of personalization, and reliability issues were identified. Conclusion: Although ChatGPT has a huge potential in promoting health behavior changes among cancer patients, its ability is minimized by several factors such as regulatory, reliability, and privacy issues. There is a need for further evidence to generalize the results across the regions.

Contents analysis of thyroid cancer-related information uploaded to YouTube by physicians in Korea: endorsing thyroid cancer screening, potentially leading to overdiagnosis

BackgroundThyroid cancer overdiagnosis is a major public health issue in South Korea, which has the highest incidence rate. The accessibility of information through the Internet, particularly on YouTube, could potentially impact excessive screening. This study aimed to analyze the content of thyroid cancer-related YouTube videos, particularly those from 2016 onwards, to evaluate the potential spread of misinformation.MethodsA total of 326 videos for analysis were collected using a video search protocol with the keyword “thyroid cancer” on YouTube. This study classified the selected YouTube videos as either provided by medical professionals or not and used topic clustering with LDA (latent dirichlet allocation), sentiment analysis with KoBERT (Korean bidirectional encoder representations from transformers), and reliability evaluation to analyze the content. The proportion of mentions of poor prognosis for thyroid cancer and the categorization of advertising content was also analyzed.ResultsVideos by medical professionals were categorized into 7 topics, with “Thyroid cancer is not a ‘Good cancer’” being the most common. The number of videos opposing excessive thyroid cancer screening decreased gradually yearly. Videos advocating screening received more favorable comments from viewers than videos opposing excessive thyroid cancer screening. Patient experience videos were categorized into 6 topics, with the “Treatment process and after-treatment” being the most common.ConclusionThis study found that a significant proportion of videos uploaded by medical professionals on thyroid cancer endorse the practice, potentially leading to excessive treatments. The study highlights the need for medical professionals to provide high-quality and unbiased information on social media platforms to prevent the spread of medical misinformation and the need for criteria to judge the content and quality of online health information.

Abstract 4840: Creating a culturally sensitive manual to increase clinical trial participation among African Americans and African Nationals

Abstract Background: Racial and ethnic minorities are immensely underrepresented in clinical trial studies in the United States. Black/African Americans, Latinos/as, Asians, American Indians, and Pacific Islanders make up roughly 30% of all clinical trials (CT) participation across all race groups. Being inclusive of all populations in CT ensures that everyone has access to modern medicines and treatments, but also, that these latest treatments work and react well to all people. Methods: We developed a manual on clinical trials with a target focus to African Americans and African Nationals. We hosted two focus groups with Blacks/African Americans in which we found they are more comfortable getting cancer related information through trusted community services, such as coming from churches. We have connected with over 80 Pastors who agreed to collaborate in clinical trials education. Results: Through outreach and engagement to African American churches in Los Angeles County, we have distributed a copy of this clinical trials educational manual to 90 churches to be disseminated during their services. Our office of Community Outreach and Engagement (COE) regularly attend community health and resource events and provide hard copies of the clinical trials manual at tables/booths designated for our participation. We have attended 50 community events and have disseminated about 1,900 copies of the CT manual so far this year 2023. This manual is also available for free download on our cancer center’s website, in which over 100 toolkits have been downloaded within the last year. Conclusions: By creating a culturally sensitive and adapted educational manual and partnering with trusted services in the community such as faith-based organizations, we can begin to break down barriers to clinical trials participation among all race and ethnic minority groups. Citation Format: Carolina Aristizabal, Eduardo Ibarra, Lourdes A. Baezconde-Garbanati. Creating a culturally sensitive manual to increase clinical trial participation among African Americans and African Nationals [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4840.

A review of cancer data fusion methods based on deep learning

With advancements in modern medical technology, an increasing amount of cancer-related information can be acquired through various means, such as genomics, proteomics, imaging, and pathology. However, these datasets come from diverse sources and possess heterogeneity and complexity in terms of data types, formats, and quality, which pose challenges for cancer diagnosis, treatment, and prognosis evaluation. Data fusion has emerged as an effective approach to address data heterogeneity and enhance data information value. Integrating cancer data of different origins and types can improve diagnostic accuracy and deepen our profound understanding of cancer. Currently, data fusion methods based on deep learning have gained considerable attention in cancer research. This study presents a comprehensive review of the most recent research and development trends of deep learning-based data fusion in cancer, with emphasis on the advancements of various data fusion methods based on heterogeneous data types (including specific methodologies, their pros, and cons), which offer substantial support for enhancing the precision of diagnosing and treating cancer. Furthermore, we present an overview of prevalent cancer data types and fusion approaches and analyze the general modeling methodologies based on deep learning. We further discuss the challenges and future directions, aiming to provide assistance and guidance for researchers endeavoring to devise deep learning solutions in the sphere of cancer research.

Characterizing user demographics in posts related to breast, lung and colon cancer on Japanese twitter (X)

Various cancer-related information is spreading on social media. Our study aimed to examine the account types associated with cancer-related tweets (currently known as posts) on Twitter (currently known as X) in Japan, specifically focusing on breast, lung, and colon cancer. Using the Twitter application programming interface, we collected tweets containing keywords of the three cancers type in August–September 2022. The accounts were categorized into seven types: Survivor, Patient’s family, Healthcare provider, Public organization, Private organization, News, and Other according to account name and texts. We analyzed the sources of the top 50 most liked and retweeted tweets. Out of 7753 identified tweets, breast cancer represented the majority (62.8%), followed by lung cancer (20.8%) and colon cancer (16.3%). Tweets came from 4976 accounts. Account types varied depending on the cancer type, with breast cancer topics more frequently from Survivor (16.0%) and lung cancer from Patient’s family (16.3%). Healthcare provider and Public organization had minimal representation across three cancer types. The trends in the top 50 tweets mirrored the distribution of accounts for each cancer type. Breast cancer-related tweets had the highest frequency. There were few from public organizations. These findings emphasize the need to consider the characteristics of cancer-related information sources when sharing and gathering information on social media.