JMIR Cancer

Understanding and Addressing Challenges With Electronic Health Record Use in Gynecological Oncology: Cross-Sectional Survey of Multidisciplinary Professionals in the United Kingdom and Co-Design of an Integrated Informatics Platform to Support Clinical Decision-Making

Abstract Background Electronic health records (EHRs) are a cornerstone of modern health care delivery, but their current configuration often fragments information across systems, impeding timely and effective clinical decision-making. In gynecological oncology, where care involves complex, multidisciplinary coordination, these limitations can significantly impact the quality and efficiency of patient management. Few studies have examined how EHR systems support clinical decision-making from the perspective of end users. This study aimed to explore multiprofessional experiences of EHR use in gynecological oncology and to develop a co-designed informatics platform to improve decision-making for ovarian cancer care. Objective This study aims to evaluate the perspectives of health care professionals on retrieving routine clinical data from EHRs in the management of ovarian cancer and to design an integrated informatics platform that supports clinical decision-making. Methods We conducted a national cross-sectional survey of 92 UK-based professionals working in gynecological oncology, including oncologists, nurses, radiologists, and other specialists in ovarian cancer. The web-based questionnaire, combining quantitative and free-text responses, assessed their experiences with EHR use, focusing on information retrieval, usability challenges, perceived risks, and benefits. In parallel, a human-centered design approach involving health care professionals, data engineers, and informatics experts codeveloped a digital informatics platform that integrates structured and unstructured data from multiple clinical systems into a unified patient summary view for clinical decision-making. Natural language processing was applied to extract genomic and surgical information from free-text records, with data pipelines validated by clinicians against original clinical system sources. Results Among 92 respondents, 84 out of 91 (92%) routinely accessed multiple EHR systems, with 26 out of 91 (29%) using 5 or more. Notably, 16 out of 92 respondents (17%) reported spending more than 50% of their clinical time searching for patient information. Key challenges included lack of interoperability (35/141 reported challenges, 24.8%), difficulty locating critical data such as genetic results (57/85 respondents, 67%), and poor organization of information. Only 10 out of 92 professionals (11%) strongly agreed that their systems provided well-organized data for clinical use. While ease of access to patient data was a key benefit, 54 out of 90 respondents (60%) reported lacking access to comprehensive patient summaries. To address these issues, our co-designed informatics platform consolidates disparate patients’ data from different EHR systems into a single visual display to support clinical decision-making and audit. Conclusions Current EHR systems are suboptimal for supporting complex gynecological oncology care. Our findings highlight the urgent need for integrated, user-centered clinical decision tools. Fragmentation and lack of interoperability hinder information retrieval and may compromise patient care. Our co-designed ovarian cancer informatics platform is a potential real-world solution to improve data visibility, clinical efficiency, and ultimately the quality of ovarian cancer care.

Usability, Acceptability, and Barriers to Implementation of a Collaborative Agenda-Setting Intervention (CASI) to Promote Person-Centered Ovarian Cancer Care: Development Study

Abstract Background People with advanced ovarian cancer and their caregivers report unmet supportive care needs. We developed a Collaborative Agenda-Setting Intervention (CASI) to elicit patients’ and caregivers’ needs through the patient portal before a clinic visit and to communicate these needs to clinicians using the electronic health record. Objective We aimed to assess the usability and acceptability of the CASI and identify barriers to and facilitators of its implementation. Methods We recruited English- and Spanish-speaking patients, caregivers, and clinicians from the gynecologic oncology program at a comprehensive cancer center. Participants used the CASI prototype and then completed individual cognitive interviews and surveys. We assessed usability with the System Usability Scale (scores range 0‐100, scores ≥70 indicate acceptable usability) and acceptability with the Acceptability of Intervention Measure and Intervention Appropriateness Measure (scores for both measures range from 1 to 5, higher scores indicate greater acceptability). Interviews were audio recorded, transcribed, and analyzed using directed content analysis. Domains and constructs from the Consolidated Framework for Implementation Research comprised the initial codebook. We analyzed survey data using descriptive statistics and compared usability and acceptability scores across patients, caregivers, and clinicians using analyses of variance. Results We enrolled 15 participants (5 patients, 5 caregivers, and 5 clinicians). The mean System Usability Scale score was 72 (SD 16). The mean Acceptability of Intervention Measure and Intervention Appropriateness Measure scores were 3.9 (SD 1.0) and 4.1 (SD 0.8), respectively. Participants viewed the CASI content and format positively overall. Several participants appreciated the CASI’s integration into the clinical workflow and its potential to increase attention to psychosocial concerns. Suggestions to refine the CASI included removing redundant items, simplifying item language, and adding options to request a conversation or opt out of supportive care referrals. Key barriers to implementing the CASI include its complexity and limited resources available to address patients’ and caregivers’ needs. Conclusions The CASI is usable and acceptable to patients with advanced ovarian cancer, caregivers, and clinicians. We identified several barriers to and facilitators of implementing the CASI. In future research, we will apply these insights to a pilot randomized controlled trial to assess the feasibility of comparing the CASI to usual care in a parallel group-randomized efficacy trial.

Needs of Patients With Gynecologic Cancer and Their Caregivers for Obtaining mHealth-Supported Self-Management: Focus Group Study

Background Family caregivers of individuals with gynecologic cancer experience high levels of distress. Web-based caregiver support interventions have demonstrated efficacy in improving caregiver outcomes. However, the lack of portability could be a limitation. Mobile health (mHealth) apps could fill this gap and facilitate communication between patient-caregiver dyads. Objective We sought to obtain information on desired usage and features to be used to design an mHealth self-management support app targeting both patients with gynecologic cancer and their caregivers. Methods We conducted Zoom focus groups with women who had been treated for gynecologic cancers (ovarian, fallopian, primary peritoneal, uterine, endometrial, cervical, and vulvar); patients were also asked to invite a self-identified “closest support person” (caregiver). A semistructured focus group guide was used to elicit information on patients’ and caregivers’ perceived gaps in information and support, desired features of an mHealth app, and interest in and preferences for app usage. After transcription, rapid qualitative analysis using a thematic matrix was used to identify common themes across groups. Results A total of 8 groups were held. The final sample included 41 individuals with gynecologic cancer and 22 support persons or caregivers (total n=63). Patients were aged between 32 and 84 years, and most (38/41, 93%) were White and married. For caregivers (n=22), 15 (68%) identified as male and 7 (32%) as female, with ages ranging between 19 and 81 years. Overall, 59% (n=13) of caregivers were spouses. Questions geared at eliciting 3 a priori topics yielded the following themes: topic 1—gaps in information and support: finding relevant information is time-consuming; patients and caregivers lack confidence in deciding the urgency of problems that arise and from whom to seek information and guidance; topic 2—desired features of the mHealth app: patients and caregivers desire centralized, curated, trustworthy information; they desire timely recommendations tailored to specific personal and cancer-related needs; they desire opportunities to interact with clinical and peer experts through the app; and topic 3—interest and preferences for app usage: need for private space in the app for patients and caregivers to get information and support without the others’ knowledge; patients and caregivers desire having control over sharing of information with other family members. Conclusions Designing a single mHealth app to be used by patients and caregivers presents unique challenges for intervention designers and app developers. Implications of the study suggest that app developers need to prioritize flexibility in app functionality and provide individuals the ability to control information sharing between patients and caregivers.

Machine Learning for Preoperative Assessment and Postoperative Prediction in Cervical Cancer: Multicenter Retrospective Model Integrating MRI and Clinicopathological Data

Abstract Background Machine learning (ML) has been increasingly applied to cervical cancer (CC) research. However, few studies have combined both clinical parameters and imaging data. At the same time, there remains an urgent need for more robust and accurate preoperative assessment of parametrial invasion and lymph node metastasis, as well as postoperative prognosis prediction. Objective The objective of this study is to develop an integrated ML model combining clinicopathological variables and magnetic resonance image features for (1) preoperative parametrial invasion and lymph node metastasis detection and (2) postoperative recurrence and survival prediction. Methods Retrospective data from 250 patients with CC (2014‐2022; 2 tertiary hospitals) were analyzed. Variables were assessed for their predictive value regarding parametrial invasion, lymph node metastasis, survival, and recurrence using 7 ML models: K-nearest neighbor (KNN), support vector machine, decision tree, random forest (RF), balanced RF, weighted DT, and weighted KNN. Performance was assessed via 5-fold cross-validation using accuracy, sensitivity, specificity, precision, F1-score, and area under the receiver operating characteristic curve (AUC). The optimal models were deployed in an artificial intelligence–assisted contouring and prognosis prediction system. Results Among 250 women, there were 11 deaths and 24 recurrences. (1) For preoperative evaluation, the integrated model using balanced RF achieved optimal performance (sensitivity 0.81, specificity 0.85) for parametrial invasion, while weighted KNN achieved the best performance for lymph node metastasis (sensitivity 0.98, AUC 0.72). (2) For postoperative prognosis, weighted KNN also demonstrated high accuracy for recurrence (accuracy 0.94, AUC 0.86) and mortality (accuracy 0.97, AUC 0.77), with relatively balanced sensitivity of 0.80 and 0.33, respectively. (3) An artificial intelligence–assisted contouring and prognosis prediction system was developed to support preoperative evaluation and postoperative prognosis prediction. Conclusions The integration of clinical data and magnetic resonance images provides enhanced diagnostic capability to preoperatively detect parametrial invasion and lymph node metastasis detection and prognostic capability to predict recurrence and mortality for CC, facilitating personalized, precise treatment strategies.

AI-Based Identification Method for Cervical Transformation Zone Within Digital Colposcopy: Development and Multicenter Validation Study

Background In low- and middle-income countries, cervical cancer remains a leading cause of death and morbidity for women. Early detection and treatment of precancerous lesions are critical in cervical cancer prevention, and colposcopy is a primary diagnostic tool for identifying cervical lesions and guiding biopsies. The transformation zone (TZ) is where a stratified squamous epithelium develops from the metaplasia of simple columnar epithelium and is the most common site of precancerous lesions. However, inexperienced colposcopists may find it challenging to accurately identify the type and location of the TZ during a colposcopy examination. Objective This study aims to present an artificial intelligence (AI) method for identifying the TZ to enhance colposcopy examination and evaluate its potential clinical application. Methods The study retrospectively collected data from 3616 women who underwent colposcopy at 6 tertiary hospitals in China between 2019 and 2021. A dataset from 4 hospitals was collected for model conduction. An independent dataset was collected from the other 2 geographic hospitals to validate model performance. There is no overlap between the training and validation datasets. Anonymized digital records, including each colposcopy image, baseline clinical characteristics, colposcopic findings, and pathological outcomes, were collected. The classification model was proposed as a lightweight neural network with multiscale feature enhancement capabilities and designed to classify the 3 types of TZ. The pretrained FastSAM model was first implemented to identify the location of the new squamocolumnar junction for segmenting the TZ. Overall accuracy, average precision, and recall were evaluated for the classification and segmentation models. The classification performance on the external validation was assessed by sensitivity and specificity. Results The optimal TZ classification model performed with 83.97% classification accuracy on the test set, which achieved average precision of 91.84%, 89.06%, and 95.62% for types 1, 2, and 3, respectively. The recall and mean average precision of the TZ segmentation model were 0.78 and 0.75, respectively. The proposed model demonstrated outstanding performance in predicting 3 types of the TZ, achieving the sensitivity with 95% CIs for TZ1, TZ2, and TZ3 of 0.78 (0.74-0.81), 0.81 (0.78-0.82), and 0.8 (0.74-0.87), respectively, with specificity with 95% CIs of 0.94 (0.92-0.96), 0.83 (0.81-0.86), and 0.91 (0.89-0.92), based on a comprehensive external dataset of 1335 cases from 2 of the 6 hospitals. Conclusions Our proposed AI-based identification system classified the type of cervical TZs and delineated their location on multicenter, colposcopic, high-resolution images. The findings of this study have shown its potential to predict TZ types and specific regions accurately. It was developed as a valuable assistant to encourage precise colposcopic examination in clinical practice.

Toward an Understanding of the Lack of Transmission of Facts About Human Papillomavirus: Qualitative Case Study

Background Human papillomavirus (HPV) is the primary cause of cervical cancer, a largely preventable disease. Although extensive information about HPV is available and could help women prevent infection, a widespread lack of knowledge transmission hinders many women in Saudi Arabia from taking necessary preventive steps. Previous studies have reported low levels of HPV awareness among women in Saudi Arabia, highlighting the importance of understanding the barriers to effective information dissemination. Identifying the factors that influence the transmission of HPV-related knowledge is essential for designing targeted and impactful public health interventions. Objective This study aimed to explore the factors that either block or facilitate the transmission of HPV-related facts among women in Saudi Arabia, using the HPV facts transmission model as a theoretical framework. Methods A qualitative case study design was used, involving semistructured interviews with 20 women in Saudi Arabia aged 23 to 42 years. Participants were recruited using convenience and snowball sampling. The data were analyzed using pattern matching to assess how participant responses aligned with 11 predefined propositions from the HPV facts transmission model, which integrates individual and social influences on health information–seeking behavior. Results Of the 11 propositions, 8 (73%) were supported by the data. Five were individual-level factors (personal need to learn, stigma, language barriers, technology use, and individual qualities), while 3 were social-level factors (social promotion, social support, and cultural norms). These factors were classified as barriers, resources, or both, depending on their influence on women’s intention to seek HPV-related knowledge. For instance, personal motivation, curiosity, and digital access facilitated knowledge acquisition, while stigma, limited Arabic-language resources, and conservative social norms served as major deterrents. Three propositions (social structure, suppression structure, and interaction or collaboration) did not align with participant experiences and were excluded from the final model. Conclusions Understanding these barriers and resources is essential for developing targeted interventions to improve HPV knowledge dissemination. Strategies should include culturally appropriate awareness campaigns, accessible Arabic-language educational materials, and the integration of digital tools to encourage confidential learning. Addressing stigma through community engagement and structured education programs can further enhance HPV fact transmission, ultimately supporting informed decision-making and preventive health behaviors among women in Saudi Arabia.

Barriers and Facilitators to the Preadoption of a Computer-Aided Diagnosis Tool for Cervical Cancer: Qualitative Study on Health Care Providers’ Perspectives in Western Cameroon

Background Computer-aided detection and diagnosis (CAD) systems can enhance the objectivity of visual inspection with acetic acid (VIA), which is widely used in low- and middle-income countries (LMICs) for cervical cancer detection. VIA’s reliance on subjective health care provider (HCP) interpretation introduces variability in diagnostic accuracy. CAD tools can address some limitations; nonetheless, understanding the contextual factors affecting CAD integration is essential for effective adoption and sustained use, particularly in resource-constrained settings. Objective This study investigated the barriers and facilitators perceived by HCPs in Western Cameroon regarding sustained CAD tool use for cervical cancer detection using VIA. The aim was to guide smooth technology adoption in similar settings by identifying specific barriers and facilitators and optimizing CAD’s potential benefits while minimizing obstacles. Methods The perspectives of HCPs on adopting CAD for VIA were explored using a qualitative methodology. The study participants included 8 HCPs (6 midwives and 2 gynecologists) working in the Dschang district, Cameroon. Focus group discussions were conducted with midwives, while individual interviews were conducted with gynecologists to comprehend unique perspectives. Each interview was audio-recorded, transcribed, and independently coded by 2 researchers using the ATLAS.ti (Lumivero, LLC) software. The technology acceptance lifecycle framework guided the content analysis, focusing on the preadoption phases to examine the perceived acceptability and initial acceptance of the CAD tool in clinical workflows. The study findings were reported adhering to the COREQ (Consolidated Criteria for Reporting Qualitative Research) and SRQR (Standards for Reporting Qualitative Research) checklists. Results Key elements influencing the sustained use of CAD tools for VIA by HCPs were identified, primarily within the technology acceptance lifecycle’s preadoption framework. Barriers included the system’s ease of use, particularly challenges associated with image acquisition, concerns over confidentiality and data security, limited infrastructure and resources such as the internet and device quality, and potential workflow changes. Facilitators encompassed the perceived improved patient care, the potential for enhanced diagnostic accuracy, and the integration of CAD tools into routine clinical practices, provided that infrastructure and training were adequate. The HCPs emphasized the importance of clinical validation, usability testing, and iterative feedback mechanisms to build trust in the CAD tool’s accuracy and utility. Conclusions This study provides practical insights from HCPs in Western Cameroon regarding the adoption of CAD tools for VIA in clinical settings. CAD technology can aid diagnostic objectivity; however, data management, workflow adaptation, and infrastructure limitations must be addressed to avoid “pilotitis”—the failure of digital health tools to progress beyond the pilot phase. Effective implementation requires comprehensive technology management, including regulatory compliance, infrastructure support, and user-focused training. Involving end users can ensure that CAD tools are fully integrated and embraced in LMICs to aid cervical cancer screening.

Design and Validation of a Chatbot-Based Cervical Cancer Screening Decision Aid for Women Experiencing Socioeconomic Disadvantage: User-Centered Approach Study

Background Cervical cancer (CC) screening participation remains suboptimal among vulnerable populations in France. This study aimed to develop and evaluate AppDate-You, a chatbot-based decision aid, to support women from socioeconomically disadvantaged areas in the French Occitanie region to make informed decisions about CC screening, particularly human papillomavirus self-sampling (HPVss). Objective This study aimed to explore the needs, preferences, and barriers related to CC screening and to design and validate a user-centered, empathetic, and effective chatbot-based decision aid to empower women experiencing socioeconomic challenges in France to make informed choices about HPVss. Methods The chatbot was developed following a validated framework for developing decision aids. The process included qualitative research involving online and in-person interviews and focus groups with women and health care professionals, followed by alpha testing with both groups and beta testing with women only. Participants included women (both French and non-French speaking) aged between 30 and 65 years from socioeconomically disadvantaged areas of the Occitanie region and health care professionals (general practitioners, gynecologists, and midwives) working with these populations. AppDate-You was made accessible through WhatsApp and Facebook Messenger, offering text-based and voice-based interactions and multimedia content. Results The exploratory phase identified key barriers to screening and digital tool preferences. Prototype testing revealed great satisfaction with the chatbot’s performance, educational value, and content quality. Contrary to the expectations of health care professionals, women from diverse backgrounds, including women who were older and socioeconomically disadvantaged, were willing and able to use the tool. Users—even those with limited digital literacy—found AppDate-You innovative, user-friendly, and informative. In the beta testing phase, 80% (12/15) of the participants expressed interest in HPVss. Some limitations were identified, such as the chatbot’s occasional repetitive responses and the need for clearer medical terminology. Conclusions This study demonstrates the potential for artificial intelligence chatbots to improve access to health education and increase cervical screening intention among underserved populations. The user-centered approach resulted in a tool that effectively meets the needs of the target population. International Registered Report Identifier (IRRID) RR2-10.2196/39288