Explainable Artificial Intelligence in Quantifying Breast Cancer Factors: Saudi Arabia Context.

Breast cancer represents a significant health concern, particularly in Saudi Arabia, where it ranks as the most prevalent cancer type among women. This study focuses on leveraging eXplainable Artificial Intelligence (XAI) techniques to predict benign and malignant breast cancer cases using various clinical and pathological features specific to Saudi Arabian patients. Six distinct models were trained and evaluated based on common performance metrics such as accuracy, precision, recall, F1 score, and AUC-ROC score. To enhance interpretability, Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) were applied. The analysis identified the Random Forest model as the top performer, achieving an accuracy of 0.72, along with robust precision, recall, F1 score, and AUC-ROC score values. Conversely, the Support Vector Machine model exhibited the poorest performance metrics, indicating its limited predictive capability. Notably, the XAI approaches unveiled variations in the feature importance rankings across models, underscoring the need for further investigation. These findings offer valuable insights into breast cancer diagnosis and machine learning interpretation, aiding healthcare providers in understanding and potentially integrating such technologies into clinical practices.

Validating the Effectiveness of the Patient-Centered Cancer Care Framework by Assessing the Impact of Work System Factors on Patient-Centered Care and Quality of Care: Interview Study With Newly Diagnosed Cancer Patients.

BACKGROUND: Patients with cancer who have recently been diagnosed have distinct requirements compared to cancer survivors. It is crucial to take into account their unique needs to ensure that they make informed decisions and are receptive to the care provided. OBJECTIVE: This study suggested a framework titled Effectiveness of Patient-Centered Cancer Care that considers the needs of newly diagnosed patients with cancer and related work system factors. This study investigated how work system factors influence the perceptions of patient-centered care, quality of care, and associated outcomes among newly diagnosed patients with cancer. Patient-centered care is defined in terms of workload and communication considerations, whereas the quality of care is assessed through indicators such as trust in physicians, satisfaction with care, and perceptions of technology. METHODS: This study used qualitative data collected through interviews with newly diagnosed patients with cancer (N=20) right after their first visits with their physicians. Thematic analysis was conducted to validate the 5 hypotheses of the framework, mapping the interactions among quality of care, patient-centered care, and work system factors. RESULTS: We found that workload and patient-centered communication impact the quality of care and that the work system elements impact the patient-centeredness (workload and communication) and the quality of care (trust in physicians, satisfaction with care, and perception of technology use). CONCLUSIONS: Qualitatively validating the proposed Effectiveness of Patient-Centered Cancer Care framework, this study demonstrated its efficacy in elucidating the interplay of various factors. The framework holds promise for informing interventions geared toward enhancing patients' experiences during their initial visits after diagnosis. There is a pressing need for heightened attention to the organizational design, patient processes, and collaborative efforts among diverse stakeholders and providers to optimize the overall patient experience.

The health information technology preferences and perceptions of newly diagnosed patients with cancer.

BACKGROUND & GOALS: Patients with new cancer diagnoses have unique needs. In this study, we explored the technological needs and preferences of new cancer patients and the challenges to technology use among these patients. METHODS: We used qualitative data from semi-structured interviews to identify the new cancer patients' technology preferences. Interviews were recorded and then transcribed verbatim. A thematic analysis was conducted to identify the technology perceptions of new cancer patients, their technology needs, and the challenges of technology. RESULTS: Most of the patients preferred mhealth technologies over other types of technologies to be used in their care management. The primary needs related to potential features in these technologies include access to information just in time, convenience, access to home care, self-management, privacy, interaction, and personalization. Patients also reported challenges of current technologies they utilized, including usability, impersonality, interoperability, and cost-effectiveness. CONCLUSION: Addressing patients' needs to increase uptake and efficient use of technologies in cancer care is critical. Growing clinical and consumer informatics technologies can potentially help cancer management if designed by employing user-centered approaches.

Perceived Patient Workload and Its Impact on Outcomes During New Cancer Patient Visits: Analysis of a Convenience Sample.

BACKGROUND: Studies exploring the workload in health care focus on the doctors' perspectives. The ecology of the health care environment is critical and different for doctors and patients. OBJECTIVE: In this study, we explore the patient workload among newly diagnosed patients with cancer during their first visit and its impact on the patient's perceptions of the quality of care (their trust in their doctors, their satisfaction with the care visits, their perception of technology use). METHODS: We collected data from the Hackensack Meridian Health, John Theurer Cancer Center between February 2021 and May 2022. The technology use considered during the visit is related to doctors' use of electronic health records. A total of 135 participants were included in the study. Most participants were 50-64 years old (n=91, 67.41%). A majority (n=81, 60%) of them were White, and only (n=16, 11.85%) went to graduate schools. RESULTS: The findings captured the significant effect of overall workload on trust in doctors and perception of health IT use within the visits. On the other hand, the overall workload did not impact patients' satisfaction during the visit. A total of 80% (n=108) of patients experienced an overall high level of workload. Despite almost 55% (n=75) of them experiencing a high mental load, 71.1% (n=96) reported low levels of effort, 89% (n=120) experienced low time pressure, 85.2% (n=115) experienced low frustration levels, and 69.6% (n=94) experienced low physical activity. The more overall workload patients felt, the less they trusted their doctors (odds ratio [OR] 0.059, 95% CI 0.001-2.34; P=.007). Low trust was also associated with the demanding mental tasks in the visits (OR 0.055, 95% CI 0.002-2.64; P<.001), the physical load (OR 0.194, 95% CI 0.004-4.23; P<.001), the time load (OR 0.183, 95% CI 0.02-2.35; P=.046) the effort needed to cope with the environment (OR 0.163, 95% CI 0.05-1.69; P<.001), and the frustration levels (OR 0.323, 95% CI 0.04-2.55; P=.03). The patients' perceptions of electronic health record use during the visit were negatively impacted by the overall workload experienced by the patients (OR 0.315, 95% CI 0.08-6.35; P=.01) and the high frustration level experienced (OR 0.111, 95% CI 0.015-3.75; P<.001). CONCLUSIONS: The study's findings established pathways for future research and have implications for cancer patients' workload. Better technology design and use can minimize perceived workload, which might contribute to the trust relationship between doctors and patients in this critical environment. Future human factors work needs to explore the workload and driving factors in longitudinal studies and assess whether these workloads might contribute to unintended patient outcomes and medical errors.

Lung Cancer Screening Decision Aid Designed for a Primary Care Setting: A Randomized Clinical Trial.

Importance: Guidelines recommend shared decision-making prior to initiating lung cancer screening (LCS). However, evidence is lacking on how to best implement shared decision-making in clinical practice. Objective: To evaluate the impact of an LCS Decision Tool (LCSDecTool) on the quality of decision-making and LCS uptake. Design, Setting, and Participants: This randomized clinical trial enrolled participants at Veteran Affairs Medical Centers in Philadelphia, Pennsylvania; Milwaukee, Wisconsin; and West Haven, Connecticut, from March 18, 2019, to September 29, 2021, with follow-up through July 18, 2022. Individuals aged 55 to 80 years with a smoking history of at least 30 pack-years who were current smokers or had quit within the past 15 years were eligible to participate. Individuals with LCS within 15 months were excluded. Of 1047 individuals who were sent a recruitment letter or had referred themselves, 140 were enrolled. Intervention: A web-based patient- and clinician-facing LCS decision support tool vs an attention control intervention. Main Outcome and Measures: The primary outcome was decisional conflict at 1 month. Secondary outcomes included decisional conflict immediately after intervention and 3 months after intervention, knowledge, decisional regret, and anxiety immediately after intervention and 1 and 3 months after intervention and LCS by 6 months. Results: Of 140 enrolled participants (median age, 64.0 [IQR, 61.0-69.0] years), 129 (92.1%) were men and 11 (7.9%) were women. Of 137 participants with data available, 75 (53.6%) were African American or Black and 62 (44.3%) were White; 4 participants (2.9%) also reported Hispanic or Latino ethnicity. Mean decisional conflict score at 1 month did not differ between the LCSDecTool and control groups (25.7 [95% CI, 21.4-30.1] vs 29.9 [95% CI, 25.6-34.2], respectively; P = .18). Mean LCS knowledge score was greater in the LCSDecTool group immediately after intervention (7.0 [95% CI, 6.3-7.7] vs 4.9 [95% CI, 4.3-5.5]; P < .001) and remained higher at 1 month (6.3 [95% CI, 5.7-6.8] vs 5.2 [95% CI, 4.5-5.8]; P = .03) and 3 months (6.2 [95% CI, 5.6-6.8] vs 5.1 [95% CI, 4.4-5.8]; P = .01). Uptake of LCS was greater in the LCSDecTool group at 6 months (26 of 69 [37.7%] vs 15 of 71 [21.1%]; P = .04). Conclusions and Relevance: In this randomized clinical trial of an LCSDecTool compared with attention control, no effect on decisional conflict occurred at 1 month. The LCSDecTool used in the primary care setting did not yield a significant difference in decisional conflict. The intervention led to greater knowledge and LCS uptake. These findings can inform future implementation strategies and research in LCS shared decision-making. Trial Registration: ClinicalTrials.gov Identifier: NCT02899754.

The Impact of Patient-Centered Care on Cancer Patients' QOC, Self-Efficacy, and Trust Towards Doctors: Analysis of a National Survey.

Patient-centered approaches impact cancer patients' perceptions and outcomes in different ways. This study explores the impact of patient-centered care practices on cancer patients' quality-of-care (QOC), self-efficacy, and trust in their doctors. We utilized cross-sectional national survey data from the National Cancer Institute collected between 2017 and 2020. All estimates were weighted using the jackknife method. We used multivariable logistic regression to test our hypotheses adjusted for the demographics of the 1932 cancer patients that responded to the survey. Findings indicate that patient-centered communication resulted in better QOC, self-efficacy, and trust in doctors. In addition, engagement in their care improved patients' trust in cancer-related information received from doctors. QOC and patients' trust in doctors were significantly improved with the patients' understanding of the next steps, addressing feelings, clear explanation of the problems, spending enough time with the clinicians, addressing uncertainty, and involvement in decisions. Patients who were given a chance to ask questions were significantly more likely to trust their doctors. Technology use did not impact any of these interactions. Patient-centered strategies should consider the needs of the patients in the cancer settings to improve overall outcomes. Organizations should also build strategies that are goal-oriented and centered around the patients' needs, as standard strategies cannot induce the wanted results.

Successful application of the innovation process to a case of Floyd Type I tracheal agenesis.

Background: Innovation is broadly defined as the act of introducing a new product, idea, or process. The field of surgery is built upon innovation, revolutionizing technology, science, and tools to improve patient care. While most innovative solutions are aimed at problems with a significant patient population, the process can also be used on orphan pathologies without obvious solutions. We present a case of tracheal agenesis, a rare congenital anomaly with an overwhelming mortality and few good treatment options, that benefited from the innovation process and achieved survival with no ventilator dependence at three years of age. Methods: Utilizing the framework of the innovation process akin to the Stanford Biodesign Program, 1) the parameters of the clinical problem were identified, 2) previous solutions and existing technologies were analyzed, newly invented solutions were brainstormed, and value analysis of the possible solutions were carried out using crowd wisdom, and 3) the selected solution was prototyped and tested using 3D modeling, iterative testing on 3D prints of actual-sized patient parts, and eventual implementation in the patient after regulatory clearance. Results: A 3D-printed external bioresorbable splint was chosen as the solution. Our patient underwent airway reconstruction with "trachealization of the esophagus": esophageotracheal fistula resection, esophagotracheoplasty, and placement of a 3D-printed polycaprolactone (PCL) stent for external esophageal airway support at five months of age. Conclusions: The innovation process provided our team with the guidance and imperative steps necessary to develop an innovative device for the successful management of an infant survivor with Floyd Type I tracheal agenesis. Article summary: We present a case of tracheal agenesis, a rare congenital anomaly with an overwhelming mortality and few good treatment options, that benefited from the innovation process and achieved survival with no ventilator dependence at three years of age.The importance of this report is to reveal how the innovation process, which is typically used for problems with significant patient population, can also be used on orphan pathologies without obvious solutions.

Managing Critical Patient-Reported Outcome Measures in Oncology Settings: System Development and Retrospective Study.

BACKGROUND: Remote monitoring programs based on the collection of patient-reported outcome (PRO) data are being increasingly adopted in oncology practices. Although PROs are a great source of patient data, the management of critical PRO data is not discussed in detail in the literature. OBJECTIVE: This first-of-its-kind study aimed to design, describe, and evaluate a closed-loop alerting and communication system focused on managing PRO-related alerts in cancer care. METHODS: We designed and developed a novel solution using an agile software development methodology by incrementally building new capabilities. We evaluated these new features using participatory design and the Fit between Individuals, Task, and Technology framework. RESULTS: A total of 8 questionnaires were implemented using alerting features, resulting in an alert rate of 7.82% (36,838/470,841) with 13.28% (10,965/82,544) of the patients triggering at least one alert. Alerts were reviewed by 501 staff members spanning across 191 care teams. All the alerts were reviewed with a median response time of 1 hour (SD 185 hours) during standard business hours. The most severe (red) alerts were documented 56.83% (2592/4561) of the time, whereas unlabeled alerts were documented 27.68% (1298/4689) of the time, signaling clinician concordance with the alert thresholds. CONCLUSIONS: A PRO-based alert and communication system has some initial benefits in reviewing clinically meaningful PRO data in a reasonable amount of time. We have discussed key system design considerations, workflow integration, and the mitigation of potential impact on the burden of care teams. The introduction of a PRO-based alert and communication system provides a reliable mechanism for care teams to review and respond to patient symptoms quickly. The system was standardized across many different oncology settings, demonstrating system flexibility. Future studies should focus on formally evaluating system usability through qualitative methods.

A Veteran-Centric Web-Based Decision Aid for Lung Cancer Screening: Usability Analysis.

BACKGROUND: Web-based tools developed to facilitate a shared decision-making (SDM) process may facilitate the implementation of lung cancer screening (LCS), an evidence-based intervention to improve cancer outcomes. Veterans have specific risk factors and shared experiences that affect the benefits and potential harms of LCS and thus may value a veteran-centric LCS decision tool (LCSDecTool). OBJECTIVE: This study aims to conduct usability testing of an LCSDecTool designed for veterans receiving care at a Veteran Affairs medical center. METHODS: Usability testing of the LCSDecTool was conducted in a prototype version (phase 1) and a high-fidelity version (phase 2). A total of 18 veterans and 8 clinicians participated in phase 1, and 43 veterans participated in phase 2. Quantitative outcomes from the users included the System Usability Scale (SUS) and the End User Computing Satisfaction (EUCS) in phase 1 and the SUS, EUCS, and Patient Engagement scale in phase 2. Qualitative data were obtained from observations of user sessions and brief interviews. The results of phase 1 informed the modifications of the prototype for the high-fidelity version. Phase 2 usability testing took place in the context of a pilot hybrid type 1 effectiveness-implementation trial. RESULTS: In the phase 1 prototype usability testing, the mean SUS score (potential range: 0-100) was 81.90 (SD 9.80), corresponding to an excellent level of usability. The mean EUCS score (potential range: 1-5) was 4.30 (SD 0.71). In the phase 2 high-fidelity usability testing, the mean SUS score was 65.76 (SD 15.23), corresponding to a good level of usability. The mean EUCS score was 3.91 (SD 0.95); and the mean Patient Engagement scale score (potential range 1 [low] to 5 [high]) was 4.62 (SD 0.67). The median time to completion in minutes was 13 (IQR 10-16). A thematic analysis of user statements documented during phase 2 high-fidelity usability testing identified the following themes: a low baseline level of awareness and knowledge about LCS increased after use of the LCSDecTool; users sought more detailed descriptions about the LCS process; the LCSDecTool was generally easy to use, but specific navigation challenges remained; some users noted difficulty understanding medical terms used in the LCSDecTool; and use of the tool evoked veterans' struggles with prior attempts at smoking cessation. CONCLUSIONS: Our findings support the development and use of this eHealth technology in the primary care clinical setting as a way to engage veterans, inform them about a new cancer control screening test, and prepare them to participate in an SDM discussion with their provider.

Impact of Health Perception and Knowledge on Genetic Testing Decisions Using the Health Belief Model.

PURPOSE: Early detection of cancer risk is essential as it is associated with a higher chance of survival, more successful treatment, and improved quality of life. Genetic testing helps at-risk patients estimate the likelihood of developing cancer in a lifetime. This study aims to indentify the factors (perceived susceptibility, severity, benefits, and self-efficacy) that impact one's decision to take the genetic test. METHODS: We examined the impacts of different factors of the health belief model on the engagement of patients in genetic testing using data from the National Cancer Institute's 2020 cross-sectional nationally representative data published in 2021. Complete surveys were answered by 3,865 participants (weighted population size = 253,815,197). All estimates were weighted to be nationally representative of the US population using the jackknife weighting method for parameter estimation. We used multivariable logistic regression to test our hypotheses for patients who have taken the genetic test for cancer risk detection. We adjusted the multivariate model for age, education, income, race, sex, cancer history, familial cancer history, and education. RESULTS: We tested five hypotheses using the health belief model. Respondents who had genetic testing were more likely to rely on their health care providers and genetic counselors to make their decisions. Respondents who had genetic tests also reported less reliability on other sources than doctors: for the internet and social media (odds ratio = 0.33; P < .001) and for journals and magazines (odds ratio = 0.48; P = .007). CONCLUSION: The findings show that patients generally rely on suggestions from their health care providers and counselors in genetic testing decisions. These findings also indicate that health care providers play a critical role in helping patients decide whether to use genetic testing to detect cancer risk in the early stages.

Engaging veteran stakeholders to identify patient-centred research priorities for optimizing implementation of lung cancer screening.

BACKGROUND: Patient engagement in research agenda setting is increasingly being seen as a strategy to improve the responsiveness of healthcare to patient priorities. Implementation of low-dose computed tomography (LDCT) screening for lung cancer is suboptimal, suggesting that research is needed. OBJECTIVES: This study aimed to describe an approach by which a Veteran patient group worked with other stakeholders to develop a research agenda for LDCT screening and to describe the research questions that they prioritized. METHODS: We worked with Veterans organizations to identify 12 Veterans or family members at risk for or having experience with lung cancer to form a Patient Advisory Council (PAC). The PAC met repeatedly from June 2018 to December 2020, both independently and jointly, with stakeholders representing clinicians, health administrators and researchers to identify relevant research topics. The PAC prioritized these topics and then identified questions within these areas where research was needed using an iterative process. Finally, they ranked the importance of obtaining answers to these questions. RESULTS: PAC members valued the co-learning generated by interactions with stakeholders, but emphasized the importance of facilitation to avoid stakeholders dominating the discussion. The PAC prioritized three broad research areas-(1) the impact of insurance on uptake of LDCT; (2) how best to inform Veterans about LDCT; and (3) follow-up and impact of screening results. Using these areas as guides, PAC members identified 20 specific questions, ranking as most important (1) innovative outreach methods, (2) the impact of screening on psychological health, and (3) the impact of outsourcing scans from VA to non-VA providers on completion of recommended follow-up of screening results. The latter two were not identified as high priority by the stakeholder group. CONCLUSIONS: We present an approach that facilitates co-learning between Veteran patients and providers, researchers and health system administrators to increase patient confidence in their ability to contribute important information to a research agenda. The research questions prioritized by the Veterans who participated in this project illustrate that for this new screening technology, patients are concerned about the practical details of implementation (e.g., follow-up) and the technology's impact on quality of life. PATIENT OR PUBLIC CONTRIBUTION: Veterans and Veteran advocates contributed to our research team throughout the entire research process, including conceiving and co-authoring this manuscript.

Adapting the design of a Web-based decision support clinical trial during the COVID-19 pandemic.

BACKGROUND: The public health crises that emerged in the COVID-19 pandemic significantly impacted the provision of medical care and placed sudden restrictions on ongoing clinical research. Patient-facing clinical research confronted unique challenges in which recruitment and study protocols were halted and then adapted to meet safety procedures during the pandemic. Our study protocol included the use of a Lung Cancer Screening Decision Tool (LCSDecTool) in the context of a primary care visit and was considerably impacted by the pandemic. We describe our experience adapting a multi-site clinical trial of the LCSDecTool within the Department of Veterans Affairs Health Care System. We conducted a randomized controlled trial (RCT) comparing the LCSDecTool to a control intervention. Outcomes included lung cancer screening (LCS) knowledge, shared decision-making, and uptake and adherence to LCS protocol. We identified three strategies that led to the successful adaptation of the study design during the pandemic: (1) multi-level coordination and communication across the organization and study sites, (2) flexibility and adaptability in research during a time of uncertainty and changes in regulation, and (3) leveraging technology to deliver the intervention and conduct study visits, which raised issues concerning equity and internal and external validity. CONCLUSION: Our experience highlights strategies successfully employed to adapt an intervention and behavioral research study protocol during the COVID-19 pandemic. This experience will inform clinical research moving forward both during and subsequent to the constraints placed on research and clinical care during the COVID-19 pandemic.

Preferences in trust regarding the provision of cancer information among adults.

BACKGROUND: Disparities associated with trust in health information exist warranting a need for research assessing this relationship among adults. Therefore, the aim of this study was to assess trust of cancer information among U.S. adults. METHODS: A weighted sample of 237,670,167 adults from the Health Information National Trends Survey (HINTS) from 2011-2014 was used for the analyses. Dependent variables were dichotomized answers to whether individuals trusted information from family/friends, the internet, or a doctor. Independent variables included age, sex, region, race/ethnicity, and cancer diagnosis to investigate associations between demographic factors and differences in trust. Logistic regression was run using R survey package. RESULTS: There were statistically significant differences in trust based on race/ethnicity, age, and cancer diagnosis. Minorities were less likely to trust information from a doctor, with Hispanics more likely to trust information from the internet (OR=1.8 (95% CI 1.36,2.43)), and Non-Hispanic Blacks trusting information from family and friends (OR=1.5 (95% CI 1.06, 2.13)). Adults ≥45 years of age were less likely to trust the doctor 'a lot' (45-64 years: OR=0.6 (95% CI 0.50, 0.83); 65+ years (OR=0.7 (95% CI 0.54, 0.92)), but more likely to not trust information from family and friends or the internet. Patients with cancer were more likely to trust information from a doctor 'a lot' (78%; p=0.01). DISCUSSION: Significant differences in preferences regarding trust in cancer information occurred based on sociodemographic characteristics. CONCLUSION: These finding suggest targeting specific population subgroups for information from sources they trust could be helpful in reducing disparities in trust.

How technology impacts communication between cancer patients and their health care providers: A systematic literature review.

OBJECTIVE: To ensure the well-being of their patients, health care providers (HCPs) are putting more effort into the quality of the communication they provide in oncology clinics. With the emergence of Health Information Technology (HIT), the dynamics between doctors and patients in oncology settings have changed. The purpose of this literature review is to explore and demonstrate how various health information technologies impact doctor-patient communication in oncology settings. METHOD: A systematic literature review was conducted in 4 databases (PubMed, Cochrane, Web of Science, IEEE Xplore) to select publications that are in English, published between January 2009 and September 2020. This review reports outcomes related to the impacts of using health information technologies on doctor-patient communication according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Reviews and Meta-Analysis guidelines (PRISMA). RESULTS: We identified 31 studies which satisfied the selection and eligibility criteria. The review revealed a diverse range of HIT used to support communication between cancer patients and their HCPs in oncology settings. Outcomes related to communication were examined to demonstrate how technology can improve access to care in clinical settings and online. When technology is used effectively to support patient knowledge and shared understanding, this increases the patient's satisfaction and ability to manage emotions, make decisions, and progress in their treatment, in addition to increasing social support and building a stronger therapeutic alliance based on shared knowledge and transparency between clinicians and patients. CONCLUSION: Technology-based solutions can help strengthen the relationship and communication between patients and their doctors. They can empower the patient's well-being, help doctors make better decisions and enhance the therapeutic alliance between them. Thus, using technology to enhance communication in healthcare settings remains beneficial if its use is structured and target oriented. Future studies should focus on comparing in-depth the difference between outpatient and inpatient settings in terms of the efforts required and the extent of the impacts from both clinicians' and cancer patients' perspectives.

Online Medical Record Nonuse Among Patients: Data Analysis Study of the 2019 Health Information National Trends Survey.

BACKGROUND: Online medical records are being used to organize processes in clinical and outpatient settings and to forge doctor-patient communication techniques that build mutual understanding and trust. OBJECTIVE: We aimed to understand the reasons why patients tend to avoid using online medical records and to compare the perceptions that patients have of online medical records based on demographics and cancer diagnosis. METHODS: We used data from the Health Information National Trends Survey Cycle 3, a nationally representative survey, and assessed outcomes using descriptive statistics and chi-square tests. The patients (N=4328) included in the analysis had experienced an outpatient visit within the previous 12 months and had answered the online behavior question regarding their use of online medical records. RESULTS: Patients who were nonusers of online medical records consisted of 58.36% of the sample (2526/4328). The highest nonuser rates were for patients who were Hispanic (460/683, 67.35%), patients who were non-Hispanic Black (434/653, 66.46%), and patients who were older than 65 years (968/1520, 63.6%). Patients older than 65 years were less likely to use online medical records (odds ratio [OR] 1.51, 95% CI 1.24-1.84, P<.001). Patients who were White were more likely to use online medical records than patients who were Black (OR 1.71, 95% CI 1.43-2.05, P<.001) or Hispanic (OR 1.65, 95% CI 1.37-1.98, P<.001). Patients who were diagnosed with cancer were more likely to use online medical records compared to patients with no cancer (OR 1.31, 95% CI 1.11-1.55, 95% CI 1.11-1.55, P=.001). Among nonusers, older patients (≥65 years old) preferred speaking directly to their health care providers (OR 1.76, 95% CI 1.35-2.31, P<.001), were more concerned about privacy issues caused by online medical records (OR 1.79, 95% CI 1.22-2.66, P<.001), and felt uncomfortable using the online medical record systems (OR 10.55, 95% CI 6.06-19.89, P<.001) compared to those aged 18-34 years. Patients who were Black or Hispanic were more concerned about privacy issues (OR 1.42, 1.09-1.84, P=.007). CONCLUSIONS: Studies should consider social factors such as gender, race/ethnicity, and age when monitoring trends in eHealth use to ensure that eHealth use does not induce greater health status and health care disparities between people with different backgrounds and demographic characteristics.

When Is a Harm a Harm? Discordance between Patient and Medical Experts' Evaluation of Lung Cancer Screening Attributes.

BACKGROUND: A shared decision-making (SDM) process for lung cancer screening (LCS) includes a discussion between clinicians and patients about benefits and potential harms. Expert-driven taxonomies consider mortality reduction a benefit and consider false-positives, incidental findings, overdiagnosis, overtreatment, radiation exposure, and direct and indirect costs of LCS as potential harms. OBJECTIVE: To explore whether patients conceptualize the attributes of LCS differently from expert-driven taxonomies. DESIGN: Cross-sectional study with semistructured interviews and a card-sort activity. PARTICIPANTS: Twenty-three Veterans receiving primary care at a Veterans Affairs Medical Center, 55 to 73 y of age with 30 or more pack-years of smoking. Sixty-one percent were non-Hispanic African American or Black, 35% were non-Hispanic White, 4% were Hispanic, and 9% were female. APPROACH: Semistructured interviews with thematic coding. MAIN MEASURES: The proportion of participants categorizing each attribute as a benefit or harm and emergent themes that informed this categorization. KEY RESULTS: In addition to categorizing reduced lung cancer deaths as a benefit (22/23), most also categorized the following as benefits: routine annual screening (8/9), significant incidental findings (20/23), follow-up in a nodule clinic (20/23), and invasive procedures (16/23). Four attributes were classified by most participants as a harm: false-positive (13/22), overdiagnosis (13/23), overtreatment (6/9), and radiation exposure (20/22). Themes regarding the evaluation of LCS outcomes were 1) the value of knowledge about body and health, 2) anticipated positive and negative emotions, 3) lack of clarity in terminology, 4) underlying beliefs about cancer, and 5) risk assessment and tolerance for uncertainty. CONCLUSIONS: Anticipating discordance between patient- and expert-driven taxonomies of the benefits and harms of LCS can inform the development and interpretation of value elicitation and SDM discussions.

Qualitative Assessment of Unmet Information Management Needs of Informal Cancer Caregivers: Four Themes to Inform Oncology Practice.

PURPOSE: Family and friends often provide informal care for patients with cancer, coordinating care and supporting patients at home. Stress, depression, and burnout are increasingly recognized among these informal caregivers. Although past research has described a range of needs, including the need for information, details about unmet informational needs for caregivers have not been fully described. We sought to assess unmet information management needs for informal caregivers in the digital era. METHODS: This was a qualitative research study with semistructured interviews and focus groups of nonprofessional caregivers for patients with cancer, facilitated using a discussion guide. Eligible caregivers supported patients in the community who were in treatment (chemotherapy or radiotherapy) or completed treatment within 3 years. Participants were recruited using informational flyers at an academic cancer center and in the local community of metropolitan Milwaukee, Wisconsin. Sessions were transcribed verbatim and analyzed inductively to identify themes. RESULTS: Thirteen caregivers participated, the majority between 41 and 60 years of age: seven of 13, 53.8%, were predominantly women; 10 of 13 (76.9%) were educated, 10 of 13 (76.9%) had graduated from college; and of modest means, six of 13 (46.2%) had household incomes < $35,000. Four themes emerged: (1) the information overload paradox, where caregivers felt overloaded by information yet had unmet informational needs; (2) navigating volatility as a caregiver, with changing or unknown expectations; (3) caregivers as information brokers, which placed new burdens on caregivers to seek, share, and protect information; and (4) care for the caregiver, including unmet information needs related to self-care. CONCLUSION: This study identified several informational challenges affecting caregivers. Caregivers have dynamic and evolving informational needs, and strategies that support caregivers through just-in-time information availability or dedicated caregiver check-ins may provide relief within the stress of caregiving.

Culture, identity, strength and spirituality: A qualitative study to understand experiences of African American women breast cancer survivors and recommendations for intervention development.

OBJECTIVE: Despite advancements in cancer treatment, racial disparities in breast cancer survival persist, with African American women experiencing lower survival rates and poorer quality of life than non-Hispanic White women. Using a social cognitive model of restorative well-being as a framework, this qualitative study sought: (a) to examine strength- and culture-related factors associated with African American female breast cancer survivors' cancer coping and post-treatment experiences and (b) to make recommendations for culturally sensitive intervention. METHODS: Eight focus groups occurred with a total of 40 local African American breast cancer survivors. Focus groups were audiotaped and transcribed verbatim. Framework analyses were used to identify themes. NVivo qualitative analysis software-managed data. RESULTS: Two major themes emerged from the focus group discussions: (a) God enables breast cancer survivorship and works every day in our lives and (b) the healthiest thing about us is that we are strong African American women. Recommendations for intervention planning and implementation were made towards intervention structure, content development and language framing in a local context. CONCLUSION: Findings suggest a need for community-based participatory survivorship interventions that are culturally and spiritually consonant and peer-based. Such interventions may respond to the cancer-related and personal needs of the target population.

Community Breast Health Education for Immigrants and Refugees: Lessons Learned in Outreach Efforts to Reduce Cancer Disparities.

Community-academic partnerships are vital to address cancer disparities in geographic areas with diverse socioeconomic, language, and cultural barriers. Regarding breast health, immigrant and refugee women are a particularly vulnerable population, with considerably lower mammography rates than most communities, including racial and ethnic minorities. To promote health care equity in this high-risk population, we developed a community-academic partnership (CAP) model to promote breast health education at community faith-based centers in the city of Milwaukee, WI. In this paper, we describe the success of our partnerships, our lessons learned, and future directions.

Oncologists' Views Regarding the Role of Electronic Health Records in Care Coordination.

BACKGROUND: Electronic health records (EHRs) play a significant role in complex health care processes, especially in information transfer with patients and care coordination among providers. EHRs may also generate unintended consequences, introducing new patient safety risks. To date, little investigation has been performed in oncology settings, despite the need for quality provider-patient communication and information transfer during oncology visits. In this qualitative study, we focused on oncology providers' perceptions of EHRs for supporting communication with patients and coordination of care with other providers. METHODS: We conducted semistructured interviews with oncologists from an urban academic medical center to learn their perceptions of the use of EHRs before, during, and after clinic visits with patients. Our interview guide was developed on the basis of the work system model. We coded transcripts using inductive content analysis. RESULTS: Data analysis yielded four main themes regarding oncologists' practices in using the EHR and perceptions about EHRs: (1) EHR use for care coordination (eg, timeliness of receiving information, SmartSet documentation); (2) EHR use in the clinic visit (eg, educating patients, using as a reinforcement tool); (3) safety hazards in care coordination associated with EHRs (eg, incomplete documentation, error propagating, no filtering mechanism to capture errors); and (4) suggestions for improvements (eg, improved SmartSet functionalities, simplification of user interface). CONCLUSION: Current EHRs do not adequately support teamwork of oncology providers, which could lead to potential hazards in the care of patients with cancer. Redesigning EHR features that are tailored to support oncology care and addressing the concerns regarding information overload, improved organization of flagging abnormal results, and documentation-related workload are needed to minimize potential safety hazards.