Predicting Social Determinants of Health in Patient Navigation: Case Study.

BACKGROUND: Patient navigation (PN) programs have demonstrated efficacy in improving health outcomes for marginalized populations across a range of clinical contexts by addressing barriers to health care, including social determinants of health (SDoHs). However, it can be challenging for navigators to identify SDoHs by asking patients directly because of many factors, including patients' reluctance to disclose information, communication barriers, and the variable resources and experience levels of patient navigators. Navigators could benefit from strategies that augment their ability to gather SDoH data. Machine learning can be leveraged as one of these strategies to identify SDoH-related barriers. This could further improve health outcomes, particularly in underserved populations. OBJECTIVE: In this formative study, we explored novel machine learning-based approaches to predict SDoHs in 2 Chicago area PN studies. In the first approach, we applied machine learning to data that include comments and interaction details between patients and navigators, whereas the second approach augmented patients' demographic information. This paper presents the results of these experiments and provides recommendations for data collection and the application of machine learning techniques more generally to the problem of predicting SDoHs. METHODS: We conducted 2 experiments to explore the feasibility of using machine learning to predict patients' SDoHs using data collected from PN research. The machine learning algorithms were trained on data collected from 2 Chicago area PN studies. In the first experiment, we compared several machine learning algorithms (logistic regression, random forest, support vector machine, artificial neural network, and Gaussian naive Bayes) to predict SDoHs from both patient demographics and navigator's encounter data over time. In the second experiment, we used multiclass classification with augmented information, such as transportation time to a hospital, to predict multiple SDoHs for each patient. RESULTS: In the first experiment, the random forest classifier achieved the highest accuracy among the classifiers tested. The overall accuracy to predict SDoHs was 71.3%. In the second experiment, multiclass classification effectively predicted a few patients' SDoHs based purely on demographic and augmented data. The best accuracy of these predictions overall was 73%. However, both experiments yielded high variability in individual SDoH predictions and correlations that become salient among SDoHs. CONCLUSIONS: To our knowledge, this study is the first approach to applying PN encounter data and multiclass learning algorithms to predict SDoHs. The experiments discussed yielded valuable lessons, including the awareness of model limitations and bias, planning for standardization of data sources and measurement, and the need to identify and anticipate the intersectionality and clustering of SDoHs. Although our focus was on predicting patients' SDoHs, machine learning can have a broad range of applications in the field of PN, from tailoring intervention delivery (eg, supporting PN decision-making) to informing resource allocation for measurement, and PN supervision.

Effects of smartphone interventions on cancer knowledge and coping among Latina breast cancer survivors: Secondary analysis of a pilot randomized controlled trial.

Objective: The My Guide smartphone application was developed to improve quality of life and symptom burden (primary outcomes) for Latina breast cancer survivors (BCS) and tested in a pilot randomized controlled trial compared to an attention-control condition (My Health smartphone application). This secondary analysis examined effects on breast cancer knowledge, coping, and cancer-related self-efficacy (intervention targets).Method: Latina BCS (N = 78) were randomized to My Guide or My Health for six weeks. Linear mixed-effects modeling evaluated the effects of time and study condition on the intervention targets. Effects by engagement were explored. Results: Both conditions showed improved breast cancer knowledge (p < 0.001), with a trend for greatest improvement among My Guide high users (p = 0.082). My Guide participants reported less self-blame overall than My Health participants (p = 0.020). There were no effects on cancer-related self-efficacy (ps > 0.05). Conclusion: Culturally-informed smartphone applications may enhance breast cancer knowledge and promote adaptive coping among Latina BCS.

Web-Based Information Seeking Behaviors of Low-Literacy Hispanic Survivors of Breast Cancer: Observational Pilot Study.

BACKGROUND: Internet searching is a useful tool for seeking health information and one that can benefit low-literacy populations. However, low-literacy Hispanic survivors of breast cancer do not normally search for health information on the web. For them, the process of searching can be frustrating, as frequent mistakes while typing can result in misleading search results lists. Searches using voice (dictation) are preferred by this population; however, even if an appropriate result list is displayed, low-literacy Hispanic women may be challenged in their ability to fully understand any individual article from that list because of the complexity of the writing. OBJECTIVE: This observational study aims to explore and describe web-based search behaviors of Hispanic survivors of breast cancer by themselves and with their caregivers, as well as to describe the challenges they face when processing health information on the web. METHODS: We recruited 7 Hispanic female survivors of breast cancer. They had the option to bring a caregiver. Of the 7 women, 3 (43%) did, totaling 10 women. We administered the Health LiTT health literacy test, a demographic survey, and a breast cancer knowledge assessment. Next, we trained the participants to search on the web with either a keyboard or via voice. Then, they had to find information about 3 guided queries and 1 free-form query related to breast cancer. Participants were allowed to search in English or in Spanish. We video and audio recorded the computer activity of all participants and analyzed it. RESULTS: We found web articles to be written for a grade level of 11.33 in English and 7.15 in Spanish. We also found that most participants preferred searching using voice but struggled with this modality. Pausing while searching via voice resulted in incomplete search queries, as it confused the search engine. At other times, background noises were detected and included in the search. We also found that participants formulated overly general queries to broaden the results list hoping to find more specific information. In addition, several participants considered their queries satisfied based on information from the snippets on the result lists alone. Finally, participants who spent more time reviewing articles scored higher on the health literacy test. CONCLUSIONS: Despite the problems of searching using speech, we found a preference for this modality, which suggests a need to avoid potential errors that could appear in written queries. We also found the use of general questions to increase the chances of answers to more specific concerns. Understanding search behaviors and information evaluation strategies for low-literacy Hispanic women survivors of breast cancer is fundamental to designing useful search interfaces that yield relevant and reliable information on the web.

Patterns of Use of Smartphone-Based Interventions Among Latina Breast Cancer Survivors: Secondary Analysis of a Pilot Randomized Controlled Trial.

BACKGROUND: Latina breast cancer survivors experience poorer health-related quality of life (HRQoL), greater symptom burden, and more psychosocial needs compared to non-Latina breast cancer survivors. eHealth platforms such as smartphone apps are increasingly being used to deliver psychosocial interventions to cancer survivors. However, few psychosocial eHealth interventions have been developed specifically for Latina breast cancer survivors. Further, little is known about how Latinas, in general, engage with eHealth interventions and whether specific participant characteristics are associated with app use in this population. We evaluated the use of 2 culturally informed, evidence-based smartphone apps for Latina breast cancer survivors-one that was designed to improve HRQoL and reduce symptom burden (My Guide) and the other to promote healthy lifestyle behaviors (My Health). OBJECTIVE: The objectives of our study were to explore the patterns of use of the My Guide intervention app and My Health attention-control app among Latina breast cancer survivors. METHODS: Eighty Latina breast cancer survivors were randomized to use the My Guide or My Health app for 6 weeks. Assessments were collected at baseline (T1), immediately after the 6-week intervention (T2), and 2 weeks after T2 (T3). Specific study outcomes included subdomains of HRQoL, symptom burden, cancer-specific distress, cancer-relevant self-efficacy, and breast cancer knowledge. RESULTS: On average, participants used their assigned app for more than 1 hour per week. Sociodemographic or psychological characteristics were not significantly associated with app use, except for employment status in the My Health group. Content related to common physical and emotional symptoms of breast cancer survivors as well as recommendations for nutrition and physical activity were most frequently accessed by My Guide and My Health participants, respectively. Lastly, clinically meaningful improvements were demonstrated in breast cancer well-being among low app users (ie, <60 minutes of use/week) of My Guide and social well-being among high app users (ie, ≥60 minutes of use/week) of My Health. CONCLUSIONS: The favorable rates of participant use across both apps suggest that Latina breast cancer survivors are interested in the content delivered across both My Guide and My Health. Furthermore, since sociodemographic variables, excluding employment status, and baseline HRQoL (psychological variable) were not related to app use, My Guide and My Health may be accessible to diverse Latina breast cancer survivors. TRIAL REGISTRATION: ClinicalTrials.gov NCT03645005; https://clinicaltrials.gov/ct2/show/NCT03645005.

Cancer-Relevant Self-Efficacy Is Related to Better Health-Related Quality of Life and Lower Cancer-Specific Distress and Symptom Burden Among Latina Breast Cancer Survivors.

BACKGROUND: Latina breast cancer survivors (BCS) often report poorer health-related quality of life (HRQOL), higher symptom burden, and greater psychosocial needs compared to non-Latina BCS. However, Latinas are underrepresented in cancer survivorship research and more work is needed to examine the factors contributing to these psychosocial disparities. This study aimed to evaluate potentially modifiable patient characteristics associated with HRQOL, breast cancer concerns, and cancer-specific distress among Latina BCS. METHODS: Baseline data was evaluated in 95 Latina BCS who participated in a smartphone-based psychosocial intervention designed to improve HRQOL. Hierarchical linear regression analyses were conducted to evaluate the associations between modifiable factors that have been shown to favorably impact outcomes in cancer populations (i.e., cancer-relevant self-efficacy, breast cancer knowledge) with overall and domain-specific HRQOL, breast cancer symptom burden, and cancer-specific distress, after controlling for sociodemographic and cancer-related characteristics. RESULTS: Greater cancer-relevant self-efficacy was related to better overall HRQOL as well as better social, emotional, and functional well-being domains. Greater cancer-relevant self-efficacy was also related to less breast cancer symptom burden and less cancer-specific distress. Breast cancer knowledge was not associated with any of the study outcomes. CONCLUSIONS: Results demonstrate that cancer-relevant self-efficacy is a significant correlate of general and domain-specific HRQOL, breast cancer symptom burden, and cancer-specific distress among Latina BCS. Future interventions in this population should target cancer-relevant self-efficacy as a possible mechanism to improve HRQOL outcomes and survivorship experiences for Latina BCS.

My health smartphone intervention decreases daily fat sources among Latina breast cancer survivors.

Breast cancer is the most common cancer among Latina women, and Latina women are at higher risk for breast cancer mortality than white women. Lifestyle factors, such as consuming a nutritious diet and engaging in regular physical activity, promote health and are protective against heart disease, type 2 diabetes, and breast cancer recurrence. Previous studies have developed and tested interventions for Latina breast cancer survivors to improve diet and increase physical activity, however, no studies to date have developed a smartphone delivered intervention. The purpose of the current study was to compare two Smartphone delivered interventions, My Health, which focused on diet and physical activity, and My Guide, which focused on psychosocial functioning, on dietary and physical activity outcomes, post-intervention, and at a 2-week follow-up assessment. Overall, participants receiving the My Health intervention reported a greater reduction in daily fat sources than the My Guide group over time. However, daily sources of fat did not differ between conditions. Walking, measured by estimated weekly metabolic equivalents, increased across time points in both groups. These preliminary findings suggest that eHealth interventions aimed at improving lifestyle factors may favorably impact nutritional intake and physical activity. Future research should utilize more comprehensive and objective measures of diet and physical activity, and incorporate more behavioral lifestyle components into the intervention in larger samples with a longer follow-up period.

Brief culturally informed smartphone interventions decrease breast cancer symptom burden among Latina breast cancer survivors.

OBJECTIVE: Latina breast cancer survivors (BCS) report more symptom burden and poorer health-related quality of life than non-Latina BCS. However, there are few evidence-based and culturally informed resources that are easily accessible to this population. This study aimed to establish the feasibility and preliminary efficacy of the My Guide and My Health smartphone applications among Latina BCS. Both applications are culturally informed and contain evidence-based information for reducing symptom burden and improving health-related quality of life (My Guide) or healthy lifestyle promotion (My Health). METHODS: Participants (N = 80) were randomized to use the My Guide or My Health smartphone applications for 6 weeks. Assessments occurred at baseline (T1) after the 6-week intervention (T2) and 2-week post-T2 (T3). Outcomes were participant recruitment and retention rates, patient-reported satisfaction, and validated measures of symptom burden and health-related quality of life. RESULTS: Recruitment was acceptable (79%), retention was excellent (>90%), and over 90% of participants were satisfied with their application. On average, participants in both conditions used the applications for more than 1 hour per week. Symptom burden declined from T1 to T2 across both conditions, but this decline was not maintained at T3. Breast cancer well-being improved from T1 to T2 across both conditions and was maintained at T3. CONCLUSIONS: Latina BCS who used the My Guide and My Health applications reported temporary decreases in symptom burden and improved breast cancer well-being over time, though there were no differential effects between conditions. Findings suggest that technology may facilitate Latina BCS engagement in care after breast cancer treatment.

An Electronic Health Intervention for Latina Women Undergoing Breast Cancer Treatment (My Guide for Breast Cancer Treatment): Protocol for a Randomized Controlled Trial.

BACKGROUND: Among Latinas and Hispanics (henceforth referred to as Latinas), breast cancer is the most commonly diagnosed cancer and the leading cause of cancer-related deaths. However, few interventions have been developed to meet the needs of Latina women undergoing active treatment for breast cancer. OBJECTIVE: This paper aims to describe the procedures and methods of My Guide for Breast Cancer Treatment and the plans for conducting a multisite randomized controlled trial to investigate the feasibility and preliminary efficacy of this smartphone-based app for Latina women in active treatment for breast cancer. METHODS: Study participants will be randomized to the My Guide for Breast Cancer Treatment intervention or the enhanced usual care control condition for 12 weeks. Participants will have access to innovative features such as gamification via virtual awards to reinforce usage and an adaptive section that presents targeted material based on their self-reported concerns and needs. Using a stepped-care approach, intervention participants will also receive telecoaching to enhance their adherence to the app. Study outcomes and intervention targets will be measured at study enrollment (before randomization), 6 and 12 weeks after initial app use. General and disease-specific health-related quality of life (HRQoL) and symptom burden are the study's primary outcomes, whereas anxiety, depression, fear of cancer recurrence, physical activity, and dietary intake are secondary outcomes. RESULTS: Recruitment began in August 2019 and is expected to be completed by August 2020. We expect to submit study results for publication by fall 2020. CONCLUSIONS: My Guide for Breast Cancer Treatment has the potential to improve HRQoL and reduce symptom burden, and increase access to supportive care resources among Latina breast cancer patients. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/14339.

Improving Health Care Career Pipeline Programs for Underrepresented Students: Program Design that Makes a Difference.

BACKGROUND: Health care career pipeline training programs are one solution to increasing the number of minority and underrepresented health care providers. The Chicago Cancer Health Equity Collaborative (ChicagoCHEC) Research Fellows Program, a tri-institutional effort between the University of Illinois at Chicago (UIC), Northeastern Illinois University (NEIU), and Northwestern University (NU), provides a holistic, 8-week summer research fellowship that facilitates self-reflection, professional development, and exposes and guides the novice undergraduate and postbaccalaureate student toward a health care career inclusive of research and scientific discovery. OBJECTIVES: The number of underrepresented students achieving health care careers is minimal. We outline curriculum development, innovation, lessons learned, and selected outcomes from the first three cohorts of the ChicagoCHEC Research Fellows program. METHODS: A tri-institutional, collaborative curricular team was formed consisting of research faculty and staff at NEIU, UIC and NU. Once accepted, fellows experience a cohort model curriculum with particular emphasis to mindful inclusion of nontraditional students. The ChicagoCHEC Research Fellows Program uses evidence-based mentorship models, group reflection, and extensive program evaluation to continuously improve its program model. CONCLUSIONS: The 48 fellow alumni from the first 3 years reported high satisfaction with the program and will continued to be tracked for academic success. The ChicagoCHEC Research Fellows program will continue to provide academic and professional tools, sponsorship, and mentorship opportunities to underrepresented students as they progress toward health care careers. A program such as the ChicagoCHEC Fellows Program can serve as a useful model for increasing the number of minority researchers in health care careers.

Community Perspectives: Developing and Implementing a Smartphone Intervention for Latina Breast Cancer Survivors in Chicago.

Compared with non-Latina White breast cancer survivors (BCS), Latina BCS have poorer health-related quality of life and greater psychosocial needs. However, Latinas are less engaged in clinical research owing to barriers including less access to health-related information, less awareness of clinical trials, and practical barriers (e.g., competing time demands). Latina BCS are in need of educational and health-related resources that are culturally informed, scalable, and accessible. In 2015, the Chicago Cancer Health Equity Collaborative (ChicagoCHEC), a National Cancer Institute research collaborative, and ALAS-WINGS, a community organization providing educational and supportive resources to Latina BCS, partnered to develop My Guide. My Guide is a smartphone application-based intervention for Latina BCS designed to improve health-related quality of life (HRQOL). This article summarizes the experiences of ChicagoCHEC and ALAS-WINGS throughout the community-engaged research (CEnR) partnership. Using existing relationships in community and academic settings via CEnR provides an ideal starting point for tailoring resources to Latina BCS and engaging Latina BCS in health-related research.

Feasibility of a Smartphone-based pilot intervention for Hispanic breast cancer survivors: a brief report.

Hispanic breast cancer survivors (BCS) are at high risk for experiencing poor health-related quality of life (HRQoL) after completion of active breast cancer treatment. Therefore, there is a need to develop culturally tailored interventions for Hispanic BCS. To date, there have been limited interventions that have demonstrated that increasing cancer-related knowledge, self-efficacy in communication, and self-management skills can improve HRQoL among Hispanic BCS. These interventions have been delivered in person or by phone, which may be burdensome for Hispanic BCS. To facilitate intervention delivery, we developed My Guide, a Smartphone application aimed at improving HRQoL among Hispanic BCS. The purpose of the current study is to describe the feasibility results of a 4-week pilot trial testing My Guide among Hispanic BCS. Twenty-five women enrolled in the study (75% recruitment rate) and 22 women were retained (91.6% retention rate). Mean time spent using My Guide across the 4 weeks was 9.25 hr, and mean score on the satisfaction survey was 65.91 (range 42-70), in which higher scores reflect greater satisfaction. Participants' scores on the Breast Cancer Knowledge Questionnaire significantly improved from study baseline (M = 9.50, SD = 2.92) to the postintervention assessment (M = 11.14, SD = 2.66), d = 0.59. Participants' HRQoL scores improved over the course of 4 weeks, but these improvements were not statistically significant. Overall, My Guide was feasible and acceptable. Future studies will assess the preliminary efficacy of My Guide in improving HRQoL in a larger, randomized trial of Hispanic BCS.

Designing an mHealth application to bridge health disparities in Latina breast cancer survivors: a community-supported design approach.

Latina breast cancer patients in the USA report significantly worse cancer-related symptom burden and health-related quality of life than non-Hispanic whites. However, health literacy (e.g. knowledge about cancer, coping skills and communication) has been found to improve quality of life. In this paper, we present a case study of the methodology used to design Mi Guía (My Guide), a mobile application that aims to improve symptom burden and health-related quality of life among Hispanic women who have completed active treatment for breast cancer by increasing their health literacy. We developed a community-supported approach to building the application, which involved: (1) eliciting feedback from community leaders such as support group organizers and facilitators who are bilingual in Spanish and English, prioritize patients' preferences and best interests and have a unique knowledge of the women and their needs;(2) conducting a formal evaluation of design principles based on previous interaction design research and user responses;(3) incorporating feedback from potential future users. In this paper, we discuss our methodology, and the challenges and benefits of this approach. We believe that future studies that aim to develop mobile technologies for underserved populations may benefit from a community-supported approach to design.

Study design and protocol for My Guide: An e-health intervention to improve patient-centered outcomes among Hispanic breast cancer survivors.

Breast cancer is the most commonly diagnosed non-skin cancer in women and the leading cause of death among Hispanic women living in the United States. Relative to non-Hispanic white women, Hispanic women report poorer health related quality of life (HRQoL) after treatment. Although eHealth interventions delivered via Smartphones are a viable approach to addressing supportive care accessibility issues while also integrating multidisciplinary approaches for improving HRQoL, few eHealth interventions have been developed that specifically target Hispanic breast cancer survivors (BCS). This manuscript describes the methodology of a multi-site, randomized controlled behavioral trial investigating the feasibility and preliminary efficacy of a Smartphone application aimed at improving HRQoL and cancer-specific distress among Hispanic BCS. Participants will be randomized to receive the intervention application, My Guide (psychoeducation & self-management program), or the health education control condition application, My Health (health education), for six weeks. All participants will also receive weekly telecoaching to enhance adherence to both control and intervention conditions. We will measure the study's primary outcomes, general and disease-specific HRQoL and cancer-specific distress, at three time points: prior to, immediately after the intervention, and eight weeks after initial application use. My Guide may have the potential to improve HRQoL, and to address issues of limited access to supportive care among Hispanic women recovering from breast cancer treatment.