Prediction of biomarker-disease associations based on graph attention network and text representation.

MOTIVATION: The associations between biomarkers and human diseases play a key role in understanding complex pathology and developing targeted therapies. Wet lab experiments for biomarker discovery are costly, laborious and time-consuming. Computational prediction methods can be used to greatly expedite the identification of candidate biomarkers. RESULTS: Here, we present a novel computational model named GTGenie for predicting the biomarker-disease associations based on graph and text features. In GTGenie, a graph attention network is utilized to characterize diverse similarities of biomarkers and diseases from heterogeneous information resources. Meanwhile, a pretrained BERT-based model is applied to learn the text-based representation of biomarker-disease relation from biomedical literature. The captured graph and text features are then integrated in a bimodal fusion network to model the hybrid entity representation. Finally, inductive matrix completion is adopted to infer the missing entries for reconstructing relation matrix, with which the unknown biomarker-disease associations are predicted. Experimental results on HMDD, HMDAD and LncRNADisease data sets showed that GTGenie can obtain competitive prediction performance with other state-of-the-art methods. AVAILABILITY: The source code of GTGenie and the test data are available at: https://github.com/Wolverinerine/GTGenie.

Redefining Health Care Data Interoperability: Empirical Exploration of Large Language Models in Information Exchange.

BACKGROUND: Efficient data exchange and health care interoperability are impeded by medical records often being in nonstandardized or unstructured natural language format. Advanced language models, such as large language models (LLMs), may help overcome current challenges in information exchange. OBJECTIVE: This study aims to evaluate the capability of LLMs in transforming and transferring health care data to support interoperability. METHODS: Using data from the Medical Information Mart for Intensive Care III and UK Biobank, the study conducted 3 experiments. Experiment 1 assessed the accuracy of transforming structured laboratory results into unstructured format. Experiment 2 explored the conversion of diagnostic codes between the coding frameworks of the ICD-9-CM (International Classification of Diseases, Ninth Revision, Clinical Modification), and Systematized Nomenclature of Medicine Clinical Terms (SNOMED-CT) using a traditional mapping table and a text-based approach facilitated by the LLM ChatGPT. Experiment 3 focused on extracting targeted information from unstructured records that included comprehensive clinical information (discharge notes). RESULTS: The text-based approach showed a high conversion accuracy in transforming laboratory results (experiment 1) and an enhanced consistency in diagnostic code conversion, particularly for frequently used diagnostic names, compared with the traditional mapping approach (experiment 2). In experiment 3, the LLM showed a positive predictive value of 87.2% in extracting generic drug names. CONCLUSIONS: This study highlighted the potential role of LLMs in significantly improving health care data interoperability, demonstrated by their high accuracy and efficiency in data transformation and exchange. The LLMs hold vast potential for enhancing medical data exchange without complex standardization for medical terms and data structure.

Tracking and Profiling Repeated Users Over Time in Text-Based Counseling: Longitudinal Observational Study With Hierarchical Clustering.

BACKGROUND: Due to their accessibility and anonymity, web-based counseling services are expanding at an unprecedented rate. One of the most prominent challenges such services face is repeated users, who represent a small fraction of total users but consume significant resources by continually returning to the system and reiterating the same narrative and issues. A deeper understanding of repeated users and tailoring interventions may help improve service efficiency and effectiveness. Previous studies on repeated users were mainly on telephone counseling, and the classification of repeated users tended to be arbitrary and failed to capture the heterogeneity in this group of users. OBJECTIVE: In this study, we aimed to develop a systematic method to profile repeated users and to understand what drives their use of the service. By doing so, we aimed to provide insight and practical implications that can inform the provision of service catering to different types of users and improve service effectiveness. METHODS: We extracted session data from 29,400 users from a free 24/7 web-based counseling service from 2018 to 2021. To systematically investigate the heterogeneity of repeated users, hierarchical clustering was used to classify the users based on 3 indicators of service use behaviors, including the duration of their user journey, use frequency, and intensity. We then compared the psychological profile of the identified subgroups including their suicide risks and primary concerns to gain insights into the factors driving their patterns of service use. RESULTS: Three clusters of repeated users with clear psychological profiles were detected: episodic, intermittent, and persistent-intensive users. Generally, compared with one-time users, repeated users showed higher suicide risks and more complicated backgrounds, including more severe presenting issues such as suicide or self-harm, bullying, and addictive behaviors. Higher frequency and intensity of service use were also associated with elevated suicide risk levels and a higher proportion of users citing mental disorders as their primary concerns. CONCLUSIONS: This study presents a systematic method of identifying and classifying repeated users in web-based counseling services. The proposed bottom-up clustering method identified 3 subgroups of repeated users with distinct service behaviors and psychological profiles. The findings can facilitate frontline personnel in delivering more efficient interventions and the proposed method can also be meaningful to a wider range of services in improving service provision, resource allocation, and service effectiveness.

The effects of language proficiency and awareness of time limit in animated vs. text-based situational judgment tests.

BACKGROUND: Situational Judgment Tests (SJTs) are commonly used in medical school admissions. However, it has been consistently found that native speakers tend to score higher on SJTs than non-native speakers, which can be particularly problematic in the admission context due to the potential risk of limited fairness. Besides type of SJT, awareness of time limit may play a role in subgroup differences in the context of cognitive load theory. This study examined the influence of SJT type and awareness of time limit against the background of language proficiency in a quasi high-stakes setting. METHODS: Participants (N = 875), applicants and students in healthcare-related study programs, completed an online study that involved two SJTs: one with a text-based stimulus and response format (HAM-SJT) and another with a video-animated stimulus and media-supported response format (Social Shapes Test, SST). They were randomly assigned to a test condition in which they were either informed about a time limit or not. In a multilevel model analysis, we examined the main effects and interactions of the predictors (test type, language proficiency and awareness of time limit) on test performance (overall, response percentage). RESULTS: There were significant main effects on overall test performance for language proficiency in favor of native speakers and for awareness of time limit in favor of being aware of the time limit. Furthermore, an interaction between language proficiency and test type was found, indicating that subgroup differences are smaller for the animated SJT than for the text-based SJT. No interaction effects on overall test performance were found that included awareness of time limit. CONCLUSION: A SJT with video-animated stimuli and a media-supported response format can reduce subgroup differences in overall test performance between native and non-native speakers in a quasi high-stakes setting. Awareness of time limit is equally important for high and low performance, regardless of language proficiency or test type.

Efficacy of Daily Text Messaging to Support Adherence to HIV Pre-Exposure Prophylaxis (PrEP) among Stimulant-Using Men Who Have Sex with Men.

Background: Men who have sex with men (MSM) who use stimulants are at increased risk for HIV infection. Adherence to pre-exposure prophylaxis (PrEP) reduces the risk of HIV infection. We evaluated the efficacy of the individualized Texting for Adherence Building (iTAB) intervention for PrEP adherence compared to standard of care (SoC) among 119 MSM who use stimulants (cocaine, methamphetamine and/or other amphetamine) from the California Collaborative Treatment Group 595 randomized control trial.Method: Three ordered levels of PrEP adherence (non-adherence, adequate adherence, and near-perfect adherence) were compared between intervention arms across study visits (weeks 12 and 48) using ordinal logistic regressions.Results: The effect of intervention arm was not significant in the final model; however, there was a 38% decrease in odds (OR = 0.62, p=.023) of having near-perfect adherence (versus non-adherence or adequate adherence) at week 48 compared to week 12, indicating a significant effect of time. In a follow-up analysis examining week 48 only, logistic regression examining PrEP adherence showed that receiving iTAB (compared to SoC) trended toward higher odds of near-perfect adherence relative to adequate adherence (OR = 2.48, p=.061). Higher HIV knowledge resulted in higher odds (OR = 1.72, p=.020) of near-perfect adherence (versus non-adherence or adequate adherence).Conclusion: HIV knowledge may influence PrEP adherence, and most notably, the iTAB intervention may support near-perfect adherence relative to adequate adherence.

Deep Learning Based CAPTCHA Recognition Network with Grouping Strategy.

Websites can improve their security and protect against harmful Internet attacks by incorporating CAPTCHA verification, which assists in distinguishing between human users and robots. Among the various types of CAPTCHA, the most prevalent variant involves text-based challenges that are intentionally designed to be easily understandable by humans while presenting a difficulty for machines or robots in recognizing them. Nevertheless, due to significant advancements in deep learning, constructing convolutional neural network (CNN)-based models that possess the capability of effectively recognizing text-based CAPTCHAs has become considerably simpler. In this regard, we present a CAPTCHA recognition method that entails creating multiple duplicates of the original CAPTCHA images and generating separate binary images that encode the exact locations of each group of CAPTCHA characters. These replicated images are subsequently fed into a well-trained CNN, one after another, for obtaining the final output characters. The model possesses a straightforward architecture with a relatively small storage in system, eliminating the need for CAPTCHA segmentation into individual characters. Following the training and testing of the suggested CNN model for CAPTCHA recognition, the experimental results demonstrate the model's effectiveness in accurately recognizing CAPTCHA characters.

Developing a text message intervention for fathers with partners experiencing perinatal depression or anxiety.

BACKGROUND: Support from fathers to their partners is important to reduce distress in mothers during the perinatal period when conditions such as depression and anxiety can be common. The SMS4dads digital platform delivers text messages to fathers but has not previously addressed specific messages to fathers with partners who are experiencing perinatal depression and/or anxiety (PNDA). AIM: To develop messages, in collaboration with experienced parents and clinicians, that are suitable for fathers whose partner is experiencing PNDA. METHODS: Messages designed to enhance the quality of partner support for mothers experiencing PNDA were drafted by the SMS4dads team based on suggestions from mothers with lived experience of PNDA. Mothers and fathers with lived experience and expert clinicians rated the messages for importance and understanding. Clinicians additionally rated clinical relevance. Open response comments from parents and clinicians were collated for each message. Re-drafted messages were screened again and checked for literacy level. RESULTS: Forty-one draft messages received a total of 170 ratings from 24 parents and 164 ratings from 32 clinicians. Over three quarters of parents and clinicians agreed or strongly agreed that messages were understandable (parents 85.6%; clinicians 77.4%), important (parents 86.3%; clinicians 86.6%), and 85.5% of clinicians rated the messages as clinically relevant. Comments from clinicians (n = 99) and parents (n = 46) were reviewed and guided message development. Thirty re-drafted messages were screened and 16 edited based on a second round of ratings and comments from parents and clinicians. CONCLUSION: Messages for fathers whose partners are experiencing depression and anxiety can be developed and evaluated in collaboration with lived experience of parents and clinicians.

Assessing the quality of digital patient-therapist communication: the development and validation of a text-based facilitative interpersonal skills task.

OBJECTIVE: Text-based communication is becoming an increasingly salient feature of the psychotherapeutic landscape. Yet little is known about the factors distinguishing high- and low-quality therapeutic conversations taking place over this modality. Prior research on therapist effects has outlined several common factors associated with better clinical outcomes. But these common factors can only be researched in the context of text-based communication if they can be measured. Accordingly, we developed and validated a new behavioral task and coding system: the Facilitative Interpersonal Skills Performance Task for Text (FIS-T) to measure therapists' messaging quality across eight dimensions of facilitative interpersonal skill. METHODS: 1150 survey-takers rated the interpersonal dynamics and response difficulty of the FIS-T Task's text-based stimuli. The FIS-T was then administered to 64 therapists. RESULTS: The FIS-T stimuli displayed similar interpersonal dynamics to those elicited by the original FIS task, demonstrated a similar range of difficulties to those of the video-based stimuli of the original FIS Task, and showed high inter-rater reliability. CONCLUSIONS: The text-based FIS-T Task demonstrates high reliability and convergent validity with the original FIS Task, making it appropriate for use in assessing the common factors in text-based therapy. Future directions in the quality assessment of internet-delivered psychotherapies are discussed.

NanoAdventure: Development of a Text-Based Adventure Game in English, Spanish, and Chinese for Communicating about Nanotechnology and the Nanoscale.

Video games and immersive, narrative experiences are often called upon to help students understand difficult scientific concepts, such as sense of scale. However, the development of educational video games requires expertise and, frequently, a sizable budget. Here, we report on the use of an interactive text-style video game, NanoAdventure, to communicate about sense of scale and nanotechnology to the public. NanoAdventure was developed on an open-source, free-to-use platform with simple coding and enhanced with free or low-cost assets. NanoAdventure was launched in three languages (English, Spanish, Chinese) and compared to textbook-style and blog-style control texts in a randomized study. Participants answered questions on their knowledge of nanotechnology and their attitudes toward nanotechnology before and after reading one randomly assigned text (textbook, blog, or NanoAdventure game). Our results demonstrate that interactive fiction is effective in communicating about sense of scale and nanotechnology as well as the relevance of nanotechnology to a general public. NanoAdventure was found to be the most "fun" and easy to read of all text styles by participants in a randomized trial. Here, we make the case for interactive "Choose Your Own Adventure" style games as another effective tool among educational game models for chemistry and science communication.

Learner autonomy, learner engagement and learner satisfaction in text-based and multimodal computer mediated writing environments.

Technology creates variant learning experiences which are context specific. This study examined the comparative potential of multimodal and text-based Computer Mediated Communication (CMC) in fostering learner autonomy, learner engagement and learner e-satisfaction as well as learner writing quality. To this end, 40 Iranian male and female EFL (English as foreign language) students were selected on the basis of their writing proficiency and were randomly assigned into text-based and multimodal CMC research groups. Learner autonomy was investigated using Van Nguyen and Habók 's learner autonomy questionnaire, which had 40 items rated on 5 point likert scale, both before and after the treatment. Student engagement was tracked by analyzing transcription of stored conversations of Moodle and Discussion logs of an online writing forum, using a coding scheme to identify cognitive, emotional, and behavioral student engagement. The potential of text-based CMC and Multimodal CMC in fostering writing quality was examined by comparing students' writing before and after treatment. Finally, students were asked to write reflective essays on their evaluation of efficacy of the learning environments. Content analysis was conducted on the open and axial coding of indicators of student satisfaction. The results of between group comparison indicated that students were more autonomous in text-based modality than in multimodal CMC. Chi-square analysis indicated that text-based CMC group outperformed multimodal CMC group in terms of behavioral and cognitive engagement. Yet, multimodal CMC group reported higher emotional and social engagement. One-way ANCOVA results also indicated that the students in text-based CMC group outperformed Multimodal CMC group in terms of writing quality. Learner e-satisfaction was examined by network mapping of open codes of student reflective essays. The study identified four categories that reflected students' e-satisfaction: learner dimension (including learners' attitude, learner internet self-efficacy), teacher dimension (including teacher presence, teacher digital competences), curriculum dimension (including curriculum flexibility, course quality, flexibility in interaction support system) and internet dimension (including internet quality and support system). However, internet dimension received negative judgments from both groups. The implications of the study and suggestions for further research are discussed.

Feasibility of implementing a text-based symptom-monitoring program of endometrial, ovarian, and breast cancer patients during treatment.

PURPOSE: To evaluate the feasibility of implementing systematic patient symptom monitoring during treatment using a smartphone. METHODS: Endometrial [n = 50], ovarian [n = 70] and breast [n = 193] cancer patients participated in text-based symptom reporting for up to 12 months. In order to promote equity, patients without a smartphone were provided with a device, with the phone charges paid by program funds. Each month, patients completed the Patient Health Questionnaire (PHQ-9), and 4 single items assessing fatigue, sleep quality, pain, and global quality of life during the past 7 days rated on a 0 (low) -10 (high) scale. Patients' responses were captured using REDCap, with oncologists receiving monthly feedback. Lay navigators provided assistance to patients with non-medical needs. RESULTS: Patients utilizing this voluntary program had an overall mean age of 60.5 (range 26-87), and 85% were non-Hispanic white. iPhones were provided to 42 patients, and navigation services were used by 69 patients. Average adherence with monthly surveys ranged between 75-77%, with breast patients having lower adherence after 5 months. The most commonly reported symptoms across cancer types were moderate levels (scores of 4-7) of fatigue and sleep disturbance. At 6 months, 71-77% of all patients believed the surveys were useful to them and their health care team. CONCLUSIONS: We established the feasibility of initiating and managing patients in a monthly text-based symptom-monitoring program. The provision of smartphones and patient navigation were unique and vital components of this program.

Online learning under COVID-19: re-examining the prominence of video-based and text-based feedback.

During the COVID-19 pandemic, higher education institutions have been faced with a rapid shift to remote digital learning across courses. The resultant proliferation of online learning in traditional, hybrid, and distance higher education courses has enhanced the possibilities for technology-supported student-centered learning design. The prominence of feedback in student-centered teaching could be argued in two ways: (1) instructed learning is based on interaction and communication in which the teacher provides personalized information to students about their progress and (2) feedback is oriented towards students' improvements, which in turn guides student engagement. Therefore, feedback addressing students' personal needs integrates multiple dimensions and profoundly influences learning. In response to J. Borup, R. E. West, and R. Thomas (2015)'s article The Impact of Text Versus Video Communication on Instructor Feedback in Blended Courses we discusses the efforts to prepare higher education for online learning. During the pandemic, teachers rapidly faced requirements for providing feedback to students remotely and performing all teaching roles online. The authors in this section build a strong argument that feedback with a supportive function is essential in a time when students and teacher are working remotely. They argued for personalized learning requiring feedback at different points of the learning process that utilizes a range of feedback functions and forms and, most of all, employs contextualization and a situated approach.

Effects of Virtual Reality training on medical students' learning motivation and competency.

OBJECTIVES: To determine the need of contemporary immersive approaches (Virtual Reality) in teaching and training at medical sector. The main objective of this study was to explore the effects of text, video and immersive technologies learning methodologies for participants' learning in public and private medical colleges and universities of Pakistan. METHODS: In this quantitative research 87 medical students of 4th year from three public and five private medical colleges and universities participated. A laparoscopy operation was selected in consultation with senior medical consultants for this experiment. The experimental material was arranged in virtual reality, video and text based learning. At completion of each of which, participants completed a questionnaire about learning motivation and learning competency through the different mediums. RESULTS: Statistical t-test was selected for the analysis of this study. By comparing the mean values of virtual reality, video, and text based learning methodologies in medical academics; result of virtual reality is at top of others. All performed model are statistically significant (P=0.000) and results can be applied at all population. CONCLUSION: Through this research, we contribute to medical students learning methodologies. In medical studies, both theoretical and practical expertise has a vital role, while repetition of hands-on practice can improve young doctors' professional competency. Virtual reality was found best for medical students in both learning motivation and learning competency. Medical students and educationist may select virtual reality as new learning methodology for curriculum learning.

Text-based phenotypic profiles incorporating biochemical phenotypes of inborn errors of metabolism improve phenomics-based diagnosis.

Phenomics is the comprehensive study of phenotypes at every level of biology: from metabolites to organisms. With high throughput technologies increasing the scope of biological discoveries, the field of phenomics has been developing rapid and precise methods to collect, catalog, and analyze phenotypes. Such methods have allowed phenotypic data to be widely used in medical applications, from assisting clinical diagnoses to prioritizing genomic diagnoses. To channel the benefits of phenomics into the field of inborn errors of metabolism (IEM), we have recently launched IEMbase, an expert-curated knowledgebase of IEM and their disease-characterizing phenotypes. While our efforts with IEMbase have realized benefits, taking full advantage of phenomics requires a comprehensive curation of IEM phenotypes in core phenomics projects, which is dependent upon contributions from the IEM clinical and research community. Here, we assess the inclusion of IEM biochemical phenotypes in a core phenomics project, the Human Phenotype Ontology. We then demonstrate the utility of biochemical phenotypes using a text-based phenomics method to predict gene-disease relationships, showing that the prediction of IEM genes is significantly better using biochemical rather than clinical profiles. The findings herein provide a motivating goal for the IEM community to expand the computationally accessible descriptions of biochemical phenotypes associated with IEM in phenomics resources.

Effectiveness of video- versus text-based computer-tailored smoking cessation interventions among smokers after one year.

BACKGROUND: In western countries, smoking prevalence rates are high among smokers unmotivated to quit and those with a lower socioeconomic status (LSES). Multiple computer tailoring and the use of audio-visual aids may improve such interventions and increase cessation in LSES smokers. This study assessed the 12-month effectiveness of a video- and text-based computer-tailored intervention. METHODS: A randomized controlled trial in the Netherlands was used in which smokers were allocated to the video-based condition (VC) (N=670), the text-based condition (TC) (N=708) or the control condition (CC) (brief generic text advice) (N=721). After 12months, self-reported prolonged abstinence was assessed and biochemically verified in respondents indicating to have quit smoking. Three analysis strategies were used to assess the effects: (1) multiple imputation (MI); (2) intention-to-treat (ITT); (3) complete case analysis (CC). RESULTS: VC was more effective in prolonged abstinence compared to CC (odds ratio (OR)=1.90, p=.005) and the text-based condition (OR=1.71, p=.01). VC was furthermore more effective than TC. No differences were found for SES and motivational levels. Results were similar when using ITT and CC. For our secondary outcome seven-day point prevalence abstinence; however, neither VC (OR=1.17, p=.34) or TC (OR=0.91, p=.52) outperformed the CC. CONCLUSION: The video-based computer-tailored intervention was effective in obtaining substantial long-term abstinence compared to the text-based version and a brief generic text advice.

Randomized Trial of the Effectiveness of Videoconferencing-Based Versus Message-Based Psychotherapy on Depression.

OBJECTIVE: The authors compared the engagement, clinical outcomes, and adverse events of text or voice message-based psychotherapy (MBP) versus videoconferencing-based psychotherapy (VCP) among adults with depression. METHODS: The study used a sequential multiple-assignment randomized trial design with data drawn from phase 1 of a two-phase small business innovation research study. In total, 215 adults (ages ≥18 years) with depression received care from Talkspace, a digital mental health care company. Participants were initially randomly assigned to receive either asynchronous MBP or weekly VCP. All therapists provided evidence-based treatments such as cognitive-behavioral therapy. After 6 weeks of treatment, participants whose condition did not show a response on the Patient Health Questionnaire-9 or was rated as having not improved on the Clinical Global Impressions scale were randomly reassigned to receive either weekly VCP plus MBP or monthly VCP plus MBP. Longitudinal mixed-effects models with piecewise linear time trends applied to multiple imputed data sets were used to address missingness of data. RESULTS: Participants who were initially assigned to the MBP condition engaged with their therapists over more weeks than did participants in the VCP condition (7.8 weeks for MBP vs. 4.9 weeks for VCP; p<0.001). No meaningful differences were observed between the two groups in rates of change by 6 or 12 weeks for depression, anxiety, disability, or global ratings of improvement. Neither treatment resulted in any adverse events. CONCLUSIONS: MBP appears to be a viable alternative to VCP for treating adults with depression.

Enhancing Medical Image Retrieval with UMLS-Integrated CNN-Based Text Indexing.

In recent years, Convolutional Neural Network (CNN) models have demonstrated notable advancements in various domains such as image classification and Natural Language Processing (NLP). Despite their success in image classification tasks, their potential impact on medical image retrieval, particularly in text-based medical image retrieval (TBMIR) tasks, has not yet been fully realized. This could be attributed to the complexity of the ranking process, as there is ambiguity in treating TBMIR as an image retrieval task rather than a traditional information retrieval or NLP task. To address this gap, our paper proposes a novel approach to re-ranking medical images using a Deep Matching Model (DMM) and Medical-Dependent Features (MDF). These features incorporate categorical attributes such as medical terminologies and imaging modalities. Specifically, our DMM aims to generate effective representations for query and image metadata using a personalized CNN, facilitating matching between these representations. By using MDF, a semantic similarity matrix based on Unified Medical Language System (UMLS) meta-thesaurus, and a set of personalized filters taking into account some ranking features, our deep matching model can effectively consider the TBMIR task as an image retrieval task, as previously mentioned. To evaluate our approach, we performed experiments on the medical ImageCLEF datasets from 2009 to 2012. The experimental results show that the proposed model significantly enhances image retrieval performance compared to the baseline and state-of-the-art approaches.

Recent Developments in Paper-Based Sensors with Instrument-Free Signal Readout Technologies (2020-2023).

Signal readout technologies that do not require any instrument are essential for improving the convenience and availability of paper-based sensors. Thanks to the remarkable progress in material science and nanotechnology, paper-based sensors with instrument-free signal readout have been developed for multiple purposes, such as biomedical detection, environmental pollutant tracking, and food analysis. In this review, the developments in instrument-free signal readout technologies for paper-based sensors from 2020 to 2023 are summarized. The instrument-free signal readout technologies, such as distance-based signal readout technology, counting-based signal readout technology, text-based signal readout technology, as well as other transduction technologies, are briefly introduced, respectively. On the other hand, the applications of paper-based sensors with instrument-free signal readout technologies are summarized, including biomedical analysis, environmental analysis, food analysis, and other applications. Finally, the potential and difficulties associated with the advancement of paper-based sensors without instruments are discussed.

Interventions to improve oral endocrine therapy adherence in breast cancer patients.

PURPOSE: Oral endocrine therapy (OET) is recommended in prevention and treatment of hormone receptor-positive breast cancer (HR+ BC). Despite the reduced incidence, recurrence, and mortality, OET adherence is poor in this patient population. The aim of this study was to review the latest literature to identify effective interventions to improve medication adherence in patients taking OET for prevention or treatment of HR+ BC. METHODS: The Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) framework was used to perform this review. We utilized PubMed, SCOPUS, EMBASE, Cochrane, and Web of Science to acquire articles using search terms including breast cancer, adherence, persistence, and acceptability. Inclusion criteria included publication in peer-reviewed journal, primary data source, longitudinal, patients on OET such as aromatase inhibitors (AIs) or selective estrogen receptor modulators (SERMs), measuring adherence, persistence, or acceptability. RESULTS: Out of 895 articles identified, 10 articles were included. Majority of patients had early-stage HR+ BC. Two out of two studies incorporating technological intervention, two out of three studies with text communication-based intervention, and three out of five studies with verbal communication-based intervention reported significant improvement in OET adherence and/or persistence. CONCLUSIONS: While the interventions tested so far have shown to improve OET adherence in HR+ BC patients in some studies, there is a need to design combination interventions addressing multiple barriers in this population. IMPLICATIONS FOR CANCER SURVIVORS: This study showcases effectiveness of novel interventions to improve OET adherence and the need to further develop patient-centered strategies to benefit all patients with HR+ BC.