Learning Hormonal Therapy Medication Adherence from an Online Breast Cancer Forum

Yin, Zhijun; Warner, Jeremy L.; Song, Lijun; Hsueh, Pei-Yun Sabrina; Chen, Ching-Hua; Malin, Bradley

doi:10.1007/978-3-030-14714-3_12

Cited by 6 publications

(9 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two studies by Yin et al 29 30 used messaging patterns to predict behaviors around cancer treatment among patients with breast cancer. In the first publication, Yin et al 29 conducted a retrospective cohort study of the association between EMR messaging patterns and discontinuation of hormone therapy in breast cancer patients.…”

Section: Resultsmentioning

confidence: 99%

“…Seeking professional suggestions (HR = 0.766, p = 0.002), expressing gratitude to health care providers (HR = 0.872, p = 0.044), and mentions of drugs used to treat side effects (HR = 0.807, p = 0.013) were associated with decreased risk of medication discontinuation. 29 30…”

Section: Resultsmentioning

confidence: 99%

“…The second study by Yin et al 30 was a retrospective cohort study in which the content of electronic messages was used to predict initiation of hormonal therapy among breast cancer patients. The authors hypothesized that online patient portal messages by breast cancer patients convey both clinical and personal factors that can be used to predict whether that patient will decide to initiative hormone therapy.…”

Section: Resultsmentioning

confidence: 99%

“…Of interest, a similar disparity was noted, as in prior outlined studies, in that 90.1% of the cohort of patients who sent messages were Caucasian. 30…”

Section: Resultsmentioning

confidence: 99%

See 3 more Smart Citations

Electronic Medical Record–Based Electronic Messaging Among Patients with Breast Cancer: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

Background: Electronic Medical Record (EMR) systems and electronic messages are an increasingly common conduit between physicians and patients. Clear benefits of this type of communication have been established, especially among cancer patients. Studies suggest that patient portals and electronic messaging platforms can help with care coordination between oncology providers and facilitate asynchronous patient-provider communication. Despite the many benefits, there is little research regarding EMR and secure messaging use, particularly among patients with breast cancer. Objectives: The objective of this systematic review was to examine the evidence supporting the use of EMR based messaging systems in patients with breast cancer. Methods: A systematic literature search of Ovid MEDLINE, PubMed, Scopus, Web of Science CINAHL, and Cochrane Library was conducted. Studies were required to be published between 2005-2022 and report data on demographic information and electronic messaging between patients and providers. Studies were excluded if they reported insufficient data, did not include breast cancer patients, or were not published in English. Results: This study identified 10 articles that met inclusion criteria. The resulting studies investigated topics such as: patterns of messaging and medication adherence, cancer screening, messaging as a predictor of behavior or outcomes, and symptom management. The literature indicates that electronic messaging with providers was associated with clinical benefits for breast cancer patients and improved screening behaviors. Conclusions: This review uncovered multiple areas to focus future research on, including ideal volume of electronic messages sent and their relation to prescription adherence, studies focusing solely on the breast cancer population, racial disparities in electronic messaging, and provider perceptions of electronic messaging. It is vital that more work be done to understand barriers and gaps in electronic medical record usage to ensure that all individuals can access this increasingly essential medical service while minimizing physician workload and burnout.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

“…Of interest, a similar disparity was noted, as in prior outlined studies, in that 90.1% of the cohort of patients who sent messages were Caucasian. 30…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Electronic Medical Record–Based Electronic Messaging Among Patients with Breast Cancer: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Three of the candidate best papers 17 18 19 brought the patient and caregiver voices into cancer informatics, through the integration of patient-reported outcomes into routine cancer care, analysis of patient forum messages for signs of problems with medication adherence, and analysis of comment topics on a large cancer center's social media page.…”

Section: Discussionmentioning

confidence: 99%

Cancer Informatics in 2017: A New Beginning and a Bright Future

Warner

Patt

2018

Yearb Med Inform

Self Cite

View full text Add to dashboard Cite

show abstract

Optimizing Word Embeddings for Patient Portal Message Datasets with a Small Number of Samples

Song,

Ni,

Warner

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Background Patient portal messages often relate to specific clinical phenomena (e.g., patients undergoing treatment for breast cancer) and, as a result, have received increasing attention in biomedical research. These messages require natural language processing and, while word embedding models, such as word2vec, have the potential to extract meaningful signals from text, they are not readily applicable to patient portal messages. This is because embedding models typically require millions of training samples to sufficiently represent semantics, while the volume of patient portal messages associated with a particular clinical phenomenon is often relatively small. Objective We introduce a novel adaptation of the word2vec model, PK-word2vec, for small-scale messages. Methods PK-word2vec incorporates the most similar terms for medical words (including problems, treatments, and tests) and non-medical words from two pre-trained embedding models as prior knowledge to improve the training process. We applied PK-word2vec on patient portal messages in the Vanderbilt University Medical Center electric health record system sent by patients diagnosed with breast cancer from December 2004 to November 2017. We evaluated the model through a set of 1000 tasks, each of which compared the relevance of a given word to a group of the five most similar words generated by PK-word2vec and a group of the five most similar words generated by the standard word2vec model. We recruited 200 Amazon Mechanical Turk (AMT) workers and 7 medical students to perform the tasks. Results The dataset was composed of 1,389 patient records and included 137,554 messages with 10,683 unique words. Prior knowledge was available for 7,981 non-medical and 1,116 medical words. In over 90% of the tasks, both reviewers indicated PK-word2vec generated more similar words than standard word2vec (p=0.01).The difference in the evaluation by AMT workers versus medical students was negligible for all comparisons of tasks’ choices between the two groups of reviewers (p =0.774 under a paired t-test). Conclusions. PK-word2vec can effectively learn word representations from a small message corpus, marking a significant advancement in processing patient portal messages.

show abstract

Learning Hormonal Therapy Medication Adherence from an Online Breast Cancer Forum

Cited by 6 publications

References 58 publications

Electronic Medical Record–Based Electronic Messaging Among Patients with Breast Cancer: A Systematic Review

Electronic Medical Record–Based Electronic Messaging Among Patients with Breast Cancer: A Systematic Review

Cancer Informatics in 2017: A New Beginning and a Bright Future

Optimizing Word Embeddings for Patient Portal Message Datasets with a Small Number of Samples

Contact Info

Product

Resources

About