Social Media Insights Into Disease Burden in Patients and Caregivers of Myelodysplastic Syndrome: Subcohort Analysis of High-Risk Patients
Bibliographic record
Abstract
Background: Social media platforms offer valuable insights into patients' experience, revealing organic conversations that reflect their immediate concerns and needs. Through active listening to lived experiences, we can identify unmet needs and discover the real-world challenges that patients and caregivers face. Objective: The aim of our study is to develop a reusable framework to collect and analyze evolving social media data, capturing insights into the experiences of individuals with myelodysplastic syndromes (MDS) and higher-risk MDS and their caregivers. The findings can inform the development of appropriate patient support interventions. Methods: We conducted a structured Google search of English-language websites relevant to MDS from January 1, 2008, to December 31, 2022, using validated URLs and keywords. Data were sourced from MDS-specific platforms to ensure clinical relevance. Contextual embeddings (rather than simple keyword matching) were applied to detect semantically meaningful mentions of "MDS." Scraping algorithms collected, cleaned, and standardized the data. Posts were classified as originating from patients or caregivers using decision-tree tagging based on contextual summaries. Users were categorized as HR-MDS based on explicit mentions of "high-risk" or by referencing criteria aligned with National Comprehensive Cancer Network guidelines (eg, blast count, transplant, chemotherapy use). Each post was analyzed for major themes and sentiment using a supervised machine learning classifier, while latent topics were identified through a semisupervised model. Results: We analyzed ~5.5 million words from 42,000 posts across 5500 threads by ~4000 users from the United States, United Kingdom, and Canada. Of the 1249 HR-MDS users identified, 587 (47%) were patients and 662 (53%) were caregivers. Dominant sentiments among HR-MDS users included concern (n=974, 78%), anxiety (n=749, 60%), frustration (n=724, 58%), fear (n=724, 58%), and confusion (n=612, 49%). Concern was the top sentiment among caregivers (n=390, 59%), while anxiety led among patients (n=323, 55%). Key topics included blood counts (n=674, 54%), disease burden (n=537, 43%), quality of life (n=450, 36%), treatment options (n=387, 31%), and disease progression (n=387, 31%). Anxiety was frequently tied to health (n=600, 48%), treatment (n=325, 26%), and the diagnostic process (n=250, 20%). Fear stemmed from complications (n=237, 19%) and progression (n=240, 19%). Confusion about diagnosis and disease understanding was reported by 300 (24%). Information-seeking behaviors revealed user interest in treatment interventions (n=238, 19%) and ongoing research (n=212, 17%). Conclusions: The application of sophisticated natural language processing techniques demonstrates promise in effectively identifying the emerging complex themes and sentiments experienced by HR-MDS users, thereby highlighting the unmet needs, barriers, and facilitators associated with the disease.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".