Analysis of Population Differences in Digital Conversations About Cancer Clinical Trials: Advanced Data Mining and Extraction Study
Bibliographic record
Abstract
BACKGROUND: Racial and ethnic diversity in clinical trials for cancer treatment is essential for the development of treatments that are effective for all patients and for identifying potential differences in toxicity between different demographics. Mining of social media discussions about clinical trials has been used previously to identify patient barriers to enrollment in clinical trials; however, a comprehensive breakdown of sentiments and barriers by various racial and ethnic groups is lacking. OBJECTIVE: The aim of this study is to use an innovative methodology to analyze web-based conversations about cancer clinical trials and to identify and compare conversation topics, barriers, and sentiments between different racial and ethnic populations. METHODS: We analyzed 372,283 web-based conversations about cancer clinical trials, of which 179,339 (48.17%) of the discussions had identifiable race information about the individual posting the conversations. Using sophisticated machine learning software and analyses, we were able to identify key sentiments and feelings, topics of interest, and barriers to clinical trials across racial groups. The stage of treatment could also be identified in many of the discussions, allowing for a unique insight into how the sentiments and challenges of patients change throughout the treatment process for each racial group. RESULTS: We observed that only 4.01% (372,283/9,284,284) of cancer-related discussions referenced clinical trials. Within these discussions, topics of interest and identified clinical trial barriers discussed by all racial and ethnic groups throughout the treatment process included health care professional interactions, cost of care, fear, anxiety and lack of awareness, risks, treatment experiences, and the clinical trial enrollment process. Health care professional interactions, cost of care, and enrollment processes were notably discussed more frequently in minority populations. Other minor variations in the frequency of discussion topics between ethnic and racial groups throughout the treatment process were identified. CONCLUSIONS: This study demonstrates the power of digital search technology in health care research. The results are also valuable for identifying the ideal content and timing for the delivery of clinical trial information and resources for different racial and ethnic groups.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.023 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".