Loading
Nonmelanoma Skin Cancer Studies / Retinal Diseases and Treatments · Journal article
Journal of Medical Internet Research · August 11, 2026
Early or partial results. Treat as a signal, not a conclusion.
This is an observational infodemiology study that uses machine learning on social media posts to characterize treatment hesitancy regarding enucleation in retinoblastoma and correlates regional sentiment with published clinical outcomes. The analysis identifies associations between negative sentiment toward enucleation and worse overall survival, and between clinical/academic Twitter participation and lower hesitancy, but cannot establish causality and relies on ecological-level outcome data from a separate meta-analysis rather than direct measurement in the study population.
Observational infodemiology study with machine learning text analysis and ecological-level outcome linkage. Twitter users posting about retinoblastoma (n=797,870 users; 2,382,511 posts). Geographic concentration in North America and Western Europe. Clinical outcome data from published literature meta-analysis.. Global social media analysis; outcomes meta-analysis unspecified by geography but regional subgroup analysis reported for Asia and Africa.
Exponential growth in posts related to treatment barriers and enucleation hesitancy after 2016 (β log-linear = 0.957, P = .002) Stronger negative sentiment toward enucleation was associated with worse overall survival outcomes (β = −0.726, 95% CI −1.224 to −0.228) Association between lower overall survival and enucleation hesitancy in Asia (β = −1.518, 95% CI −2.602 to −0.434) and Africa (β = −0.812, 95% CI −1.412 to −0.021)
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
This study suggests that monitoring social media sentiment and barriers may help identify populations at risk of treatment delays or refusal, and that increased clinical and academic engagement on social platforms may reduce hesitancy. However, because the design is observational with ecological-level outcome linkage, clinicians should not interpret the sentiment-survival association as causal; the findings warrant further investigation through direct patient surveys and intervention studies before informing practice changes.
An observational infodemiology study using machine learning on social media data with cross-sectional associations to clinical outcomes; generates hypotheses about treatment hesitancy but lacks causal inference, experimental design, or direct patient enrollment.
As stated by the source record.
Quoted from the source exactly as published.
This study suggests that monitoring social media sentiment and barriers may help identify populations at risk of treatment delays or refusal, and that increased clinical and academic engagement on social platforms may reduce hesitancy. However, because the design is observational with ecological-level outcome linkage, clinicians should not interpret the sentiment-survival association as causal; the findings warrant further investigation through direct patient surveys and intervention studies before informing practice changes.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Abstract Background The use of social media in cancer research, patient support, and information sharing has been well documented. Objective Using retinoblastoma as a model, we use the information provided from Twitter (subsequently rebranded X) to understand patients’ treatment-seeking behavior and barriers, as well as investigate its application in research and epidemiology for rare diseases. Methods Posts on retinoblastoma were extracted from Twitter. We trained BERT (Bidirectional Encoder Representations from Transformers) models to identify relevance and conducted sentiment analysis. The hierarchical Dirichlet process was trained to identify topics with BERTopic used as a sensitivity analysis. We enriched user profiles with OpenStreetMap-based geotagging and CoreNLP-based occupation tagging. Retinoblastoma outcomes were obtained from a systematic review and meta-analysis, which covered articles published between January 1, 1981, and October 8, 2021. Results The dataset covered 2,382,511 posts from 797,870 Twitter users. Most of the information dissemination and discussion originated from North America and Western Europe. A lack of disease understanding and the need for more support and counseling remained the most significant barriers to receiving treatment worldwide, as reflected by both the intensity and number of posts. The number of new posts per year related to treatment barriers and enucleation hesitancy showed exponential growth after 2016 (β log-linear =0.957, P =.002). For the perceived barriers to treatment, sentiment was the strongest over time for worries over treatment failure (β linear =−0.003, P =.79, estimate 2022 =0.679). Posts with higher negative sentiment intensity related to enucleation were concentrated in Central and Southern America, Asia, and Africa. Stronger negative sentiment toward enucleation ( β =−0.726, 95% CI −1.224 to −0.228) was associated with worse overall survival outcomes. The association between lower overall survival rates and enucleation hesitancy was observed in Asia ( β =−1.518, 95% CI −2.602 to −0.434) and Africa ( β =−0.812, 95% CI −1.412 to −0.021) in the subgroup analysis. The active participation of clinical staff ( β =−0.105, 95% CI −0.186 to −0.024; P =.01) and academia ( β =−0.116, 95% CI −0.208 to −0.024; P =.01) on retinoblastoma topics on Twitter correlated with lower enucleation hesitancy. Conclusions Computational social media analysis can generate actionable insights for public health interventions for retinoblastoma. Negative sentiment toward enucleation is associated with poorer survival. The active participation of clinical staff and academia on Twitter is correlated with lower enucleation hesitancy. However, they remain underrepresented in social media discussions, suggesting a significant opportunity for greater engagement from stakeholders and targeted information dissemination to improve acceptance and outcomes in vulnerable zones.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.