Comorbidities and emotions - unpacking the sentiments of pediatric patients with multiple long-term conditions through social media feedback: A large language model-driven study.

OBJECTIVES

The emotional and psychological challenges faced by children with multiple long-term conditions (MLTCs) remain underexplored. This study aimed to analyze sentiments and emotions expressed by this vulnerable population and their caregivers on social media, assess the effects of comorbidities and the COVID-19 pandemic on emotional well-being.

METHODS

Narratives from the Care Opinion platform (2008-2023) were analyzed by a model called CoEmoBERT, developed using the large language model, distilroberta-base transformer model. The CoEmoBERT-based sentiment analysis categorized emotions into "Positive", "Negative", and "Neutral," with further refinements into specific emotions such as "Sad," "Fear", "Satisfied" etc. through pretraining and transferring process. Comorbidity associations with emotions were analyzed. We further examined the impact of the COVID-19 pandemic on patient sentiments and investigated temporal trends in emotional expressions.

RESULTS

Of 389 narratives, 93.8 % reflected negative sentiments, with "Sad" (60.9 %) and "Fear" (15.4 %) being the most prevalent. Negative emotions were linked to severe comorbidities like asthma, cancer, and chronic pain, highlighting the emotional burden of managing MLTCs. Positive sentiments (5.9 %) were associated with effective communication and exceptional healthcare experiences. The analysis revealed strong associations between certain comorbidity combinations and specific emotional responses, with mental health conditions showing the most diverse range of comorbidities and emotional impacts. The COVID-19 pandemic exacerbated negative sentiments, particularly sadness and disgust.

CONCLUSION

This study underscores the significant emotional burden on children with MLTCs, emphasizing the need for integrated care approaches to both physical and emotional well-being. These findings can guide the development of patient-centered care for this population.