Impact of Off-Time on Quality of Life in Parkinson’s Patients and Their Caregivers: Insights from Social Media

Abstract

Introduction. In Parkinson’s disease (PD), the quality of life of both patients and caregivers is affected. While key issues relating to quality of life may not emerge in conversations with healthcare professionals (HCPs), unguarded social media conversations can provide insight into how people with Parkinson’s disease (PwPD) and their caregivers are affected. We conducted a qualitative and quantitative netnographic study of PD conversations posted on social media sites over a 12-month period. Objective. To identify key themes and issues for PwPD. Methods. Using predefined and piloted search terms, we identified 392,962 social media posts (between March 31, 2020, and March 31, 2021, for the UK and France, and between September 30, 2019, and March 31, 2021, for Italy, Spain, and Germany). A random sample of these posts was then analyzed using natural language processing (NLP), and quantitative, qualitative,in-depth contextual analysis was also performed. Results. Key themes that emerged in the PD conversation related to the changing experience of symptoms over time are the physical, emotional, and cognitive impact of symptoms, the management and treatment of PD, disease awareness among the general public, and the caregiver burden. The emotional impact of motor symptoms on PwPD is significant, particularly when symptoms increase and PwPD lose their independence, which may exacerbate existing anxiety and depression. Nonmotor symptoms can also compound the difficulties with managing the physical impact of motor symptoms. The burden of nonmotor symptoms is felt by both PwPD and their caregivers, with the impact of nonmotor symptoms on cognitive processes particularly frustrating for caregivers. The experience of off-time was also featured in the online conversation. Some PwPD believe there is a lack of adequate management from healthcare professionals, who may not appreciate their concerns or take sufficient time to discuss their needs. Conclusion. This study identified key themes that PwPD and their caregivers discuss online. These findings help signpost issues of importance to PwPD and areas in which their care may be improved.

In Their Own Words: Fears Expressed by People with Parkinson’s Disease in an Online Symptom Database

“…Of note, the framework methodology used in this analysis differs from the machine-learning approach employed in other analyses of PD-PROP, demonstrating the value of triangulating qualitative and quantitative methods in understanding complex conditions like PD. Moreover, the fears identified in this sample can be validated against the wider PD-PROP dataset or other large online datasets such as internet forums or social media [20][21][22].…”

Year 2022 in Medical Natural Language Processing: Availability of Language Models as a Step in the Democratization of NLP in the Biomedical Area

“…Nevertheless, the trends observed within this set of keywords are also reflected in the analysis provided in the following sections. [23], construction of cohorts of similar patients [24], processing of electronic medical records [25], understanding of patient's answers in a French medical chatbot [26]; • German: evaluation of Transformers on clinical notes [27]; • Greek: improving the performance of localized healthcare virtual assistants [28]; • Hindi: classification of COVID-19 texts [29], chatbot for information sexual and reproductive health for young people [30]; • Italian: analysis of social media for quality of life in Parkinson's patients [31], sentiment analysis of opinion on COVID-19 vaccines [32,33], estimation of the incidence of infectious disease cases [34]; • Japanese: understanding psychiatric illness [35], detection of adverse events from narrative clinical documents [36]; • Korean: BERT model for processing med-ical documents [37], sentiment analysis of tweets about COVID-19 vaccines [38];…”

“…We can also notice new and rare languages like Bengali, Malayalam, Hindi, Greek, or Serbian. Another interesting fact is that some publications address multilingual data or data in several languages: ICD-10 coding in English, Spanish and Swedish [44], analysis of social media for quality of life in Parkinson's patients and their caregivers in English, French, Italian, Spanish, and German [31], term normalization using the UMLS [48].…”

“…We can even tell that the availability of such models leads to the democratization of this NLP approach. Indeed, without the help of NLP researchers, biologists, radiologists, pharmacists and other clinicians can now use these models within the clinical context and we can find several such experiments, such as: analysis of tweets for user opinions and side effects on COVID-19 vaccines [66,33], fact-checking of posts on COVID-19 vaccines [67], identification of social determinants of health in EHRs [68], analysis of literature for drug-induced liver injury [69], labeling of diagnosis in cardiovascular Magnetic resonance imaging (MRI) [70], analysis of social media on the quality of life in Parkinson's patients [31], extraction of biomedical relations from the scientific literature [71].…”

“…• when other sources of information are not freely available, such as in languages other than English [7,9,19,20,22,38,43,47]; • when researchers investigate questions related to patients and population, while these questions are not discussed with medical doctors or require large population samples. We can mention for instance sentiment analysis on medication and vaccines [7,20,33,38,43,47], and adverse drug effects [76,77]; • when mental health of patients is concerned in cases like depression [9, 4, 78], eating disorders [79], suicide detection and prevention [19,80], quality of life of patients [31,81], and drug misuse [82][83][84].…”