Investigating mental and physical disorders associated with COVID-19 in online health forums

Abstract

Objectives: Online health forums provide rich and untapped real-time data on population health. Through novel data extraction and natural language processing (NLP) techniques, we characterise the evolution of mental and physical health concerns relating to the COVID-19 pandemic among online health forum users. Setting and design: We obtained data from 739,434 posts by 53,134 unique users of three leading online health forums: HealthBoards, Inspire and HealthUnlocked, from the period 1st January 2020 to 31st May 2020. Using NLP, we analysed the content of posts related to COVID-19. Primary outcome measures: (i) Proportion of forum posts containing COVID-19 keywords (ii) Proportion of forum users making their very first post about COVID-19 (iii) Number of COVID-19 related posts containing content related to physical and mental health comorbidities Results: Posts discussing COVID-19 and related comorbid disorders spiked in early- to mid-March around the time of global implementation of lockdowns prompting a large number of users to post on online health forums for the first time. The pandemic and corresponding public response has had a significant impact on posters' queries regarding mental health. Conclusions: We demonstrate it is feasible to characterise the content of online health forum user posts regarding COVID-19 and measure changes over time. Social media data sources such as online health forums can be harnessed to strengthen population-level mental health surveillance.

A survey on clinical natural language processing in the United Kingdom from 2007 to 2022

“…The sums of NHS involved and industry involved project budgets are plotted alongside the budget of all projects across five 3-year periods. review 57,114,117,119,120 , drug-related 58,100,116,118 , randomised clinical trials [127][128][129] and generic classifications (such as classifying or clustering documents) 51,54,60,75,79,80,105,106,112,135,139 .…”

“…Oncology 33,34,48,49,55,75,117 and cardiovascular diseases 62,65,66,83 were the next two most frequently studied areas following treatments. Other disease areas included infectious 42,43,82,96,133,135 , respiratory 56,82,96,133,135 and autoimmune 138 diseases. In particular, there were four studies on COVID-19 82,96,133,135 .…”

“…Other disease areas included infectious 42,43,82,96,133,135 , respiratory 56,82,96,133,135 and autoimmune 138 diseases. In particular, there were four studies on COVID-19 82,96,133,135 . The rest were studies that belong to the 'general applicability' category, meaning they were tools or models not designed for specific health categories or diseases.…”

“…This is to use NLP for classifying a disease occurrence or extracting information about a disease with no focus on the overall clinical application. Studies in this category include [34][35][36][37][38][39][40][45][46][47][48][49]56,[58][59][60][61][62][65][66][67][68][69][70][71][72][73][76][77][78][79][80]100,103,112,[115][116][117][118]121,122,124,[128][129][130]134,135,139 .…”

“…Rule-based describes 18.9% of the studies using manuallycreated rules for classifications or extractions 37,38,44,53,74,86,94,96,98,99,[101][102][103]105,107,111,115,123,134,135 .…”