Flare-IBD: development and validation of a questionnaire based on patients' messages on an internet forum for early detection of flare in inflammatory bowel disease: study protocol

Extracting big data from the internet to support the development of a new patient-reported outcome measure for breast implant illness: a proof of concept study

PURPOSE

Individuals with health conditions often use online patient forums to share their experiences. These patient data are freely available and have rarely been used in patient-reported outcomes (PRO) research. Web scraping, the automated identification and coding of webpage data, can be employed to collect patient experiences for PRO research. The objective of this study was to assess the feasibility of using web scraping to support the development of a new PRO measure for breast implant illness (BII).

METHODS

Nine publicly available BII-specific web forums were chosen post-consultation with two prominent BII advocacy leaders. The Python Selenium and Pandas packages were used to automate extraction of de-identified text from the individual posts/comments into a spreadsheet. Data were coded using a line-by-line approach and constant comparison was used to create top-level domains and sub-domains.

RESULTS

6362 unique codes were identified and organized into four top-level domains of information needs, symptom experiences, life impact of BII, and care experiences. Information needs of women included seeking/sharing information pre-breast implant surgery, post-breast implant surgery, while contemplating explant surgery, and post-explant surgery. Symptoms commonly described by women included fatigue, brain fog, and musculoskeletal symptoms. Many comments described BII's impact on daily activities and psychosocial wellbeing. Lastly, some comments described negative care experiences and experiences related to advocating for themselves to providers.

CONCLUSION

This proof-of-concept study demonstrated the feasibility of employing web scraping as a cost-effective, efficient method to understand the experiences of women with BII. These data will be used to inform the development of a BII-specific PROM.

Patient and Public Involvement in Research: Lessons for Inflammatory Bowel Disease

Participatory research, also referred to as patient and public involvement, is an approach that involves collaborating with patients affected by the focus of the research, on the design, development and delivery of research to improve outcomes. There are two broad justifications for this: first, that it enhances the quality and relevance of research, and second, that it satisfies the ethical argument for patient inclusion in decisions about them. This synergistic and collaborative effort, which bridges the divide between researchers and participants with the lived condition, is now a mainstream activity and widely accepted as best practice. Although there has been a substantial increase in the literature over the past two decades, little has been published on how participatory research has been used in inflammatory bowel disease [IBD] research and little guidance as to how researchers should go about this. With an increasing incidence and prevalence worldwide, combined with declining study enrolment in an era of perennial unmet need, there are a multitude of benefits of participatory research to IBD patients and investigators, including research output that is informed and relevant to the real world. A key example of participatory research in IBD is the I-CARE study, a large-scale, pan-European observational study assessing the safety of advanced therapies, which had significant patient involvement throughout the study. In this review, we provide a comprehensive overview of the benefits and challenges of participatory research and discuss opportunities of building strategic alliances between IBD patients, healthcare providers and academics to strengthen research outcomes.

Web-based and machine learning approaches for identification of patient-reported outcomes in inflammatory bowel disease

BACKGROUND

Messages from an Internet forum are raw material that emerges in a natural setting (i.e., non-induced by a research situation).

AIMS

The FLARE-IBD project aimed at using an innovative approach consisting of collecting messages posted by patients in an Internet forum and conducting a machine-learning study (data analysis/language processing) for developing a patient-reported outcome measuring flare in inflammatory bowel disease meeting international requirements.

METHODS

We used web-based and machine learning approaches, in the following steps. 1) Web-scraping to collect all available posts in an Internet forum (23 656 messages) and extracting metadata from the forum. 2) Twenty patients were randomly assigned 50 extracted messages; participants indicated whether the message corresponded or not to the flare phenomenon (labeling). If yes, participants were asked to identify excerpts from the text they considered significant flare markers (annotation). 3) The set of annotated messages underwent a vocabulary analysis.

RESULTS

The phenomenon of flare was circumscribed with the identification of 20 surrogate flare markers classified into five dimensions with their frequency within extracted labeled data: impact on life, symptoms, extra-intestinal manifestations, drugs and environmental factors. Web-based and machine-learning approaches met international recommendations to inform the content and structure for the development of patient-reported outcomes.

Point-of-Care Monitoring of Colitis Using Intestinal Alkaline Phosphatase in Inflammatory Bowel Disease

Intestinal Alkaline Phosphatase (IAP) was investigated as a potential biomarker to monitor colitis in a mouse model of Inflammatory Bowel Disease (IBD). We developed a Point-Of-Care (POC) assay to detect IAP with a glucose meter in 15 min. We synthesized a paracetamol-bearing compound specifically cleaved by IAP to release paracetamol, which can be detected with a personal glucometer. Interleukin 10 deficient (IL 10-/-) mouse model samples were used to compare the IAP level in mice with mild or severe colitis. The results showed that fecal IAP level was significantly lower in each mouse sample with severe colitis than with mild colitis. Mice treated with anti-Tumor Necrosis Factor-alpha (anti-TNF-α) to decrease inflammation exhibited a much higher level of IAP than those without treatment (IAP levels from anti-TNF-α treated vs nontreated = 2.80 U vs 0.11 U, P < 0.0001). Taken together, IAP can be considered as a potential biomarker to monitor colitis, and a rapid, user-friendly POC glucometer-based assay can be potentially used to monitor colitis levels and inflammation flareups in IBD.