Treatment for hidradenitis suppurativa is diverse, yet frequently unsatisfactory. The aims of this study were to create a reproducible artificial intelligence-based patient-reported outcome platform for evaluation of the clinical characteristics and comorbidities of patients with hidradenitis suppurativa, and to use this to grade treatment effectiveness. A retrospective patient- reported outcome study was conducted, based on online questionnaires completed by English-speaking patients registered to the hidradenitis suppurativa StuffThatWorks® online community. Data collected included patient characteristics, comorbidities and treatment satisfaction. These were recoded into scalable labels using a combination of machine learning algorithm, manual coding and validation. A model of treatment effectiveness was generated. The cohort included 1,050 patients of mean ± standard deviation age 34.3 ± 10.3 years. Greater severity of hidradenitis suppurativa was associated with younger age at onset (p < 0.001) and male sex (p < 0.001). The most frequent comorbidities were depression (30%), anxiety (26.4%), and polycystic ovary syndrome (16.6%). Hurley stage I patients rated topical agents, dietary changes, turmeric, and pain relief measures more effective than tetracyclines. For Hurley stage II, adalimumab was rated most effective. For Hurley stage III, adalimumab, other biologic agents, systemic steroids, and surgical treatment were rated more effective than tetracyclines. Patients with hidradenitis suppurativa often have comorbid psychiatric and endocrine diseases. This model of treatment effectiveness provides a direct comparison of standard and complementary options.

Background and AimsInternet and social media platforms have become an unprecedented source for sharing self‐experience, potentially allowing the collection and integration of health data with patient experience. StuffThatWorks (STW) is an online open platform that applies machine learning and the power of crowdsourcing, where patients with chronic medical conditions can self‐report and compare their individual outcomes using a structured online questionnaire. We aimed to conduct a cross‐sectional, international, crowdsourcing, artificial‐intelligence (AI) web‐based study of patients with Crohn's disease (CD) self‐reporting their outcomes.MethodsA proprietary STW Bayesian inference model was built to measure improvement in CD severity (on scale of 1–5) for each treatment and ranked treatments using effectiveness. The effectiveness of first‐line biological treatments was analyzed by multiple comparisons and by calculating odds ratios and 95% confidence intervals for each treatment pair.ResultsWe included 7593 self‐reported CD patients for the analysis. Most of the participants were female (75.8%) and from English‐speaking countries (95.7%). Overall, anti‐TNF drugs were the most reported tried treatment (52.8%). Infliximab (IFX) was ranked as the most effective treatment by the STW effectiveness model followed by bowel surgery (second), adalimumab (ADA, third), ustekinumab (UST, 4rd), and vedolizumab (VDZ, fifth). In paired comparison analyses, IFX was most effective, ADA had similar effectiveness compared to UST and all three were more effective than VDZ.ConclusionWe present the first online crowdsourcing AI platform‐based study of self‐reported treatment effectiveness in CD. Net‐based crowdsourcing patient‐reported outcome platforms can potentially help both clinicians and patients select the best treatment for their condition.

No abstract

Plantar Fasciitis (PF) is a disorder of connective tissue that supports the longitudinal arch of the foot. The fascia runs along the sole with insertion to the heads of the metatarsal bones and origin in the calcaneus. It is one of the most frequent diagnoses for patients in general and foot clinics, and one of the common causes for heel pain which may develop into chronic heel pain, change the way we walk and lead to foot, knee, hip or back problems. PF is the most common type of plantar fascia injury. The purpose of this study is to describe the natural history of PF, including the ethnicity, early and main symptoms, aggravating factors, comorbidities and treatments for PF, based on the patient-reported data from active PF community in an online crowdsourcing platform, StuffThatWorks. Analyses were made in order to discover characteristics which have a clinical importance. Totally 3835 patients were included in this retrospective observational study. The results show that crowdsourcing is a valid approach for data collection, as expected results with regard to clinical aspects such as age-of-onset, early and main symptoms were witnessed. Furthermore, the patient-reported data show three characteristics which have a very high clinical relevance: high level of physical activity, being overweight and age. In addition, leads for future studies were established.

No abstract