Assessing the accuracy of a digital symptom checker tool for suggestion of reproductive health conditions: a clinical vignettes study (Preprint)

Autor: Kimberly Peven, Aidan Wickham, Octavia Wilks, Yusuf C. Kaplan, Andrei Marhol, Saddif Ahmed, Ryan Bamford, Carley Prentice, András Meczner, Matthew Fenech, Stephen Gilbert, Anna Klepchukova, Sonia Ponzo
Rok vydání: 2023
Popis: BACKGROUND Reproductive health conditions such as endometriosis, uterine fibroids and polycystic ovary syndrome affect a large proportion of women and people who menstruate worldwide. Prevalence estimates for these conditions range from 5-40% of women of reproductive age. Long diagnostic delays, up to 12 years, are common and contribute to health complications and increased healthcare costs. Symptom checker apps provide users with information and tools to better understand their symptoms and thus have the potential to reduce the time to diagnosis for reproductive health conditions. OBJECTIVE This study aims to evaluate the accuracy of three symptom checkers developed by Flo Health assessing symptoms of endometriosis, uterine fibroids and polycystic ovary syndrome (PCOS) against current medical guidelines. METHODS Independent general practitioners were recruited to create clinical case vignettes of simulated users with and without the conditions of interest. Vignettes were reviewed, modified and approved by separate general practitioners. A further independent panel of general practitioners reviewed the cases and designated a final classification. Vignettes were entered into the symptom checkers and the outcomes were compared with the final classification from the panel using accuracy metrics including percent agreement, sensitivity and specificity. RESULTS A total of 24 cases were created per condition. Overall, exact matches between the vignette classification and the symptom checker outcome was 83.3% for endometriosis and uterine fibroids, and 87.5% for PCOS. While sensitivity was high for all conditions (>81%) and very high (100%) for PCOS, specificity was >81% for endometriosis and uterine fibroids and 75% for PCOS. CONCLUSIONS The single condition symptom checkers have high levels of accuracy for endometriosis, uterine fibroids and PCOS. Given long delays in diagnosis for many reproductive health conditions, which lead to increased medical costs and potential health complications for individuals and healthcare providers, innovative health apps and symptom checkers hold the potential to improve care pathways.
Databáze: OpenAIRE