Assessing data gathering of chatbot based symptom checkers - a clinical vignettes study.

BACKGROUND: The burden on healthcare systems is mounting continuously owing to population growth and aging, overuse of medical services, and the recent COVID-19 pandemic. This overload is also causing reduced healthcare quality and outcomes. One solution gaining momentum is the integration of intelligent self-assessment tools, known as symptom-checkers, into healthcare-providers' systems. To the best of our knowledge, no study so far has investigated the data-gathering capabilities of these tools, which represent a crucial resource for simulating doctors' skills in medical-interviews. OBJECTIVES: The goal of this study was to evaluate the data-gathering function of currently available chatbot symptom-checkers. METHODS: We evaluated 8 symptom-checkers using 28 clinical vignettes from the repository of MSD-Manual case studies. The mean number of predefined pertinent findings for each case was 31.8 ± 6.8. The vignettes were entered into the platforms by 3 medical students who simulated the role of the patient. For each conversation, we obtained the number of pertinent findings retrieved and the number of questions asked. We then calculated the recall-rates (pertinent-findings retrieved out of all predefined pertinent-findings), and efficiency-rates (pertinent-findings retrieved out of the number of questions asked) of data-gathering, and compared them between the platforms. RESULTS: The overall recall rate for all symptom-checkers was 0.32(2,280/7,112;95 %CI 0.31-0.33) for all pertinent findings, 0.37(1,110/2,992;95 %CI 0.35-0.39) for present findings, and 0.28(1140/4120;95 %CI 0.26-0.29) for absent findings. Among the symptom-checkers, Kahun platform had the highest recall rate with 0.51(450/889;95 %CI 0.47-0.54). Out of 4,877 questions asked overall, 2,280 findings were gathered, yielding an efficiency rate of 0.46(95 %CI 0.45-0.48) across all platforms. Kahun was the most efficient tool 0.74 (95 %CI 0.70-0.77) without a statistically significant difference from Your.MD 0.69(95 %CI 0.65-0.73). CONCLUSION: The data-gathering performance of currently available symptom checkers is questionable. From among the tools available, Kahun demonstrated the best overall performance.

Mortality in Ankylosing Spondylitis According to Treatment: A Nationwide Retrospective Cohort Study of 5,900 Patients From Israel.

OBJECTIVE: In this large population-based study we aimed: 1) to assess mortality in patients with ankylosing spondylitis (AS) compared to the general population, considering demographics, comorbidities, and treatment, and 2) to assess factors associated with mortality within patients with AS. METHODS: This study was designed as a retrospective cohort study using the electronic database of the largest health maintenance organization in Israel. All patients with AS diagnosed between 2002 and 2018 were included. Controls were matched by age, sex, clinic, and enrollment time. Follow-up continued until death or the end of the study. RESULTS: The study comprised 5,930 AS patients and 29,018 matched controls who were followed up for a median period of 7.5 years. There were 667 deaths within the AS cohort and 2,919 deaths within controls; the mean age at death was 76.9 years and 77.1 years, respectively (P = 0.74). A total of 3,249 AS patients (54.8%) were treated only with nonsteroidal antiinflammatory drugs, 1,760 (29.7%) were treated with tumor necrosis factor inhibitors (TNFi), and 1,687 (28.4%) with disease-modifying antirheumatic drugs (DMARDs). Mortality rates were increased among AS patients compared to controls, with an age- and sex-adjusted hazard ratio (HR) of 1.19 (95% confidence interval [95% CI] 1.10-1.30). The association was significant for men (HR 1.15 [95% CI 1.04-1.27]) and women (HR 1.32 [95% CI 1.13-1.54]), and after adjusting for background comorbidities (HR 1.14 [95% CI 1.05-1.24]). AS patients treated with TNFi or with a combination of TNFi and DMARDs did not have significant difference in mortality rates compared to controls (HR 0.67 [95% CI 0.38-1.18] and HR 0.93 [95% CI 0.69-1.25], respectively). Age, male sex, mean C-reactive protein (CRP) levels and general comorbidities were predictors of mortality within the AS cohort. CONCLUSION: AS patients had an increased mortality risk compared to the general population after adjusting for age, sex, and baseline comorbidities. AS patients treated with TNFi did not demonstrate excess mortality compared to matched controls. Within the AS cohort, age, male sex, background comorbidities, and higher CRP levels were identified as risk factors for mortality.

Low Vitamin D Levels Predict Mortality in Ankylosing Spondylitis Patients: A Nationwide Population-Based Cohort Study.

In this study, we aimed to examine the effect of vitamin D deficiency on all-cause mortality in ankylosing spondylitis (AS) patients and in the general population. This is a retrospective-cohort study based on the electronic database of the largest health-maintenance organization in Israel. AS patients who were first diagnosed between 2002-2007 were included. Controls were matched by age, gender and enrollment-time. Follow-up continued until death or end of study follow-up on 1 July 2019. Laboratory measures of serum 25-hydroxyvitamin-D levels during the entire follow-up period were obtained. A total of 919 AS patients and 4519 controls with a mean time of follow-up of 14.3 years were included. The mean age at the time of enrollment was 52 years, and 22% of them were females. AS was associated with a higher proportion of vitamin D deficiency (odds ratio 1.27 [95% confidence-interval (CI) 1.03-1.58]). In AS patients, insufficient levels of vitamin D (< 30 ng/mL) were significantly associated with increased incidence of all-cause mortality (hazard ratio (HR) 1.59 [95% CI 1.02-2.50]). This association was more prominent with the decrease in vitamin D levels (< 20 ng/mL, HR 1.63 [95% CI 1.03-2.60]; <10 ng/mL, HR 1.79 [95% CI 1.01-3.20]) and among male patients (< 30 ng/mL, HR 2.11 [95% CI 1.20-3.72]; <20 ng/mL, HR 2.12 [95% CI 1.19-3.80]; <10 ng/mL, HR 2.23 [95% CI 1.12-4.43]). However, inadequate levels of vitamin D among controls were not associated with an increased all-cause mortality. Our study has shown that vitamin D deficiency is more common in AS patients than controls and is linked to an increased risk for all-cause mortality. These results emphasize the need for randomized-controlled trials to evaluate the benefits of vitamin D supplementation as a secondary prevention of mortality in patients with chronic inflammatory rheumatic disease.