RESUMO
Background and aims: SCORE2/SCORE2-OP cardiovascular risk (CVR) charts and online calculators do not apply to patients with comorbidities, target organ damage, or atherosclerotic cardiovascular disease, for whom the assessment relies on the conventional consultation of the 2021 ESC guidelines (qualitative approach). To simplify the CVR evaluation, we developed an integrated multi-language and free-to-use web application. This study assessed the agreement between the conventional method versus our web app. Methods: A cross-sectional study was carried out on 1306 consecutive patients aged 40+ years referred to our center for the diagnosis and management of hypertension and dyslipidemia. Two double-blind operators performed the CVR assessment and classified each patient into low-moderate-, high-, and very-high-risk categories by using the conventional method (SCORE2/SCORE2-OP charts and consultation of the 2021 ESC guidelines) and the web app. The Kappa statistics were used to compare the two methods. Results: The mean age was 60.3 ± 11.9 years, with male prevalence (51.4%). Patients in primary prevention were 77.0%. According to the SCORE2/SCORE2-OP charts and 2021 ESC guideline consultation, the CVR was low-moderate in 18.6% (n° 243), high in 36.8% (n° 480), and very high in 44.6% (n° 583). According to the web app, individual CVR was low-moderate in 19.5% (n° 255), high in 35.4% (n° 462), and very high in 45.1% (n° 589). The two methods strongly agreed (Kappa = 0.960, p < 0.001), with a 97.5% concordance. Conclusions: our application has excellent reliability in a broad "real life" population and may help non-expert users and busy clinicians to assess individual CVR appropriately, representing a free-to-use, simple, time-sparing and widely available alternative to the conventional CVR evaluation using SCORE2/SCORE2-OP and 2021 ESC guideline charts.
RESUMO
BACKGROUND AND OBJECTIVES: Timely identification of dysarthria progression in patients with bulbar-onset amyotrophic lateral sclerosis (ALS) is relevant to have a comprehensive assessment of the disease evolution. To this goal literature recognized the utmost importance of the assessment of the number of syllables uttered by a subject during the oral diadochokinesis (DDK) test. METHODS: To support clinicians, this work proposes a remote deep learning-based system, which consists (i) of a web application to acquire audio tracks of bulbar-onset ALS patients and healthy control subjects while performing the oral DDK test (i.e., repeating the /pa/, /pa-ta-ka/ and /oo-ee/ syllables) and (ii) a DDK-AID network designed to process the acquired audio signals which have different duration and to output the number of per-task syllables repeated by the subject. RESULTS: The DDK-AID network overcomes the comparative method achieving a mean Accuracy of 90.23 in counting syllables repeated by the eleven bulbar-onset ALS-patients while performing the oral DDK test. CONCLUSIONS: The proposed remote monitoring system, in the light of the achieved performance, represents an important step towards the implementation of self-service telemedicine systems which may ensure customised care plans.
