JMIR Publications

ABSTRACT

Background:

Early detection of changes in vital signs typically correlates with faster identification of changes in the patient’s health status and the escalation of care if necessary. Alterations in vital signs preceding clinical deterioration are well documented, and the early identification of preventable outcomes is crucial for timely intervention.

Objective:

In this study, vital parameters (heart rate, respiratory rate, oxygen saturation, and blood pressure) will be measured using the 'comestai' application to confirm the accuracy of photoplethysmography (PPG) methods compared to standard clinical practice devices, analyzing a large and diverse population. Additionally, the application will facilitate big data collection to enhance the algorithm's performance in measuring hemoglobin, glycated hemoglobin and total cholesterol.

Methods:

To achieve the objectives of this study, 3.000 subjects will be consecutively enrolled from June 2024 to December 2024. In all patients personal data collection and medical condition and treatment overview will be recorded. The "By Face" method for rPPG vital signs data collection involves recording subjects' faces using the front camera of mobile devices (iOS and Android) for approximately 1.5 minutes. Simultaneously, vital signs will be continuously collected for about 1.5 minutes using the reference devices alongside data collected via the comestai application; biochemical results will be also recorded.

Results:

The accuracy of the app measurements compared to the reference devices and standard tests will be assessed for all parameters. Confidence intervals will be calculated using the bootstrap method. The proposed approach's effectiveness was evaluated using various quality criteria, including the mean error (ME), standard deviation (STD), mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE). The correlation between measurements obtained using the app and those from reference devices and standard tests will be evaluated using the Pearson correlation coefficient. The agreement between the two sets of measurements (app vs reference devices/standard tests) will be represented using Bland-Altman plots. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and likelihood ratios were calculated to determine the ability of the new application to accurately measure vital signs.

Conclusions:

our study will enhance and support the accuracy data on vital sign detection through PPG, also introducing measurements of biochemical risk indicators. The evaluation of a large population will allow for continuous improvement in the performance and accuracy of artificial intelligence algorithms, reducing errors. Expanding research opportunities to evaluate mHealth solutions as effective and dependable screening tools is useful for preventive strategies. App solutions, such as comestai, may present new opportunities and challenges related to technology use in the healthcare sector, offering insights and guiding future research directions. Clinical Trial: The study protocol was registered in ClinicalTrials.gov (ID: NCT0642756).