Developing AIDI (the Aidar Decompensation Index) -- a Multisensor-Based Machine Learning Technology for Real-Time Automated Detection of Post-Acute Sequelae of COVID-19: Protocol for an Observational Study (Preprint)

Abstract

Emerging as the new epidemic, post-acute sequelae of COVID-19, a condition characterized by the persistence of COVID-19 symptoms beyond 3 months, is anticipated to substantially alter the lives of millions of people globally. Patients with severe episode of COVID-19 have been significantly more likely to be hospitalized in the following months. Pathophysiological mechanisms for delayed complications are still poorly understood, with a dissociation seen between ongoing symptoms and objective measures of cardiopulmonary health. COVID-19 is anticipated to alter the long-term trajectory of many chronic cardiovascular and pulmonary diseases which are abundant in those at risk of severe disease.

The overall objective of the study is to use a single, integrated device, MouthLab, which measures 10 vital health parameters in 60 seconds, and a cloud-based proprietary analytics engine, to develop and validate the Aidar Decompensation Index (AIDI) to predict decompensation in health among patients who previously had severe COVID-19.

A total of 200 participants who are patients in the United States Department of Veterans Affairs (VA) healthcare system, and who had ‘severe’ COVID-19 infection during the acute phase, defined as requiring hospitalization, within 3-6 months before enrollment. Participants shall be 18 years and older. All participants will be instructed to use the MouthLab device to capture daily physiological data and complete monthly symptom surveys. Structured data collection tables will be developed to extract the clinical characteristics of those who experience decompensation events (DEs). The performance of AIDI will depend on the magnitude of difference in physiological signals between those experiencing decompensation events (DEs) and those who do not, and the time until a DE (i.e., the closer to the event the easier the prediction). Information about demographics, symptoms (MRC dyspnea scale, Post-COVID Functional Status), comorbidities, and other clinical characteristics will be tagged and added to the biomarker data. The resultant predicted probability of decompensation will be translated into the AIDI index, where there will be a linear relationship between the risk score and the AIDI index. To improve prediction accuracy, data may be stratified based on biological sex, race, ethnicity, or underlying clinical characteristics into sub-groups to determine if there are differences in performance and detection lead times among the groups. Through the application of appropriate algorithmic techniques, the study expects the model to have a sensitivity of >80% with a positive predicted value of >70%.

Recruitment began in January 2023, and the first patient was enrolled in January 2023. Publication of the complete results and data from the study is expected in 2024.

The focus on identifying predictor variables using a combination of biosensor-derived physiological features, should enable the capture of heterogeneous characteristics of post-acute sequelae of COVID-19-related complications across diverse populations.

ClinicalTrials.gov NCT05220306