An AI-driven mHealth solution to support clinical management of long COVID patients: prospective multicenter observational study 2022 Fuster-Casanovas

ABSTRACT

Background:

COVID-19 pandemic has evidenced the weaknesses of most health systems around the world, collapsing them, and depleting their available healthcare resources. Fortunately, the development and enforcement of specific public health policies such as vaccination, mask wearing and social distancing, among others, has made possible to reduce the prevalence and complications associated with COVID-19 in the acute phase. However, the aftermath of the global pandemic leads us to find an efficient approach to manage patients with long COVID. This is a great opportunity to leverage on innovative digital health solutions to provide exhausted healthcare systems with the most cost-effective and efficient tools available to support the clinical management of this population. In this context, the SENSING-AI project is committed to deliver an AI-driven mHealth solution that supports not only a better self-management of long COVID patients but also the healthcare staff in charge of the management and follow-up of this population.

Objective:

To build a knowledge base around the long COVID clinical pathway that enables the development of an AI-driven mHealth solution based on behavior change and mental wellbeing techniques to improve patients’ self-management while providing useful and timely clinical decision support services to healthcare professionals based on risk stratification models and early detection of exacerbations.

Methods:

Publicly available health and lifestyle data registries will be consulted and complemented with a retrospective cohort of anonymized data collected from clinical information of patients diagnosed with long COVID. Furthermore, a prospective patient-generated dataset will be captured using wearable devices and validated patient-reported outcomes questionnaires to complement the retrospective cohort. Finally, the FAIR (Findability, Accessibility, Interoperability, and Reuse) Guiding Principles for scientific data management and stewardship will be applied to the resulting dataset to encourage the continuous process of discovery, evaluation and reuse of information for the research community at large.

Results:

The SENSING-AI cohort is expected to be completed in early 2022. It is expected that sufficient data will be obtained to generate artificial intelligence models based on behavior change and mental wellbeing techniques to improve patients’ self-management while providing useful and timely clinical decision support services to healthcare professionals based on risk stratification models and early detection of exacerbations.

Conclusions:

SENSING-AI focuses on maximizing the usefulness of long COVID patients’ generated data. We must foresee a scenario for the immediate future in which we not only talk about COVID-19 in the acute phase, but we must also provide healthcare professionals with innovative solutions to support them in a cost-effective and efficient management of long COVID cases. Clinical Trial: Registered at clinicaltrials.gov. The NCT identifier (NCT05204615) for the prospective study.

Open access, https://preprints.jmir.org/preprint/37704/accepted