A real-time integrated framework to support clinical decision making for covid-19 patients

Abstract

Background: The COVID-19 pandemic affected healthcare systems worldwide. Predictive models developed by Artificial Intelligence (AI) and based on timely, centralized and standardized real world patient data could improve management of COVID-19 to achieve better clinical outcomes. The objectives of this manuscript are to describe the structure and technologies used to construct a COVID-19 Data Mart architecture and to present how a large hospital has tackled the challenge of supporting daily management of COVID-19 pandemic emergency, by creating a strong retrospective knowledge base, a real time environment and integrated information dashboard for daily practice and early identification of critical condition at patient level. This framework is also used as an informative, continuously enriched data lake, which is a base for several on-going predictive studies.

Methods: The information technology framework for clinical practice and research was described. It was developed using SAS Institute software analytics tool and SAS® Vyia® environment and Open-Source environment R ® and Python ® for fast prototyping and modeling. The included variables and the source extraction procedures were presented.

Results: The Data Mart covers a retrospective cohort of 5528 patients with SARS-CoV-2 infection. People who died were older, had more comorbidities, reported more frequently dyspnea at onset, had higher d-dimer, C-reactive protein and urea nitrogen. The dashboard was developed to support the management of COVID-19 patients at three levels: hospital, single ward and individual care level.

Interpretation: The COVID-19 Data Mart based on integration of a large collection of clinical data and an AI-based integrated framework has been developed, based on a set of automated procedures for data mining and retrieval, transformation and integration, and has been embedded in the clinical practice to help managing daily care. Benefits from the availability of a Data Mart include the opportunity to build predictive models with a machine learning approach to identify undescribed clinical phenotypes and to foster hospital networks. A real-time updated dashboard built from the Data Mart may represent a valid tool for a better knowledge of epidemiological and clinical features of COVID-19, especially when multiple waves are observed, as well as for epidemic and pandemic events of the same nature (e. g. with critical clinical conditions leading to severe pulmonary inflammation). Therefore, we believe the approach presented in this paper may find several applications in comparable situations even at region or state levels. Finally, models predicting the course of future waves or new pandemics could largely benefit from network of DataMarts.

Fig. 1

Generator infrastructure to create and automatically update the COVID-19 Data Marts from Operational Data Warehouses and Production Databases.

Fig. 2

simplified view of patient-centered COVID-19 Data Mart in place at Policlinico Gemelli.

Fig. 3

Conceptual view of Dashboard profiling for General Use, Hospital Management, Ward and Patient Care.

Fig. 4

A. Weekly retrospective overview of cohort, split by wards, compared with non-COVID-19 inpatients evolution. Fig. 4B Daily view of new hospitalized patients, total patients in charge, filtered view of outcomes.

Fig. 5

A. Cumulative clinical dashboard displaying incidence of comorbidities, average age for inpatients over time, symptoms and evolution of average days of symptoms onset. Fig. 5B Drill down for the historical cohort of COVID-19 patients with evolution over time of IL-6 at baseline and comparison with most recent hospitalized patients. Fig. 5C. Same dashboard as 5B for D-Dmer.

Fig. 6

A. Summary ward dashboard: newly hospitalized, total in charge, transfer to ICU, split by outcome. Fig. 6B Drill-down at war: historical compare with current average PaO2/FiO2 ratio and length of stay; list of patients with alert flag for most critical cases. Fig. 6C. Patient drill-down dashboard example, providing history of PaO2/FiO2 ratio and fever, last outcome of TC, swab sequence and days from symptom onset.