JMIR Publications

ABSTRACT

Background:

In March 2020, the World Health Organization declared COVID-19 a global pandemic, necessitating an understanding of factors influencing severe disease outcomes. High hospitalization rates for COVID-19 underscore the need for robust risk prediction tools to determine estimated risk for future hospitalization for outpatients with COVID-19. We introduced the "COVID-19 Risk Tier Assessment Tool" (CRTAT), designed to enhance clinical decision-making for outpatients.

Objective:

This study aimed to assess whether CRTAT offers more accurate risk tier assignments compared to medical provider insights alone.

Methods:

We studied COVID-19 positive patients enrolled in Emory Healthcare's Virtual Outpatient Management Clinic (VOMC), a telemedicine monitoring program, from May 27, 2020 through August 24, 2020 who were not hospitalized at the time of enrollment. The primary analysis used patients from this program who later experienced hospitalization from COVID-19. We retroactively created a matched group of non-hospitalized patients for comparison, matched by age, gender, and risk factors. Data extracted from clinical notes were entered into CRTAT. We used descriptive statistics to show comparison of the risk tier assignment reported by algorithm trained healthcare providers versus the risk tier assignment produced by the data entry tool.

Results:

Our patients were primarily under 60 years old (67% hospitalized and 71% non-hospitalized). Moderate risk factors were prevalent (hospitalized: 52% reported only 1, 10% 2, and 19% 3 or more; non-hospitalized group: 52% 1, 24% 2, and 19% 3 or more. Around 45% of the total sample had high-risk factors (52% hospitalized and 38% non-hospitalized). Approximately 83% of the sample reported non-specific symptoms and the symptoms were generally mild (57% hospitalized and 67% non-hospitalized). Most patient visits were seen within the first 1-6 days of their illness (45%) with symptoms reported as stable over this period (70% hospitalized and 33% non-hospitalized). Of 42 matched patients (21 hospitalized and 21 not hospitalized), 26 had identical risk tier assignments and 16 had discrepancies between VOMC providers and CRTAT. Elements that led to different risk tier assignments were identified to be: (1) provider “missed” comorbidity (n=6), (2) provider noted comorbidity but under-coded risk (n=10), and/or (3) provider mis-coded symptom severity and course (n=7).

Conclusions:

CRTAT, a point-of-care data entry tool, more accurately categorized patients into hospitalization tiers, particularly those hospitalized, underscored by CRTAT's ability to identify critical factors in patient history and clinical status. Clinical decision-making regarding patient management, resource allocation, and treatment plans could be enhanced by using similar risk assessment data entry tools for other disease states, such as influenza and community acquired pneumonia. The COVID-19 pandemic has accelerated the adoption of telemedicine, enabling remote patient tools like CRTAT. Future research should explore the long-term impact of outpatient clinical risk assessment tools and their contribution to better patient care.