What drives

long-COVID?
Understanding complex interactions
with real world data

arcadia.io
What drives long-COVID? Understanding complex interactions with real world data

As many as 1 in 10 people may have symptoms of COVID-19

for months after their initial infection, driving a staggering
total number of long-COVID cases that continues to increase.
As part of our work with the COVID Patient Recovery
Alliance, Arcadia analyzed a massive real world data set
to identify potential drivers of long-COVID.

Our key finding is that vaccination against COVID-19 reduces

the likelihood that patients will experience long-COVID
symptoms in the event that they are infected. Our data
also suggest that a single dose of a COVID-19 vaccine, even
if received after the patient is diagnosed with COVID, still
correlates with a reduced likelihood of presenting long-COVID
symptoms. We’ve intended this summary of our analysis to
be useful for a broad health care audience; for more detailed
clinical or technical information about our COVID-19 work
and research data asset, please visit arcadia.io/c19

Our study “Reduced Incidence of

Long-COVID Symptoms Related to
Administration of COVID-19 Vaccines
Both Before COVID-19 Diagnosis
and Up to 12 Weeks After” (Michael
A. Simon, Ryan D. Luginbuhl, Richard
Parker) is currently available on
MedRxiv. →

1
What drives long-COVID? Understanding complex interactions with real world data

“I bring to your attention the fact that

a number of individuals who virologically
have recovered from [their COVID-19]
infection, in fact have persistence
measured in weeks to months of
symptomatology that does not appear
to be due to persistence of the virus.
They’re referred to as long haulers.
They have fatigue, myalgia, fever, and
involvement of the neurological system,
as well as cognitive abnormalities,
such as the inability to concentrate.”
Dr. Anthony “Tony” Fauci
Testimony to the Senate HELP Committee
September 23, 2020

2
What drives long-COVID? Understanding complex interactions with real world data

Long-COVID

The COVID Patient Recovery Alliance defines long-COVID as the currently-accepted

term to describe signs and symptoms that continue or develop after acute COVID-19
that are not explained by an alternative diagnosis.

It includes both ongoing symptomatic COVID-19 as well as post-COVID-19 syndrome,

the onset and persistence of COVID symptoms during and after infection.

COVID SYMPTOMS CAN APPEAR WEEKS AFTER DIAGNOSIS

Initial exposure can occur from individuals who are asymptomatic or symptomatic. If infected…

Some patients develop symptoms right …while others are asymptomatic …and some never have symptoms
away (between 2 days and 2 weeks)… during this period… at all.
Infection

Current CDC guidance: patients are most CDC indicates patients are still likely to be
contagious between 2 days before and 3 contagious between 2 days before and
days after the appearance of symptoms. 3 days after the first positive COVID test

Acute COVID-19 can last up to …and can bring later-onset acute symptoms
4 weeks after symptom onset… to initially asymptomatic patients.
Acute COVID

Until the virus is no longer replicating Patients who are initially asymptomatic may
in the respiratory tract and a nasal experience increased symptoms and even require
swab turns up negative. hospitalization later in the acute phase.

Many patients ... but some Additional chronic conditions Late-onset COVID-19 can occur in
recover with no suffer from are reported by many patients months previously asymptomatic patients
additional post-acute after their initial infection, ranging from who begin reporting COVID-19 symptoms
Long-COVID

symptoms… COVID-19 persisting respiratory issues, fatigue, weeks or even months after the acute
symptoms and weakness, to chronic cognitive phase has ended.
for weeks issues and hair loss.
or months.

Both persisting and late-onset COVID-19 symptoms as well as post-infection onset of chronic conditions
are considered long-COVID.

Long-COVID is a critical development of models of care, and ensure Arcadia is a contributor to the Alliance,
research priority for the adequate payment for long-COVID patients lending our research data asset and data
COVID Patient Recovery who served their communities and nation science expertise to this important cause.
Alliance, which brings together key thought during the pandemic; whose COVID-19-
leaders in business, health care, research, related costs are extraordinary and For more information about the PRA,
academia, data and analytics, and patient burdensome; or who are underserved by visit covid19patientrecovery.org
advocacy to develop national solutions that existing programs.
coordinate diverse data sources, inform the

3
What drives long-COVID? Understanding complex interactions with real world data

A LONG COVID ROAD TRAVELLED

1 MILLION COVID-19 CASES AND THEIR SYMPTOMATIC JOURNEY

1 M I L L I O N C O V I D - 1 9 C A S E S A N D T H E I R S Y M P T O M AT I C J O U R N E Y
P L A C E H O L D E R P O S T E R D E S C R I P T I O N

What happens
Diagnosis
once a patient is
diagnosed with
Weeks 0-4

COVID-19?
The journey varies.
Some remain
A Asymptomatic Symptomatic Deceased asymptomatic.
Hospitalized Others develop
immediate symptoms
(gastrointestinal,
cardiovascular, and/
Weeks 4-8

or others) and then

Deceased
quickly recover—or
may be hospitalized.
Some only begin to
develop symptoms
weeks after
Asymptomatic Symptomatic Hospitalized diagnosis. And for
many, COVID
symptoms persist for
many weeks and
may seem unending.
Weeks 8-12

Deceased
There is no single
long-COVID
experience. Patients
suffer from a wide
range of symptoms
Asymptomatic Symptomatic Hospitalized over highly variable
timeframes. The
complex nature of
this condition makes
it challenging to
Weeks 12-16

identify potential
Deceased
drivers—but data
science can offer
some insights.

View more
Asymptomatic Symptomatic Hospitalized
visualizations in
our online gallery.
Weeks 16-20

Deceased

Quantity of symptoms across cases

Quantity of cases by four week time periods

Asymptomatic Symptomatic Hospitalized

Constitutional Long COVID Lower Incidence Higher Incidence Long COVID Lower Incidence Higher Incidence

Respiratory Symptomatic Hospitalized

Other
Loss of sense of taste
Chills
Altered Mental Status
Loss of sense of smell
Digestive Changes
Sore Throat
Anorexia
Vomiting
Nasal Congestion
Nausea and Vomiting
Myalgia
Nausea
Diarrhea
Fever
Palpitations
Illness, unspecified
General Weakness
Headache
Weakness
General Muscle
Cough
Fatigue
Chest Pain
Abdominal Pain
Dyspnea
Malaise
Arthralgia

Nausea and Vomiting

Abdominal Pain
Fatigue
Chest Pain
Arthralgia
Fever
Cough
General Weakness
Dyspnea
Other
Malaise
General Muscle Weakness

Equivalent to 50K
cases or symptoms Case Case
Musculoskeletal Symptoms Symptoms
Gastrointestinal weeks 16-20 weeks 16-20

Cardiovascular
ENMT (Ears, Nose, Mouth, Throat)
Neurological

© 2021 ARCADIA.IO
© 2021 ARCADIA.IO
4
What drives long-COVID? Understanding complex interactions with real world data

Exploring factors driving long-COVID

Arcadia used exploratory data analysis to surface factors that might increase patient
susceptibility to long-COVID symptoms. Exploratory data analysis does not
assign causal relationships, but it does help understand complex interactions and
drive hypothesis creation. Our findings identify strong directions for productive
future research.

Our analysis involved the following practical, concrete steps, which can be applied
to other problems where you need to understand potential relationships between
complex interactions using a massive real world data set.

1. Analyze patient conditions

We established baselines for patients who had been diagnosed and treated for
COVID-19 using a broad spectrum of chronic and acute conditions, both COVID-
associated and not. Understanding the prevalence of chronic conditions in the
populations we studied helped us characterize the incidence of COVID-related
symptoms and conditions as patients recovered.

2. Select a data set

We needed a real-world data set that not only had a sufficient population of COVID-19
patients but also represented a more general population of active patients to support
an exploratory analysis. Arcadia’s research data asset includes de-identified,
aggregated, HIPAA-compliant data on over 100 million patients. At the time this study
was conducted, our data included 1.3 million COVID-19 positive patients of whom
~689,000 had data from an electronic medical records (EMR) system.

ARCADIA’S COVID-19 POPULATION AS OF JANUARY 2022

2.8M 2.4M 8.9M

COVID-19 positive patients with data from an EMR (88%) COVID-19 vaccinated patients
600K

500K

400K

300K

200K

100K

Jan 2020 Jan 2021 Jan 2022

Patients diagnosed with COVID-19 Patients first vaccinated against COVID-19

5
What drives long-COVID? Understanding complex interactions with real world data

Arcadia’s massive and growing real world data asset

Arcadia’s research data asset was built to support the needs
of healthcare organizations taking on value-based care.
Insights generated from the full spectrum of healthcare data
support research into both common conditions like diabetes
and rare diseases like spinal muscular atrophy (SMA).

DATA ASSET OVERVIEW THERAPEUTIC AREA COVERAGE

National coverage 4.6M diabetic patients

Sourced from 45M active patients

3.6M 1.9M
Have 2+ year Have 5+ year
history history

1.9M 19k
Have 3+ A1c Distinct
lab results NPIs

Comorbid condition profile

Depression 365,219

100M+ 24%
COPD 517,605
Heart 583,679
Patient lives Integrated Vascular 704,444
claims records Obesity 836,282
CHF 873,623

Full spectrum of healthcare data 1,877 patients with

spinal muscular atrophy
$357B 348M 150k Sourced from 60M active patients
Health Clinical Distinct
costs visits EHR NPIs 1,108 24
Diagnosed in Taking
2.8B 5.9B 1.1B last 2 years Spinraza
Diagnoses Lab Written
& problems results prescriptions

6
What drives long-COVID? Understanding complex interactions with real world data

3. Define and refine cohorts

We included 25.8 million patients of any age who were seen clinically at least once
prior to January 1, 2020 and were alive as of March 1, 2020. Of those, our COVID-
positive (COV+) group included 1.06 million patients with a positive COVID-19 PCR
or antigen test or a diagnosis by a provider in a clinical setting.

Both our COV+ patients and the 24.7 million patient control group (COV-) had diverse
racial and ethnic representation.

4. Classify conditions
A “condition” is a clinical diagnosis that associates a disease, sign, or symptom with
a patient at a point in time. We used the AHRQ Chronic Condition Indicators to split
out chronic and acute events. We also used AHRQ’s clinical classification system1
to define broad diagnostic groupings. We then identified COVID-associated conditions2
that superseded these broad diagnostic groupings.

5. Insert events of interest

In addition to diagnostic criteria, we added other events sourced from EHR or claims-
based data that we thought might be useful to our model, like hospitalizations related
to a COVID diagnosis, vitals and labs, medications, and COVID-19 vaccinations.

6. Understand timing and condition onset

Looking at events the week they occurred (rather than the date) allowed us to simplify
our view and compress the data without reducing their value.

Pre-existing conditions and symptoms Chronic conditions and symptoms

preceding the index date emerging on or after the index date

Index date 4 8 12 16 20 t
Weeks past index date

1 More information about the AHRQ Clinical Classification Software and its classifiers is available at: https://www.hcup-us.
ahrq.gov/toolssoftware/ccsr/ccs_refined.jsp
2 Using value sets of COVID-associated conditions courtesy of Clinical Architecture with their permission.

7
What drives long-COVID? Understanding complex interactions with real world data

7. Analyze prevalence
We looked at the prevalence of conditions present prior to our study period (and
verified the data against existing literature) to create baselines for the COV+ group and
the COV- control group. Here, we started to see some qualitative differences between
the groups – for example, COV+ patients were 11.7% more likely to suffer from obesity.

8. Analyze incidence
As we continued to work through our analysis, we needed to figure out what
separated long-COVID patients from the COV+ group and from the COV- control group.

Incidence counts indicate the onset of new or acute conditions or symptoms.

By analyzing shifts in incidence counts relative to the timing of COVID diagnosis
and treatment, we established a baseline. We then compared the baselines for the
COV+ group against clusters that have experienced long-COVID symptoms.

Exploratory data analysis is particularly well-suited to pulling

out hidden insights about complex interactions. By analyzing
the symptomatic journeys of more than 1 million COVID
patients, our model helped us surface factors that strongly
correlate with whether a patient develops long-COVID.

8
What drives long-COVID? Understanding complex interactions with real world data

Our findings
The COVID data and our initial analysis support the
hypothesis that vaccination reduces the odds of experiencing
long-COVID symptoms, even if the vaccination occurs after
COVID-19 infection.

• P
 atients who are vaccinated and then infected are 4–6 times less likely to experience
long-COVID symptoms and 7–10 times less likely to report more than one symptom.

• Patients who are first vaccinated after they are diagnosed with COVID-19 are still
less likely to experience multiple long-COVID symptoms compared to patients who
remain unvaccinated: 4-6 times less likely if vaccinated within a month after
diagnosis and 3 times less likely if vaccinated within two months of diagnosis.

• The protective effect of a vaccine administered after infection declines within

2 months of infection.

VACCINES REDUCE THE LIKELIHOOD OF DEVELOPING LONG-COVID

Reduced likelihood of Reduced likelihood of

any long-COVID symptom more than 1 long-COVID symptom

First vaccine dose received… Likelihood Odds ratio 95% CI p-value Likelihood Odds ratio 95% CI p-value

Prior to diagnosis 4.5x 0.220 0.196 – 0.245 < 0.005 8.8x 0.113 0.090 – 0.143 < 0.005

0–4 weeks after diagnosis 2.6x 0.382 0.353 – 0.413 5.3x 0.189 0.163 – 0.220

4–8 weeks after diagnosis 1.9x 0.535 0.506 – 0.567 3.2x 0.317 0.289 – 0.348

8–12 weeks after diagnosis 1.3x 0.747 0.713 – 0.784 2.2x 0.458 0.426 – 0.493

9
What drives long-COVID? Understanding complex interactions with real world data

What are the key findings from this study?

These findings were an unexpected and exciting development from Arcadia’s
ongoing work with the COVID-19 Patient Recovery Alliance. The most important
takeaways are:

• COVID vaccines not only reduce the incidence and terrible effects of acute COVID
infection but they also reduce the likelihood and severity of long-COVID symptoms
in the aftermath of that infection.

• These findings offer evidence that vaccination soon after infection is still highly
protective against long-COVID, extending the window of opportunity for the
unvaccinated to protect themselves against long-COVID symptoms.

• The protective effect of vaccination against long-COVID increases the personal

protection offered by vaccination to the recipient, which may encourage
increased prophylactic vaccination and, with continued support from evidence,
therapeutic vaccination.

What else can we learn about long-COVID from a massive RWD dataset?
A massive RWD dataset like Arcadia’s permits us to explore a number of additional
avenues of study, including:

• The differences in long-COVID experiences based on demographic factors, including

age, sex, race, ethnicity, and socioeconomic status.

• The impact of pre-existing conditions on presence and severity of long-COVID

symptoms, including the onset of new chronic conditions.

• Differences in long-COVID symptoms for patients treated with different medications

and therapeutics during the acute phase of their COVID infection.

• Variation in expression of long-COVID symptoms based on combinations of likely

COVID variant and vaccination status.

• Impact of multiple COVID infections and vaccinations on long-COVID, especially

as their effects on the immune system continue to rise in importance.

We are grateful for the opportunity to better serve our

customers and contribute work to address a monumental
public health crisis, and we look forward to continuing
our work with the COVID-19 Patient Recovery Alliance.

10
For more information about our COVID-19 work,
please visit arcadia.io/c19

To learn more about Arcadia’s RWD,

please contact hello@arcadia.io

Arcadia is dedicated to making a difference with healthcare data. We transform data from disparate sources into targeted insights, putting
them in the decision-making workflow to improve lives and outcomes. In doing so, we have created the data supply chain for enterprise-wide,
evidence-based healthcare management. Through our partnerships with the nation’s leading health systems, payers, and life sciences companies,
we are growing a community of innovation to provide better care, maximize future value, and evolve together to meet emerging challenges and
opportunities. For more information, visit arcadia.io.

@arcadiaHealthIT linkedin.com/company/arcadia-io 781-202-3600

© 2022 arcadia.io