Skip to main content

Table 4 The 15 variables with highest NRIs for predicting presence of PASC among males, based on the optimal stochastic gradient boosting model with 11,221 trees, together with ORME during the year before PASC diagnosis

From: Using machine learning involving diagnoses and medications as a risk prediction tool for post-acute sequelae of COVID-19 (PASC) in primary care

Males

ICD- 10 or ATC code

Description

NRI (%)

ORME

U07, U08, U09, U11 and U12

COVID- 19—in hospitalized patients

41.7

31.6

R53

Malaise and fatigue

11.5

7.9

G933

Post-viral and related fatigue syndromes

6.4

28.4

R06

Dyspnea

4.9

6.5

R05

Cough

4.1

4.4

J01, J02, J03, J06 and J20

Upper respiratory tract infections

3.5

3.4

R00

Tachycardia

2.5

5.2

B34

Viral infection of unspecified site

2.1

3.3

R03 A and R03B (ATC)

Adrenergics, inhalants and other drugs for obstructive airway diseases, inhalants

1.5

1.8

R51

Headache

1.4

3.1

F43

Reaction to severe stress and adjustment orders

1.2

2.6

R05 (ATC)

Cough and cold preparations

1.2

2.2

J45 and J46

Asthma

1.1

2.0

  1. NRI normalized relative influence, PASC post-acute sequelae of COVID- 19, ORME odds ratio for marginal effects, ICD- 10 International Classification of Diseases Tenth Revision, ATC Anatomical Therapeutic Chemical