Table 4 Multivariable regression models comparing models for time-averaged HAQ-DI outcome, individual comorbidities versus comorbidity clusters
From: Assessing clusters of comorbidities in rheumatoid arthritis: a machine learning approach
No comorbidities | + Individual comorbidities | + Clustering K mode | + Clustering regression | + Clustering DIANA | |
|---|---|---|---|---|---|
Beta coefficient (95% confidence interval) | |||||
Race/ethnicity | |||||
Asian | − 0.00 (− 0.05, 0.04) | 0.02 (− 0.02, 0.06) | 0.01 (− 0.03, 0.05) | 0.01 (− 0.04, 0.05) | − 0.00 (− 0.05, 0.04) |
Black | 0.02 (− 0.00, 0.05) | 0.02 (− 0.00, 0.04) | 0.02 (− 0.00, 0.05) | 0.02 (− 0.00, 0.04) | 0.02 (− 0.00, 0.04) |
Hispanic | 0.02 (− 0.00, 0.04) | 0.02 (0.00, 0.05) | 0.02 (− 0.00, 0.05) | 0.02 (− 0.00, 0.05) | 0.02 (− 0.00, 0.04) |
Other | 0.06 (0.02, 0.09) | 0.06 (0.03, 0.10) | 0.06 (0.02, 0.09) | 0.06 (0.03, 0.10) | 0.06 (0.02, 0.09) |
White | reference | reference | reference | reference | reference |
Duration of RA, years | 0.00 (0.00, 0.00) | 0.00 (0.00, 0.00) | 0.00 (0.00, 0.00) | 0.00 (0.00, 0.00) | 0.00 (0.00, 0.00) |
Erosions | − 0.00 (− 0.02, 0.01) | − 0.00 (− 0.01, 0.01) | − 0.01 (− 0.02, 0.01) | − 0.00 (− 0.01, 0.01) | − 0.00 (− 0.02, 0.01) |
Serologic status, positive | − 0.02 (− 0.04, − 0.01) | − 0.02 (− 0.03, − 0.00) | − 0.02 (− 0.03, − 0.01) | − 0.02 (− 0.03, − 0.01) | − 0.02 (− 0.04, − 0.01) |
CDAI, baseline | 0.00 (0.00, 0.00) | 0.00 (− 0.00, 0.00) | 0.00 (0.00, 0.00) | 0.00 (0.00, 0.00) | 0.00 (0.00, 0.00) |
HAQ-DI, baseline | 0.63 (0.61, 0.64) | 0.59 (0.57, 0.60) | 0.61 (0.60, 0.63) | 0.61 (0.59, 0.62) | 0.63 (0.61, 0.64) |
Individual comorbidities | |||||
Coronary artery disease | --- | 0.03 (0.02,0.05) | --- | ||
Heart failure | --- | 0.12 (0.07, 0.16) | --- | ||
Hypertension | --- | 0.04 (0.02, 0.05) | --- | ||
DVT/PE | --- | 0.04 (-0.00, 0.07) | --- | ||
Stroke/TIA | --- | 0.05 (0.02, 0.08) | --- | ||
Arrhythmia | --- | − 0.01 (− 0.08, 0.06) | --- | ||
GI bleed | --- | 0.01 (− 0.02, 0.04) | --- | ||
Liver disease | --- | − 0.01 (− 0.04, 0.02) | --- | ||
Solid tumor | --- | − 0.01 (− 0.04, 0.03) | --- | ||
NMSC | --- | − 0.00 (− 0.02, 0.02) | --- | ||
Lymphoma | --- | − 0.02 (− 0.08, 0.05) | --- | ||
Other cancer | --- | 0.01 (− 0.01, 0.03) | --- | ||
Melanoma | --- | 0.02 (− 0.02, 0.06) | --- | ||
Diabetes | --- | 0.04 (0.02, 0.05) | --- | ||
Hyperlipidemia | --- | − 0.01 (− 0.03, 0.01) | --- | ||
Osteoporosis | --- | 0.02 (0.01, 0.04) | --- | ||
Demyelinating | --- | 0.03 (− 0.04, 0.11) | --- | ||
Mental health | --- | 0.07 (0.06, 0.08) | --- | ||
Fibromyalgia | --- | 0.12 (0.10, 0.14) | --- | ||
Psoriasis | --- | 0.03 (0.01, 0.06) | --- | ||
Asthma/COPD | --- | 0.01 (− 0.01, 0.03) | --- | ||
RA Lung | --- | 0.02 (− 0.01, 0.05) | --- | ||
Acute kidney injury | --- | 0.01 (− 0.01, 0.02) | --- | ||
Clusters from ML | |||||
1 | --- | --- | reference | reference | reference |
2 | --- | --- | − 0.01 (− 0.03, 0.01) | 0.12 (0.10, 0.15) | − 0.03 (− 0.11,0.05) |
3 | --- | --- | 0.07 (0.05, 0.09) | 0.02 (− 0.00, 0.04) | − 0.06 (− 0.16,0.03) |
4 | --- | --- | 0.08 (0.06, 0.10) | − 0.03 (− 0.05, − 0.01) | − 0.05 (− 0.16, 0.06) |
5 | --- | --- | − 0.02 (− 0.04, 0.00) | 0.05 (0.02, 0.07) | − 0.08 (− 0.43, 0.26) |
Degrees of freedom | 22 | 46 | 26 | 26 | 26 |
Model fit statistics | |||||
Adjusted R2 | 0.47 | 0.50 | 0.48 | 0.48 | 0.47 |
Root mean square error | 0.30 | 0.29 | 0.29 | 0.29 | 0.30 |