Table 4.
Clinical variables with the top-ranked weights (/N stands for the clinical variable presented in N months before the prediction date).
| Sr. No. | ICDa-9/occurrence time | Medication/occurrence time |
| 1 | 493.9×asthma/0-5b (meaning diagnosed with asthma multiple times before exacerbation) | Methylprednisolone/0, 1c |
| 2 | 786.07 wheezing/0-2d | Prednisone/0, 1, 2c |
| 3 | 496.0 chronic airway obstruction not elsewhere classified/0, 1e | Ipratropium/0, 1, 2c |
| 4 | 530.81 esophageal reflux/0b | Midazolam/0, 1, 2d |
| 5 | V46.2 dependence on supplemental oxygen/0d | Hydromorphone/0-2e |
| 6 | 787.02 nausea alone/0d | Heparin/0, 1d |
| 7 | 786.50 unspecified chest pain/0d | Acetaminophen-oxycodone/0b |
| 8 | V08 HIV infection status/0e | Fentanyl/0e |
| 9 | 786.59 other chest pain/0d | Methylprednisolone/2-4e |
| 10 | 786.05 shortness of breath/0d | Glycopyrrolate/0b |
| 11 | V58.69 long-term (current) use of other medications/0e | Lidocaine/0d |
| 12 | 784.0 headache/0e | Dexamethasone/0d |
| 13 | 346.90 migraine, unspecified, without mention of intractable migraine without mention of status migrainosus/0e | Promethazine/0d |
| 14 | V58.66 long-term (current) use of aspirin/0b | Atorvastatin/0d |
| 15 | 491.21 obstructive chronic bronchitis with (acute) exacerbation/0e | Furosemide/0c |
aICD: International Classification of Disease Code.
bIdentified possible risk factors of asthma exacerbations by the domain expert. The authors regard these as containing valuable information.
cThese medications can be used to treat asthma or control the symptoms of asthma. In this study, it was difficult to determine whether these medications are risk factors as we were unable to investigate the dosage of these medications in the current study. Inappropriate medication use, short-acting beta agonists/inhaled corticosteroids, could also lead to asthma exacerbations.
dThese factors were symptoms, comorbidities, or combined medications. We believe they were not risk factors for asthma exacerbations.
eIt could hardly be determined whether these factors caused asthma exacerbations, but they demonstrated high associations. The authors regard these as containing valuable information.