Performance of the IHBI risk assessment tools for hypertension (as built in this study) on Kuwaiti natives and Asian expatriates
| Risk assignment by the IHBI (k-NN) tool | Risk assignment by the IHBI_Aggregate (k-NN) tool | |||
|---|---|---|---|---|
| Data set | Hypertensive patients (%) | Non-hypertensive patients (%) | Hypertensive patients (%) | Non-hypertensive patients (%) |
| All Ethnicities (k=8,N=10632) | ||||
| ‘Low’ risk | 1.1 | 37.6 | 0.28 | 37.6 |
| ‘Borderline’ risk | 6.5 | 31.8 | 4.9 | 31.9 |
| ‘High’ risk | 92.4 | 30.6 | 94.8 | 30.5 |
| Kuwaiti natives (k=8,N=5513)* | ||||
| ‘Low’ risk | 0.43 | 22.8 | 0.26 | 27 |
| ‘Borderline’ risk | 4.9 | 34.7 | 5.6 | 38.1 |
| ‘High’ risk | 94.6 | 42.5 | 94.2 | 34.9 |
| Asian expatriates (k=8,N=3036)* | ||||
| ‘Low’ risk | 1.2 | 43.6 | 0.1 | 48.5 |
| ‘Borderline’ risk | 4.1 | 27.4 | 2.6 | 26.1 |
| ‘High’ risk | 94.7 | 29.1 | 97.3 | 25.5 |
*Split schema used is (0–1)—‘low’ risk; (2–3)—‘borderline’ risk; (4–8)—‘high’ risk.
k-NN, k-nearest neighbours.