Table 3.
Summary accuracy estimates produced by three types of tools for risk assessment
| Violent offending (n=30)* | Sexual offending (n=20)† | Criminal offending (n=23)‡ | |
|---|---|---|---|
| Summary estimates (95% CI) from summary receiver operating characteristic curve | |||
| Diagnostic odds ratio | 6.07 (4.58 to 8.05) | 3.88 (2.36 to 6.40) | 2.84 (2.09 to 3.88) |
| Sensitivity | 0.92 (0.88 to 0.94) | 0.88 (0.83 to 0.92) | 0.41 (0.28 to 0.56) |
| Specificity | 0.36 (0.28 to 0.44) | 0.34 (0.20 to 0.51) | 0.80 (0.67 to 0.89) |
| Individual study estimates (median (IQR)) | |||
| Area under the curve | 0.72 (0.68-0.78) | 0.74 (0.66-0.77) | 0.66 (0.58-0.67) |
| Positive predictive value | 0.41 (0.27-0.60) | 0.23 (0.09-0.41) | 0.52 (0.32-0.59) |
| Negative predictive value | 0.91 (0.81-0.95) | 0.93 (0.82-0.98) | 0.76 (0.61-0.84) |
| Number needed to detain | 2 (2-4) | 5 (2-11) | 2 (2-3) |
| Number safely discharged | 10 (4-18) | 14 (5-48) | 3 (2-6) |
CI=confidence interval; IQR=interquartile range; n=number of samples.
*HCR-20, SARA, SAVRY, and VRAG.
†SORAG, Static-99, and SVR-20.
‡LSI-R and PCL-R.