Table 2.
Evaluation of algorithms trained to predict physical, sexual, psychosocial well-beings at 2 year follow-up
| 2 Year follow-up score lower than baseline | 2 Year follow-up score higher than baseline | |||
|---|---|---|---|---|
| Accuracy (95% CI) | AUC (95% CI) | Accuracy (95% CI) | AUC (95% CI) | |
| Physical well-being | ||||
| Logistic regression with elastic net penalty | ||||
| Test set (n = 1320) | 0.67(0.66–0.68) | 0.71(0.70–0.72) | 0.70(0.69–0.71) | 0.77(0.75–0.78) |
| Additional validation set (n = 218) | 0.63(0.56–0.69) | 0.69(0.62–0.76) | 0.76(0.69–0.81) | 0.82(0.76–0.87) |
| XGBoost tree | ||||
| Test set (n = 1320) | 0.66(0.64–0.67) | 0.70(0.69–0.72) | 0.70(0.69–0.71) | 0.77(0.76–0.78) |
| Additional validation set (n = 218) | 0.64(0.57–0.71) | 0.69(0.62–0.76) | 0.75(0.69–0.81) | 0.81(0.75–0.86) |
| Neural network | ||||
| Test set (n = 1320) | 0.65(0.64–0.67) | 0.70(0.68–0.71) | 0.69(0.69–0.71) | 0.76(0.75–0.77) |
| Additional validation set (n = 218) | 0.64 (0.58–0.71) | 0.70(0.63–0.77) | 0.75(0.69–0.81) | 0.81(0.75–0.86) |
| Sexual well-being | ||||
| Logistic regression with elastic net penalty | ||||
| Test set (n = 1247) | 0.69(0.68–0.70) | 0.75(0.74–0.77) | 0.72(0.71–0.74) | 0.77(0.76–0.79) |
| Additional validation set (n = 207) | 0.69(0.62–0.75) | 0.76(0.70–0.82) | 0.69(0.62–0.75) | 0.76(0.69–0.82) |
| XGBoost tree | ||||
| Test set (n = 1247) | 0.69(0.68–0.70) | 0.75(0.74–0.76) | 0.72(0.70–0.73) | 0.76(0.74–0.77) |
| Additional validation set (n = 207) | 0.70(0.63–0.76) | 0.77(0.70–0.83) | 0.69(0.62–0.75) | 0.76(0.70–0.83) |
| Neural network | ||||
| Test set (n = 1247) | 0.67(0.66–0.69) | 0.75(0.73–0.76) | 0.71(0.69–0.72) | 0.77(0.76–0.79) |
| Additional validation set (n = 207) | 0.70(0.63–0.76) | 0.77(0.70–0.83) | 0.67(0.60–0.73) | 0.74(0.67–0.81) |
| Psychosocial well-being | ||||
| Logistic regression with elastic net penalty | ||||
| Test set (n = 1319) | 0.73(0.71–0.74) | 0.72(0.70–0.74) | 0.69(0.68–0.70) | 0.76(0.75–0.77) |
| Additional validation set (n = 219) | 0.71(0.65–0.77) | 0.66(0.58–0.73) | 0.60(0.53–0.66) | 0.66(0.59–0.73) |
| XGBoost tree | ||||
| Test set (n = 1319) | 0.70(0.69–0.71) | 0.68(0.66–0.70) | 0.70(0.69–0.72) | 0.77(0.76–0.79) |
| Additional validation set (n = 219) | 0.70(0.63–0.76) | 0.66(0.58–0.74) | 0.62(0.55–0.68) | 0.66(0.59–0.74) |
| Neural network | ||||
| Test set (n = 1319) | 0.71(0.70–0.73) | 0.72(0.70–0.73) | 0.70(0.69–0.71) | 0.76(0.75–0.78) |
| Additional validation set (n = 219) | 0.71(0.64–0.77) | 0.64(0.55–0.72) | 0.60(0.53–0.66) | 0.66(0.58–0.73) |
AUC Area-under-the-receiver-operating-characteristic-curve