Back to Article
Development of a Hemodialysis Data Collection and Clinical Information System and Establishment of an Intradialytic Blood Pressure/Pulse Rate Predictive Model
Journal of Artificial Intelligence and Big Data
| Vol 5, Issue 2
Table 3. Summary of best performances for BP/PRprediction taskusing different hiddenlayer numbers inANN models (based on MAE).
| Number of Hidden layers | Training loss | Validation loss | Test loss |
| 2 | 7.52 | 12.65 | 13.26 |
| 4 | 7.27 | 12.04 | 12.57 |
| 6 | 9.84 | 11.90 | 11.37 |
| 7 | 12.64 | 13.10 | 13.26 |
| 8 | 10.51 | 12.05 | 11.47 |
| 10 | 9.54 | 11.17 | 11.56 |
| 12 | 11.89 | 12.73 | 13.42 |