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 5. Summary of best performances for BP/PRprediction taskusing different inputfeatures in LSTM models (based on MAE).
| Features | Training loss | Validation loss | Test loss |
| All 15 features | 2.94 | 12.11 | 12.15 |
| Only 13 features | 3.29 | 12.06 | 11.28 |
| Only four artery-related features | 3.55 | 12.36 | 12.25 |
| Three specific features, excluding any artery-related features | 12.98 | 16.17 | 15.84 |