| Evidences-based Evaluation: |
|
|
| Replicating existing medical discoveries |
√ |
– |
| Time–sliced evaluation |
– |
√ |
| Manual literature search |
– |
√ |
| Intersection evaluation |
– |
√ |
| Derive reference sets from literature |
– |
√ |
| Compare results with curated databases |
√ |
– |
| Compare results using other resources |
√ |
– |
| Comparison with baselines: |
|
|
| Comparison with existing LBD tools |
√ |
– |
| Comparison with previous LBD techniques |
– |
√ |
| Comparison with previous LBD work |
– |
√ |
| Comparison with other state-of-art methods |
– |
√ |
| Expert-oriented Evaluation: |
|
|
| Expert-based evaluation |
– |
√ |
| Qualitative analysis of several selected results |
– |
√ |
| User-oriented Evaluation: |
|
|
| User-based evaluation |
– |
√ |
| User-experience evaluation |
– |
√ |
| Proven from Experiments: |
|
|
| Clinical Tests (or relevant other experiments) |
– |
√ |
| Scalability Analysis: |
|
|
| Processing time analysis |
– |
√ |
| Storage analysis |
– |
√ |
| Evaluate Ranking Technique: |
|
|
| Evaluate ranking positions |
– |
√ |
| Evaluation ranking scores |
– |
√ |
| Evaluate the quality of the output: |
|
|
| Evaluate the interestingness of results |
– |
√ |
| Evaluation of quality and coherence of stories |
– |
√ |
