# 5-class ECG Classification on PTB-XL (Cross-subject) Source: [5-class ECG Classification on PTB-XL (Cross-subject)]() Collection index: [llms.txt]() Data updated: 2026-05-22T09:06:37.413Z Evaluation of 5-class ECG signal classification performance using the cross-subject split of the PTB-XL dataset, reporting Accuracy, F1 Score, and Area Under ROC Curve (AUR). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | 5-class ECG classification | | Dataset (including any stated split) | PTB-XL ECG-5 (Cross-subject) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. - [AUC (ROC)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | SoftShape | 73.94 | Not recorded | 6a0fe30cf984739ed6739d93 | | BioFormer | 73.37 | Not recorded | 6a0fe30cf984739ed6739d93 | | Crossformer | 73.3 | Not recorded | 6a0fe30cf984739ed6739d93 | | PatchTST | 73.23 | Not recorded | 6a0fe30cf984739ed6739d93 | | Medformer | 72.87 | Not recorded | 6a0fe30cf984739ed6739d93 | | MTST | 72.14 | Not recorded | 6a0fe30cf984739ed6739d93 | | Reformer | 71.72 | Not recorded | 6a0fe30cf984739ed6739d93 | | Informer | 71.43 | Not recorded | 6a0fe30cf984739ed6739d93 | | Transformer | 70.59 | Not recorded | 6a0fe30cf984739ed6739d93 | | Nonformer | 70.56 | Not recorded | 6a0fe30cf984739ed6739d93 | | iTransformer | 69.28 | Not recorded | 6a0fe30cf984739ed6739d93 | | Autoformer | 61.68 | Not recorded | 6a0fe30cf984739ed6739d93 | | FEDformer | 57.2 | Not recorded | 6a0fe30cf984739ed6739d93 | ### SoftShape Accuracy: 73.94. Result ID: 6a101b77fbc373592c0947e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"A.Rank":"3.61","Reproduced":"true"}. This record does not assert independent reproduction. ### BioFormer Accuracy: 73.37. Result ID: 6a101b77fbc373592c0947e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"A.Rank":"1.47","Reproduced":"true"}. This record does not assert independent reproduction. ### Crossformer Accuracy: 73.3. Result ID: 6a101b77fbc373592c0947e2. [Reporting paper]() Recorded evaluation configuration: {"A.Rank":"6.47"}. This record does not assert independent reproduction. ### PatchTST Accuracy: 73.23. Result ID: 6a101b77fbc373592c0947e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"A.Rank":"8.17"}. This record does not assert independent reproduction. ### Medformer Accuracy: 72.87. Result ID: 6a101b77fbc373592c0947e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"A.Rank":"4.94"}. This record does not assert independent reproduction. ### MTST Accuracy: 72.14. Result ID: 6a101b77fbc373592c0947e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"A.Rank":"8.33"}. This record does not assert independent reproduction. ### Reformer Accuracy: 71.72. Result ID: 6a101b77fbc373592c0947dc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"A.Rank":"5.25"}. This record does not assert independent reproduction. ### Informer Accuracy: 71.43. Result ID: 6a101b77fbc373592c0947dd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"A.Rank":"7.42"}. This record does not assert independent reproduction. ### Transformer Accuracy: 70.59. Result ID: 6a101b77fbc373592c0947db. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"A.Rank":"7.29"}. This record does not assert independent reproduction. ### Nonformer Accuracy: 70.56. Result ID: 6a101b77fbc373592c0947e0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"A.Rank":"7.12"}. This record does not assert independent reproduction. ### iTransformer Accuracy: 69.28. Result ID: 6a101b77fbc373592c0947e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"A.Rank":"7.94"}. This record does not assert independent reproduction. ### Autoformer Accuracy: 61.68. Result ID: 6a101b77fbc373592c0947de. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"A.Rank":"12.25"}. This record does not assert independent reproduction. ### FEDformer Accuracy: 57.2. Result ID: 6a101b77fbc373592c0947df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"A.Rank":"10.67"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.