SPECTF Heart
Donated on 9/30/2001
Data on cardiac Single Proton Emission Computed Tomography (SPECT) images. Each patient classified into two categories: normal and abnormal.
Dataset Characteristics
Multivariate
Subject Area
Health and Medicine
Associated Tasks
Classification
Feature Type
Integer
# Instances
267
# Features
44
Dataset Information
Additional Information
The dataset describes diagnosing of cardiac Single Proton Emission Computed Tomography (SPECT) images. Each of the patients is classified into two categories: normal and abnormal. The database of 267 SPECT image sets (patients) was processed to extract features that summarize the original SPECT images. As a result, 44 continuous feature pattern was created for each patient. The CLIP3 algorithm was used to generate classification rules from these patterns. The CLIP3 algorithm generated rules that were 77.0% accurate (as compared with cardilogists' diagnoses). SPECTF is a good data set for testing ML algorithms; it has 267 instances that are descibed by 45 attributes. Predicted attribute: OVERALL_DIAGNOSIS (binary) NOTE: See the SPECT heart data for binary data for the same classification task.
Has Missing Values?
No
Variables Table
| Variable Name | Role | Type | Description | Units | Missing Values |
|---|---|---|---|---|---|
| diagnosis | Target | Integer | no | ||
| F1R | Feature | Integer | no | ||
| F1S | Feature | Integer | no | ||
| F2R | Feature | Integer | no | ||
| F2S | Feature | Integer | no | ||
| F3R | Feature | Integer | no | ||
| F3S | Feature | Integer | no | ||
| F4R | Feature | Integer | no | ||
| F4S | Feature | Integer | no | ||
| F5R | Feature | Integer | no |
0 to 10 of 45
Additional Variable Information
1. OVERALL_DIAGNOSIS: 0,1 (class attribute, binary) 2. F1R: continuous (count in ROI (region of interest) 1 in rest) 3. F1S: continuous (count in ROI 1 in stress) 4. F2R: continuous (count in ROI 2 in rest) 5. F2S: continuous (count in ROI 2 in stress) 6. F3R: continuous (count in ROI 3 in rest) 7. F3S: continuous (count in ROI 3 in stress) 8. F4R: continuous (count in ROI 4 in rest) 9. F4S: continuous (count in ROI 4 in stress) 10. F5R: continuous (count in ROI 5 in rest) 11. F5S: continuous (count in ROI 5 in stress) 12. F6R: continuous (count in ROI 6 in rest) 13. F6S: continuous (count in ROI 6 in stress) 14. F7R: continuous (count in ROI 7 in rest) 15. F7S: continuous (count in ROI 7 in stress) 16. F8R: continuous (count in ROI 8 in rest) 17. F8S: continuous (count in ROI 8 in stress) 18. F9R: continuous (count in ROI 9 in rest) 19. F9S: continuous (count in ROI 9 in stress) 20. F10R: continuous (count in ROI 10 in rest) 21. F10S: continuous (count in ROI 10 in stress) 22. F11R: continuous (count in ROI 11 in rest) 23. F11S: continuous (count in ROI 11 in stress) 24. F12R: continuous (count in ROI 12 in rest) 25. F12S: continuous (count in ROI 12 in stress) 26. F13R: continuous (count in ROI 13 in rest) 27. F13S: continuous (count in ROI 13 in stress) 28. F14R: continuous (count in ROI 14 in rest) 29. F14S: continuous (count in ROI 14 in stress) 30. F15R: continuous (count in ROI 15 in rest) 31. F15S: continuous (count in ROI 15 in stress) 32. F16R: continuous (count in ROI 16 in rest) 33. F16S: continuous (count in ROI 16 in stress) 34. F17R: continuous (count in ROI 17 in rest) 35. F17S: continuous (count in ROI 17 in stress) 36. F18R: continuous (count in ROI 18 in rest) 37. F18S: continuous (count in ROI 18 in stress) 38. F19R: continuous (count in ROI 19 in rest) 39. F19S: continuous (count in ROI 19 in stress) 40. F20R: continuous (count in ROI 20 in rest) 41. F20S: continuous (count in ROI 20 in stress) 42. F21R: continuous (count in ROI 21 in rest) 43. F21S: continuous (count in ROI 21 in stress) 44. F22R: continuous (count in ROI 22 in rest) 45. F22S: continuous (count in ROI 22 in stress) - all continuous attributes have integer values from the 0 to 100 - dataset is divided into: -- training data ("SPECTF.train" 80 instances) -- testing data ("SPECTF.test" 187 instances)
Reviews
There are no reviews for this dataset yet.
pip install ucimlrepo
from ucimlrepo import fetch_ucirepo # fetch dataset spectf_heart = fetch_ucirepo(id=96) # data (as pandas dataframes) X = spectf_heart.data.features y = spectf_heart.data.targets # metadata print(spectf_heart.metadata) # variable information print(spectf_heart.variables)
Cios,Krzysztof, Kurgan,Lukasz, and Goodenday,Lucy. (2001). SPECTF Heart. UCI Machine Learning Repository. https://doi.org/10.24432/C5N015.
@misc{misc_spectf_heart_96,
author = {Cios,Krzysztof, Kurgan,Lukasz, and Goodenday,Lucy},
title = {{SPECTF Heart}},
year = {2001},
howpublished = {UCI Machine Learning Repository},
note = {{DOI}: https://doi.org/10.24432/C5N015}
}Creators
Krzysztof Cios
Lukasz Kurgan
Lucy Goodenday
DOI
License
This dataset is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) license.
This allows for the sharing and adaptation of the datasets for any purpose, provided that the appropriate credit is given.