Abstract
Pattern generalization capabilities of neural networks are evaluated in two models: 1) prediction of coronary lesions from myocardial perfusion SPECT data; and 2) determination of comments to stress test results (EST). The SPECT network correctly predicted the stenosed/occluded vessel in all single-vessel disease cases, while the success rate was 83% for multi-vessel diseases. The EST network provided 106/125 correct interpretations. It is concluded that the functional success on software simulated neural networks is derived from the underlying computing model. Input values are comparable to multidimensional vectors since they are sequences of values wherein value position in the sequence is as important as the value itself. Interneural connections are numerical matrices instead. Network knowledge is included in the matrices that define each particular network. This structure allows some generalization ability since the response can always be computed for unexpected or incomplete data clusters.
| Original language | English |
|---|---|
| Title of host publication | Computers in Cardiology |
| Publisher | Publ by IEEE |
| Pages | 599-601 |
| Number of pages | 3 |
| ISBN (Print) | 0818622253 |
| Publication status | Published - May 1991 |
| Event | Computers in Cardiology - Proceedings - Chicago, IL, USA Duration: Sep 23 1990 → Sep 26 1990 |
Other
| Other | Computers in Cardiology - Proceedings |
|---|---|
| City | Chicago, IL, USA |
| Period | 9/23/90 → 9/26/90 |
Fingerprint
ASJC Scopus subject areas
- Software
- Cardiology and Cardiovascular Medicine
Cite this
Efficient performance of neural network models as artificial intelligence prediction tools in cardiology. / Cianflone, D.; Carandente, O.; Carlino, M.; Meloni, C.; Chierchia, S. L.
Computers in Cardiology. Publ by IEEE, 1991. p. 599-601.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Efficient performance of neural network models as artificial intelligence prediction tools in cardiology
AU - Cianflone, D.
AU - Carandente, O.
AU - Carlino, M.
AU - Meloni, C.
AU - Chierchia, S. L.
PY - 1991/5
Y1 - 1991/5
N2 - Pattern generalization capabilities of neural networks are evaluated in two models: 1) prediction of coronary lesions from myocardial perfusion SPECT data; and 2) determination of comments to stress test results (EST). The SPECT network correctly predicted the stenosed/occluded vessel in all single-vessel disease cases, while the success rate was 83% for multi-vessel diseases. The EST network provided 106/125 correct interpretations. It is concluded that the functional success on software simulated neural networks is derived from the underlying computing model. Input values are comparable to multidimensional vectors since they are sequences of values wherein value position in the sequence is as important as the value itself. Interneural connections are numerical matrices instead. Network knowledge is included in the matrices that define each particular network. This structure allows some generalization ability since the response can always be computed for unexpected or incomplete data clusters.
AB - Pattern generalization capabilities of neural networks are evaluated in two models: 1) prediction of coronary lesions from myocardial perfusion SPECT data; and 2) determination of comments to stress test results (EST). The SPECT network correctly predicted the stenosed/occluded vessel in all single-vessel disease cases, while the success rate was 83% for multi-vessel diseases. The EST network provided 106/125 correct interpretations. It is concluded that the functional success on software simulated neural networks is derived from the underlying computing model. Input values are comparable to multidimensional vectors since they are sequences of values wherein value position in the sequence is as important as the value itself. Interneural connections are numerical matrices instead. Network knowledge is included in the matrices that define each particular network. This structure allows some generalization ability since the response can always be computed for unexpected or incomplete data clusters.
UR - http://www.scopus.com/inward/record.url?scp=0026150380&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0026150380&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0026150380
SN - 0818622253
SP - 599
EP - 601
BT - Computers in Cardiology
PB - Publ by IEEE
ER -