Efficient performance of neural network models as artificial intelligence prediction tools in cardiology

D. Cianflone, O. Carandente, M. Carlino, C. Meloni, S. L. Chierchia

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

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 languageEnglish
Title of host publicationComputers in Cardiology
PublisherPubl by IEEE
Pages599-601
Number of pages3
ISBN (Print)0818622253
Publication statusPublished - May 1991
EventComputers in Cardiology - Proceedings - Chicago, IL, USA
Duration: Sep 23 1990Sep 26 1990

Other

OtherComputers in Cardiology - Proceedings
CityChicago, IL, USA
Period9/23/909/26/90

Fingerprint

Cardiology
Neural Networks (Computer)
Artificial Intelligence
Single-Photon Emission-Computed Tomography
Artificial intelligence
Neural networks
Exercise Test
Software
Perfusion

ASJC Scopus subject areas

  • Software
  • Cardiology and Cardiovascular Medicine

Cite this

Cianflone, D., Carandente, O., Carlino, M., Meloni, C., & Chierchia, S. L. (1991). Efficient performance of neural network models as artificial intelligence prediction tools in cardiology. In Computers in Cardiology (pp. 599-601). Publ by IEEE.

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 proceedingConference contribution

Cianflone, D, Carandente, O, Carlino, M, Meloni, C & Chierchia, SL 1991, Efficient performance of neural network models as artificial intelligence prediction tools in cardiology. in Computers in Cardiology. Publ by IEEE, pp. 599-601, Computers in Cardiology - Proceedings, Chicago, IL, USA, 9/23/90.
Cianflone D, Carandente O, Carlino M, Meloni C, Chierchia SL. Efficient performance of neural network models as artificial intelligence prediction tools in cardiology. In Computers in Cardiology. Publ by IEEE. 1991. p. 599-601
Cianflone, D. ; Carandente, O. ; Carlino, M. ; Meloni, C. ; Chierchia, S. L. / Efficient performance of neural network models as artificial intelligence prediction tools in cardiology. Computers in Cardiology. Publ by IEEE, 1991. pp. 599-601
@inproceedings{7d39459b0b0a415a9b8c15d9a3a62588,
title = "Efficient performance of neural network models as artificial intelligence prediction tools in cardiology",
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.",
author = "D. Cianflone and O. Carandente and M. Carlino and C. Meloni and Chierchia, {S. L.}",
year = "1991",
month = "5",
language = "English",
isbn = "0818622253",
pages = "599--601",
booktitle = "Computers in Cardiology",
publisher = "Publ by IEEE",

}

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

SN - 0818622253

SP - 599

EP - 601

BT - Computers in Cardiology

PB - Publ by IEEE

ER -