1. Cardiac Risk Stratification in Renal Transplantation Using a Form of Artificial Intelligence
- Author
-
John M. Barry, William M. Bennett, Douglas J. Norman, Thomas F Heston, and Richard A. Wilson
- Subjects
Adult ,Male ,medicine.medical_specialty ,Heart Diseases ,neural network ,Stress testing ,risk stratification ,computer.software_genre ,Risk Factors ,Stress test ,Internal medicine ,medicine ,Humans ,Risk factor ,Kidney transplantation ,expert system ,Artificial neural network ,business.industry ,Middle Aged ,renal transplantation ,medicine.disease ,artificial intelligence ,Kidney Transplantation ,Expert system ,expert network ,Transplantation ,Thallium Radioisotopes ,Exercise Test ,Cardiology ,Female ,Artificial intelligence ,Cardiology and Cardiovascular Medicine ,business ,computer ,coronary artery disease ,Follow-Up Studies ,Kidney disease - Abstract
The purpose of this study was to determine if an expertnetwork, a form of artificial intelligence, could effectivelystratify cardiac risk in candidates for renal transplant.Input into the expert network consisted of clinical riskfactors and thallium-201 stress test data. Clinical riskfactor screening alone identified 95 of 189 patients ashigh risk. These 95 patients underwent thallium-201stress testing, and 53 had either reversible or fixed defects.The other 42 patients were classified as low risk.This algorithm made up the ‘‘expert system,’’ and duringthe 4-year follow-up period had a sensitivity of 82%,specificity of 77%, and accuracy of 78%. An artificial neural network was added to the expert system, creatingan expert network. Input into the neural networkconsisted of both clinical variables and thallium-201stress test data. There were 5 hidden nodes and the output(end point) was cardiac death. The expert networkincreased the specificity of the expert system alone from77% to 90% (p
- Published
- 2023
- Full Text
- View/download PDF