Brain volumes characterisation using hierarchical neural networks
Artificial Intelligence in Medicine
| Hi-index | 0.00 |
Methods of artificial neural networks are applied to the development of the decision support system for differential diagnostics of three types of stroke. Diagnostic sensitivity and positive predictive value were used as the basic criteria for estimation of efficiency of the developed algorithm. Their values appeared to be 97% and 99% respectively, and these results significantly exceed both the existing level of physicians’ diagnostics, and the efficiencies of statistical algorithms developed earlier. C-code was generated, and web-based application was realized. Research of algorithm’s efficiency continues.