Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloNeural networks as a tool to predict syncope risk in the Emergency Department
Anno di pubblicazione2017
Formato
  • Elettronico
  • Cartaceo
Autore/iGiorgio Costantino, Greta Falavigna, Monica Solbiati, Ivo Casagranda, Benjamin C. Sun, Shamai A. Grossman, James V. Quinn, Matthew J. Reed, Andrea Ungar, Nicola Montano, Raffaello Furlan, Roberto Ippoliti
Affiliazioni autoriDipartimento di Medicina Interna e Specializzazioni Mediche, Fondazione IRCCS Ca' Granda, Ospedale Maggiore Policlinico, Via Francesco Sforza 35, 20122 Milano, Italy; CNRIRCrES, Research Institute on Sustainable Economic Growth, Moncalieri, Italy; Dipartimento di Scienze Cliniche e di Comunita, Universita degli Studi di Milano, Milano, Italy; Department of Emergency Medicine, Ospedale di Alessandria, Alessandria, Italy; Department of Emergency Medicine, Center for Policy Research-Emergency Medicine, Oregon Health and Science University, Portland, OR, USA; Department of Emergency Medicine, Harvard Medical School, Beth Israel Deaconess Medical Center, Boston, MA, USA; Division of Emergency Medicine, Stanford University, Stanford, CA, USA; Emergency Medicine Research Group Edinburgh, Royal Infirmary of Edinburgh, Edinburgh, UK; Syncope Unit, Geriatric Medicine and Cardiology, Careggi University Hospital, Firenze, Italy; Department of Biomedical Sciences, Humanitas University--Humanitas Research Hospital, Rozzano, Italy; Ospedale di Alessandria, Alessandria, Italy
Autori CNR e affiliazioni
  • GRETA FALAVIGNA
Lingua/e
  • inglese
AbstractAims There is no universally accepted tool for the risk stratification of syncope patients in the Emergency Department. The aim of this study was to investigate the short-term predictive accuracy of an artificial neural network (ANN) in stratifying the risk in this patient group. ................................................................................................................................................................................................... Methods and results We analysed individual level data from three prospective studies, with a cumulative sample size of 1844 subjects. Each dataset was reanalysed to reduce the heterogeneity among studies defining abnormal electrocardiogram (ECG) and serious outcomes according to a previous consensus. Ten variables from patient history, ECG, and the circumstances of syncope were used to train and test the neural network. Given the exploratory nature of this work, we adopted two approaches to train and validate the tool. One approach used 4/5 of the data for the training set and 1/5 for the validation set, and the other approach used 9/10 for the training set and 1/10 for the validation set. The sensitivity, specificity, and area under the receiver operating characteristic curve of ANNs in identifying short-term adverse events after syncope were 95% [95% confidence interval (CI) 80-98%], 67% (95% CI 62- 72%), 0.69 with the 1/5 approach and 100% (95% CI 84-100%), 79% (95% CI 72-85%), 0.78 with the 1/10 approach. ................................................................................................................................................................................................... Conclusion The results of our study suggest that ANNs are effective in predicting the short-term risk of patients with syncope. Prospective studies are needed in order to compare ANNs' predictive capability with existing rules and clinical judgment.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da1891
Pagine a1895
Pagine totali-
RivistaEuropace (Lond. Engl.)
Attiva dal 1999
Editore: W.B. Saunders, - Philadelphia
Paese di pubblicazione: Regno Unito
Lingua: inglese
ISSN: 1099-5129
Titolo chiave: Europace (Lond. Engl.)
Titolo proprio: Europace (Lond. Engl.)
Titolo abbreviato: Europace (Lond. Engl.)
Titoli alternativi:
  • European pacing, arrhythmias, and cardiac electrophysiology (Lond. Engl.)
  • Epace (Lond. Engl.)
Numero volume della rivista19
Fascicolo della rivista-
DOI10.1093/europace/euw336
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)-
Parole chiaveArtificial neural networks, Syncope, Emergency Department, Risk stratification, Discrimination, Calibration
Link (URL, URI)http://europace.oxfordjournals.org/content/early/2016/12/24/europace.euw336
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione02/10/2016
Note/Altre informazioni-
Strutture CNR
  • IRCRES — Istituto di Ricerca sulla Crescita Economica Sostenibile
Moduli/Attività/Sottoprogetti CNR
  • DUS.AD010.004.001 : Evoluzione del sistema industriale italiano ed europeo
Progetti Europei-
Allegati