Open Access Open Access  Restricted Access Subscription Access

Computer Aided Detection System for Prediction of the Malaise during Hemodialysis


Affiliations
1 Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Via Orabona 4, 70125 Bari, Italy
2 Dipartimento Interateneo di Fisica “M. Merlin”, Universit'a degli studi di Bari “A.Moro”, Via Orabona 4, 70125 Bari, Italy
3 Nephrology, Dialysis and Transplantation Unit, University of Bari “A. Moro”, Piazza G. Cesare, 11 – Policlinico, 70124 Bari, Italy
4 Department of Physical Sciences, Earth and Environment, University of Siena, Strada Laterina 8, 53100 Siena, Italy
 

Monitoring of dialysis sessions is crucial as different stress factors can yield suffering or critical situations. Specialized personnel is usually required for the administration of this medical treatment; nevertheless, subjects whose clinical status can be considered stable require different monitoring strategies when compared with subjects with critical clinical conditions. In this case domiciliary treatment or monitoring can substantially improve the quality of life of patients undergoing dialysis. In this work, we present a Computer Aided Detection (CAD) system for the telemonitoring of patients’ clinical parameters. The CAD was mainly designed to predict the insurgence of critical events; it consisted of two Random Forest (RF) classifiers: the first one (RF1) predicting the onset of any malaise one hour after the treatment start and the second one (RF2) again two hours later. The developed system shows an accurate classification performance in terms of both sensitivity and specificity. The specificity in the identification of nonsymptomatic sessions and the sensitivity in the identification of symptomatic sessions for RF2 are equal to 86.60% and 71.40%, respectively, thus suggesting the CAD as an effective tool to support expert nephrologists in telemonitoring the patients.
User
Notifications
Font Size

Abstract Views: 115

PDF Views: 3




  • Computer Aided Detection System for Prediction of the Malaise during Hemodialysis

Abstract Views: 115  |  PDF Views: 3

Authors

Sabina Tangaro
Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Via Orabona 4, 70125 Bari, Italy
Annarita Fanizzi
Dipartimento Interateneo di Fisica “M. Merlin”, Universit'a degli studi di Bari “A.Moro”, Via Orabona 4, 70125 Bari, Italy
Nicola Amoroso
Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Via Orabona 4, 70125 Bari, Italy
Roberto Corciulo
Nephrology, Dialysis and Transplantation Unit, University of Bari “A. Moro”, Piazza G. Cesare, 11 – Policlinico, 70124 Bari, Italy
Elena Garuccio
Department of Physical Sciences, Earth and Environment, University of Siena, Strada Laterina 8, 53100 Siena, Italy
Loreto Gesualdo
Nephrology, Dialysis and Transplantation Unit, University of Bari “A. Moro”, Piazza G. Cesare, 11 – Policlinico, 70124 Bari, Italy
Giuliana Loizzo
Nephrology, Dialysis and Transplantation Unit, University of Bari “A. Moro”, Piazza G. Cesare, 11 – Policlinico, 70124 Bari, Italy
Deni Aldo Procaccini
Nephrology, Dialysis and Transplantation Unit, University of Bari “A. Moro”, Piazza G. Cesare, 11 – Policlinico, 70124 Bari, Italy
Lucia Verno
Nephrology, Dialysis and Transplantation Unit, University of Bari “A. Moro”, Piazza G. Cesare, 11 – Policlinico, 70124 Bari, Italy
Roberto Bellotti
Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Via Orabona 4, 70125 Bari, Italy

Abstract


Monitoring of dialysis sessions is crucial as different stress factors can yield suffering or critical situations. Specialized personnel is usually required for the administration of this medical treatment; nevertheless, subjects whose clinical status can be considered stable require different monitoring strategies when compared with subjects with critical clinical conditions. In this case domiciliary treatment or monitoring can substantially improve the quality of life of patients undergoing dialysis. In this work, we present a Computer Aided Detection (CAD) system for the telemonitoring of patients’ clinical parameters. The CAD was mainly designed to predict the insurgence of critical events; it consisted of two Random Forest (RF) classifiers: the first one (RF1) predicting the onset of any malaise one hour after the treatment start and the second one (RF2) again two hours later. The developed system shows an accurate classification performance in terms of both sensitivity and specificity. The specificity in the identification of nonsymptomatic sessions and the sensitivity in the identification of symptomatic sessions for RF2 are equal to 86.60% and 71.40%, respectively, thus suggesting the CAD as an effective tool to support expert nephrologists in telemonitoring the patients.