Header

UZH-Logo

Maintenance Infos

Prediction of lumbar disc herniation patients' satisfaction with the aid of an artificial neural network


Matis, Georgios K; Chrysou, Olga I; Silva, Danilo; Karanikas, Michail A; Baltsavias, Gerasimos; Lyratzopoulos, Nikolaos; Baroutas, Spyridon; Birbilis, Theodossios A (2016). Prediction of lumbar disc herniation patients' satisfaction with the aid of an artificial neural network. Turkish neurosurgery, 26(2):253-259.

Abstract

AIM: To identify key determinants of lumbar disc herniation (LDH) patients' satisfaction and to evaluate the efficiency of an artificial neural network (ANN) model to prognosticate satisfaction derived from the hospital stay in this specific patient group.
MATERIAL AND METHODS: A single item question was used to assess patient satisfaction. Principal component analysis evaluated several aspects of care (15 items). An ANN encompassed all variables and its prediction ability was tested. The ANN performance was correlated to a binary logistic regression (BLR) model.
RESULTS: Higher levels of satisfaction were reported by females, older patients, Greeks, and patients with elementary education staying in not rural areas. A history of a single previous hospitalisation was correlated with more satisfaction. The accuracy of ANN was 96% for satisfaction prediction outperforming the BLR model.
CONCLUSION: Satisfactory health services are influenced by sex, age, nationality, and number of prior admissions. The self-perceived health state plays also a crucial role. The current study is the first one reporting on the capability of an ANN to accurately predict the satisfaction levels of LDH patients.

Abstract

AIM: To identify key determinants of lumbar disc herniation (LDH) patients' satisfaction and to evaluate the efficiency of an artificial neural network (ANN) model to prognosticate satisfaction derived from the hospital stay in this specific patient group.
MATERIAL AND METHODS: A single item question was used to assess patient satisfaction. Principal component analysis evaluated several aspects of care (15 items). An ANN encompassed all variables and its prediction ability was tested. The ANN performance was correlated to a binary logistic regression (BLR) model.
RESULTS: Higher levels of satisfaction were reported by females, older patients, Greeks, and patients with elementary education staying in not rural areas. A history of a single previous hospitalisation was correlated with more satisfaction. The accuracy of ANN was 96% for satisfaction prediction outperforming the BLR model.
CONCLUSION: Satisfactory health services are influenced by sex, age, nationality, and number of prior admissions. The self-perceived health state plays also a crucial role. The current study is the first one reporting on the capability of an ANN to accurately predict the satisfaction levels of LDH patients.

Statistics

Altmetrics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Clinic for Neuroradiology
Dewey Decimal Classification:610 Medicine & health
Language:English
Date:2016
Deposited On:08 Feb 2017 11:05
Last Modified:08 Feb 2017 11:05
Publisher:Turk Norosirurji Dernegi
ISSN:1019-5149
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.5137/1019-5149.JTN.8492-13.0
PubMed ID:26956822

Download

Full text not available from this repository.
View at publisher