2006
DOI: 10.2169/internalmedicine.45.1419
|View full text |Cite
|
Sign up to set email alerts
|

Neural Network Modeling to Stratify Peritoneal Membrane Transporter in Predialytic Patients

Abstract: The artificial neural network (ANN) model is an artificial construct composed of individual nonlinear processing elements arranged in highly interconnected layers based on the paradigm of biological neural networks (1). Every processing element is interconnected through a set of weighted signals similar to the synaptic connections involved in memory 0.727 and 0.880 (p<0.0001). The best sensitivity and specificity were 71.4% (95% CI,.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2008
2008
2024
2024

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 8 publications
(5 citation statements)
references
References 5 publications
0
5
0
Order By: Relevance
“…The average AUROC value observed in the current study compares favourably with previous ANN-based prediction models in medical applications such as predicting psychosis outcomes, predicting response to chemotherapy and classifying tumours (AUROCs 0.70–0.91) [ 13 , 34 , 35 ]. In nephrologic applications, such as screening for glomerulopathy using urine biomarkers, predicting erythropoeitin responsiveness, stratifying PD membrane characteristics and predicting delayed renal allograft dysfunction, AUROC values ranged from 0.65 to 0.95 and sensitivities and specificities ranged from 64 to 92% and 65 to 92%, respectively [ 16–25 ].…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…The average AUROC value observed in the current study compares favourably with previous ANN-based prediction models in medical applications such as predicting psychosis outcomes, predicting response to chemotherapy and classifying tumours (AUROCs 0.70–0.91) [ 13 , 34 , 35 ]. In nephrologic applications, such as screening for glomerulopathy using urine biomarkers, predicting erythropoeitin responsiveness, stratifying PD membrane characteristics and predicting delayed renal allograft dysfunction, AUROC values ranged from 0.65 to 0.95 and sensitivities and specificities ranged from 64 to 92% and 65 to 92%, respectively [ 16–25 ].…”
Section: Discussionmentioning
confidence: 99%
“…ANNs have been used successfully as a prediction tool in a variety of medical and non-medical situations [ 13 ]. In nephrology, ANNs have been used successfully to screen for glomerulopathy using urine biomarkers, to predict erythropoeitin responsiveness, to stratify PD membrane characteristics and to predict delayed renal allograft dysfunction [ 16–25 ].…”
Section: Introductionmentioning
confidence: 99%
“…In this study, calibration was assessed using the HosmerLemeshow goodnessoffit (H) statistic, which divides subjects into deciles based on pre dicted probabilities and then computes chisquare values from the observed and expected frequen cies. [19][20][21] A statistically good fitness was defined as P > 0.05. To provide an unbiased estimate of the models' discrimination and calibration, 22 these val ues were calculated from an external data set derived from anesthesia records for the period of March to June 2008 (in total, 343 records were registered for which general anesthesia was the primary anesthetic technique) that were not used in the modelbuilding processing.…”
Section: External Validation Data Setmentioning
confidence: 99%
“…Since high peritoneal membrane transport status is associated with higher morbidity and mortality, determining peritoneal membrane transport status can result in a better prognosis. A study used artificial neural network (ANN) model for predialytic stratification of 111 uremic patients on the basis of peritoneal membrane transport status from a 5-year PD database [ 18 ]. The evaluation of peritoneal membrane transport status by the ANN model, if predictable before PD, will help clinicians make decisions about more suitable dialysis modality.…”
Section: Clinical Approachmentioning
confidence: 99%