2012
DOI: 10.1186/1471-2466-12-40
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: BackgroundTuberculosis (TB) remains a public health issue worldwide. The lack of specific clinical symptoms to diagnose TB makes the correct decision to admit patients to respiratory isolation a difficult task for the clinician. Isolation of patients without the disease is common and increases health costs. Decision models for the diagnosis of TB in patients attending hospitals can increase the quality of care and decrease costs, without the risk of hospital transmission. We present a predictive model for pred… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
36
0
2

Year Published

2013
2013
2023
2023

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 44 publications
(38 citation statements)
references
References 28 publications
0
36
0
2
Order By: Relevance
“…These algorithms have been used to develop prediction models in various fields. [23][24][25] The CART methodology with the Gini index rule was used for the following 2 models: model 1, a prediction model using a prerehabilitation data set; and model 2, a prediction model using a data set of prerehabilitation and 2 weeks after surgery (see table 1). The pruning rule in the CART included bootstrapped V-fold cross-validation using the…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…These algorithms have been used to develop prediction models in various fields. [23][24][25] The CART methodology with the Gini index rule was used for the following 2 models: model 1, a prediction model using a prerehabilitation data set; and model 2, a prediction model using a data set of prerehabilitation and 2 weeks after surgery (see table 1). The pruning rule in the CART included bootstrapped V-fold cross-validation using the…”
Section: Discussionmentioning
confidence: 99%
“…ADL disabilities, chair-stand-30 (CS-30) test results, and pain intensity at 2 weeks after surgery were included as predictors. ADL disabilities during hospitalization were assessed, since such functional limitations during hospitalization were found to be strong predictors of mortality [17][18][19][20][21][22][23] and long-term care placement. [24][25][26][27] The Barthel Index 19 is an ordinal scale used to measure performance in ADL (ie, feeding oneself, bathing, dressing, grooming, and the ability to move) on a scale of 0 to 100 (0, very dependent; 100, independent).…”
Section: Variablesmentioning
confidence: 99%
“…The main advantages of CART are its simplicity, and the fact that the usage of the variables can be displayed in the tree which better allows the reader to comprehend the data. [40] CART's discriminatory power decreases with each subsequent division. By using PCs obtained from PCA as input variants for CART, we achieve better understanding on the weights of those PCs in the identification of different groups.…”
Section: Discussionmentioning
confidence: 99%
“…Gorunescu (2011) noted that the greatest benefit of decision tree approaches is flexibility, understandability and usefulness in prediction. Delen et al (2005) used a series of decision tree algorithms (ID3, C4.5, C5 (Quinlan, 1993), and CART (Aguiar et al, 2012)) to identify variables and corresponding thresholds which separate observations in branches containing a set of leaves. Delen et al (2005) outlined that the objective of decision tree algorithms is to minimise the number of homogeneous groups, and went on to apply the C5 algorithm to breast cancer data, extracting the most important features for the breast cancer prognosis.…”
Section: Data Mining and Features Filteringmentioning
confidence: 99%