scholarly journals Predicting in-hospital length of stay for very-low-birth-weight preterm infants using machine learning techniques

Author(s):  
Wei-Ting Lin ◽  
Tsung-Yu Wu ◽  
Yen-Ju Chen ◽  
Yu-Shan Chang ◽  
Chyi-Her Lin ◽  
...  
Author(s):  
Monica Eneriz-Wiemer ◽  
Lee Sanders ◽  
Mary McIntyre ◽  
Fernando Mendoza ◽  
D. Do ◽  
...  

To ensure timely appropriate care for low-birth-weight (LBW) infants, healthcare providers must communicate effectively with parents, even when language barriers exist. We sought to evaluate whether non-English primary language (NEPL) and professional in-person interpreter use were associated with differential hospital length of stay for LBW infants, who may incur high healthcare costs. We analyzed data for 2047 infants born between 1 January 2008 and 30 April 2013 with weight <2500 g at one hospital with high NEPL prevalence. We evaluated relationships of NEPL and in-person interpreter use on length of stay, adjusting for medical severity. Overall, 396 (19%) had NEPL parents. Fifty-three percent of NEPL parents had documented interpreter use. Length of stay ranged from 1 to 195 days (median 11). Infants of NEPL parents with no interpreter use had a 49% shorter length of stay (adjusted incidence rate ratio (IRR) 0.51, 95% confidence interval (CI) 0.43–0.61) compared to English-speakers. Infants of parents with NEPL and low interpreter use (<25% of hospital days) had a 26% longer length of stay (adjusted IRR 1.26, 95% CI 1.06–1.51). NEPL and high interpreter use (>25% of hospital days) showed a trend for an even longer length of stay. Unmeasured clinical and social/cultural factors may contribute to differences in length of stay.


PLoS ONE ◽  
2015 ◽  
Vol 10 (6) ◽  
pp. e0131685 ◽  
Author(s):  
Dino Numerato ◽  
Giovanni Fattore ◽  
Fabrizio Tediosi ◽  
Rinaldo Zanini ◽  
Mikko Peltola ◽  
...  

PLoS ONE ◽  
2017 ◽  
Vol 12 (5) ◽  
pp. e0177040
Author(s):  
Dino Numerato ◽  
Giovanni Fattore ◽  
Fabrizio Tediosi ◽  
Rinaldo Zanini ◽  
Mikko Peltola ◽  
...  

2018 ◽  
Vol 3 (1) ◽  
pp. 18 ◽  
Author(s):  
Alfensi Faruk ◽  
Endro Setyo Cahyono

Machine learning (ML) is a subject that focuses on the data analysis using various statistical tools and learning processes in order to gain more knowledge from the data. The objective of this research was to apply one of the ML techniques on the low birth weight (LBW) data in Indonesia. This research conducts two ML tasks; including prediction and classification. The binary logistic regression model was firstly employed on the train and the test data. Then; the random approach was also applied to the data set. The results showed that the binary logistic regression had a good performance for prediction; but it was a poor approach for classification. On the other hand; random forest approach has a very good performance for both prediction and classification of the LBW data set


Author(s):  
Luciana Volpiano Fernandes ◽  
Ana Lucia Goulart ◽  
Amélia Miyashiro Nunes dos Santos ◽  
Marina Carvalho de Moraes Barros ◽  
Camila Campos Guerra ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document