Prediction of major complications affecting very low birth weight infants

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Prediction of major complications affecting very low birth weight infants. / Rinta-Koski, Olli-Pekka; Särkkä, Simo; Hollmen, Jaakko; Leskinen, Markus; Rantakari, Krista; Andersson, Sture.

2017 IEEE LIFE SCIENCES CONFERENCE (LSC). IEEE, 2017. p. 186-189.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Rinta-Koski, O-P, Särkkä, S, Hollmen, J, Leskinen, M, Rantakari, K & Andersson, S 2017, Prediction of major complications affecting very low birth weight infants. in 2017 IEEE LIFE SCIENCES CONFERENCE (LSC). IEEE, pp. 186-189, IEEE Life Sciences Conference, Sydney, Australia, 13/12/2017. https://doi.org/10.1109/LSC.2017.8268174

APA

Rinta-Koski, O-P., Särkkä, S., Hollmen, J., Leskinen, M., Rantakari, K., & Andersson, S. (2017). Prediction of major complications affecting very low birth weight infants. In 2017 IEEE LIFE SCIENCES CONFERENCE (LSC) (pp. 186-189). IEEE. https://doi.org/10.1109/LSC.2017.8268174

Vancouver

Rinta-Koski O-P, Särkkä S, Hollmen J, Leskinen M, Rantakari K, Andersson S. Prediction of major complications affecting very low birth weight infants. In 2017 IEEE LIFE SCIENCES CONFERENCE (LSC). IEEE. 2017. p. 186-189 https://doi.org/10.1109/LSC.2017.8268174

Author

Rinta-Koski, Olli-Pekka ; Särkkä, Simo ; Hollmen, Jaakko ; Leskinen, Markus ; Rantakari, Krista ; Andersson, Sture. / Prediction of major complications affecting very low birth weight infants. 2017 IEEE LIFE SCIENCES CONFERENCE (LSC). IEEE, 2017. pp. 186-189

Bibtex - Download

@inproceedings{09095a00199f4c3aa73bd168c290cd7c,
title = "Prediction of major complications affecting very low birth weight infants",
abstract = "Bronchopulmonary dysplasia (BPD), necrotizing enterocolitis (NEC), and retinopathy of prematurity (ROP) are severe complications affecting Very Low Birth Weight (VLBW) infants. Our findings show that data gathered in the intensive care unit during the first 24 or 72 hours of care can be used to predict whether a VLBW infant is at risk of developing BPD. Using Gaussian process classification, we achieved classification results with areas under the receiver operator characteristic curve of 0.85 (standard error (SE) 0.05) for 24h and 0.87 (SE 0.06) for 72h BPD data. This compares favourably with results achieved using the clinical standard SNAP-II and SNAPPE-II scores. Sensitivity for BPD was 0.52 (SE 0.06). Sensitivity for NEC and ROP was close to zero, suggesting that NEC and ROP can not be reliably predicted with this approach from our data set.",
keywords = "biomedical time series analysis, Gaussian process classification, bronchopulmonary dysplasia, necrotizing enterocolitis, retinopathy of prematurity, neonatal intensive care, very low birth weight infants",
author = "Olli-Pekka Rinta-Koski and Simo S{\"a}rkk{\"a} and Jaakko Hollmen and Markus Leskinen and Krista Rantakari and Sture Andersson",
year = "2017",
doi = "10.1109/LSC.2017.8268174",
language = "English",
pages = "186--189",
booktitle = "2017 IEEE LIFE SCIENCES CONFERENCE (LSC)",
publisher = "IEEE",

}

RIS - Download

TY - GEN

T1 - Prediction of major complications affecting very low birth weight infants

AU - Rinta-Koski, Olli-Pekka

AU - Särkkä, Simo

AU - Hollmen, Jaakko

AU - Leskinen, Markus

AU - Rantakari, Krista

AU - Andersson, Sture

PY - 2017

Y1 - 2017

N2 - Bronchopulmonary dysplasia (BPD), necrotizing enterocolitis (NEC), and retinopathy of prematurity (ROP) are severe complications affecting Very Low Birth Weight (VLBW) infants. Our findings show that data gathered in the intensive care unit during the first 24 or 72 hours of care can be used to predict whether a VLBW infant is at risk of developing BPD. Using Gaussian process classification, we achieved classification results with areas under the receiver operator characteristic curve of 0.85 (standard error (SE) 0.05) for 24h and 0.87 (SE 0.06) for 72h BPD data. This compares favourably with results achieved using the clinical standard SNAP-II and SNAPPE-II scores. Sensitivity for BPD was 0.52 (SE 0.06). Sensitivity for NEC and ROP was close to zero, suggesting that NEC and ROP can not be reliably predicted with this approach from our data set.

AB - Bronchopulmonary dysplasia (BPD), necrotizing enterocolitis (NEC), and retinopathy of prematurity (ROP) are severe complications affecting Very Low Birth Weight (VLBW) infants. Our findings show that data gathered in the intensive care unit during the first 24 or 72 hours of care can be used to predict whether a VLBW infant is at risk of developing BPD. Using Gaussian process classification, we achieved classification results with areas under the receiver operator characteristic curve of 0.85 (standard error (SE) 0.05) for 24h and 0.87 (SE 0.06) for 72h BPD data. This compares favourably with results achieved using the clinical standard SNAP-II and SNAPPE-II scores. Sensitivity for BPD was 0.52 (SE 0.06). Sensitivity for NEC and ROP was close to zero, suggesting that NEC and ROP can not be reliably predicted with this approach from our data set.

KW - biomedical time series analysis

KW - Gaussian process classification

KW - bronchopulmonary dysplasia

KW - necrotizing enterocolitis

KW - retinopathy of prematurity

KW - neonatal intensive care

KW - very low birth weight infants

U2 - 10.1109/LSC.2017.8268174

DO - 10.1109/LSC.2017.8268174

M3 - Conference contribution

SP - 186

EP - 189

BT - 2017 IEEE LIFE SCIENCES CONFERENCE (LSC)

PB - IEEE

ER -

ID: 20479882