Predicting mortality risk for preterm infants using deep learning models with time-series vital sign data
Abstract Mortality remains an exceptional burden of extremely preterm birth. Current clinical mortality prediction scores are calculated using a few static variable measurements, such as gestational age, birth weight, temperature, and blood pressure at admission. While these models do provide some i...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-07-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-021-00479-4 |
| _version_ | 1797641790985076736 |
|---|---|
| author | Jiarui Feng Jennifer Lee Zachary A. Vesoulis Fuhai Li |
| author_facet | Jiarui Feng Jennifer Lee Zachary A. Vesoulis Fuhai Li |
| author_sort | Jiarui Feng |
| collection | DOAJ |
| description | Abstract Mortality remains an exceptional burden of extremely preterm birth. Current clinical mortality prediction scores are calculated using a few static variable measurements, such as gestational age, birth weight, temperature, and blood pressure at admission. While these models do provide some insight, numerical and time-series vital sign data are also available for preterm babies admitted to the NICU and may provide greater insight into outcomes. Computational models that predict the mortality risk of preterm birth in the NICU by integrating vital sign data and static clinical variables in real time may be clinically helpful and potentially superior to static prediction models. However, there is a lack of established computational models for this specific task. In this study, we developed a novel deep learning model, DeepPBSMonitor (Deep Preterm Birth Survival Risk Monitor), to predict the mortality risk of preterm infants during initial NICU hospitalization. The proposed deep learning model can effectively integrate time-series vital sign data and fixed variables while resolving the influence of noise and imbalanced data. The proposed model was evaluated and compared with other approaches using data from 285 infants. Results showed that the DeepPBSMonitor model outperforms other approaches, with an accuracy, recall, and AUC score of 0.888, 0.780, and 0.897, respectively. In conclusion, the proposed model has demonstrated efficacy in predicting the real-time mortality risk of preterm infants in initial NICU hospitalization. |
| first_indexed | 2024-03-11T13:50:47Z |
| format | Article |
| id | doaj.art-f6e5f1a2356849fd9a78f78113584b38 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-11T13:50:47Z |
| publishDate | 2021-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-f6e5f1a2356849fd9a78f78113584b382023-11-02T09:20:53ZengNature Portfolionpj Digital Medicine2398-63522021-07-01411810.1038/s41746-021-00479-4Predicting mortality risk for preterm infants using deep learning models with time-series vital sign dataJiarui Feng0Jennifer Lee1Zachary A. Vesoulis2Fuhai Li3Institute for Informatics, Washington University School of MedicineWashington University School of MedicineDepartment of Pediatrics, Division of Newborn Medicine, Washington University School of MedicineInstitute for Informatics, Washington University School of MedicineAbstract Mortality remains an exceptional burden of extremely preterm birth. Current clinical mortality prediction scores are calculated using a few static variable measurements, such as gestational age, birth weight, temperature, and blood pressure at admission. While these models do provide some insight, numerical and time-series vital sign data are also available for preterm babies admitted to the NICU and may provide greater insight into outcomes. Computational models that predict the mortality risk of preterm birth in the NICU by integrating vital sign data and static clinical variables in real time may be clinically helpful and potentially superior to static prediction models. However, there is a lack of established computational models for this specific task. In this study, we developed a novel deep learning model, DeepPBSMonitor (Deep Preterm Birth Survival Risk Monitor), to predict the mortality risk of preterm infants during initial NICU hospitalization. The proposed deep learning model can effectively integrate time-series vital sign data and fixed variables while resolving the influence of noise and imbalanced data. The proposed model was evaluated and compared with other approaches using data from 285 infants. Results showed that the DeepPBSMonitor model outperforms other approaches, with an accuracy, recall, and AUC score of 0.888, 0.780, and 0.897, respectively. In conclusion, the proposed model has demonstrated efficacy in predicting the real-time mortality risk of preterm infants in initial NICU hospitalization.https://doi.org/10.1038/s41746-021-00479-4 |
| spellingShingle | Jiarui Feng Jennifer Lee Zachary A. Vesoulis Fuhai Li Predicting mortality risk for preterm infants using deep learning models with time-series vital sign data npj Digital Medicine |
| title | Predicting mortality risk for preterm infants using deep learning models with time-series vital sign data |
| title_full | Predicting mortality risk for preterm infants using deep learning models with time-series vital sign data |
| title_fullStr | Predicting mortality risk for preterm infants using deep learning models with time-series vital sign data |
| title_full_unstemmed | Predicting mortality risk for preterm infants using deep learning models with time-series vital sign data |
| title_short | Predicting mortality risk for preterm infants using deep learning models with time-series vital sign data |
| title_sort | predicting mortality risk for preterm infants using deep learning models with time series vital sign data |
| url | https://doi.org/10.1038/s41746-021-00479-4 |
| work_keys_str_mv | AT jiaruifeng predictingmortalityriskforpreterminfantsusingdeeplearningmodelswithtimeseriesvitalsigndata AT jenniferlee predictingmortalityriskforpreterminfantsusingdeeplearningmodelswithtimeseriesvitalsigndata AT zacharyavesoulis predictingmortalityriskforpreterminfantsusingdeeplearningmodelswithtimeseriesvitalsigndata AT fuhaili predictingmortalityriskforpreterminfantsusingdeeplearningmodelswithtimeseriesvitalsigndata |