Literature DB >> 33874944

Prediction of neonatal deaths in NICUs: development and validation of machine learning models.

Abbas Sheikhtaheri1, Mohammad Reza Zarkesh2,3, Raheleh Moradi4, Farzaneh Kermani5.   

Abstract

BACKGROUND: Prediction of neonatal deaths in NICUs is important for benchmarking and evaluating healthcare services in NICUs. Application of machine learning techniques can improve physicians' ability to predict the neonatal deaths. The aim of this study was to present a neonatal death risk prediction model using machine learning techniques.
METHODS: This study was conducted in Tehran, Iran in two phases. Initially, important risk factors in neonatal death were identified and then several machine learning models including Artificial Neural Network (ANN), decision tree (Random Forest (RF), C5.0 and CHART tree), Support Vector Machine (SVM), Bayesian Network and Ensemble models were developed. Finally, we prospectively applied these models to predict neonatal death in a NICU and followed up the neonates to compare the outcomes of these neonates with real outcomes.
RESULTS: 17 factors were considered important in neonatal mortality prediction. The highest Area Under the Curve (AUC) was achieved for the SVM and Ensemble models with 0.98. The best precision and specificity were 0.98 and 0.94, respectively for the RF model. The highest accuracy, sensitivity and F-score were achieved for the SVM model with 0.94, 0.95 and 0.96, respectively. The best performance of models in prospective evaluation was for the ANN, C5.0 and CHAID tree models.
CONCLUSION: Using the developed machine learning models can help physicians predict the neonatal deaths in NICUs.

Entities:  

Keywords:  Death; Machine learning; Neonate; Prediction

Year:  2021        PMID: 33874944     DOI: 10.1186/s12911-021-01497-8

Source DB:  PubMed          Journal:  BMC Med Inform Decis Mak        ISSN: 1472-6947            Impact factor:   2.796


  18 in total

Review 1.  Machine Learning and Artificial Intelligence: Definitions, Applications, and Future Directions.

Authors:  J Matthew Helm; Andrew M Swiergosz; Heather S Haeberle; Jaret M Karnuta; Jonathan L Schaffer; Viktor E Krebs; Andrew I Spitzer; Prem N Ramkumar
Journal:  Curr Rev Musculoskelet Med       Date:  2020-02

2.  Artificial intelligence, machine learning and deep learning: definitions and differences.

Authors:  D Jakhar; I Kaur
Journal:  Clin Exp Dermatol       Date:  2019-06-24       Impact factor: 3.470

3.  Antenatal prediction of neonatal mortality in very premature infants.

Authors:  Anita C J Ravelli; Jelle M Schaaf; Ben Willem J Mol; Pieter Tamminga; Martine Eskes; Joris A M van der Post; Ameen Abu-Hanna
Journal:  Eur J Obstet Gynecol Reprod Biol       Date:  2014-02-28       Impact factor: 2.435

4.  Postoperative neonatal mortality prediction using superlearning.

Authors:  Jennifer N Cooper; Peter C Minneci; Katherine J Deans
Journal:  J Surg Res       Date:  2018-01       Impact factor: 2.192

5.  A clinical decision support system for prediction of pregnancy outcome in pregnant women with systemic lupus erythematosus.

Authors:  Khadijeh Paydar; Sharareh R Niakan Kalhori; Mahmoud Akbarian; Abbas Sheikhtaheri
Journal:  Int J Med Inform       Date:  2016-11-01       Impact factor: 4.046

6.  Development and validation of the Neonatal Mortality Score-9 Mexico to predict mortality in critically ill neonates.

Authors:  Horacio Márquez-González; María Valeria Jiménez-Báez; C Mireya Muñoz-Ramírez; Lucelli Yáñez-Gutiérrez; Ana C Huelgas-Plaza; Eduardo Almeida-Gutiérrez; Antonio Rafael Villa-Romero
Journal:  Arch Argent Pediatr       Date:  2015-06       Impact factor: 0.694

7.  A prediction model for neonatal mortality in low- and middle-income countries: an analysis of data from population surveillance sites in India, Nepal and Bangladesh.

Authors:  Tanja A J Houweling; David van Klaveren; Sushmita Das; Kishwar Azad; Prasanta Tripathy; Dharma Manandhar; Melissa Neuman; Erik de Jonge; Jasper V Been; Ewout Steyerberg; Anthony Costello
Journal:  Int J Epidemiol       Date:  2019-02-01       Impact factor: 7.196

8.  Prediction of perinatal death using machine learning models: a birth registry-based cohort study in northern Tanzania.

Authors:  Innocent B Mboya; Michael J Mahande; Mohanad Mohammed; Joseph Obure; Henry G Mwambi
Journal:  BMJ Open       Date:  2020-10-19       Impact factor: 2.692

9.  Developing a Fuzzy Expert System to Predict the Risk of Neonatal Death.

Authors:  Reza Safdari; Maliheh Kadivar; Mostafa Langarizadeh; Ahmadreaza Farzaneh Nejad; Farzaneh Kermani
Journal:  Acta Inform Med       Date:  2016-02-02

10.  Predicting Metabolic Syndrome With Machine Learning Models Using a Decision Tree Algorithm: Retrospective Cohort Study.

Authors:  Cheng-Sheng Yu; Yu-Jiun Lin; Chang-Hsien Lin; Sen-Te Wang; Shiyng-Yu Lin; Sanders H Lin; Jenny L Wu; Shy-Shin Chang
Journal:  JMIR Med Inform       Date:  2020-03-23
View more
  4 in total

1.  [Establishment of a predictive nomogram model for predicting the death of very preterm infants during hospitalization].

Authors:  Zhen-Zhen Jue; Juan Song; Zhu-Ye Zhou; Wen-Dong Li; Yu-Yang Yue; Fa-Lin Xu
Journal:  Zhongguo Dang Dai Er Ke Za Zhi       Date:  2022-06-15

2.  Machine Learning Models to Predict In-Hospital Mortality among Inpatients with COVID-19: Underestimation and Overestimation Bias Analysis in Subgroup Populations.

Authors:  Javad Zarei; Amir Jamshidnezhad; Maryam Haddadzadeh Shoushtari; Ali Mohammad Hadianfard; Maria Cheraghi; Abbas Sheikhtaheri
Journal:  J Healthc Eng       Date:  2022-06-23       Impact factor: 3.822

3.  Cardiopulmonary resuscitation of infants at birth: predictable or unpredictable?

Authors:  Mohammad Reza Zarkesh; Raheleh Moradi; Azam Orooji
Journal:  Acute Crit Care       Date:  2022-08-29

4.  Machine Learning Models for Predicting Mortality in 7472 Very Low Birth Weight Infants Using Data from a Nationwide Neonatal Network.

Authors:  Hyun Jeong Do; Kyoung Min Moon; Hyun-Seung Jin
Journal:  Diagnostics (Basel)       Date:  2022-03-03
  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.