Abstract
Background
The work aims to provide a method for assessing newborn infants' risk to determine whether they need to be admitted to the NICU before birth. Term neonates who were admitted to the NICU are known to have health problems, a greater mortality risk, and higher healthcare costs. Researchers want to develop an algorithm that estimates the risk of NICU admission for this particular subset of newborns using an integrated statistical approach. This risk assessment might lower the morbidity, mortality, and healthcare expenses related to NICU hospitalizations by assisting in the early identification of possible instances.
Method
The data was collected from a multispecialty hospital using hospital-based records from the obstetrics and gynecology department. All the clinical and demographic parameters are described as per requirement. A multivariate statistical analysis was done to identify potential risk factors for NICU admission. Four classification models were used to predict NICU admission. All the models were evaluated based on their performance matrices.
Results
In multivariate analysis, we found Preterm deliveries (β = 1.003 Aor = 2.727 95% CI = 1.54,4.80 P < 0.001), Hypertension (β = − 1.419 Aor = 0.242 95% CI = 0.112,0.523 P < 0.001), AFI (β = 1.262 Aor = 3.53 95% CI = 1.06,11.69 P = 0.039), Birth weight (< 2.5 kg) (β = 1.011 Aor = 2.75 95% CI = 1.57,4.81 P < 0.001), Mode of Delivery(LSCS)(β = 1.196 Aor = 3.307 95% CI = 1.95,5.60 P < 0.001) and maternal complication (β = 6.962 OR = 7.69 95% CI = 5.67,13.69 P < 0.001) are the potential risk factors for NICU admission. The decision tree performed the highest accuracy (0.921) and AUC (0.966) as compared to other models to predict NICU admission.
Conclusion
Using an explainable feature learning technique to predict NICU admissions contributes to better global health data utilization and a more hopeful future in healthcare.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs13224-024-02009-0/MediaObjects/13224_2024_2009_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs13224-024-02009-0/MediaObjects/13224_2024_2009_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs13224-024-02009-0/MediaObjects/13224_2024_2009_Fig3_HTML.png)
Abbreviations
- RF:
-
Random forest
- KNN:
-
K nearest neighbor
- LR:
-
Logistic regression
- AFI:
-
Amniotic fluid index
- SVM:
-
Support vector machine
- NICU:
-
Neonatal intensive care unit
References
Varma JR, Nimbalkar SM, Patel D, Phatak AG. The level and sources of stress in mothers of infants admitted in neonatal intensive care unit. Indian J Psychol Med. 2019;41(4):338–42. https://doi.org/10.4103/ijpsym.ijpsym_415_18.
García-Molina P, Balaguer-López E, García-Fernández FP, Ferrera-Fernández MD, Blasco JM, Verdú J. Pressure ulcers’ incidence, preventive measures, and risk factors in neonatal intensive care and intermediate care units. Int Wound J. 2018;15(4):571–9. https://doi.org/10.1111/iwj.12900.
Talisman S, Guedalia J, Farkash R, Avitan T, Srebnik N, Kasirer Y, Schimmel MS, Ghanem D, Unger R, Grisaru GS. NICU admission for term neonates in a large single-center population: a comprehensive assessment of risk factors using a tandem analysis approach. J Clin Med. 2022;11(15):4258. https://doi.org/10.3390/jcm11154258.
Kinney HC, Hefti MM, Goldstein RD, Haynes RL. Sudden infant death syndrome. Dev Neuropathol. 2018. https://doi.org/10.1002/9781119013112.ch25.
Khan AA, Zahidie A, Rabbani F. Interventions to reduce neonatal mortality from neonatal tetanus in low and middle income countries-a systematic review. BMC Public Health. 2013;13(1):1–7. https://doi.org/10.1186/1471-2458-13-322.
Rammohan A, Iqbal K, Awofeso N. Reducing neonatal mortality in India: critical role of access to emergency obstetric care. PLoS ONE. 2013;8(3):e57244. https://doi.org/10.1371/journal.pone.0057244.
Javaid M, Haleem A, Singh RP, Suman R, Rab S. Significance of machine learning in healthcare: Features, pillars and applications. Int J Intell Netw. 2022;3:58–73. https://doi.org/10.1016/j.i**.2022.05.002.
Jung Y, Hu J. AK-fold averaging cross-validation procedure. J Nonparametr Stat. 2015;27(2):167–79. https://doi.org/10.1080/10485252.2015.1010532.
Wong TT. Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recogn. 2015;48(9):2839–46. https://doi.org/10.1016/j.patcog.2015.03.009.
Katz MH. Multivariable analysis: a primer for readers of medical research. Ann Intern Med. 2003;138(8):644–50. https://doi.org/10.7326/0003-4819-138-8-200304150-00012.
Ramadan A, Kamel A, Taha A, El-Shabrawy A, Abdel-Fatah NA. A multivariate data analysis approach for investigating daily statistics of countries affected with COVID-19 pandemic. Heliyon. 2020;6(11):e05575. https://doi.org/10.1016/j.heliyon.2020.e05575.
Mishra A, Harichandrakumar KT, Binu VS, Satheesh S, Nair NS. Multivariate approach in analyzing medical data with correlated multiple outcomes: an exploration using ACCORD trial data. CEGH. 2021;11:100785. https://doi.org/10.1016/j.cegh.2021.100785.
Kim Y, Choi YK, Emery S. Logistic regression with multiple random effects: a simulation study of estimation methods and statistical packages. Am Stat. 2013;67(3):171–82. https://doi.org/10.1080/00031305.2013.817357.
Kumar V, Khosla C. (2018) Data cleaning-A thorough analysis and survey on unstructured data. In: 2018 8th international conference on cloud computing, data science & engineering (Confluence). 305–309. IEEE. https://doi.org/10.1109/CONFLUENCE.2018.8442950
Panda NR. A review on logistic regression in medical research. Natl J Commun Med. 2022;13(04):265–70. https://doi.org/10.55489/njcm.134202222.
Marvin G, Alam MG. Explainable feature learning for predicting neonatal intensive care unit (NICU) admissions. In: 2021 IEEE International conference on biomedical engineering, computer and information technology for health (BECITHCON). 2021; 69–74. IEEE. https://doi.org/10.1109/BECITHCON54710.2021.9893719
Sheikhtaheri A, Zarkesh MR, Moradi R, Kermani F. Prediction of neonatal deaths in NICUs: development and validation of machine learning models. BMC Med Inform Decis Mak. 2021;21(1):1–4. https://doi.org/10.1186/s12911-021-01497-8.
Shovers SM, Bachman SS, Popek L, Turchi RM. Maternal postpartum depression: risk factors, impacts, and interventions for the NICU and beyond. Curr Opin Pediatr. 2021;33(3):331–41. https://doi.org/10.1097/mop.0000000000001011.
Stoelhorst GM, Rijken M, Martens SE, Brand R, den Ouden AL, Wit JM, Veen S, (2005) Leiden Follow-Up Project on Prematurity Changes in neonatology: comparison of two cohorts of very preterm infants (gestational age< 32 weeks): the Project On Preterm and Small for Gestational Age Infants 1983 and the Leiden Follow-Up Project on Prematurity 1996-1997. Pediatrics. 115(2):396-405. https://doi.org/10.1542/peds.2004-1497
Ruth CA, Roos N, Hildes-Ripstein E, Brownell M. The influence of gestational age and socioeconomic status on neonatal outcomes in late preterm and early term gestation: a population based study. BMC Pregnancy Childbirth. 2012;12(1):1–8. https://doi.org/10.1186/1471-2393-12-62.
Chourasia N, Surianarayanan P, Adhisivam B, Vishnu BB. NICU admissions and maternal stress levels. Indian J of Pediatrics. 2013;80:380–4. https://doi.org/10.1007/s12098-012-0921-7.
Acknowledgements
We wish to acknowledge the study participant and the Department of Obstetrics and Gynecology for the necessary help & support for data collection and research.
Funding
No funding provided for this research.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There is no potential conflict of interest.
Ethical Approval
The data were collected using standard treatment protocols, and hence, there was no direct risk to the participants. This study was approved by the Institutional Ethics Committee.
Informed Consent
Informed consent was obtained from all individual participants involved in the study.
Human and Animal Participants
This research was carried out in accordance with the Helsinki Declaration's standards.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Panda, N.R., Mahanta, K.L., Pati, J.K. et al. Development and Validation of Prediction Model for Neonatal Intensive Care Unit (NICU) Admission Using Machine Learning and Multivariate Statistical Approach. J Obstet Gynecol India (2024). https://doi.org/10.1007/s13224-024-02009-0
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13224-024-02009-0