Library Subscription: Guest
Begell Digital Portal Begell Digital Library eBooks Journals References & Proceedings Research Collections
Critical Reviews™ in Biomedical Engineering
SJR: 0.243 SNIP: 0.376 CiteScore™: 0.79

ISSN Print: 0278-940X
ISSN Online: 1943-619X

Critical Reviews™ in Biomedical Engineering

DOI: 10.1615/CritRevBiomedEng.2018025933
pages 93-115

Estimation of Caffeine Regimens: A Machine Learning Approach for Enhanced Clinical Decision Making at a Neonatal Intensive Care Unit (NICU)

Rudresh Deepak Shirwaikar
Departments of Computer Science and Engineering, Manipal Institute of Technology, Manipal, India
Dinesh Acharya U
Departments of Computer Science and Engineering, Manipal Institute of Technology, Manipal, India
Krishnamoorthi Makkithaya
Departments of Computer Science and Engineering, Manipal Institute of Technology, Manipal, India
Surulivelrajan Mallayaswamy
Department of Pharmacy Practice, Manipal Academy of Higher Education, Manipal, India
Leslie Edward Simon Lewis
Department of Paediatrics, Manipal Academy of Higher Education, Manipal, India


The decision-making process for estimating the optimal dosage is critical in clinical settings. In the neonatal intensive care unit (NICU), preterm neonates suffering from apnea of prematurity, optimum drug dosage can make a difference between life and death. To improve clinical decision making in the NICU, we have developed prediction models using machine learning algorithms. We have used optimized Support Vector Machine (SVM), decision trees with ensembles created using Bagging, Boosting, Random Forest, optimized Multi Layer Perceptron (MLP) and Deep Learning to predict adequacy of caffeine, a methylxanthine used to prevent the development of recurrent apneas, to reduce the need for mechanical ventilation. The respective models developed were evaluated using 100 clinical caffeine cases collected from the Neonatal Intensive Care Unit (NICU) of Kasturba Medical College, Manipal. Our results indicate that a deep belief network (DBN) having an area under curve (AUC) of 0.91, followed by an optimized MLP with the Score for Neonatal Acute Physiology I (SNAP I) as an input feature, outperform other models for assessing the drug effectiveness. Furthermore, the optimized MLP followed by a DBN, with SNAP I as an input feature is a more accurate model for predicting the therapeutic concentration of caffeine. These results suggest that the proposed SNAP I (illness severity score) acts as a critical input variable to enhance the performance of the prediction model. The machine learning approach is very useful for building decision support systems in the NICU in general, and it provides specific solutions to optimize the administration of lifesaving drugs to neonates who are very sensitive to dosages. Using our method, physicians can assess the adequacy and efficacy of caffeine on the study population in a NICU before administering it to neonates.

Articles with similar content:

A Review of Spasticity Treatments: Pharmacological and Interventional Approaches
Critical Reviews™ in Physical and Rehabilitation Medicine, Vol.25, 2013, issue 1-2
Eric Y. Chang, Daniela Alexandru, Sujin Lee, Tahseen Mozaffar, Daniel Yanni, Nilasha Ghosh
Survey of Spectral Methods of Embedding of Watermarks into Audio Signals
Journal of Automation and Information Sciences, Vol.42, 2010, issue 10
Natalya V. Koshkina
Telecommunications and Radio Engineering, Vol.76, 2017, issue 6
V. V. Barannik, A. N. Alimpiev, S. A. Sidchenko
Shared Use of Vector Quantization and Fractal Coding of Images
Telecommunications and Radio Engineering, Vol.66, 2007, issue 13
A. V. Shmoilov, A. V. Tezin
Symmetrization of Depth Functions for the Construction of Affine-Invariant Classifiers Based on the Depth-Ellipsoidal Neighborhoods
Journal of Automation and Information Sciences, Vol.48, 2016, issue 5
Alexander A. Galkin