A nested stacking ensemble model for predicting districts with high and low maternal mortality ratio (MMR) in India

  • PDF / 2,213,552 Bytes
  • 14 Pages / 595.276 x 790.866 pts Page_size
  • 32 Downloads / 239 Views

DOWNLOAD

REPORT


ORIGINAL RESEARCH

A nested stacking ensemble model for predicting districts with high and low maternal mortality ratio (MMR) in India Sourabh Shastri1 • Paramjit Kour1 • Sachin Kumar1 • Kuljeet Singh1 Anand Sharma2 • Vibhakar Mansotra1



Received: 15 June 2020 / Accepted: 6 November 2020  Bharati Vidyapeeth’s Institute of Computer Applications and Management 2020

Abstract The ensemble is an efficacious machine learning framework that combines variety of algorithms for better performance and effective prediction. Over the past few years, numerous researchers proposed wide variety of ensemble methodologies in the field of healthcare industry. In the present research paper, a nested ensemble has been suggested based on Stacking and Voting schemes for prediction and analysis of Maternal Mortality Ratio (MMR) in India. The presented nested ensemble combines Base Learners and Meta Learners by employing different classification algorithms and prediction results were afterwards evaluated by using K-fold cross validation and thus, facilitating the statistical distribution of results. Further, the effectiveness of the ensemble was investigated by comparing its performance with the various single learning

Vibhakar Mansotra: Mentor. & Sourabh Shastri [email protected] Paramjit Kour [email protected] Sachin Kumar [email protected] Kuljeet Singh [email protected] Anand Sharma [email protected] Vibhakar Mansotra [email protected] 1

Department of Computer Science and IT, University of Jammu, Jammu and Kashmir, Kathua 184104, India

2

Department of IT and Research, Guru Kashi University, Punjab, India

algorithms in terms of accuracy, precision, recall, F-measure and ROC. Keywords Ensemble  Stacking  Voting  Base learners  Meta learners

1 Introduction India, a low-middle income country is the second most populous country of the world that has been drawing attention concerning health profile. Globally, the Maternal Mortality Ratio (MMR) declined from 385/100,000 live births in 1990 to 216/100,000 in 2015. In a similar timeframe, estimated MMR of India ranged from 556 to 174 per 100,000 live births in between 1990 and 2015 and by 2015, the country contributed to 15% of global maternal deaths [7]. Maternal mortality highlights a health burden on women during and just after pregnancy when women are at risk of complications, particularly in developing countries like India. Maternal Mortality Ratio (MMR) is a standard measure for measuring maternal deaths which mainly occur while a woman is pregnant or within 42 days of the termination of pregnancy, during labor or delivery or after childbirth. These deaths mostly happen due to preventable causes [28, 48] which include ante-partum hemorrhage, postpartum hemorrhage, ruptured uterus, high blood pressure or eclampsia, severe bleeding, infection after termination of pregnancy and pulmonary embolism. The prominent factors like early age marriage or pregnancy, poverty, malnutrition, illiteracy, unsafe abortion and less time gap between two deliveries