A Recommendation System to Enhance Midwives' Capacities in Low-Income Countries

Maternal and child mortality is a public health problem that disproportionately affects lowand middle-income countries. Every day, 800 women and 6,700 newborns die from complications related to pregnancy or childbirth. And for every maternal death, about 20 women suffer serious birth injuries. However, nearly all of these deaths and negative health outcomes are preventable. Midwives are key to revert this situation, and thus it is essential to strengthen their capacities and the quality of their education. This is the aim of the Safe Delivery App, a digital job aid and learning tool to enhance the knowledge, confidence and skills of health practitioners. Here, we use the behavioral logs of the App to implement a recommendation system that presents each midwife with suitable contents to continue gaining expertise. We focus on predicting the click-through rate, the probability that a given user will click on a recommended content. We evaluate four deep learning models and show that all of them produce highly accurate predictions.

[1]  Steffen Rendle,et al.  Factorization Machines , 2010, 2010 IEEE International Conference on Data Mining.

[2]  Alexei Botchkarev,et al.  A New Typology Design of Performance Metrics to Measure Errors in Machine Learning Regression Algorithms , 2019, Interdisciplinary Journal of Information, Knowledge, and Management.

[3]  David L. Blazes,et al.  Four steps to precision public health , 2016, Nature.

[4]  Gang Fu,et al.  Deep & Cross Network for Ad Click Predictions , 2017, ADKDD@KDD.

[5]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[6]  Yunming Ye,et al.  DeepFM: A Factorization-Machine based Neural Network for CTR Prediction , 2017, IJCAI.

[7]  David L Buckeridge,et al.  Precision, Equity, and Public Health and Epidemiology Informatics – A Scoping Review , 2020, Yearbook of Medical Informatics.

[8]  Chih-Jen Lin,et al.  Field-aware Factorization Machines for CTR Prediction , 2016, RecSys.

[9]  H. S. Nielsen,et al.  Association Between the Safe Delivery App and Quality of Care and Perinatal Survival in Ethiopia: A Randomized Clinical Trial. , 2016, JAMA pediatrics.

[10]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[11]  C. Homer,et al.  Potential impact of midwives in preventing and reducing maternal and neonatal mortality and stillbirths: a Lives Saved Tool modelling study , 2020, The Lancet. Global health.

[12]  Shawn Dolley,et al.  Big Data’s Role in Precision Public Health , 2018, Front. Public Health.

[13]  Wang Jun,et al.  Product-Based Neural Networks for User Response Prediction , 2016 .

[14]  Xing Xie,et al.  xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems , 2018, KDD.

[15]  Bo Yuan,et al.  A Dual Input-aware Factorization Machine for CTR Prediction , 2020, IJCAI.

[16]  Siobhan O'Connor,et al.  Big data and data science in health care: What nurses and midwives need to know. , 2018, Journal of clinical nursing.

[17]  Anna Guitart,et al.  Midwifery Learning and Forecasting: Predicting Content Demand with User-Generated Logs , 2021, ArXiv.

[18]  Yantao Yu,et al.  An Input-aware Factorization Machine for Sparse Prediction , 2019, IJCAI.

[19]  Cristiano Roberto Cervi,et al.  Recommender systems in mobile apps for health a systematic review , 2017, 2017 12th Iberian Conference on Information Systems and Technologies (CISTI).

[20]  Jun Wang,et al.  Product-Based Neural Networks for User Response Prediction , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[21]  Anna Guitart,et al.  A Machine-Learning Item Recommendation System for Video Games , 2018, 2018 IEEE Conference on Computational Intelligence and Games (CIG).