Demand sensing and digital tracking for maternal child health (MCH) in Uganda: a pilot study for 'E+TRA health'.

BACKGROUND: Thirteen essential maternal child health (MCH) commodities, identified by the UN Commission on Life-Saving Commodities for Women and Children, could save the lives of more than 6 million women and children in Low-and-Middle-Income Countries (LMICs) if made available at the point of care. To reduce stockout of those commodities and improve the health supply chains in LMICs, the Electronic TRAcking system for healthcare commodities (E+TRA Health), an all-in-one out-of-box solution, was developed to track and manage medical commodities at lower-level health facilities in rural areas. It aims to support real-time monitoring and decision-making to (1) reduce the time needed to prepare orders, (2) reduce stockout and overstock cases of targeted medical supplies, (3) help improve patient outcomes. In this study, we adopted an integrated approach to analyze the process of information flow, identify and address critical paths of essential supplies associated with maternal health in the Ugandan health system. METHODS: We apply system engineering principles and work with community partners in hospitals to develop care process workflow charts (based on essential services) for the lifecycle of maternal health continuum of care. Based on this chart, we develop a cloud-based offline-compatible smart sync platform named "E+TRA Health" to triangulate (1) patient admission, diagnoses, delivery information, testing reports from laboratories, (2) inventory information from main store, stores in MCH unit, and (3) lab, to identify the critical list of medical and laboratory supplies, their lead times for procurement and then generate reports and suggested procurement plans for real time decision-making. RESULTS: The E+TRA Health platform was piloted in two Healthcare Center IV facilities in Uganda over a period of 6 months. The system collected more than 5000 patient records and managed more than 500 types of medicines. The pilot study demonstrated the functionalities of E+TRA Health and its feasibility to sense demand from point of care. CONCLUSION: E+TRA Health is the first to triangulate supply and demand data from three different departments (main store, lab, and MCH) to forecast and generate orders automatically to meet patient demands. It is capable of generating reports required by Ministry of Health in real time compared to one-week lead-time using paper-based systems. This prompts frontline stakeholders to generate efficient, reliable and sustainable strategic healthcare plans with real time data. This system improves patient outcomes through better commodity availability by sensing true patient demands.

Evolutionary Algorithm for Improving Decision Tree with Global Discretization in Manufacturing.

Due to the recent advance in the industrial Internet of Things (IoT) in manufacturing, the vast amount of data from sensors has triggered the need for leveraging such big data for fault detection. In particular, interpretable machine learning techniques, such as tree-based algorithms, have drawn attention to the need to implement reliable manufacturing systems, and identify the root causes of faults. However, despite the high interpretability of decision trees, tree-based models make a trade-off between accuracy and interpretability. In order to improve the tree's performance while maintaining its interpretability, an evolutionary algorithm for discretization of multiple attributes, called Decision tree Improved by Multiple sPLits with Evolutionary algorithm for Discretization (DIMPLED), is proposed. The experimental results with two real-world datasets from sensors showed that the decision tree improved by DIMPLED outperformed the performances of single-decision-tree models (C4.5 and CART) that are widely used in practice, and it proved competitive compared to the ensemble methods, which have multiple decision trees. Even though the ensemble methods could produce slightly better performances, the proposed DIMPLED has a more interpretable structure, while maintaining an appropriate performance level.