When a person chooses a healthcare provider, they are trading off cost, convenience, and a latent third factor: “perceived quality”. In urban areas of lower- and middle-income countries (LMICs), including slums, individuals have a wide range of choice in healthcare provider, and we hypothesised that people do not choose the nearest and cheapest provider. This would mean that people are willing to incur additional cost to visit a provider they would perceive to be offering better healthcare. In this article, we aim to develop a method towards quantifying this notion of “perceived quality” by using a generalised access cost calculation to combine monetary and time costs relating to a visit, and then using this calculated access cost to observe facilities that have been bypassed. The data to support this analysis comes from detailed survey data in four slums, where residents were questioned on their interactions with healthcare services, and providers were surveyed by our team. We find that people tend to bypass more informal local services to access more formal providers, especially public hospitals. This implies that public hospitals, which tend to incur higher access costs, have the highest perceived quality (i.e., people are more willing to trade cost and convenience to visit these services). Our findings therefore provide evidence that can support the ‘crowding out’ hypothesis first suggested in a 2016 Lancet Series on healthcare provision in LMICs.

Shortest path queries over graphs are usually considered as isolated tasks, where the goal is to return the shortest path for each individual query. In practice, however, such queries are typically part of a system (e.g., a road network) and their execution dynamically affects other queries and network parameters, such as the loads on edges, which in turn affects the shortest paths. We study the problem of collectively processing shortest path queries, where the objective is to optimize a collective objective, such as minimizing the overall cost. We define a temporal load-aware network that dynamically tracks expected loads while satisfying the desirable 'first in, first out' property. We develop temporal load-aware extensions of widely used shortest path algorithms, and a scalable collective routing solution that seeks to reduce system-wide congestion through dynamic path reassignment. Experiments illustrate that our collective approach to this NP-hard problem achieves improvements in a variety of performance measures, such as, i) reducing average travel times by up to 63%, ii) producing fairer suggestions across queries, and iii) distributing load across up to 97% of a city's road network capacity. The proposed approach is generalizable, which allows it to be adapted for other concurrent query processing tasks over networks.

Understanding the cost of accessing services in a transit network, and how this varies spatially and temporally is vital for transport agencies to make effective decisions. However, to understand this at the city-scale typically demands the computation of a very large number of shortest path queries, which is computationally infeasible in a practical setting. In this work we define the notion of an access query, an analytical query which returns the aggregate access costs to a set of points of interest within a given time interval. To solve the computational bottleneck, we develop a solution that uses semi-supervised machine learning to efficiently compute these aggregate access costs using a gravity-model. The solution dynamically generates a descriptive representation of the connectivity between origins and destinations in a multi-modal network, and dynamically labels a small subset of the overall trips which are used to form a target vector for the learning algorithm. We also consider the fair distribution of access across spatio-temporal dimensions. The solution can reduce processing times by up to 97%, while maintaining high levels of accuracy; the predicted journey times to services are accurate to within 3.3 minutes, and a high level of correlation (85%) to the ground truth is achieved.