The mortality rates and the space-time patterns of John Snow's cholera epidemic map

Abstract

Background: Snow's work on the Broad Street map is widely known as a pioneering example of spatial epidemiology. It lacks, however, two significant attributes required in contemporary analyses of disease incidence: population at risk and the progression of the epidemic over time. Despite this has been repeatedly suggested in the literature, no systematic investigation of these two aspects was previously carried out. Using a series of historical documents, this study constructs own data to revisit Snow's study to examine the mortality rate at each street location and the space-time pattern of the cholera outbreak.

Methods: This study brings together records from a series of historical documents, and prepares own data on the estimated number of residents at each house location as well as the space-time data of the victims, and these are processed in GIS to facilitate the spatial-temporal analysis. Mortality rates and the space-time pattern in the victims' records are explored using Kernel Density Estimation and network-based Scan Statistic, a recently developed method that detects significant concentrations of records such as the date and place of victims with respect to their distance from others along the street network. The results are visualised in a map form using a GIS platform.

Results: Data on mortality rates and space-time distribution of the victims were collected from various sources and were successfully merged and digitised, thus allowing the production of new map outputs and new interpretation of the 1854 cholera outbreak in London, covering more cases than Snow's original report and also adding new insights into their space-time distribution. They confirmed that areas in the immediate vicinity of the Broad Street pump indeed suffered from excessively high mortality rates, which has been suspected for the past 160 years but remained unconfirmed. No distinctive pattern was found in the space-time distribution of victims' locations.

Conclusions: The high mortality rates identified around the Broad Street pump are consistent with Snow's theory about cholera being transmitted through contaminated water. The absence of a clear space-time pattern also indicates the water-bourne, rather than the then popular belief of air bourne, nature of cholera. The GIS data constructed in this study has an academic value and would cater for further research on Snow's map.

Fig. 1

Estimated residential population in each house at the time of the cholera outbreak

Fig. 2

A map of victim locations including additional records

Fig. 3

Daily number of cholera deaths (August-September 1854)

Fig. 4

Location of victims reported in a Week 3, b Week 4, and c Week 5

Fig. 5

Death from cholera recorded in the study area on a 7 September; b 8 September, c 9 September, and d 12 September 1854

Fig. 6

KDE of the cholera death: a KDE using Snow’s original data (578 cases); b KDE using the new data (623 cases)

Fig. 7

Spatial-temporal KDE: a Week 3, b Week 4, and c Week 5

Fig. 8

a Network clusters based on population at risk, and b Network clusters based on death counts

Fig. 9

An overlay of KDE and the clusters detected through NetScan