Epidemiologic application of verbal autopsy to investigate the high occurrence of cancer along Huai River Basin, China

Abstract

Background: In 2004, the media repeatedly reported water pollution and "cancer villages" along the Huai River in China. Due to the lack of death records for more than 30 years, a retrospective survey of causes of death using verbal autopsy was carried out to investigate cancer rates in this area.

Methods: An epidemiologic study was designed to compare numbers of deaths and causes of death between the study areas with water pollution and the control areas without water pollution in S County and Y District in 2005. The study areas were selected based on the distribution of the Huai River and its tributaries. Verbal autopsy was used to assist cause of death (COD) diagnoses and to verify mortality rates. The standard mortality rates (SMRs) of cancer in the study area were compared with those in the control areas. In order to verify the difference between mortality rates due to cancers in the study and the control areas, patients who reported having cancer in the survey received a second diagnosis by national and provincial oncologists with pathological and laboratory examinations. Comparisons were made to determine if differential cancer prevalence rates in the study and control areas were similar to the difference in mortality due to cancer in these study and control areas. Mortality rates of cancers in study and control areas were also compared with national statistics for the rural population of China.

Results: Over five years, 3,301 deaths were identified, including 1,158 cancer deaths. The annual average SMRs of cancer in the study areas of S County and Y District were 277.8/100,000 and 223.6/100,000, respectively, which is three to four times higher than those in the control areas. In addition, a total of 626 cases of cancer in the study and control areas were confirmed. The prevalence rates of cancer were 545/100,000 and 128.1/100,000 per year in the study and control areas in S County, respectively, and 440.9/100,000 and 200/100,000 per year in the study and control areas in Y District, respectively. The mortality and prevalence rates of digestive cancers were higher in the study areas than the control areas. In 2000, the SMR for cancer in rural areas nationwide was 120.9/100,000, and in study areas in S County and Y District, the excess rates of deaths were 184/100,000 and 138.8/100,000, respectively.

Conclusions: The death rates of digestive cancers were much higher in the study areas of S County and Y District. The patterns for between-area differences in prevalence and mortality rates of cancer were similar. Verbal autopsy is shown to be a useful tool in retrospective mortality surveys in low-resource areas with limited access to health care.

Figure 1

Map of study and control areas in S County and Y District.

Figure 2

Comparison of cause-specific mortality fractions for major causes of death in study and control areas in S County and Y District and rural areas nationwide.

Figure 3

Comparison of mortality and prevalence rates (1/100,000) for all types of cancer and liver cancer in S County and Y District, July 2002-June 2005.