A probabilistic approach to interpreting verbal autopsies: methodology and preliminary validation in Vietnam

Abstract

Scand J Public Health 2003; 31(Suppl. 62): 32-37 Aims: Verbal autopsy (VA) has become an important tool in the past 20 years for determining cause of death in communities where there is no routine registration. In many cases, expert physicians have been used to interpret the VA findings and so assign individual causes of death. However, this is time consuming and not always repeatable. Other approaches such as algorithms and neural networks have been developed in some settings. This paper aims to develop a method that is simple, reliable and consistent, which could represent an advance in VA interpretation. Methods: This paper describes the development of a Bayesian probability model for VA interpretation as an attempt to find a better approach. This methodology and a preliminary implementation are described, with an evaluation based on VA material from rural Vietnam. Results: The new model was tested against a series of 189 VA interviews from a rural community in Vietnam. Using this very basic model, over 70% of individual causes of death corresponded with those determined by two physicians, increasing to over 80% if those cases ascribed to old age or as being indeterminate by the physicians were excluded. Discussion: Although there is a clear need to improve the preliminary model and to test more extensively with larger and more varied datasets, these preliminary results suggest that there may be good potential in this probabilistic approach.

Analysis of the childhood fatal drowning situation in Bangladesh: exploring prevention measures for low-income countries

“…Verbal autopsy, which was used in this study, is considered a useful tool for ascertaining causes of death in settings where the proportion of people who die under medical care is low and there is no routine registration 20 21…”

Verbal autopsy

“…31 A Bayesian approach to defining the probability of a given cause of death in the presence of a particular symptom or sign could improve the performance of expert algorithms. 30,32 A model for selected causes of death using this apt t proach showed a 90% concordance with causes of death derived by physician review. 32 However, this approach has not been validated against a gold standard such as diagnoses from hospital records.…”

“…15 Ascertaining causes of large numbers of deaths by physician review is both timet consuming and costtineffective. 30 Algorithms would increase the relit t ability of VA tools and allow automation of the causetoftdeath coding process. Expert algorithms are predefined diagt t nostic criteria agreed to by a panel of physicians.…”

The InterVA model: verbal autopsy interpretation in rural Ethiopia

“…1 A new probabilistic approach has recently been proposed that has given promising preliminary results. 2,3 This approach ap--plies Bayes' theorem to VA interpretation in an attempt to overcome concerns associ--ated with expert assessment while also addressing the limitations of algorithmic approaches. This model has already been evaluated on a preliminary basis in Viet Nam, 2 and is now known as InterVA.…”

“…2,3 This approach ap--plies Bayes' theorem to VA interpretation in an attempt to overcome concerns associ--ated with expert assessment while also addressing the limitations of algorithmic approaches. This model has already been evaluated on a preliminary basis in Viet Nam, 2 and is now known as InterVA. Data on deaths in the community have been collected at the Butajira Rural Health Program (BRHP) Demographic Surveillance Site (DSS) since 1987.…”