Comparison of machine learning algorithms applied to symptoms to determine infectious causes of death in children: national survey of 18,000 verbal autopsies in the Million Death Study in India

Abstract

Background: Machine learning (ML) algorithms have been successfully employed for prediction of outcomes in clinical research. In this study, we have explored the application of ML-based algorithms to predict cause of death (CoD) from verbal autopsy records available through the Million Death Study (MDS).

Methods: From MDS, 18826 unique childhood deaths at ages 1-59 months during the time period 2004-13 were selected for generating the prediction models of which over 70% of deaths were caused by six infectious diseases (pneumonia, diarrhoeal diseases, malaria, fever of unknown origin, meningitis/encephalitis, and measles). Six popular ML-based algorithms such as support vector machine, gradient boosting modeling, C5.0, artificial neural network, k-nearest neighbor, classification and regression tree were used for building the CoD prediction models.

Results: SVM algorithm was the best performer with a prediction accuracy of over 0.8. The highest accuracy was found for diarrhoeal diseases (accuracy = 0.97) and the lowest was for meningitis/encephalitis (accuracy = 0.80). The top signs/symptoms for classification of these CoDs were also extracted for each of the diseases. A combination of signs/symptoms presented by the deceased individual can effectively lead to the CoD diagnosis.

Conclusions: Overall, this study affirms that verbal autopsy tools are efficient in CoD diagnosis and that automated classification parameters captured through ML could be added to verbal autopsies to improve classification of causes of death.

Keywords: Cause of death; Child mortality; Infectious disease; Machine learning; Million Death Study; Prediction model; Verbal autopsy.

Fig. 1

Bubble plot depicting distribution of symptoms across six infectious diseases. X-axis represents disease class and y-axis represents symptoms coded by rule-based method. The bubble size is proportional to percentage of records positive for the symptom in the disease class. The plot was generated using ggplot2 R package [40]

Fig. 2

Tree-based clustering of symptoms for six clusters. The vertical axis represents distance between clusters

Fig. 3

Disease-symptom network of top 10 features obtained from SVM model. Green nodes represent symptoms and blue nodes represent diseases. The size of disease node is proportional to number of records corresponding to the disease in the dataset. Edge represents association between disease and symptom and its width is proportional to percentage of records positive for the symptom. The network was created using igraph R package [48]