Format

Send to

Choose Destination
PLoS One. 2019 Apr 15;14(4):e0213829. doi: 10.1371/journal.pone.0213829. eCollection 2019.

Machine learning performance in a microbial molecular autopsy context: A cross-sectional postmortem human population study.

Author information

1
Texas A&M University, Department of Computer Science and Engineering, College Station, TX, United States of America.
2
Michigan State University, Department of Entomology, East Lansing, MI, United States of America.
3
Wayne County Medical Examiner's Office, Detroit, MI, United States of America.
4
University of Michigan, Department of Pathology, Ann Arbor, MI, United States of America.
5
Mississippi State University, Department of Biological Sciences, Mississippi State, MS, United States of America.
6
Texas A&M University, Department of Chemistry, College Station, TX, United States of America.
7
Michigan State University, Department of Osteopathic Medical Specialties, East Lansing, MI, United States of America.
8
Michigan State University, Ecology, Evolutionary Biology, and Behavior Program, East Lansing, MI, United States of America.
9
Texas A&M University, Department of Biochemistry and Biophysics, College Station, TX, United States of America.
10
Texas A&M University, Department of Entomology, College Station, TX, United States of America.

Abstract

BACKGROUND:

The postmortem microbiome can provide valuable information to a death investigation and to the human health of the once living. Microbiome sequencing produces, in general, large multi-dimensional datasets that can be difficult to analyze and interpret. Machine learning methods can be useful in overcoming this analytical challenge. However, different methods employ distinct strategies to handle complex datasets. It is unclear whether one method is more appropriate than others for modeling postmortem microbiomes and their ability to predict attributes of interest in death investigations, which require understanding of how the microbial communities change after death and may represent those of the once living host.

METHODS AND FINDINGS:

Postmortem microbiomes were collected by swabbing five anatomical areas during routine death investigation, sequenced and analyzed from 188 death cases. Three machine learning methods (boosted algorithms, random forests, and neural networks) were compared with respect to their abilities to predict case attributes: postmortem interval (PMI), location of death, and manner of death. Accuracy depended on the method used, the numbers of anatomical areas analyzed, and the predicted attribute of death.

CONCLUSIONS:

All algorithms performed well but with distinct features to their performance. Xgboost often produced the most accurate predictions but may also be more prone to overfitting. Random forest was the most stable across predictions that included more anatomic areas. Analysis of postmortem microbiota from more than three anatomic areas appears to yield limited returns on accuracy, with the eyes and rectum providing the most useful information correlating with circumstances of death in most cases for this dataset.

Conflict of interest statement

The authors have declared that no competing interests exist.

Supplemental Content

Full text links

Icon for Public Library of Science Icon for PubMed Central
Loading ...
Support Center