- author = "Chris Poulin and Brian Shiner and Paul Thompson and Linas Vepstas and Yinong Young-Xu and Benjamin Goertzel and Bradley Watts and Laura Flashman and Thomas McAllister",
- title = "Predicting the Risk of Suicide by Analyzing the Text of Clinical Notes",
- journal = "PLoS ONE",
- year = "2014",
- volume = "9",
- number = "1",
- pages = "e85733",
- month = jan # " 28",
- keywords = "genetic algorithms, genetic programming, NLP, POSES, MOSES",
- ISSN = "1932-6203",
-
URL = "
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3904866",
-
URL = "http://www.ncbi.nlm.nih.gov/pubmed/24489669",
-
URL = "http://dx.doi.org/10.1371/journal.pone.0085733",
-
DOI = "
doi:10.1371/journal.pone.0085733",
- size = "7 pages",
- abstract = "We developed linguistics-driven prediction models to estimate the risk of suicide. These models were generated from unstructured clinical notes taken from a national sample of U.S. Veterans Administration (VA) medical records. We created three matched cohorts: veterans who committed suicide, veterans who used mental health services and did not commit suicide, and veterans who did not use mental health services and did not commit suicide during the observation period (n = 70 in each group). From the clinical notes, we generated datasets of single keywords and multi-word phrases, and constructed prediction models using a machine-learning algorithm based on a genetic programming framework. The resulting inference accuracy was consistently 65percent or more. Our data therefore suggests that computerised text analytics can be applied to unstructured medical records to estimate the risk of suicide. The resulting system could allow clinicians to potentially screen seemingly healthy patients at the primary care level, and to continuously evaluate the suicide risk among psychiatric patients.",
-
notes = "'This report describes the suicidality prediction
models created under the DARPA DCAPS program in
association with the Durkheim Project
http://durkheimproject.org/' from
http://arxiv.org/abs/1310.6775
'CORRECTION: The first sentence of the Competing interests statement is incorrect. The Competing interests statement should read: CP is President of Patterns and Predictions, whose company in conjunction with PT and LV, has a patent pending in relation to information discussed in the Appendix 1. There are no further patents, products in development or marketed products to declare. This does not alter our adherence to all of the PLOS ONE policies on sharing data and materials.' Published: March 20, 2014
Dartmouth College",
