John P. Pestian
ABSTRACT
We hypothesize that machine-learning algorithms (MLA) can classify completer and simulated suicide notes as well as mental health professionals (MHP). Five MHPs classified 66 simulated or completer notes; MLAs were used for the same task. Results: MHPs were accurate 71% of the time; using the sequential minimization optimization algorithm (SMO) MLAs were accurate 78% of the time. There was no significant difference between the MLA and MPH classifiers. This is an important first step in developing an evidence based suicide predictor for emergency department use.
- Jeffrey A Bridge, Tina R Goldstein, and David A Brent. Adolescent suicide and suicidal behavior. J Child Psychol Psychiatry, 47(3--4):372--394, 2006.Google Scholar
Cross Ref
- P M Lewinsohn, P Rohde, and J R Seeley. Psychosocial risk factors for future adolescent suicide attempts. J Consult Clin Psychol, 62(2):297--305, 1994.Google ScholarCross Ref
- E S Shneidman. Suicide as psychache. J Nerv Ment Dis, 181(3):145--147, 1993.Google ScholarCross Ref
- ES Shneidman and NL Farberow. Clues to Suicide. McGraw Hill Paperbacks, 1957.Google Scholar
- I. H. Witten and E. Frank. Data Mining: Practical Machine Learning Tools ad Techniques. Morgan Kaufman, 2nd edition, 2005. Google ScholarDigital Library
Index Terms
- Using natural language processing to classify suicide notes
Recommendations
Classification of neurologic outcomes from medical notes using natural language processing
Graphical abstractDisplay Omitted
Highlights- Neurologic outcomes are typically extracted by manual chart review of EHR notes.
- Chart review is laborious, limiting the scope of EHR based neurologic outcome studies.
- The NLP model can automatically extract neurological outcomes ...
AbstractNeurologic disability level at hospital discharge is an important outcome in many clinical research studies. Outside of clinical trials, neurologic outcomes must typically be extracted by labor intensive manual review of clinical notes in the ...
Using natural language processing to provide personalized learning opportunities from trainee clinical notes
Display Omitted Portfolios used to assess medical trainees usually require manual review.We provide students automated, customized feedback via natural language processing.Our system searches trainees' clinical notes for two geriatric-related ...
Comments