Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Computer-assisted interpretation in forensic toxicology: morphine-involved deaths.

V R Spiehler1

  • 1Diagnostic Products Corporation, Los Angeles, CA 90045.

Journal of Forensic Sciences
|September 1, 1989
PubMed
Summary

Artificial intelligence (AI) software successfully interpreted morphine-involved deaths by analyzing case data. AI programs accurately predicted outcomes, aiding forensic toxicology interpretation.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Blind trials of an onsite saliva drug test for marijuana and opiates.

Journal of forensic sciences·2001
Same author

Validation of an automated microplate enzyme immunoassay for screening of postmortem blood for drugs of abuse.

Journal of analytical toxicology·1998
Same author

Setting cutoff concentrations for immunoassay screening of postmortem blood.

Journal of forensic sciences·1998
Same author

Elimination of ephedrine and pseudoephedrine cross-reactivity in the Coat-A-Count Methamphetamine radioimmunoassay.

Journal of analytical toxicology·1993
Same author

Confirmation and certainty in toxicology screening.

Clinical chemistry·1988
Same author

Brain concentrations of cocaine and benzoylecgonine in fatal cases.

Journal of forensic sciences·1985

Area of Science:

  • Forensic Toxicology
  • Computational Toxicology
  • Artificial Intelligence in Medicine

Background:

  • Morphine-related fatalities require accurate interpretation of complex case data.
  • Traditional interpretation methods can be time-consuming and subjective.

Purpose of the Study:

  • To evaluate the utility of artificial intelligence (AI) computer software in analyzing patterns and relationships in morphine-involved deaths.
  • To assess AI's ability to aid in the interpretation of forensic toxicology cases.

Main Methods:

  • Analysis of case data from 200 morphine-involved deaths using AI software (Expert 4, BEAGLE, KnowledgeMaker).
  • Parameters included blood and tissue morphine levels, demographics, drug use, time of death, and co-administered drugs.
  • AI programs were used to estimate dose, response, time after dosing, and to develop interpretative rules and decision trees.

Related Experiment Videos

Main Results:

  • AI programs achieved 70-90% success in classifying cases regarding response and time of death.
  • Key predictors for response were blood unconjugated morphine, blood total morphine, and liver total morphine.
  • Predictors for time of death included blood unconjugated morphine and brain total morphine.
  • Specific AI-derived rules identified characteristics of morphine overdoses and rapid deaths.

Conclusions:

  • Commercially available, inexpensive AI programs can effectively assist in interpreting forensic toxicology data.
  • AI demonstrates potential for improving the accuracy and efficiency of analyzing complex drug-related fatalities.