TY - JOUR
T1 - Discovering the Unclassified Suicide Cases Among Undetermined Drug Overdose Deaths Using Machine Learning Techniques
AU - Liu, Daphne
AU - Yu, Mia
AU - Duncan, Jeffrey
AU - Fondario, Anna
AU - Kharrazi, Hadi
AU - Nestadt, Paul S.
N1 - Publisher Copyright:
© 2019 The American Association of Suicidology
PY - 2020/4/1
Y1 - 2020/4/1
N2 - Objective: The Centers for Disease Control and Prevention (CDC) monitor accidental and intentional deaths to answer questions that are critical for the development of effective prevention and resource allocation. CDC's National Violent Death Reporting System (NVDRS) is a major innovation in surveillance linking individual-level data from multiple sources. However, suicide underreporting is common, particularly from drug overdose deaths. This study sought to assess machine learning (ML) techniques in quantifying drug overdose suicide underreporting rates. Methods: Clinical, sociodemographic, toxicological, and proximal stressor data on overdose decedents (n = 2,665) were extracted from Utah's NVDRS from 2012 to 2015. The existing well-determined cases were used to train and test our ML models. We assessed and compared multiple machine learning methods including Logistic Regression, Random Forest Classifier, Support Vector Machines, and Artificial Neural Networks. We applied a majority voting methodology to classify undetermined drug overdose deaths. Results: Overdose suicide rates were estimated to be underreported by 33% across all years, increasing yearly from 29% in 2012 to 37% in 2015. The overall test accuracies for all models ranged from 92.3% to 94.6%. Conclusions: This research identifies a cost-effective, replicable, and expandable ML-based methodology to estimate the true rates of suicide which may be partially masked during the opioid epidemic.
AB - Objective: The Centers for Disease Control and Prevention (CDC) monitor accidental and intentional deaths to answer questions that are critical for the development of effective prevention and resource allocation. CDC's National Violent Death Reporting System (NVDRS) is a major innovation in surveillance linking individual-level data from multiple sources. However, suicide underreporting is common, particularly from drug overdose deaths. This study sought to assess machine learning (ML) techniques in quantifying drug overdose suicide underreporting rates. Methods: Clinical, sociodemographic, toxicological, and proximal stressor data on overdose decedents (n = 2,665) were extracted from Utah's NVDRS from 2012 to 2015. The existing well-determined cases were used to train and test our ML models. We assessed and compared multiple machine learning methods including Logistic Regression, Random Forest Classifier, Support Vector Machines, and Artificial Neural Networks. We applied a majority voting methodology to classify undetermined drug overdose deaths. Results: Overdose suicide rates were estimated to be underreported by 33% across all years, increasing yearly from 29% in 2012 to 37% in 2015. The overall test accuracies for all models ranged from 92.3% to 94.6%. Conclusions: This research identifies a cost-effective, replicable, and expandable ML-based methodology to estimate the true rates of suicide which may be partially masked during the opioid epidemic.
UR - http://www.scopus.com/inward/record.url?scp=85073969876&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073969876&partnerID=8YFLogxK
U2 - 10.1111/sltb.12591
DO - 10.1111/sltb.12591
M3 - Article
C2 - 31536175
AN - SCOPUS:85073969876
SN - 0363-0234
VL - 50
SP - 333
EP - 344
JO - Suicide and Life-Threatening Behavior
JF - Suicide and Life-Threatening Behavior
IS - 2
ER -