Latest Articles and News - Jul 25, 2025
post on 25 Jul 2025
Improving Drug Identification in Overdose Death Surveillance using Large Language Models.
The rising rate of drug-related deaths in the United States, largely driven by fentanyl, requires timely and accurate surveillance. However, critical overdose data are often buried in free-text coroner reports, leading to delays and information loss when coded into ICD (International Classification of Disease)-10 classifications. Natural language processing (NLP) models may automate and enhance overdose surveillance, but prior applications have been limited. A dataset of 35,433 death records from multiple U.S. jurisdictions in 2020 was used for model training and internal testing. External validation was conducted using a novel separate dataset of 3,335 records from 2023-2024. Multiple NLP approaches were evaluated for classifying specific drug involvement from unstructured death certificate text. These included traditional single- and multi-label classifiers, as well as fine-tuned encoder-only language models such as Bidirectional Encoder Representations from Transformers (BERT) and BioClinicalBERT, and contemporary decoder-only large language models such as Qwen 3 and Llama 3. Model performance was assessed using macro-averaged F1 scores, and 95% confidence intervals were calculated to quantify uncertainty. Fine-tuned BioClinicalBERT models achieved near-perfect performance, with macro F1 scores >=0.998 on the internal test set. External validation confirmed robustness (macro F1=0.966), outperforming conventional machine learning, general-domain BERT models, and various decoder-only large language models. NLP models, particularly fine-tuned clinical variants like BioClinicalBERT, offer a highly accurate and scalable solution for overdose death classification from free-text reports. These methods can significantly accelerate surveillance workflows, overcoming the limitations of manual ICD-10 coding and supporting near real-time detection of emerging substance use trends.
https://pubmed.ncbi.nlm.nih.gov/40709305/Racial/Ethnic and Regional Disparities in Opioid-Involved Overdose Deaths among Children and Adolescents in the United States.
Despite the opioid crisis being declared a national emergency in 2017, few studies have examined disparities in overdose mortality trends among children and adolescents. This study assessed trends in opioid-involved overdose mortality among U.S. individuals aged 0 to 19 years, categorized by age, sex, race/ethnicity, census region, opioid type (prescription, synthetic, and heroin), and county rural/urban designation, from 1999 to 2019. Mortality data were sourced from the Centers for Disease Control and Prevention's Wide-ranging Online Data for Epidemiologic Research Database. Opioid-related deaths were identified using ICD-10 codes. Crude and age-adjusted mortality rates (AAMR) were assessed by age, sex, race/ethnicity, census region, opioid type, and county rural/urban designation. Temporal trends were analyzed using Joinpoint regression to estimate annual percentage changes (APC) and average APC. 95% confidence intervals were derived using the Empirical Quantile method and the Parametric Method. Between 1999 and 2019, 10,799 children and adolescents died from opioid overdoses (AAMR = 0.6 per 100,000; 95% CI: 0.6-0.6). From 2013-2019, overall mortality increased by 4.5% annually (95% CI: 0.91, 15.54). Mortality trends increased among Non-Hispanic Black (APC = 7.84; 95% CI: 5.12-10.56) and Hispanic individuals (APC = 5.29; 95% CI: 2.84-7.74) from 1999 to 2019, while remaining stable among Non-Hispanic White individuals from 2004 to 2019 (APC = -0.69; 95% CI: -2.09 to 0.58). Mortality rates also increased in the Northeast from 1999 to 2019 (APC = 4.23; 95% CI: 2.70-5.78) and in the West from 2015 to 2019 (APC = 21.96; 95% CI: 13.50-39.67), with a sharp increase in deaths involving synthetic opioids from 2014 to 2019 (APC = 43.37; 95% CI: 21.13-120.46). Opioid overdose mortality trends among US children and adolescents have increased in recent years. Contemporary rises are most pronounced among Non-Hispanic Black and Hispanic children, in the Northeastern and Western regions, and from synthetic opioids. The disparities in opioid-related deaths underscores the need for targeted interventions and continued research to inform public health strategies.
https://pubmed.ncbi.nlm.nih.gov/40707842/
Related News
Latest Research and Studies
Latest Articles and News - Jul 28, 2025
Post on 28 Jul 2025
Latest Research and Studies
Latest Articles and News - Jul 24, 2025
Post on 24 Jul 2025
Latest Research and Studies
Latest Articles and News - Jul 22, 2025
Post on 22 Jul 2025
Latest Research and Studies
Latest Articles and News - Jul 21, 2025
Post on 21 Jul 2025