Stemming the Tide of the US Overdose Crisis: How Can We Leverage the Power of Data Science and Artificial Intelligence?

Tags:
Early View Perspective
Topics:
Health IT Opioids

Policy Points:

  • We can leverage data science and artificial intelligence to inform state and local resource allocation for overdose prevention.
  • Data science and artificial intelligence can help us answer four questions: (1) What is the impact of laws on access to interventions and overdose risk? (2) Where should interventions be targeted? (3) Which types of demographic subgroups benefit the most and the least from interventions? and (4) Which types of interventions should they invest in for each setting and population?
  • Advances in data science and artificial intelligence can accelerate the pace at which we can answer these critical questions and help inform an effective overdose prevention response.

The Overdose Crisis: Epidemiologic Profile and Potential Solutions

People in the United States are dying at record numbers from overdose.1 Overdose deaths increased from fewer than 17,000 deaths in 1999 to an estimated 100,000 deaths approximately 25 years after, with a peak of almost 108,000 deaths in 2022.2 Racial/ethnic minoritized groups are now particularly affected: in 2023, the highest rates of overdose were among non-Hispanic Black and American Indian/Alaska Native Americans.3 Although overdoses increasingly involve both opioids and stimulants, opioids contribute to over three-quarters of all overdose deaths, primarily driven by illegally manufactured synthetic opioids like fentanyl.1

Provisional data indicate that we have seen an overall decline in US overdose deaths in the past 2 years, with a decline of 4% in 2022–2023 and 17% in 2023–2024.4 Despite this substantial decline, the number of deaths per year remain higher than they were prior to the start of the COVID-19 pandemic. Further, this decline has been unequally experienced across racial and ethnic groups. According to the latest available race-specific data, White populations saw a 7% decline in 2022–2023 compared with a 3% increase among Black Americans, a 39.4% increase among Native Hawaiian or Other Pacific Islander populations, and no change among other racial/ethnic groups.3 These patterns signal a need to develop targeted and tailored interventions that effectively reduce both total overdose deaths and disparities in overdose.

References

1

Drug overdose deaths: facts and figures. National Institute on Drug Abuse, National Institutes of Health. August 21, 2024. Accessed July 25, 2023. https://nida.nih.gov/research-topics/trends-statistics/overdose-death-ratesGoogle Scholar

2

Spencer MR, Garnett MF, Miniño AM. Drug Overdose Deaths in the United States, 2002–2022. NCHS Data Brief No 491. National Center for Health Statistics; 2024.Google Scholar

3

Garnett MF, Miniño AM. Drug Overdose in the United States, 2003–2023. NCHS Data Brief No 522. National Center for Health Statistics; 2024.Google Scholar

4

Ahmad FB, Cisewski JA, Rossen LM, Sutton P. Provisional drug overdose death counts. National Center for Health Statistics. Updated May 14, 2025. Accessed January 1, 2025. https://dx.doi.org/10.15620/cdc/20250305008ViewGoogle Scholar


Citation:
Stemming the Tide of the US Overdose Crisis: How Can We Leverage the Power of Data Science and Artificial Intelligence? Milbank Q. 2025;103(SI):0610.