> ## Content Index
> Fetch the complete content index at: https://www.coios.me/llms.txt
> Use this file to discover other available public pages before exploring further.

# An LLM identified NYC overdose deaths from investigator narratives with 92% sensitivity
- URL: https://www.coios.me/an-llm-identified-nyc-overdose-deaths-from-investigator/
- Published: 2026-10-03T13:00:25.000Z
- Updated: 2026-10-03T17:40:25.000Z
- Description: Two language models trained on 9,263 New York City death investigation narratives from 2022-2023 identified suspected overdose deaths with 92% sensitivity and 88% positive predictive value, outperforming the medical examiner's existing surveillance tool and logistic regression.
- Author: Daniel Ryan
- Tags: Weighing data and models, AI in medicine, Alcohol and drug use, United States, #peer-reviewed, #new, #item, #source-2026-10

Researchers trained two language models (LLaMA-8B-Instruct and ClinicalModernBERT) on 9,263 narrative death investigation reports from the New York City Office of Chief Medical Examiner for 2022-2023, using a two-step pipeline that first extracted 18 expert-defined textual indicators of overdose. LLaMA-8B-Instruct reached 88% positive predictive value, 92% sensitivity and 76% specificity (macro-F1 0.85), and ClinicalModernBERT reached 83% PPV and 67% specificity. Both exceeded the office's existing surveillance tool and conventional logistic regression on the same reports, in an internal evaluation.

*Why it is interesting: Tests whether language models can read unstructured death investigation text well enough for cause-of-death surveillance, with specificity the weaker measure.*

Source

[American journal of public health, 1 October 2026](https://doi.org/10.2105/ajph.2026.308698?ref=coios.me)

DOI

10.2105/ajph.2026.308698

Type

Peer-reviewed article

Design

Model development and internal evaluation on 9,263 narrative death investigation reports, New York City OCME, 2022–2023, two LLM families against the incumbent tool and logistic regression

Verdict

New finding

Driver

[AI in medicine](https://www.coios.me/d-ai-medicine/)

Driver

[Alcohol and drug use](https://www.coios.me/d-alcohol-drugs/)