Development of a Machine Learning Model Using Multiple, Heterogeneous Data Sources to Estimate Weekly US Suicide Fatalities | Zendy

Daejin Choi | Zendy; Steven A. Sumner | Zendy; Kristin M. Holland | Zendy; John Draper | Zendy; Sean Murphy | Zendy; Daniel A. Bowen | Zendy; Marissa L. Zwald | Zendy; Jing Wang | Zendy; Royal Law | Zendy; Jordan Taylor | Zendy; Chaitanya Konjeti | Zendy; Munmun De Choudhury | Zendy

Open Access

Development of a Machine Learning Model Using Multiple, Heterogeneous Data Sources to Estimate Weekly US Suicide Fatalities

Author(s) -

Daejin Choi,

Steven A. Sumner,

Kristin M. Holland,

John Draper,

Sean Murphy,

Daniel A. Bowen,

Marissa L. Zwald,

Jing Wang,

Royal Law,

Jordan Taylor,

Chaitanya Konjeti,

Munmun De Choudhury

Publication year - 2020

Publication title -

jama network open

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 3.278

H-Index - 39

ISSN - 2574-3805

DOI - 10.1001/jamanetworkopen.2020.30932

Subject(s) - poison control , suicide prevention , medicine , medical emergency , demography , psychology , sociology

Key Points Question Can real-time streams of secondary information related to suicide be used to accurately estimate suicide fatalities in the US in real time? Findings In this national cross-sectional study, combining information from 8 data streams encompassing various health services and online data sources enabled accurate, real-time estimation of US suicide fatalities with meaningful correlation to week-to-week epidemiological trends and a less than 1% error compared with actual counts. Meaning These findings advance the first efforts to create a population-level system for enabling real-time epidemiological trend monitoring of suicide fatalities.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research