Anomaly Detection Methods for Overdose (ADMO) was developed by the Johns Hopkins Bloomberg School of Public Health’s Surveillance and Outbreak Response Team (SORT) in partnership with CSTE and a workgroup of state, Tribal, local, and territorial (STLT) epidemiologists. The ADMO approach is a set of standardized and customizable statistical methods that detect anomalies in count data. By using it, users can identify anomalies over time and space. It is not used to detect clusters. 

Below, you can find resources for implementing ADMO in your jurisdiction, including on-demand training videos, detailed instructions for preparing standardized data, customizing the R-based code, understanding the statistical methods, and interpreting results to support timely overdose surveillance and public health response. 

Anomaly Detection Methods for Overdose (ADMO) was developed by the Johns Hopkins Bloomberg School of Public Health’s Surveillance and Outbreak Response Team (SORT) in partnership with CSTE and a workgroup of state, Tribal, local, and territorial (STLT) epidemiologists. The ADMO approach is a set of standardized and customizable statistical methods that detect anomalies in count data. By using it, users can identify anomalies over time and space. It is not used to detect clusters. 

Below, you can find resources for implementing ADMO in your jurisdiction, including on-demand training videos, detailed instructions for preparing standardized data, customizing the R-based code, understanding the statistical methods, and interpreting results to support timely overdose surveillance and public health response. 

Resources 

Technical Guidance for Analytic Code

The purpose of the technical guidance is to expand upon the methods and concepts used in the analytic code. Specifically, this guidance describes:  

• the data sources, variables, and format required to use the code; 

• the statistical rationale and analytic workflow of the code; 

• instructions on customizing code, which is programmed in R; and 

• guidance on the interpretation of results, statistical outputs, and visualizations.  

Analytic R Code 

• Data Analysis RMD File & Data Formatting RMD File  

Mock Datasets 

• ADMO Mock Data File 

• ADMO Formatted Data File