MedCoder - Coding literal text cause of death information reported on death certificates to ICD-10

Section 1: Use Case Identifiers

Use Case ID: HHS-CDC-00043
Agency: HHS
Op Div/Staff Div: CDC
Use Case Topic Area: Health & Medical
Is the AI use case found in the below list of general commercial AI products and services?
None of the above.
What is the intended purpose and expected benefits of the AI?
MedCoder is a subsystem of CDC's National Center for Health Statistics (NCHS) National Vital Statistics System for coding causes of death indicated on the death certificates to the International Classification of Diseases 10th Revision (ICD-10) codes.

With the implementation of MedCoder, the percentage of deaths that can be automatically and accurately coded has risen from 70-75% using the previous coding system to over 85%. This improvement translates into substantial cost savings, amounting to hundreds of thousands of dollars that would have been spent on manual coding. Additionally, it significantly enhances the timeliness of data related to urgent public health concerns such as COVID and drug overdose deaths, enabling near real-time surveillance.
Describe the AI system's outputs.
MedCoder assists with the identifying cause of death codes from death certificates using ICD-10 Underlying cause codes and automatically identifies and rejects complex causes of death as well as frequently miscoded ones, requiring manual coding or review. Additionally, in production, MedCoder utilizes natural language processing (NLP) to cleanse and standardize literal text cause of death statements before performing coding.
Stage of Development: Operation and Maintenance
Is the AI use case rights-impacting, safety-impacting, both, or neither?
Neither

Section 2: Use Case Summary

Date Initiated: 10/2017
Date when Acquisition and/or Development began: 02/2018
Date Implemented: 06/2022
Date Retired: N/A
Was the AI system involved in this use case developed (or is it to be developed) under contract(s) or in-house?
Developed in-house.
Provide the Procurement Instrument Identifier(s) (PIID) of the contract(s) used.
N/A
Is this AI use case supporting a High-Impact Service Provider (HISP) public-facing service?
N/A
Does this AI use case disseminate information to the public?
No
How is the agency ensuring compliance with Information Quality Act guidelines, if applicable?
N/A
Does this AI use case involve personally identifiable information (PII) that is maintained by the agency?
No
Has the Senior Agency Official for Privacy (SAOP) assessed the privacy risks associated with this AI use case?
ongoing

Section 3: Data and Code

Do you have access to an enterprise data catalog or agency-wide data repository that enables you to identify whether or not the necessary datasets exist and are ready to develop your use case?
Yes
Describe any agency-owned data used to train, fine-tune, and/or evaluate performance of the model(s) used in this use case.
N/A
Is there available documentation for the model training and evaluation data that demonstrates the degree to which it is appropriate to be used in analysis or for making predictions?
Documentation is widely available
Which, if any, demographic variables does the AI use case explicitly use as model features?
Sex/Gender
Does this project include custom-developed code?
Yes
If the code is open-source, provide the link for the publicly available source code.
N/A

Section 4: AI Enablement and Infrastructure

Does this AI use case have an associated Authority to Operate (ATO) for an AI system?
Yes
System Name: National Vital Statistics System (NVSS)
How long have you waited for the necessary developer tools to implement the AI use case?
More than 12 months
For this AI use case, is the required IT infrastructure provisioned via a centralized intake form or process inside the agency?
Yes
Do you have a process in place to request access to computing resources for model training and development of the AI involved in this use case?
No
Has communication regarding the provisioning of your requested resources been timely?
Yes
How are existing data science tools, libraries, data products, and internally-developed AI infrastructure being re-used for the current AI use case?
None
Has information regarding the AI use case, including performance metrics and intended use of the model, been made available for review and feedback within the agency?
Limited documentation for review