Generative AI for analysis and identification of Medicare improper payments by provider type and HCPC code
The 2022 Medicare Fee-For-Service Improper Payments Report reveals an estimated $80.57 billion in improper payments, with a payment error rate of 15.62%. This paper uses generative AI to analyze and identify which provider types and HCPC codes are most strongly associated with these errors. The pape...
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Published: |
Elsevier,
2023-12-01T00:00:00Z.
|
| Subjects: | |
| Online Access: | Connect to this object online. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The 2022 Medicare Fee-For-Service Improper Payments Report reveals an estimated $80.57 billion in improper payments, with a payment error rate of 15.62%. This paper uses generative AI to analyze and identify which provider types and HCPC codes are most strongly associated with these errors. The paper employs generative AI to produce two Python codes: one generates a time-series trend graph of Medicare improper payments from 2010 to 2022, and the other calculates the number of payment errors by provider type and HCPC code. These codes are designed for novice and non-programmers. Three datasets are used, such as Medicare Fee-for-Service Comprehensive Error Rate Testing dataset released on March 8, 2023, merged codes such as HCPC codes and PCT codes. The result suggests what systems should be improved to reduce Medicare improper payments. Generative AI is being introduced to help novice and non-programmers analyze Medicare improper payments with datasets, aiding researchers in conducting similar tasks in the future. |
|---|---|
| Item Description: | 2667-2766 10.1016/j.rcsop.2023.100387 |