Decoding substance use disorder severity from clinical notes using a large language model
Abstract Substance use disorder (SUD) poses a major concern due to its detrimental effects on health and society. SUD identification and treatment depend on a variety of factors such as severity, co-determinants (e.g., withdrawal symptoms), and social determinants of health. Existing diagnostic codi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | npj Mental Health Research |
| Online Access: | https://doi.org/10.1038/s44184-024-00114-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861481388638208 |
|---|---|
| author | Maria Mahbub Gregory M. Dams Sudarshan Srinivasan Caitlin Rizy Ioana Danciu Jodie Trafton Kathryn Knight |
| author_facet | Maria Mahbub Gregory M. Dams Sudarshan Srinivasan Caitlin Rizy Ioana Danciu Jodie Trafton Kathryn Knight |
| author_sort | Maria Mahbub |
| collection | DOAJ |
| description | Abstract Substance use disorder (SUD) poses a major concern due to its detrimental effects on health and society. SUD identification and treatment depend on a variety of factors such as severity, co-determinants (e.g., withdrawal symptoms), and social determinants of health. Existing diagnostic coding systems used by insurance providers, like the International Classification of Diseases (ICD-10), lack granularity for certain diagnoses, but American clinicians will add this granularity (as that found within the Diagnostic and Statistical Manual of Mental Disorders classification or DSM-5) as supplemental unstructured text in clinical notes. Traditional natural language processing (NLP) methods face limitations in accurately parsing such diverse clinical language. Large language models (LLMs) offer promise in overcoming these challenges by adapting to diverse language patterns. This study investigates the application of LLMs for extracting severity-related information for various SUD diagnoses from clinical notes. We propose a workflow employing zero-shot learning of LLMs with carefully crafted prompts and post-processing techniques. Through experimentation with Flan-T5, an open-source LLM, we demonstrate its superior recall compared to the rule-based approach. Focusing on 11 categories of SUD diagnoses, we show the effectiveness of LLMs in extracting severity information, contributing to improved risk assessment and treatment planning for SUD patients. |
| format | Article |
| id | doaj-art-88ba39d7cb1b482da352aeeac6c8e679 |
| institution | Kabale University |
| issn | 2731-4251 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Mental Health Research |
| spelling | doaj-art-88ba39d7cb1b482da352aeeac6c8e6792025-02-09T13:00:19ZengNature Portfolionpj Mental Health Research2731-42512025-02-014111010.1038/s44184-024-00114-6Decoding substance use disorder severity from clinical notes using a large language modelMaria Mahbub0Gregory M. Dams1Sudarshan Srinivasan2Caitlin Rizy3Ioana Danciu4Jodie Trafton5Kathryn Knight6Oak Ridge National LaboratoryProgram Evaluation and Resource Center, Office of Mental Health and Office of Suicide Prevention, Veterans Health Administration, Department of Veterans AffairsOak Ridge National LaboratoryOak Ridge National LaboratoryOak Ridge National LaboratoryProgram Evaluation and Resource Center, Office of Mental Health and Office of Suicide Prevention, Veterans Health Administration, Department of Veterans AffairsOak Ridge National LaboratoryAbstract Substance use disorder (SUD) poses a major concern due to its detrimental effects on health and society. SUD identification and treatment depend on a variety of factors such as severity, co-determinants (e.g., withdrawal symptoms), and social determinants of health. Existing diagnostic coding systems used by insurance providers, like the International Classification of Diseases (ICD-10), lack granularity for certain diagnoses, but American clinicians will add this granularity (as that found within the Diagnostic and Statistical Manual of Mental Disorders classification or DSM-5) as supplemental unstructured text in clinical notes. Traditional natural language processing (NLP) methods face limitations in accurately parsing such diverse clinical language. Large language models (LLMs) offer promise in overcoming these challenges by adapting to diverse language patterns. This study investigates the application of LLMs for extracting severity-related information for various SUD diagnoses from clinical notes. We propose a workflow employing zero-shot learning of LLMs with carefully crafted prompts and post-processing techniques. Through experimentation with Flan-T5, an open-source LLM, we demonstrate its superior recall compared to the rule-based approach. Focusing on 11 categories of SUD diagnoses, we show the effectiveness of LLMs in extracting severity information, contributing to improved risk assessment and treatment planning for SUD patients.https://doi.org/10.1038/s44184-024-00114-6 |
| spellingShingle | Maria Mahbub Gregory M. Dams Sudarshan Srinivasan Caitlin Rizy Ioana Danciu Jodie Trafton Kathryn Knight Decoding substance use disorder severity from clinical notes using a large language model npj Mental Health Research |
| title | Decoding substance use disorder severity from clinical notes using a large language model |
| title_full | Decoding substance use disorder severity from clinical notes using a large language model |
| title_fullStr | Decoding substance use disorder severity from clinical notes using a large language model |
| title_full_unstemmed | Decoding substance use disorder severity from clinical notes using a large language model |
| title_short | Decoding substance use disorder severity from clinical notes using a large language model |
| title_sort | decoding substance use disorder severity from clinical notes using a large language model |
| url | https://doi.org/10.1038/s44184-024-00114-6 |
| work_keys_str_mv | AT mariamahbub decodingsubstanceusedisorderseverityfromclinicalnotesusingalargelanguagemodel AT gregorymdams decodingsubstanceusedisorderseverityfromclinicalnotesusingalargelanguagemodel AT sudarshansrinivasan decodingsubstanceusedisorderseverityfromclinicalnotesusingalargelanguagemodel AT caitlinrizy decodingsubstanceusedisorderseverityfromclinicalnotesusingalargelanguagemodel AT ioanadanciu decodingsubstanceusedisorderseverityfromclinicalnotesusingalargelanguagemodel AT jodietrafton decodingsubstanceusedisorderseverityfromclinicalnotesusingalargelanguagemodel AT kathrynknight decodingsubstanceusedisorderseverityfromclinicalnotesusingalargelanguagemodel |