Artificial Intelligence in Identifying Patients With Undiagnosed Nonalcoholic Steatohepatitis
**Background:** Although increasing in prevalence, nonalcoholic steatohepatitis (NASH) is often undiagnosed in clinical practice. **Objective:** This study identified patients in the Veterans Affairs (VA) health system who likely had undiagnosed NASH using a machine learning algorithm. **Methods:*...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Columbia Data Analytics, LLC
2024-09-01
|
| Series: | Journal of Health Economics and Outcomes Research |
| Online Access: | https://doi.org/10.36469/001c.123645 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823860318675140608 |
|---|---|
| author | Onur Baser Gabriela Samayoa Nehir Yapar Erdem Baser |
| author_facet | Onur Baser Gabriela Samayoa Nehir Yapar Erdem Baser |
| author_sort | Onur Baser |
| collection | DOAJ |
| description | **Background:** Although increasing in prevalence, nonalcoholic steatohepatitis (NASH) is often undiagnosed in clinical practice.
**Objective:** This study identified patients in the Veterans Affairs (VA) health system who likely had undiagnosed NASH using a machine learning algorithm.
**Methods:** From a VA data set of 25 million adult enrollees, the study population was divided into NASH-positive, non-NASH, and at-risk cohorts. We performed a claims data analysis using a machine learning algorithm. To build our model, the study population was randomly divided into an 80% training subset and a 20% testing subset and tested and trained using a cross-validation technique. In addition to the baseline model, a gradient-boosted classification tree, naïve Bayes, and random forest model were created and compared using receiver operator characteristics, area under the curve, and accuracy. The best performing model was retrained on the full 80% training subset and applied to the 20% testing subset to calculate the performance metrics.
**Results:** In total, 4 223 443 patients met the study inclusion criteria, of whom 4903 were positive for NASH and 35 528 were non-NASH patients. The remainder was in the at-risk patient cohort, of which 514 997 patients (12%) were identified as likely to have NASH. Age, obesity, and abnormal liver function tests were the top determinants in assigning NASH probability.
**Conclusions:** Utilization of machine learning to predict NASH allows for wider recognition, timely intervention, and targeted treatments to improve or mitigate disease progression and could be used as an initial screening tool. |
| format | Article |
| id | doaj-art-f56afee7e367443797342187d7d9d1a9 |
| institution | Kabale University |
| issn | 2327-2236 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Columbia Data Analytics, LLC |
| record_format | Article |
| series | Journal of Health Economics and Outcomes Research |
| spelling | doaj-art-f56afee7e367443797342187d7d9d1a92025-02-10T16:13:31ZengColumbia Data Analytics, LLCJournal of Health Economics and Outcomes Research2327-22362024-09-01112Artificial Intelligence in Identifying Patients With Undiagnosed Nonalcoholic SteatohepatitisOnur BaserGabriela SamayoaNehir YaparErdem Baser**Background:** Although increasing in prevalence, nonalcoholic steatohepatitis (NASH) is often undiagnosed in clinical practice. **Objective:** This study identified patients in the Veterans Affairs (VA) health system who likely had undiagnosed NASH using a machine learning algorithm. **Methods:** From a VA data set of 25 million adult enrollees, the study population was divided into NASH-positive, non-NASH, and at-risk cohorts. We performed a claims data analysis using a machine learning algorithm. To build our model, the study population was randomly divided into an 80% training subset and a 20% testing subset and tested and trained using a cross-validation technique. In addition to the baseline model, a gradient-boosted classification tree, naïve Bayes, and random forest model were created and compared using receiver operator characteristics, area under the curve, and accuracy. The best performing model was retrained on the full 80% training subset and applied to the 20% testing subset to calculate the performance metrics. **Results:** In total, 4 223 443 patients met the study inclusion criteria, of whom 4903 were positive for NASH and 35 528 were non-NASH patients. The remainder was in the at-risk patient cohort, of which 514 997 patients (12%) were identified as likely to have NASH. Age, obesity, and abnormal liver function tests were the top determinants in assigning NASH probability. **Conclusions:** Utilization of machine learning to predict NASH allows for wider recognition, timely intervention, and targeted treatments to improve or mitigate disease progression and could be used as an initial screening tool.https://doi.org/10.36469/001c.123645 |
| spellingShingle | Onur Baser Gabriela Samayoa Nehir Yapar Erdem Baser Artificial Intelligence in Identifying Patients With Undiagnosed Nonalcoholic Steatohepatitis Journal of Health Economics and Outcomes Research |
| title | Artificial Intelligence in Identifying Patients With Undiagnosed Nonalcoholic Steatohepatitis |
| title_full | Artificial Intelligence in Identifying Patients With Undiagnosed Nonalcoholic Steatohepatitis |
| title_fullStr | Artificial Intelligence in Identifying Patients With Undiagnosed Nonalcoholic Steatohepatitis |
| title_full_unstemmed | Artificial Intelligence in Identifying Patients With Undiagnosed Nonalcoholic Steatohepatitis |
| title_short | Artificial Intelligence in Identifying Patients With Undiagnosed Nonalcoholic Steatohepatitis |
| title_sort | artificial intelligence in identifying patients with undiagnosed nonalcoholic steatohepatitis |
| url | https://doi.org/10.36469/001c.123645 |
| work_keys_str_mv | AT onurbaser artificialintelligenceinidentifyingpatientswithundiagnosednonalcoholicsteatohepatitis AT gabrielasamayoa artificialintelligenceinidentifyingpatientswithundiagnosednonalcoholicsteatohepatitis AT nehiryapar artificialintelligenceinidentifyingpatientswithundiagnosednonalcoholicsteatohepatitis AT erdembaser artificialintelligenceinidentifyingpatientswithundiagnosednonalcoholicsteatohepatitis |