Replicating prediction algorithms for hospitalization and corticosteroid use in patients with inflammatory bowel disease.
<h4>Introduction</h4>Previous work had shown that machine learning models can predict inflammatory bowel disease (IBD)-related hospitalizations and outpatient corticosteroid use based on patient demographic and laboratory data in a cohort of United States Veterans. This study aimed to re...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2021-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0257520 |
| _version_ | 1830413980622913536 |
|---|---|
| author | Ryan W Gan Diana Sun Amanda R Tatro Shirley Cohen-Mekelburg Wyndy L Wiitala Ji Zhu Akbar K Waljee |
| author_facet | Ryan W Gan Diana Sun Amanda R Tatro Shirley Cohen-Mekelburg Wyndy L Wiitala Ji Zhu Akbar K Waljee |
| author_sort | Ryan W Gan |
| collection | DOAJ |
| description | <h4>Introduction</h4>Previous work had shown that machine learning models can predict inflammatory bowel disease (IBD)-related hospitalizations and outpatient corticosteroid use based on patient demographic and laboratory data in a cohort of United States Veterans. This study aimed to replicate this modeling framework in a nationally representative cohort.<h4>Methods</h4>A retrospective cohort design using Optum Electronic Health Records (EHR) were used to identify IBD patients, with at least 12 months of follow-up between 2007 and 2018. IBD flare was defined as an inpatient/emergency visit with a diagnosis of IBD or an outpatient corticosteroid prescription for IBD. Predictors included demographic and laboratory data. Logistic regression and random forest (RF) models were used to predict IBD flare within 6 months of each visit. A 70% training and 30% validation approach was used.<h4>Results</h4>A total of 95,878 patients across 780,559 visits were identified. Of these, 22,245 (23.2%) patients had at least one IBD flare. Patients were predominantly White (87.7%) and female (57.1%), with a mean age of 48.0 years. The logistic regression model had an area under the receiver operating curve (AuROC) of 0.66 (95% CI: 0.65-0.66), sensitivity of 0.69 (95% CI: 0.68-0.70), and specificity of 0.74 (95% CI: 0.73-0.74) in the validation cohort. The RF model had an AuROC of 0.80 (95% CI: 0.80-0.81), sensitivity of 0.74 (95% CI: 0.73-0.74), and specificity of 0.72 (95% CI: 0.72-0.72) in the validation cohort. Important predictors of IBD flare in the RF model were the number of previous flares, age, potassium, and white blood cell count.<h4>Conclusion</h4>The machine learning modeling framework was replicated and results showed a similar predictive accuracy in a nationally representative cohort of IBD patients. This modeling framework could be embedded in routine practice as a tool to distinguish high-risk patients for disease activity. |
| first_indexed | 2024-12-20T20:34:45Z |
| format | Article |
| id | doaj.art-8a3c6b4a2c1f4064b127a5e3d11dc3e5 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-20T20:34:45Z |
| publishDate | 2021-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-8a3c6b4a2c1f4064b127a5e3d11dc3e52022-12-21T19:27:16ZengPublic Library of Science (PLoS)PLoS ONE1932-62032021-01-01169e025752010.1371/journal.pone.0257520Replicating prediction algorithms for hospitalization and corticosteroid use in patients with inflammatory bowel disease.Ryan W GanDiana SunAmanda R TatroShirley Cohen-MekelburgWyndy L WiitalaJi ZhuAkbar K Waljee<h4>Introduction</h4>Previous work had shown that machine learning models can predict inflammatory bowel disease (IBD)-related hospitalizations and outpatient corticosteroid use based on patient demographic and laboratory data in a cohort of United States Veterans. This study aimed to replicate this modeling framework in a nationally representative cohort.<h4>Methods</h4>A retrospective cohort design using Optum Electronic Health Records (EHR) were used to identify IBD patients, with at least 12 months of follow-up between 2007 and 2018. IBD flare was defined as an inpatient/emergency visit with a diagnosis of IBD or an outpatient corticosteroid prescription for IBD. Predictors included demographic and laboratory data. Logistic regression and random forest (RF) models were used to predict IBD flare within 6 months of each visit. A 70% training and 30% validation approach was used.<h4>Results</h4>A total of 95,878 patients across 780,559 visits were identified. Of these, 22,245 (23.2%) patients had at least one IBD flare. Patients were predominantly White (87.7%) and female (57.1%), with a mean age of 48.0 years. The logistic regression model had an area under the receiver operating curve (AuROC) of 0.66 (95% CI: 0.65-0.66), sensitivity of 0.69 (95% CI: 0.68-0.70), and specificity of 0.74 (95% CI: 0.73-0.74) in the validation cohort. The RF model had an AuROC of 0.80 (95% CI: 0.80-0.81), sensitivity of 0.74 (95% CI: 0.73-0.74), and specificity of 0.72 (95% CI: 0.72-0.72) in the validation cohort. Important predictors of IBD flare in the RF model were the number of previous flares, age, potassium, and white blood cell count.<h4>Conclusion</h4>The machine learning modeling framework was replicated and results showed a similar predictive accuracy in a nationally representative cohort of IBD patients. This modeling framework could be embedded in routine practice as a tool to distinguish high-risk patients for disease activity.https://doi.org/10.1371/journal.pone.0257520 |
| spellingShingle | Ryan W Gan Diana Sun Amanda R Tatro Shirley Cohen-Mekelburg Wyndy L Wiitala Ji Zhu Akbar K Waljee Replicating prediction algorithms for hospitalization and corticosteroid use in patients with inflammatory bowel disease. PLoS ONE |
| title | Replicating prediction algorithms for hospitalization and corticosteroid use in patients with inflammatory bowel disease. |
| title_full | Replicating prediction algorithms for hospitalization and corticosteroid use in patients with inflammatory bowel disease. |
| title_fullStr | Replicating prediction algorithms for hospitalization and corticosteroid use in patients with inflammatory bowel disease. |
| title_full_unstemmed | Replicating prediction algorithms for hospitalization and corticosteroid use in patients with inflammatory bowel disease. |
| title_short | Replicating prediction algorithms for hospitalization and corticosteroid use in patients with inflammatory bowel disease. |
| title_sort | replicating prediction algorithms for hospitalization and corticosteroid use in patients with inflammatory bowel disease |
| url | https://doi.org/10.1371/journal.pone.0257520 |
| work_keys_str_mv | AT ryanwgan replicatingpredictionalgorithmsforhospitalizationandcorticosteroiduseinpatientswithinflammatoryboweldisease AT dianasun replicatingpredictionalgorithmsforhospitalizationandcorticosteroiduseinpatientswithinflammatoryboweldisease AT amandartatro replicatingpredictionalgorithmsforhospitalizationandcorticosteroiduseinpatientswithinflammatoryboweldisease AT shirleycohenmekelburg replicatingpredictionalgorithmsforhospitalizationandcorticosteroiduseinpatientswithinflammatoryboweldisease AT wyndylwiitala replicatingpredictionalgorithmsforhospitalizationandcorticosteroiduseinpatientswithinflammatoryboweldisease AT jizhu replicatingpredictionalgorithmsforhospitalizationandcorticosteroiduseinpatientswithinflammatoryboweldisease AT akbarkwaljee replicatingpredictionalgorithmsforhospitalizationandcorticosteroiduseinpatientswithinflammatoryboweldisease |