Machine learning using clinical data at baseline predicts the medium-term efficacy of ustekinumab in patients with ulcerative colitis
Abstract Predicting the therapeutic response to biologics before administration is a key clinical challenge in ulcerative colitis (UC). We previously reported a model for predicting the efficacy of vedolizumab (VDZ) for UC using a machine-learning approach. Ustekinumab (UST) is now available for tre...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-55126-1 |
| _version_ | 1797274669959610368 |
|---|---|
| author | Hiromu Morikubo Ryuta Tojima Tsubasa Maeda Katsuyoshi Matsuoka Minoru Matsuura Jun Miyoshi Satoshi Tamura Tadakazu Hisamatsu |
| author_facet | Hiromu Morikubo Ryuta Tojima Tsubasa Maeda Katsuyoshi Matsuoka Minoru Matsuura Jun Miyoshi Satoshi Tamura Tadakazu Hisamatsu |
| author_sort | Hiromu Morikubo |
| collection | DOAJ |
| description | Abstract Predicting the therapeutic response to biologics before administration is a key clinical challenge in ulcerative colitis (UC). We previously reported a model for predicting the efficacy of vedolizumab (VDZ) for UC using a machine-learning approach. Ustekinumab (UST) is now available for treating UC, but no model for predicting its efficacy has been developed. When applied to patients with UC treated with UST, our VDZ prediction model showed positive predictive value (PPV) of 56.3% and negative predictive value (NPV) of 62.5%. Given this limited predictive ability, we aimed to develop a UST-specific prediction model with clinical features at baseline including background factors, clinical and endoscopic activity, and blood test results, as we did for the VDZ prediction model. The top 10 features (Alb, monocytes, height, MCV, TP, Lichtiger index, white blood cell count, MCHC, partial Mayo score, and CRP) associated with steroid-free clinical remission at 6 months after starting UST were selected using random forest. The predictive ability of a model using these predictors was evaluated by fivefold cross-validation. Validation of the prediction model with an external cohort showed PPV of 68.8% and NPV of 71.4%. Our study suggested the importance of establishing a drug-specific prediction model. |
| first_indexed | 2024-03-07T15:01:36Z |
| format | Article |
| id | doaj.art-a3cc3ac1e3b6464091bcd5e33b2e05d0 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-07T15:01:36Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-a3cc3ac1e3b6464091bcd5e33b2e05d02024-03-05T19:06:51ZengNature PortfolioScientific Reports2045-23222024-02-0114111110.1038/s41598-024-55126-1Machine learning using clinical data at baseline predicts the medium-term efficacy of ustekinumab in patients with ulcerative colitisHiromu Morikubo0Ryuta Tojima1Tsubasa Maeda2Katsuyoshi Matsuoka3Minoru Matsuura4Jun Miyoshi5Satoshi Tamura6Tadakazu Hisamatsu7Department of Gastroenterology and Hepatology, Kyorin University School of MedicineDepartment of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu UniversityDepartment of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu UniversityDivision of Gastroenterology and Hepatology, Department of Internal Medicine, Toho University Sakura Medical CenterDepartment of Gastroenterology and Hepatology, Kyorin University School of MedicineDepartment of Gastroenterology and Hepatology, Kyorin University School of MedicineDepartment of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu UniversityDepartment of Gastroenterology and Hepatology, Kyorin University School of MedicineAbstract Predicting the therapeutic response to biologics before administration is a key clinical challenge in ulcerative colitis (UC). We previously reported a model for predicting the efficacy of vedolizumab (VDZ) for UC using a machine-learning approach. Ustekinumab (UST) is now available for treating UC, but no model for predicting its efficacy has been developed. When applied to patients with UC treated with UST, our VDZ prediction model showed positive predictive value (PPV) of 56.3% and negative predictive value (NPV) of 62.5%. Given this limited predictive ability, we aimed to develop a UST-specific prediction model with clinical features at baseline including background factors, clinical and endoscopic activity, and blood test results, as we did for the VDZ prediction model. The top 10 features (Alb, monocytes, height, MCV, TP, Lichtiger index, white blood cell count, MCHC, partial Mayo score, and CRP) associated with steroid-free clinical remission at 6 months after starting UST were selected using random forest. The predictive ability of a model using these predictors was evaluated by fivefold cross-validation. Validation of the prediction model with an external cohort showed PPV of 68.8% and NPV of 71.4%. Our study suggested the importance of establishing a drug-specific prediction model.https://doi.org/10.1038/s41598-024-55126-1Ulcerative colitisMachine learningUstekinumabSteroid-free clinical remissionPrediction model |
| spellingShingle | Hiromu Morikubo Ryuta Tojima Tsubasa Maeda Katsuyoshi Matsuoka Minoru Matsuura Jun Miyoshi Satoshi Tamura Tadakazu Hisamatsu Machine learning using clinical data at baseline predicts the medium-term efficacy of ustekinumab in patients with ulcerative colitis Scientific Reports Ulcerative colitis Machine learning Ustekinumab Steroid-free clinical remission Prediction model |
| title | Machine learning using clinical data at baseline predicts the medium-term efficacy of ustekinumab in patients with ulcerative colitis |
| title_full | Machine learning using clinical data at baseline predicts the medium-term efficacy of ustekinumab in patients with ulcerative colitis |
| title_fullStr | Machine learning using clinical data at baseline predicts the medium-term efficacy of ustekinumab in patients with ulcerative colitis |
| title_full_unstemmed | Machine learning using clinical data at baseline predicts the medium-term efficacy of ustekinumab in patients with ulcerative colitis |
| title_short | Machine learning using clinical data at baseline predicts the medium-term efficacy of ustekinumab in patients with ulcerative colitis |
| title_sort | machine learning using clinical data at baseline predicts the medium term efficacy of ustekinumab in patients with ulcerative colitis |
| topic | Ulcerative colitis Machine learning Ustekinumab Steroid-free clinical remission Prediction model |
| url | https://doi.org/10.1038/s41598-024-55126-1 |
| work_keys_str_mv | AT hiromumorikubo machinelearningusingclinicaldataatbaselinepredictsthemediumtermefficacyofustekinumabinpatientswithulcerativecolitis AT ryutatojima machinelearningusingclinicaldataatbaselinepredictsthemediumtermefficacyofustekinumabinpatientswithulcerativecolitis AT tsubasamaeda machinelearningusingclinicaldataatbaselinepredictsthemediumtermefficacyofustekinumabinpatientswithulcerativecolitis AT katsuyoshimatsuoka machinelearningusingclinicaldataatbaselinepredictsthemediumtermefficacyofustekinumabinpatientswithulcerativecolitis AT minorumatsuura machinelearningusingclinicaldataatbaselinepredictsthemediumtermefficacyofustekinumabinpatientswithulcerativecolitis AT junmiyoshi machinelearningusingclinicaldataatbaselinepredictsthemediumtermefficacyofustekinumabinpatientswithulcerativecolitis AT satoshitamura machinelearningusingclinicaldataatbaselinepredictsthemediumtermefficacyofustekinumabinpatientswithulcerativecolitis AT tadakazuhisamatsu machinelearningusingclinicaldataatbaselinepredictsthemediumtermefficacyofustekinumabinpatientswithulcerativecolitis |