Laboratory Data and IBDQ—Effective Predictors for the Non-Invasive Machine-Learning-Based Prediction of Endoscopic Activity in Ulcerative Colitis
A suitable, non-invasive biomarker for assessing endoscopic disease activity (EDA) in ulcerative colitis (UC) has yet to be identified. Our study aimed to develop a cost-effective and non-invasive machine learning (ML) method that utilizes the cost-free Inflammatory Bowel Disease Questionnaire (IBDQ...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/12/11/3609 |
| _version_ | 1797597316169859072 |
|---|---|
| author | Otilia Gavrilescu Iolanda Valentina Popa Mihaela Dranga Ruxandra Mihai Cristina Cijevschi Prelipcean Cătălina Mihai |
| author_facet | Otilia Gavrilescu Iolanda Valentina Popa Mihaela Dranga Ruxandra Mihai Cristina Cijevschi Prelipcean Cătălina Mihai |
| author_sort | Otilia Gavrilescu |
| collection | DOAJ |
| description | A suitable, non-invasive biomarker for assessing endoscopic disease activity (EDA) in ulcerative colitis (UC) has yet to be identified. Our study aimed to develop a cost-effective and non-invasive machine learning (ML) method that utilizes the cost-free Inflammatory Bowel Disease Questionnaire (IBDQ) score and low-cost biological predictors to estimate EDA. Four random forest (RF) and four multilayer perceptron (MLP) classifiers were proposed. The results show that the inclusion of IBDQ in the list of predictors that were fed to the models improved accuracy and the AUC for both the RF and the MLP algorithms. Moreover, the RF technique performed noticeably better than the MLP method on unseen data (the independent patient cohort). This is the first study to propose the use of IBDQ as a predictor in an ML model to estimate UC EDA. The deployment of this ML model can furnish doctors and patients with valuable insights into EDA, a highly beneficial resource for individuals with UC who need long-term treatment. |
| first_indexed | 2024-03-11T03:04:45Z |
| format | Article |
| id | doaj.art-7efc4650cf4247fa81e10a74a06f80fc |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-11T03:04:45Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-7efc4650cf4247fa81e10a74a06f80fc2023-11-18T08:03:59ZengMDPI AGJournal of Clinical Medicine2077-03832023-05-011211360910.3390/jcm12113609Laboratory Data and IBDQ—Effective Predictors for the Non-Invasive Machine-Learning-Based Prediction of Endoscopic Activity in Ulcerative ColitisOtilia Gavrilescu0Iolanda Valentina Popa1Mihaela Dranga2Ruxandra Mihai3Cristina Cijevschi Prelipcean4Cătălina Mihai5Medicale I Department, “Grigore T. Popa” University of Medicine and Pharmacy, 700115 Iasi, RomaniaMedicale II Department, “Grigore T. Popa” University of Medicine and Pharmacy, 700115 Iasi, RomaniaMedicale I Department, “Grigore T. Popa” University of Medicine and Pharmacy, 700115 Iasi, RomaniaMedicale II Department, “Grigore T. Popa” University of Medicine and Pharmacy, 700115 Iasi, Romania“Saint Spiridon” County Hospital, 700111 Iasi, RomaniaMedicale I Department, “Grigore T. Popa” University of Medicine and Pharmacy, 700115 Iasi, RomaniaA suitable, non-invasive biomarker for assessing endoscopic disease activity (EDA) in ulcerative colitis (UC) has yet to be identified. Our study aimed to develop a cost-effective and non-invasive machine learning (ML) method that utilizes the cost-free Inflammatory Bowel Disease Questionnaire (IBDQ) score and low-cost biological predictors to estimate EDA. Four random forest (RF) and four multilayer perceptron (MLP) classifiers were proposed. The results show that the inclusion of IBDQ in the list of predictors that were fed to the models improved accuracy and the AUC for both the RF and the MLP algorithms. Moreover, the RF technique performed noticeably better than the MLP method on unseen data (the independent patient cohort). This is the first study to propose the use of IBDQ as a predictor in an ML model to estimate UC EDA. The deployment of this ML model can furnish doctors and patients with valuable insights into EDA, a highly beneficial resource for individuals with UC who need long-term treatment.https://www.mdpi.com/2077-0383/12/11/3609ulcerative colitisdisease activitynon-invasive biomarkersquality of lifemachine learning |
| spellingShingle | Otilia Gavrilescu Iolanda Valentina Popa Mihaela Dranga Ruxandra Mihai Cristina Cijevschi Prelipcean Cătălina Mihai Laboratory Data and IBDQ—Effective Predictors for the Non-Invasive Machine-Learning-Based Prediction of Endoscopic Activity in Ulcerative Colitis Journal of Clinical Medicine ulcerative colitis disease activity non-invasive biomarkers quality of life machine learning |
| title | Laboratory Data and IBDQ—Effective Predictors for the Non-Invasive Machine-Learning-Based Prediction of Endoscopic Activity in Ulcerative Colitis |
| title_full | Laboratory Data and IBDQ—Effective Predictors for the Non-Invasive Machine-Learning-Based Prediction of Endoscopic Activity in Ulcerative Colitis |
| title_fullStr | Laboratory Data and IBDQ—Effective Predictors for the Non-Invasive Machine-Learning-Based Prediction of Endoscopic Activity in Ulcerative Colitis |
| title_full_unstemmed | Laboratory Data and IBDQ—Effective Predictors for the Non-Invasive Machine-Learning-Based Prediction of Endoscopic Activity in Ulcerative Colitis |
| title_short | Laboratory Data and IBDQ—Effective Predictors for the Non-Invasive Machine-Learning-Based Prediction of Endoscopic Activity in Ulcerative Colitis |
| title_sort | laboratory data and ibdq effective predictors for the non invasive machine learning based prediction of endoscopic activity in ulcerative colitis |
| topic | ulcerative colitis disease activity non-invasive biomarkers quality of life machine learning |
| url | https://www.mdpi.com/2077-0383/12/11/3609 |
| work_keys_str_mv | AT otiliagavrilescu laboratorydataandibdqeffectivepredictorsforthenoninvasivemachinelearningbasedpredictionofendoscopicactivityinulcerativecolitis AT iolandavalentinapopa laboratorydataandibdqeffectivepredictorsforthenoninvasivemachinelearningbasedpredictionofendoscopicactivityinulcerativecolitis AT mihaeladranga laboratorydataandibdqeffectivepredictorsforthenoninvasivemachinelearningbasedpredictionofendoscopicactivityinulcerativecolitis AT ruxandramihai laboratorydataandibdqeffectivepredictorsforthenoninvasivemachinelearningbasedpredictionofendoscopicactivityinulcerativecolitis AT cristinacijevschiprelipcean laboratorydataandibdqeffectivepredictorsforthenoninvasivemachinelearningbasedpredictionofendoscopicactivityinulcerativecolitis AT catalinamihai laboratorydataandibdqeffectivepredictorsforthenoninvasivemachinelearningbasedpredictionofendoscopicactivityinulcerativecolitis |