Performance of Machine Learning Algorithms for Predicting Disease Activity in Inflammatory Bowel Disease

Risk Factors and Prediction of 28-Day-All Cause Mortality Among Critically Ill Patients with Acute Pancreatitis Using Machine Learning Techniques: A Retrospective Analysis of Multi-Institutions

Objective

This study aimed to identify the risk factors and construct a reliable prediction model of 28-day all-cause mortality in critically ill patients with acute pancreatitis (AP) using machine learning techniques.

Methods

A total of 534 patients from three different institutions were included. Thirty-eight possible variables were collected from the Intensive care unit (ICU) admission for investigation. Patients were split into a training cohort (n = 400) and test cohort (n = 134) according to their source of hospital. The synthetic minority oversampling technique (SMOTE) was introduced to handle the inherent class imbalance. Six machine learning algorithms were applied in this study. The optimal machine learning model was chosen after patients in the test cohort were selected to validate the models. SHapley Additive exPlanation (SHAP) analysis was performed to rank the importance of variable. The predictive performance of the models was evaluated by the calibration curve, area under the receiver operating characteristics curves (AUROC), and decision clinical analysis.

Results

About 13.5% (72/534) of all patients eventually died of all-cause within 28 days of ICU admission. Eight important variables were screened out, including white blood cell count, platelets, body temperature, age, blood urea nitrogen, red blood cell distribution width, SpO2, and hemoglobin. The support vector machine (SVM) algorithm performed best in predicting 28-d all-cause death. Its AUROC reached 0.877 (95% CI: 0.809 to 0.927, p < 0.001), the Youden index was 0.634 (95% CI: 0.459 to 0.717). Based on the risk stratification system, the difference between the high-risk and low-risk groups was significantly different.

Conclusion

In conclusion, this study developed and validated SVM model, which better predicted 28-d all-cause mortality in critically ill patients with AP. In the future, we will continue to include patients from more institutions to conduct validation in different contexts and countries.

Precision Medicine in Inflammatory Bowel Disease: A Spotlight on Emerging Molecular Biomarkers

Inflammatory bowel diseases (IBD) remain challenging in terms of understanding their causes and in terms of diagnosing, treating, and monitoring patients. Modern diagnosis combines biomarkers, imaging, and endoscopic methods. Common biomarkers like CRP and fecal calprotectin, while invaluable tools, have limitations and are not entirely specific to IBD. The limitations of existing markers and the invasiveness of endoscopic procedures highlight the need to discover and implement new markers. With an ideal biomarker, we could predict the risk of disease development, as well as the possibility of response to a particular therapy, which would be significant in elucidating the pathogenesis of the disease. Recent research in the fields of machine learning, proteomics, epigenetics, and gut microbiota provides further insight into the pathogenesis of the disease and is also revealing new biomarkers. New markers, such as BAFF, PGE-MUM, oncostatin M, microRNA panels, αvβ6 antibody, and S100A12 from stool, are increasingly being identified, with αvβ6 antibody and oncostatin M being potentially close to being presented into clinical practice. However, the specificity of certain markers still remains problematic. Furthermore, the use of expensive and less accessible technology for detecting new markers, such as microRNAs, represents a limitation for widespread use in clinical practice. Nevertheless, the need for non-invasive, comprehensive markers is becoming increasingly important regarding the complexity of treatment and overall management of IBD.

Establishing a machine learning model based on dual-energy CT enterography to evaluate Crohn's disease activity

OBJECTIVES

The simplified endoscopic score of Crohn's disease (SES-CD) is the gold standard for quantitatively evaluating Crohn's disease (CD) activity but is invasive. This study aimed to develop and validate a machine learning (ML) model based on dual-energy CT enterography (DECTE) to noninvasively evaluate CD activity.

METHODS

We evaluated the activity in 202 bowel segments of 46 CD patients according to the SES-CD score and divided the segments randomly into training set and testing set at a ratio of 7:3. Least absolute shrinkage and selection operator (LASSO) was used for feature selection, and three models based on significant parameters were established based on logistic regression. Model performance was evaluated using receiver operating characteristic (ROC), calibration, and clinical decision curves.

RESULTS

There were 110 active and 92 inactive bowel segments. In univariate analysis, the slope of spectral curve in the venous phases (λHU-V) has the best diagnostic performance, with an area under the ROC curve (AUC) of 0.81 and an optimal threshold of 1.975. In the testing set, the AUC of the three models established by the 7 variables to differentiate CD activity was 0.81-0.87 (DeLong test p value was 0.071-0.766, p > 0.05), and the combined model had the highest AUC of 0.87 (95% confidence interval (CI): 0.779-0.959).

CONCLUSIONS

The ML model based the DECTE can feasibly evaluate CD activity, and DECTE parameters provide a quantitative analysis basis for evaluating specific bowel activities in CD patients.

CRITICAL RELEVANCE STATEMENT

The machine learning model based on dual-energy computed tomography enterography can be used for evaluating Crohn's disease activity noninvasively and quantitatively.

KEY POINTS

Dual-energy CT parameters are related to Crohn's disease activity. Three machine learning models effectively evaluated Crohn's disease activity. Combined models based on conventional and dual-energy CT have the best performance.

Utility of four machine learning approaches for identifying ulcerative colitis and Crohn's disease

Objective

Peripheral blood routine parameters (PBRPs) are simple and easily acquired markers to identify ulcerative colitis (UC) and Crohn's disease (CD) and reveal the severity, whereas the diagnostic performance of individual PBRP is limited. We, therefore used four machine learning (ML) models to evaluate the diagnostic and predictive values of PBRPs for UC and CD.

Methods

A retrospective study was conducted by collecting the PBRPs of 414 inflammatory bowel disease (IBD) patients, 423 healthy controls (HCs), and 344 non-IBD intestinal diseases (non-IBD) patients. We used approximately 70 % of the PBRPs data from both patients and HCs for training, 30 % for testing, and another group for external verification. The area under the receiver operating characteristic curve (AUC) was used to evaluate the diagnosis and prediction performance of these four ML models.

Results

Multi-layer perceptron artificial neural network model (MLP-ANN) yielded the highest diagnostic performance than the other three models in six subgroups in the training set, which is helpful for discriminating IBD and HCs, UC and CD, active CD and remissive CD, active UC and remissive UC, non-IBD and HCs, and IBD and non-IBD with the AUC of 1.00, 0.988, 0.942, 1.00, 0.986, and 0.97 in the testing set, as well as the AUC of 1.00, 1.00, 0.773, 0.904, 1.00 and 0.992 in the external validation set.

Conclusion

PBRPs-based MLP-ANN model exhibited good performance in discriminating between UC and CD and revealing the disease activity; however, a larger sample size and more models need to be considered for further research.