Clinical and Laboratory Characteristics of Anaemia in Hospitalized Patients with Inflammatory Bowel Disease

Development and Validation of Predictive Models for Inflammatory Bowel Disease Diagnosis: A Machine Learning and Nomogram-Based Approach

Background

Inflammatory bowel disease (IBD) is a chronic, incurable gastrointestinal disease without a gold standard for diagnosis. This study aimed to develop predictive models for diagnosing IBD, Crohn's disease (CD), and Ulcerative colitis (UC) by combining two approaches: machine learning (ML) and traditional nomogram models.

Methods

 Cohorts 1 and 2 comprised data from the UK Biobank (UKB), and the First Hospital of Jilin University, respectively, which represented the initial laboratory tests upon admission for 1135 and 237 CD patients, 2192 and 326 UC patients, and 1798 and 298 non-IBD patients. Cohorts 1 and 2 were used to create predictive models. The parameters of the machine learning model established by Cohorts 1 and 2 were merged, and nomogram models were developed using Logistic regression. Cohort 3 collected initial laboratory tests from 117 CD patients, 197 UC patients, and 241 non IBD patients at a tertiary hospital in different regions of China for external testing of three nomogram models.

Results

For Cohort 1, ML-IBD-1, ML-CD-1 and ML-UC-1 models developed using the LightGBM algorithm demonstrated exceptional discrimination (ML-IBD-1: AUC = 0.788; ML-CD-1: AUC = 0.772; ML-UC-1: AUC = 0.841). For Cohort 2, ML-IBD-2, ML-CD-2, and ML-UC-2 models developed using XGBoost and Logistic Regression algorithms demonstrated exceptional discrimination (ML-IBD-2: AUC = 0.894; ML-CD-2: AUC = 0.932; ML-UC-2: AUC = 0.778). The nomogram model exhibits good diagnostic capability (nomogram-IBD: AUC=0.778, 95% CI (0.688-0.868); nomogram-CD: AUC=0.744, 95% CI (0.710-0.778); nomogram-UC, AUC=0.702, 95% CI (0.591-0.814)). The predictive ability of the three models was validated in cohort 3 (nomogram-IBD: AUC=0.758, 95% CI (0.683-0.832); nomogram-CD: AUC=0.791, 95% CI (0.717-0.865); nomogram-UC, AUC=0.817, 95% CI (0.702-0.932)).

Conclusion

This study utilized three cohorts and developed risk prediction models for IBD, CD, and UC with good diagnostic capability, based on conventional laboratory data using ML and nomogram.

Inflammatory Bowel Diseases in the Elderly: A Focus on Disease Characteristics and Biological Therapy Patterns

Background: The incidence of inflammatory bowel diseases (IBDs) in elderly patients is constantly increasing. It results from the combination of an aging population with compounding prevalence of IBD, as well as the growing burden of elderly-onset IBD. The clinical characteristics of elderly patients differ from young subjects with IBD due to the multimorbidity or polypharmacy, affecting the choice of adequate therapeutic options. The aim of this study was to determine the clinical aspects and biological therapy safety in elderly Polish IBD patients. Methods: We conducted a retrospective study aimed at describing the demographic, clinical, and management characteristics of IBD patients treated with a biological therapy in two referral centers within the National Drug Program in Poland. Results: Out of the entire group of 366 studied patients, 51 (13.9%) were aged over 60-32 with ulcerative colitis (UC) and 19 with Crohn's disease (CD). The disease location was predominantly ileocolonic (57.89%) in patients with CD and pancolitis for patients with UC (56.25%). Most of the elderly IBD subjects were characterized by significant comorbidities, with Charlson Comorbidity Index (CCI) ≥ 1 in 66.67% patients. The probability of stopping biological therapy due to adverse events had the tendency to be higher in the CCI ≥ 1 group (20.58% vs. 5.88% in CCI = 0; p = 0.087). The main reasons for the therapy discontinuation included hypersensitivity reactions and liver enzyme abnormalities. Conclusions: In conclusion, our results underline the importance of assessing the comorbidity status instead of the age prior to initiating biological therapy, analyzing additional safety risks, and close monitoring in IBD patients with multiple comorbidities.

Potential Diagnostic Role of Hepcidin in Anemic Patients Affected by Inflammatory Bowel Disease: A Systematic Review

BACKGROUND

Anemia is the main extraintestinal comorbidity of Inflammatory Bowel Disease (IBD). Differentiating the type of anemia in these disorders is still a challenge. Hepcidin could be a promising biomarker to identify iron deficiency anemia (IDA), anemia of chronic disease (ACD) and the concomitant presence of both IDA and ACD.

METHODS

To evaluate the potential role of hepcidin dosage in the management of anemia in IBD patients, we performed a systematic review by a comprehensive literature analysis of original papers reporting the dosage of hepcidin in IBD patients. In all the articles reviewed, the dosage of ferritin was reported, and the correlation between hepcidin and ferritin has been used to compare these two biomarkers.

RESULTS

A total of 12 articles concerning the dosage of hepcidin in IBD were included, comprising in total of 976 patients. The results of the hepcidin values in IBD patients when compared with controls were conflicting. In fact, four articles described an increase in this biomarker, three showed a decrease and five did not find significant differences. The correlation with ferritin was positive and significant. In three studies, some differences between hepcidin dosages and ferritin levels indicate a possible role when IDA and ACD could be present at the same time.

CONCLUSIONS

Considering the contradictory data of the studies, the diagnostic role of hepcidin as a biomarker remains elusive in IBD patients. These differences could be due to the clinical characteristics of the patients enrolled that should be better defined in the future. A suitable clinical trial should be designed to outline the possible role of hepcidin in differentiating IDA, ACD and concomitant IDA and ACD in IBD patients. At the moment, ferritin still remains the best marker to diagnose these conditions, in addition to hemoglobin, transferrin saturation and CRP as recommended by the ECCO guidelines.

Clinical Significance of Erythroferrone and Bone Morphogenetic Protein-6 in Patients with Anemia in the Course of Inflammatory Bowel Disease

In recent years, a steady increase in the incidence of inflammatory bowel diseases (IBD) has been observed with anemia as their most common extraintestinal symptom. Erythroferrone and Bone Morphogenetic Protein 6 (BMP-6) are recently identified cytokines involved in the process of increased erythropoiesis in anemia of various pathomechanisms. The aim of this study was to analyze the concentration of erythroferrone and BMP-6 in IBD patients in relation to clinical and laboratory data. The study comprised 148 patients: 118 with IBD, including 73 (61.85%) diagnosed with anemia (42 with Crohn's disease (CD) (66.7%) and 31 (56.4%) with ulcerative colitis (UC)) and 30 as a control group. The erythroferrone concentration was significantly higher in IBD patients with anemia (p = 0.009) and higher in UC patients both with and without anemia (p = 0.018), compared to the control group. In CD, no similar difference was observed between patients with and without anemia. Regarding BMP-6, higher levels were found in CD patients with anemia compared to the control group (p = 0.021). The positive correlation between BMP-6 and iron concentration in UC was also noticed. In conclusion, we confirm an increase in erythroferrone concentration in the entire group of IBD patients with anemia, while BMP-6 levels were higher only in anemic CD patients. Due to the clinical importance of anemia in IBD, this problem is worth further analysis and research projects.