Surgical treatment of colonic Crohn's disease: a national snapshot study

Machine learning for temporary stoma after intestinal resection in surgical decision-making of Crohn's disease

BACKGROUND

Crohn's disease (CD) often necessitates surgical intervention, with temporary stoma creation after intestinal resection (IR) being a crucial decision. This study aimed to construct novel models based on machine learning (ML) to predict temporary stoma formation after IR for CD.

METHODS

Patient data who underwent IR for CD at our center between July 2017 and March 2023 were collected for inclusion in this retrospective study. Eligible CD patients were randomly divided into training and validation cohorts. Feature selection was executed using the least absolute shrinkage and selection operator. We employed three ML algorithms including traditional logistic regression, novel random forest and XG-Boost to create prediction models. The area under the curve (AUC), accuracy, sensitivity, specificity, precision, recall, and F1 score were used to evaluate these models. SHapley Additive exPlanation (SHAP) approach was used to assess feature importance.

RESULTS

A total of 252 patients with CD were included in the study, 150 of whom underwent temporary stoma creation after IR. Eight independent predictors emerged as the most valuable features. An AUC between 0.886 and 0.998 was noted among the three ML algorithms. The random forest (RF) algorithms demonstrated the most optimal performance (0.998 in the training cohort and 0.780 in the validation cohort). By employing the SHAP method, we identified the variables that contributed to the model and their correlation with temporary stoma formation after IR for CD.

CONCLUSIONS

The proposed RF model showed a good predictive ability for identifying patients at high risk for temporary stoma formation after IR for CD, which can assist in surgical decision-making in CD management, provide personalized guidance for temporary stoma formation, and improve patient outcomes.

Predicting short-term major postoperative complications in intestinal resection for Crohn's disease: A machine learning-based study

BACKGROUND

Due to the complexity and numerous comorbidities associated with Crohn's disease (CD), the incidence of postoperative complications is high, significantly impacting the recovery and prognosis of patients. Consequently, additional studies are required to precisely predict short-term major complications following intestinal resection (IR), aiding surgical decision-making and optimizing patient care.

AIM

To construct novel models based on machine learning (ML) to predict short-term major postoperative complications in patients with CD following IR.

METHODS

A retrospective analysis was performed on clinical data derived from a patient cohort that underwent IR for CD from January 2017 to December 2022. The study participants were randomly allocated to either a training cohort or a validation cohort. The logistic regression and random forest (RF) were applied to construct models in the training cohort, with model discrimination evaluated using the area under the curves (AUC). The validation cohort assessed the performance of the constructed models.

RESULTS

Out of the 259 patients encompassed in the study, 5.0% encountered major postoperative complications (Clavien-Dindo ≥ III) within 30 d following IR for CD. The AUC for the logistic model was 0.916, significantly lower than the AUC of 0.965 for the RF model. The logistic model incorporated a preoperative CD activity index (CDAI) of ≥ 220, a diminished preoperative serum albumin level, conversion to laparotomy surgery, and an extended operation time. A nomogram for the logistic model was plotted. Except for the surgical approach, the other three variables ranked among the top four important variables in the novel ML model.

CONCLUSION

Both the nomogram and RF exhibited good performance in predicting short-term major postoperative complications in patients with CD, with the RF model showing more superiority. A preoperative CDAI of ≥ 220, a diminished preoperative serum albumin level, and an extended operation time might be the most crucial variables. The findings of this study can assist clinicians in identifying patients at a higher risk for complications and offering personalized perioperative management to enhance patient outcomes.

Segmental Versus Total Colectomy for Crohn's Disease in the Biologic Era: Results From The SCOTCH International, Multicentric Study

BACKGROUND

The extent of resection in colonic Crohn's disease [cCD] is still a topic of debate, depending on the number of locations, the risk of recurrence and permanent stoma, and the role of medical therapy.

METHODS

The Segmental COlecTomy for CroHn's disease [SCOTCH] international study is a retrospective analysis on six tertiary centre prospective databases, comprising all consecutive, unselected patients operated on between 2000 and 2019 with segmental colectomy [SC] or total colectomy [TC] for cCD. The primary aim was long-term surgical recurrence. Secondary aims were perioperative complications, stoma formation and predictors of recurrence.

RESULTS

Among 687 patients, SC was performed in 285 [41.5%] and TC in 402 [58.5%]. Mean age at diagnosis and surgery, disease duration, and follow-up were 30 ± 15.8, 40.4 ± 15.4, 10.4 ± 8.6 and 7.1 ± 5.2 years respectively. Isolated cCD, inflammatory pattern, perianal CD, younger age, longer disease duration and preoperative maximal therapy were more frequent in TC, while SC presented more small bowel locations and perforating disease, required fewer 90-day re-admissions, and fewer temporary and definitive stomas. Morbidity and mortality were similar. The 15-year surgical recurrence was 44% in TC and 27% in SC [p = 0.006]. In patients with one to three diseased segments, recurrence risk was related to the omission of biological therapy (hazard ratio [HR] 5.6), the number of segments [HR 2.5], perianal disease [HR 1.9] and paediatric diagnosis [HR 2.8].

CONCLUSION

When technically feasible, SC is safe and reduces temporary and permanent stoma. Young age, number of locations and perianal disease adversely affect, but postoperative biological therapy significantly reduces, the long-term surgical recurrence.

Pretreatment with millet-derived selenylated soluble dietary fiber ameliorates dextran sulfate sodium-induced colitis in mice by regulating inflammation and maintaining gut microbiota balance

Inflammatory activation and intestinal flora imbalance play key roles in the development and progression of inflammatory bowel disease (IBD). Soluble dietary fiber (SDF) and selenium have been proven to be effective for preventing and relieving IBD. This study investigated and compared the therapeutic efficacy of millet-derived selenylated-soluble dietary fiber (Se-SDF) against dextran sulfate sodium (DSS)-induced colitis in mice alone or through the synergistic interaction between selenium and SDF. In female mice, Se-SDF markedly alleviated body weight loss, decreased colon length, reduced histological damage scores, and enhanced IL-10 expression to maintain the barrier function of intestinal mucosa compared to male mice. The 16S rRNA sequence analysis further indicated that pretreatment with Se-SDF restored the gut microbiota composition in female mice by increasing the relative abundance of Lactobacillus and the Firmicutes/Bacteroidetes ratio. In conclusion, these findings demonstrated that Se-SDF can protect against DSS-induced colitis in female mice by regulating inflammation and maintaining gut microbiota balance. This study, therefore, provides new insights into the development of Se-SDF as a supplement for the prevention and treatment of colitis.

Prehabilitation prior to intestinal resection in Crohn's disease patients: An opinion review

Patients with Crohn's disease (CD) are at a considerable risk for intestinal surgery. Approximately 25% of patients with CD will undergo an intestinal resection within 10 years of diagnosis. Postoperative complications after CD surgery have been reported in 20%-47% of the patients. Both general and CD-related risk factors are associated with postoperative complications, and comprise non-modifiable (e.g., age) and potentially modifiable risk factors (e.g., malnutrition). Prehabilitation focuses on the preoperative period with strategies designed to optimize modifiable risk factors concerning the physical and mental condition of the individual patient. The aim of prehabilitation is to enhance postoperative recovery and return to or even improve preoperative functional capacity. Preoperative improvement of nutritional status, physical fitness, cessation of smoking, psychological support, and critical revision of preoperative use of CD medication are important strategies. Studies of the effect on postoperative outcome in CD patients are scarce, and guidelines lack recommendations on tailored management. In this opinion review, we review the current evidence on the impact of screening and management of nutritional status, physical fitness, CD medication and laboratory values on the postoperative course following an intestinal resection in CD patients. In addition, we aim to provide guidance for individualized multimodal prehabilitation in clinical practice concerning these modifiable factors.