Burden and Trends of IBD in 5 Asian Countries From 1990 to 2019: A Comparison With the United States and the United Kingdom

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.

Global, Regional, and National Burdens with Temporal Trends of Early-, Intermediate-, and Later-Onset Gastric Cancer from 1990 to 2019 and Predictions up to 2035

Simple Summary

Early, intermediate, and late-onset gastric cancer (EOGC, IOGC, LOGC) incidence and death rates differed globally, regionally, and nationally in 2019. From 1990 to 2019, EOGC showed a slower decrease in incidence rate worldwide than IOGC and LOGC, whereas EOGC and LOGC showed slower decreases in mortality than IOGC. The worldwide incidence rate of EOGC was predicted to increase substantially from 2020 to 2035, while that for LOGC was predicted to increase slightly and that for IOGC was predicted to remain stable over the same period. This study revealed significant differences in the burdens and temporal trends of EOGC, IOGC, and LOGC, and highlighted the importance of tailored cancer-control measures in neglected subpopulations, especially in patients with EOGC.

Abstract

Background: Evidence for estimating and predicting the temporal trends of gastric cancer in different age groups is lacking. Methods: Data of early-, intermediate-, and later-onset gastric cancer (EOGC, IOGC, LOGC) was from the Global Burden of Diseases Study 2019. The incidences and deaths due to EOGC, IOGC, and LOGC were analyzed by period, sex, geographic location, and sociodemographic incidence. Temporal trends were evaluated by estimated annual percentage changes (EAPCs). The incidences and temporal trends were predicted until 2035. Results: There were substantial differences in the incidence and death rates of the three populations at global, regional and national levels in 2019. From 1990 to 2019, EOGC (EAPC, −0.84) showed a slower decrease in incidence rate worldwide than IOGC (EAPC, −1.77) and LOGC (EAPC, −1.10), whereas EOGC and LOGC showed slower decreases in mortality than IOGC. The worldwide incidence rate of EOGC (EAPC, 1.44) was predicted to increase substantially from 2020 to 2035, while that for LOGC (EAPC, 0.43) was predicted to increase slightly and that for IOGC (EAPC, −0.01) was predicted to remain stable over the same period. Conclusions: This study revealed differences in the burdens and temporal trends of EOGC, IOGC, and LOGC, and highlighted the importance of tailored cancer-control measures in neglected subpopulations, especially in patients with EOGC.