Cataract Surgery in Uveitis: Risk Factors, Outcomes, and Complications

Predicting the risk of gastroparesis in critically ill patients after CME using an interpretable machine learning algorithm - a 10-year multicenter retrospective study

Background

Gastroparesis following complete mesocolic excision (CME) can precipitate a cascade of severe complications, which may significantly hinder postoperative recovery and diminish the patient's quality of life. In the present study, four advanced machine learning algorithms-Extreme Gradient Boosting (XGBoost), Random Forest (RF), Support Vector Machine (SVM), and k-nearest neighbor (KNN)-were employed to develop predictive models. The clinical data of critically ill patients transferred to the intensive care unit (ICU) post-CME were meticulously analyzed to identify key risk factors associated with the development of gastroparesis.

Methods

We gathered 34 feature variables from a cohort of 1,097 colon cancer patients, including 87 individuals who developed gastroparesis post-surgery, across multiple hospitals, and applied a range of machine learning algorithms to construct the predictive model. To assess the model's generalization performance, we employed 10-fold cross-validation, while the receiver operating characteristic (ROC) curve was utilized to evaluate its discriminative capacity. Additionally, calibration curves, decision curve analysis (DCA), and external validation were integrated to provide a comprehensive evaluation of the model's clinical applicability and utility.

Results

Among the four predictive models, the XGBoost algorithm demonstrated superior performance. As indicated by the ROC curve, XGBoost achieved an area under the curve (AUC) of 0.939 in the training set and 0.876 in the validation set, reflecting exceptional predictive accuracy. Notably, in the k-fold cross-validation, the XGBoost model exhibited robust consistency across all folds, underscoring its stability. The calibration curve further revealed a favorable concordance between the predicted probabilities and the actual outcomes of the XGBoost model. Additionally, the DCA highlighted that patients receiving intervention under the XGBoost model experienced significantly greater clinical benefit.

Conclusion

The onset of postoperative gastroparesis in colon cancer patients remains an elusive challenge to entirely prevent. However, the prediction model developed in this study offers valuable assistance to clinicians in identifying key high-risk factors for gastroparesis, thereby enhancing the quality of life and survival outcomes for these patients.

Uveitic Flare-Ups After Gonioscopy-Assisted Transluminal Trabeculotomy (GATT) in Patients with Uveitic Glaucoma

PURPOSE

To assess the risk of gonioscopy-assisted transluminal trabeculotomy (GATT) inducing an uveitic flare-up in patients with uveitic glaucoma (UG).

METHODS

This retrospective study included consecutive UG patients who underwent GATT at a single medical center between June 2020 and September 2022. The main outcome measure was the occurrence of a surgery-related uveitic complication defined as either an uveitic flare-up defined by the Standardization of Uveitis Nomenclature (SUN) criteria, or the appearance of cystoid macular edema (CME) from 2 weeks to 3 months after surgery.

RESULTS

A total of 25 eyes of 22 patients were included in the study. Age ranged from 10-78 and 64% were women. The most common uveitic etiologies were juvenile idiopathic arthritis (JIA, 24%) and herpetic infection (24%). A total of 48%of the patients were on systemic immunosuppressants prior and unrelated to surgery. Eight eyes (32%) had severe glaucomatous damage prior to surgery, and 20% of the patients had undergone previous glaucoma surgery. Two cases (8%) demonstrated uveitic flare-up in the early postoperative period: a case of mild anterior chamber reaction and a case of CME with persistent edema prior to surgery. Average intraocular pressure (IOP) was reduced from 26.7 mm Hg on four medications to 12.2 on 1.1 after 1 year. One patient required reoperation for IOP control.

CONCLUSIONS

With careful pre and postoperative care, GATT seems to be a low-risk procedure for uveitic flare-ups in patients with UG.

Incidence and Remission of Post-Surgical Cystoid Macular Edema Following Cataract Surgery in Eyes With Intraocular Inflammation

PURPOSE

To evaluate the incidence, remission, and relapse of post-surgical cystoid macular edema (PCME) following cataract surgery in inflammatory eye disease.

METHODS

A total of 1859 eyes that had no visually significant macular edema prior to cataract surgery while under tertiary uveitis management were included. Standardized retrospective chart review was used to gather clinical data. Univariable and multivariable logistic regression models with adjustment for inter-eye correlations were performed.

RESULTS

PCME causing VA 20/50 or worse was reported in 286 eyes (15%) within 6 months of surgery. Adults age 18-64 years as compared to children (adjusted odds ratio [aOR] = 2.42, for ages 18 to 44 years and aOR = 1.93 for ages 45 to 64 years, overall P = .02); concurrent use of systemic immunosuppression (conventional aOR 1.53 and biologics aOR = 2.68, overall P = .0095); preoperative VA 20/50 or worse (overall P < .0001); cataract surgery performed before 2000 (overall P = .03) and PMCE in fellow eye (aOR = 3.04, P = .0004) were associated with development of PCME within 6 months of cataract surgery. PCME resolution was seen in 81% of eyes at 12 months and 91% of eyes at 24 months. CME relapse was seen in 12% eyes at 12 months and 19% eyes at 24 months.

CONCLUSIONS

PCME occurs frequently in uveitic eyes undergoing cataract surgery; however, most resolve within a year. CME recurrences likely are due to the underlying disease process and not relapses of PCME.

Machine learning-based prediction of gastroparesis risk following complete mesocolic excision

BACKGROUND

Gastroparesis is a major complication following complete mesocolic excision (CME) and significantly impacts patient outcomes. This study aimed to create a machine learning model to pinpoint key risk factors before, during, and after surgery, effectively predicting the risk of gastroparesis after CME.

METHODS

The study involved 1146 patients with colon cancer, out of which 95 developed gastroparesis. Data were collected on 34 variables, including demographics, chronic conditions, pre-surgery test results, types of surgery, and intraoperative details. Four machine learning techniques were employed: extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). The evaluation involved k-fold cross-validation, receiver operating characteristic (ROC) analysis, calibration curves, decision curve analysis (DCA), and external validation.

RESULTS

XGBoost excelled in its performance for predictive models. ROC analysis showed high accuracy for XGBoost, with area under the curve (AUC) scores of 0.976 for the training set and 0.906 for the validation set. K-fold cross-validation confirmed the model's stability, and calibration curves indicated high predictive accuracy. Additionally, DCA highlighted XGBoost's superior patient benefits for intervention treatments. An AUC of 0.77 in external validation demonstrated XGBoost's strong generalization ability.

CONCLUSION

The XGBoost-fueled predictive model for post-surgery colon cancer patients proved highly effective. It underlined gastroparesis as a significant post-operative issue, associated with advanced age, prolonged surgeries, extensive intraoperative blood loss, surgical techniques, low serum protein levels, anemia, diabetes, and hypothyroidism.