Prediction of thirty-day morbidity and mortality after duodenal switch using an artificial neural network

Evaluation of patients on immunosuppressants undergoing sleeve gastrectomy, Roux-en-Y gastric bypass, and duodenal switch: analysis of 19,414 patients

BACKGROUND

Bariatric surgery is being offered to more medically complex patients, including patients on immunosuppressants, although outcomes after different bariatrics surgeries have not been studied in this population.

OBJECTIVES

We compared perioperative safety of sleeve gastrectomy (SG), Roux-en-Y gastric bypass (RYGB), and duodenal switch (DS) in patients on immunosuppression.

SETTING

National sample from the Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program (MBSAQIP) database.

METHODS

The MBSAQIP database was queried from the years 2015 to 2021 for adult patients on chronic immunosuppression who underwent SG, RYGB, or DS. Revisional, open, endoscopic, or emergency surgeries were excluded, as were patients with an American Society of Anesthesiologists class of 5 and patients without full 30-day follow-up. Propensity-score matching was performed with a 3:3:1 ratio (SG:RYGB:DS) controlling for surgical approach, sex, age, functional status, American Society of Anesthesiologists, body mass index, and comorbidities.

RESULTS

There were 19,414 patients on immunosuppression who underwent SG (n = 14,358), RYGB (n = 4864), or DS (n = 192). After propensity-score matching , RYGB and DS had longer LOS (P < .01), greater global 30-day complication (P < .01), and 30-day reoperation rates (P = .048). Compared with SG and RYGB, DS had greater rates of patients requiring mechanical ventilation >48-hour postoperatively (P < .05). Compared with SG, DS had greater rates of renal insufficiency (P = .01), organ space infection (P = .01), unplanned intubation (P < .01), and unplanned intensive care unit admission (P < .01).

CONCLUSIONS

For patients on immunosuppression, SG carried the lowest complication and reoperation rates, whereas DS had overall complication rates in line with RYGB.

Rates and Risk Factors for 30-Day Morbidity After One-Stage Vertical Banded Gastroplasty Conversions: A Retrospective Analysis

Background: The vertical banded gastroplasty (VBG) is a historic restrictive bariatric operation often requiring further surgery. In this investigation utilizing the 2021 Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program (MBSAQIP) national dataset, we aim to better define the outcomes of VBG conversions.Methods: We queried the 2021 MBSAQIP dataset for patients who underwent a conversion from a VBG to Roux-en-Y gastric bypass (RYGB) or sleeve gastrectomy (SG). Demographics, comorbidities, laboratory values, and additional patient factors were examined. Rates of key consequential outcome measures 30-day readmission, reoperation, reintervention, mortality, and a composite endpoint (at least 1 of the 4) were further calculated.Results: We identified 231 patients who underwent conversion from VBG to SG (n = 23), RYGB (n = 208), or other anatomy (n = 6), of which 93% of patients were female, and 22% of non-white race. The median age was 56 years and body-mass index (BMI) was 43 kg/m2. The most common surgical indications included weight considerations (48%), reflux (25%), anatomic causes (eg, stricture, fistula, and ulcer; 10%), and dysphagia (6.5%). Thirty-day morbidity rates included reoperation (7.8%), readmission (9.1%), reintervention (4.3%), mortality (.4%), and the composite endpoint (15%). Upon bivariate analysis, we did not identify any specific risk factor for the 30-day composite endpoint.Discussion: One-stage VBG conversions to traditional bariatric anatomy are beset with higher 30-day morbidity relative to primary procedures. Additional MBSAQIP data will be required for aggregation, to better characterize the risk factors inherent in these operations.

Machine learning improves prediction of postoperative outcomes after gastrointestinal surgery: a systematic review and meta-analysis

BACKGROUND

Machine learning (ML) approaches have become increasingly popular in predicting surgical outcomes. However, it is unknown whether they are superior to traditional statistical methods such as logistic regression (LR). This study aimed to perform a systematic review and meta-analysis to compare the performance of ML vs LR models in predicting postoperative outcomes for patients undergoing gastrointestinal (GI) surgery.

METHODS

A systematic search of Embase, MEDLINE, Cochrane, Web of Science, and Google Scholar was performed through December 2022. The primary outcome was the discriminatory performance of ML vs LR models as measured by the area under the receiver operating characteristic curve (AUC). A meta-analysis was then performed using a random effects model.

RESULTS

A total of 62 LR models and 143 ML models were included across 38 studies. On average, the best-performing ML models had a significantly higher AUC than the LR models (ΔAUC, 0.07; 95% CI, 0.04-0.09; P < .001). Similarly, on average, the best-performing ML models had a significantly higher logit (AUC) than the LR models (Δlogit [AUC], 0.41; 95% CI, 0.23-0.58; P < .001). Approximately half of studies (44%) were found to have a low risk of bias. Upon a subset analysis of only low-risk studies, the difference in logit (AUC) remained significant (ML vs LR, Δlogit [AUC], 0.40; 95% CI, 0.14-0.66; P = .009).

CONCLUSION

We found a significant improvement in discriminatory ability when using ML over LR algorithms in predicting postoperative outcomes for patients undergoing GI surgery. Subsequent efforts should establish standardized protocols for both developing and reporting studies using ML models and explore the practical implementation of these models.

Prediction of 30-Day Morbidity and Mortality After Conversion of Sleeve Gastrectomy to Roux-en-Y Gastric Bypass: Use of an Artificial Neural Network

BACKGROUND

Conversion of sleeve gastrectomy to Roux-en-Y gastric bypass is indicated primarily for unsatisfactory weight loss or gastroesophageal reflux disease (GERD). This study aimed to use a comprehensive database to define predictors of 30-day reoperation, readmission, reintervention, or mortality. An artificial neural network (ANN) was employed to optimize prediction of the composite endpoint (occurrence of 1+ morbid event).

METHODS

Areview of 8895 patients who underwent conversion for weight-related or GERD-related indications was performed using the 2021 MBSAQIP national dataset. Demographics, comorbidities, laboratory values, and other factors were assessed for bivariate and subsequent multivariable associations with the composite endpoint (P ≤ .05). Factors considered in the multivariable model were imputed into a three-node ANN with 20% randomly withheld for internal validation, to optimize predictive accuracy. Models were compared using receiver operating characteristic (ROC) curve analysis.

RESULTS

39% underwent conversion for weight considerations and 61% for GERD. Rates of 30-day reoperation, readmission, reintervention, mortality, and the composite endpoint were 3.0%, 7.1%, 2.1%, .1%, and 9.1%, respectively. Of the nine factors associated with the composite endpoint on bivariate analysis, only non-white race (P < .001; odds ratio 1.4), lower body-mass index (P < .001; odds ratio .22), and therapeutic anticoagulation (P = .001; odds ratio 2.0) remained significant upon multivariable analysis. Areas under ROC curves for the multivariable regression, ANN training, and validation sets were .587, .601, and .604, respectively.

DISCUSSION

Identification of risk factors for morbidity after conversion offers critical information to improve patient selection and manage postoperative expectations. ANN models, with appropriate clinical integration, may optimize prediction of morbidity.

Artificial intelligence: Applications in critical care gastroenterology

Gastrointestinal (GI) complications frequently necessitate intensive care unit (ICU) admission. Additionally, critically ill patients also develop GI complications requiring further diagnostic and therapeutic interventions. However, these patients form a vulnerable group, who are at risk for developing side effects and complications. Every effort must be made to reduce invasiveness and ensure safety of interventions in ICU patients. Artificial intelligence (AI) is a rapidly evolving technology with several potential applications in healthcare settings. ICUs produce a large amount of data, which may be employed for creation of AI algorithms, and provide a lucrative opportunity for application of AI. However, the current role of AI in these patients remains limited due to lack of large-scale trials comparing the efficacy of AI with the accepted standards of care.