Machine learning prediction model for postoperative ileus following colorectal surgery.

BACKGROUND: Postoperative ileus (POI) continues to be a major cause of morbidity following colorectal surgery. Despite best efforts, the incidence of POI in colorectal surgery remains high (~30%). This study aimed to investigate machine learning techniques to identify risk factors for POI in colorectal surgery patients, to help guide further preventative strategies. METHODS: A TRIPOD-guideline-compliant retrospective study was conducted for major colorectal surgery patients at a single tertial care centre (2018-2022). The primary outcome was the occurrence of POI, defined as not achieving GI-2 (outcome measure of time to first stool and tolerance of oral diet) by day four. Multivariate logistic regression, decision trees, radial basis function and multilayer perceptron (MLP) models were trained using a random allocation of patients to training/testing data sets (80/20). The area under the receiver operating characteristic (AUROC) curves were used to evaluate model performance. RESULTS: Of 504 colorectal surgery patients, 183 (36%) experienced POI. Multivariate logistic regression, decision trees, radial basis function and MLP models returned an AUROC of 0.722, 0.706, 0.712 and 0.800, respectively. The MLP model had the highest sensitivity and specificity values. In addition to well-known risk factors for POI, such as postoperative hypokalaemia, surgical approach, and opioid use, the MLP model identified sarcopenia (ranked 4/30) as a potentially modifiable risk factor for POI. CONCLUSION: MLP outperformed other models in predicting POI. Machine learning can provide valuable insights into the importance and ranking of specific predictive variables for POI. Further research into the predictive value of preoperative sarcopenia for POI is required.

Pyridostigmine to Reduce the duration of postoperative Ileus after Colorectal surgery (PyRICo-RCT): randomized clinical trial.

BACKGROUND: Postoperative ileus, driven by the cholinergic anti-inflammatory pathway, is the most common complication in patients undergoing colorectal surgery. By inhibiting acetylcholinesterase, pyridostigmine can potentially modulate the cholinergic anti-inflammatory pathway and accelerate gastrointestinal recovery. This study aimed to assess the efficacy of pyridostigmine in improving gastrointestinal recovery after colorectal surgery. METHODS: This double-blinded RCT enrolled adult patients undergoing elective colorectal surgery at two hospitals in South Australia. Patients were randomized to 60 mg oral pyridostigmine or placebo twice daily starting 6 h after surgery until the first passage of stool. The primary outcome was GI-2, a validated composite measure of time to first stool and tolerance of oral diet. Secondary outcomes included incidence of postoperative ileus (defined as GI-2 greater than 4 days), duration of hospital stay, and 30-day complications, evaluated by intention-to-treat univariate analysis. RESULTS: Of 130 patients recruited (mean(s.d.) age 58.4(16.4) years; 73 men, 56%), 65 were allocated to each arm. The median GI-2 was 1 day shorter with pyridostigmine compared with placebo (2 (i.q.r. 1-3) versus 3 (2-4) days; P = 0.015). However, there were no significant differences in postoperative ileus (17.2 versus 21.5%; P = 0.532) or duration of hospital stay (median 5 (i.q.r. 4-8.75) versus 5 (4-7.5) days; P = 0.921). Similarly, there were no significant differences in overall complications, anastomotic leak, cardiac complications, or patient-reported side effects. CONCLUSION: Pyridostigmine resulted in a quicker return of GI-2 and was well tolerated. Larger multicentre studies are required to determine the optimal dosing and evaluate the impact of pyridostigmine in different surgical settings. Registration number: ACTRN12621000530820 (https://anzctr.org.au).

The Association of Weight With Surgical Morbidity in Infants Undergoing Enterostomy Reversal: A Study of the NSQIP-Pediatrics Database.

INTRODUCTION: Optimal criteria and timing for enterostomy closure (EC) in neonates is largely based on clinical progression and adequate weight, with most institutions using 2.0-2.5 kg as the minimum acceptable weight. It is unclear how the current weight cutoff affects post-operative morbidity. AIM: To determine how infant weight at the time of EC influences 30-day complications. METHODS: Infants weighing ≤4000 g who underwent EC were identified in the 2012-2019 ACS NSQIP-P database. Demographics, comorbidities, and 30-day outcomes were assessed using univariate analysis. Multivariable logistic regression controlling for ASA score, nutritional support, and ventilator support was used to estimate the independent association of weight on risk of 30-day complications. RESULTS: A total of 1692 neonates from the NSQIP-P database during the years 2012-2019 met inclusion criteria. Neonates weighing <2.5 kg were significantly more likely to have a younger gestational age, require ventilator support, and have concurrent comorbidities. Major morbidity, a composite outcome of the individual postoperative complications, was observed in 283 (16.7%) infants. ASA classifications 4 and 5, dependence on nutritional support, and ventilator support were independently associated with increased risk of 30-day complications. With respect to weight, we found no significant difference in major morbidity between infants weighing <2.5 kg and infants weighing ≥2.5 kg. CONCLUSION: Despite using a robust, national dataset, we could find no evidence that a defined weight cut-off was associated with a reduction in major morbidity, indicating that weight should not be a priority factor when determining eligibility for neonatal EC. LEVEL OF EVIDENCE: III.

Development of an FRα Companion Diagnostic Immunohistochemical Assay for Mirvetuximab Soravtansine.

CONTEXT.­: Folate receptor-α (FRα, encoded by the FOLR1 gene) is overexpressed in several solid tumor types, including epithelial ovarian cancer (EOC), making it an attractive biomarker and target for FRα-based therapy in ovarian cancer. OBJECTIVE.­: To describe the development, analytic verification, and clinical performance of the VENTANA FOLR1 Assay (Ventana Medical Systems Inc) in EOC. DESIGN.­: We used industry standard studies to establish the analytic verification of the VENTANA FOLR1 Assay. Furthermore, the VENTANA FOLR1 Assay was used in the ImmunoGen Inc-sponsored SORAYA study to select patients for treatment with mirvetuximab soravtansine (MIRV) in platinum-resistant EOC. RESULTS.­: The VENTANA FOLR1 Assay is highly reproducible, demonstrated by a greater than 98% overall percent agreement (OPA) for repeatability and intermediate precision studies, greater than 93% OPA for interreader and greater than 96% for intrareader studies, and greater than 90% OPA across all observations in the interlaboratory reproducibility study. The performance of the VENTANA FOLR1 Assay in the SORAYA study was evaluated by the overall staining acceptability rate, which was calculated using the number of patient specimens that were tested with the VENTANA FOLR1 Assay that had an evaluable result. In the SORAYA trial, data in patients who received MIRV demonstrated clinically meaningful efficacy, and the overall staining acceptability rate of the assay was 98.4%, demonstrating that the VENTANA FOLR1 Assay is safe and effective for selecting patients who may benefit from MIRV. Together, these data showed that the assay is highly reliable, consistently producing evaluable results in the clinical setting. CONCLUSIONS.­: The VENTANA FOLR1 Assay is a robust and reproducible assay for detecting FRα expression and identifying a patient population that derived clinically meaningful benefit from MIRV in the SORAYA study.