Can We Predict Incisional Hernia?

Abstract

Objective: The aim of this study was to identify procedure-specific risk factors independently associated with incisional hernia (IH) and demonstrate the feasibility of preoperative risk stratification through the use of an IH risk calculator app and decision–support interface. Summary Background Data: IH occurs after 10% to 15% of all abdominal surgeries (AS) and remains among the most challenging, seemingly unavoidable complications. However, there is a paucity of readily available, actionable tools capable of predicting IH occurrence at the point-of-care. Methods: Patients (n = 29,739) undergoing AS from 2005 to 2016 were retrospectively identified within inpatient and ambulatory databases at our institution. Surgically treated IH, complications, and costs were assessed. Predictive models were generated using regression analysis and corroborated using a validation group. Results: The incidence of operative IH was 3.8% (N = 1127) at an average follow-up of 57.9 months. All variables were weighted according to β-coefficients generating 8 surgery-specific predictive models for IH occurrence, all of which demonstrated excellent risk discrimination (C-statistic = 0.76–0.89). IH occurred most frequently after colorectal (7.7%) and vascular (5.2%) surgery. The most common occurring risk factors that increased the likelihood of developing IH were history of AS (87.5%) and smoking history (75%). An integrated, surgeon-facing, point-of-care risk prediction instrument was created in an app for preoperative estimation of hernia after AS. Conclusions: Operative IH occurred in 3.8% of patients after nearly 5 years of follow-up in a predictable manner. Using a bioinformatics approach, risk models were transformed into 8 unique surgery-specific models. A risk calculator app was developed which stakeholders can access to identify high-risk IH patients at the point-of-care.

How to Develop a Risk Prediction Smartphone App

“…The individual risk model parameters were incorporated into specialty-specific modules and implemented into an accessible Web-based platform (http://www.pennherniariskcalc.com) and an iOS/Android compatible mobile app, entitled “Penn Hernia Risk Calculator.” 25 The final app contains the following pages in successive order (Figure 4):The user is first presented with a home-page disclaimer that the user must acknowledge before proceeding. Our disclaimer states: “This tool and the underlying data are not intended to replace clinical judgment, but as an adjunct to predict risk.…”

“…We have illustrated how this was achieved in our case through the development of the point-of-care Penn Hernia Risk Calculator app and have provided our blueprint for those who desire to pursue similar efforts. 25…”

“…Our app aids clinicians in predicting incisional hernia occurrence, following abdominal surgery (1), which has a long list of modifiable risk factors, such as smoking status and BMI (2). 25 The period of preoperative planning prior to a non-emergent abdominal surgery fulfills criteria (3) and (4).…”

“…Herein, we will provide examples of how our team completed this step, but as our goal is not to guide model development, rather app creation, we will provide a cursory explanation. For a detailed explanation on how our team generated the statistical model, refer to Basta et al’s 25 publication.…”

Artificial Intelligence-Assisted Surgery: Potential and Challenges

“…For example, in oncological liver surgery, one would like to have a system that combines patient information (laboratory results, imaging, comorbidities, and previous surgeries) with evidence-based information (scientific publications) and surgical experience (the clinical course of previously treated patients) to avoid post-hepatectomy liver failure or to choose the optimal multimodal treatment. Similarly, AI may help to improve systems of predictive analytics that estimate survival after pancreatoduodenectomy for pancreatic cancer [47] or secondary effects of surgery, such as incisional hernia [48].…”