Page 40 - Read Online

Page 428 Liu et al. Art Int Surg. 2025;5:425-33 https://dx.doi.org/10.20517/ais.2025.01

Table 1. Included studies
Publication
Title Authors Use of AI
year
[26]
Use of the KSVM-based system for the definition, validation and identification of Licari et al. 2019 Predict
the incisional hernia recurrence risk factors complications
[28]
Neural network model to detect long-term skin and soft tissue infection after O’Brien et al. 2020 Predict
hernia repair complications
[22]
Biomechanics applied to incisional hernia repair - considering the critical and the Kallinowski et al. 2021 Preoperative
gained resistance towards impacts related to pressure planning
Development and validation of image-based deep learning models to predict Elhage et al. [25] 2021 Predict
surgical complexity and complications in abdominal wall reconstruction complications
Novel machine learning approach for the prediction of hernia recurrence, surgical Hassan et al. [29] 2022 Predict
complication, and 30-day readmission after abdominal wall reconstruction complications
Preoperative computed tomography morphological features indicative of incisional McAuliffe et al. [21] 2022 Predict occurrence
hernia formation after abdominal surgery
Predicting rare outcomes in abdominal wall reconstruction using image-based Ayuso et al. [27] 2023 Predict
deep learning models complications
Optimal computed tomography-based biomarkers for prediction of incisional Talwar et al. [17] 2024 Predict occurrence
hernia formation
[35]
Exploring the potential of ChatGPT-4 in responding to common questions about Li et al. 2024 Answer patient
abdominoplasty: an AI-based case study of a plastic surgery consultation questions
[37]
How appropriate are recommendations of online chat-based artificial intelligence Lima et al. 2024 Answer patient
(ChatGPT) to common questions on ventral hernia repair? questions
[30]
Deep learning model utilizing clinical data alone outperforms image-based model Wilson et al. 2024 Predict
for hernia recurrence following abdominal wall reconstruction with long-term complications
follow up
Can AI answer my questions? Utilizing artificial intelligence in the perioperative Lim et al. [36] 2024 Answer patient
assessment for abdominoplasty patients questions
AI: Artificial intelligence.

DISCUSSION
Predicting hernia occurrence
Two studies have evaluated the use of AI to predict incisional hernia. Talwar et al. aimed to establish a
predictive framework using advanced image analysis and machine learning by analyzing CT scans from 212
[17]
adult patients who underwent elective colorectal surgery between 2005 and 2016 . The images were
analyzed for 279 features, including abdominopelvic volume, body wall skeletal musculature volume, and
pelvic volume pressure ratio. The authors identified optimal predictive biomarkers for incisional hernia:
volumes and ratios of visceral adipose tissue (VAT), inner and outer aspects of the body wall skeletal
musculature. Machine learning models were then trained on these CT-based biomarkers to predict hernia
occurrence, using ensemble boosting, random forest, and support vector machine (SVM) algorithms.

Ensemble boosting combines multiple algorithms to enhance predictive performance, often outperforming
individual models . It involves stacking decision trees or neural networks to improve accuracy. The
[18]
random forest method uses multiple decision trees run in parallel, each built on random data subsets, with
final predictions derived from aggregating individual tree outputs . SVM algorithms are widely used for
[19]
handling both linear and non-linear classification tasks . Among these, ensemble boosting was the best-
[20]
performing classifier.

A second study also assessed CT imaging to predict incisional hernia following colorectal surgery . Using
[21]
an SVM algorithm, this study evaluated the predictive accuracy of various features and found that widening
of the rectus complex, increased visceral volume, and body wall skeletal muscle atrophy were all indicative
of hernia risk. Both studies highlight increased intra-abdominal pressure - as measured by 3D imaging