Page 76 - Read Online

Page 34 McGivern et al. Art Int Surg 2023;3:27-47 https://dx.doi.org/10.20517/ais.2022.39

Table 2. Summary of included studies focusing on prognostic uses of AI in HPB surgery
Year of AI
Authors Location Organ Aim Design Data
publication method
[36]
Singal et al. 2013 USA L ML Develop and compare predictive Prospective Patient factors
models for HCC development study
among cirrhotic patients using
conventional regression analysis
and machine-learning algorithms
[37]
Banerjee et al. 2015 USA L ML/CV RVI was assessed for its ability to Prospective CT images
predict MVI and outcomes in evaluation of a
patients with HCC who underwent retrospective
surgical resection or liver cohort
transplant
Walczak et al. [38] 2017 USA P ML Assess the accuracy of artificial Retrospective Patient factors
neural networks in predicting study
survival in patients with pancreatic
cancer using both clinical and
patient-centered data
[39]
Ying Zhou et al. 2017 China L ML/CV Develop a CT-based radiomics Retrospective CT images
signature and assess its ability to study
preoperatively predict the early
recurrence (≤ 1 year) of
hepatocellular carcinoma (HCC)
[40]
Zheng et al. 2018 China L ML/CV Developed a CT–based radiomic Retrospective CT images
nomogram to predict recurrence- study
free survival rates for HCC after
resection, ablation, and transplant
[41]
Ivanics et al. 2019 Canada L ML Leverage machine learning to Retrospective Patient factors
develop an accurate post- study
transplantation HCC recurrence
prediction calculator
Sala Elarre et al. [42] 2019 Spain P ML Evaluated the 2-year relapse risk Retrospective Patient factors
for pancreatic cancer patients study
based on a machine-learning
algorithm
Marinelli et al. [43] 2019 USA L NLP/DL Determine if weakly supervised Retrospective Radiology
learning/active transfer learning study reports/CT
can hasten clinical deployment of images
deep learning models for liver
segmentation
Naseif et al. [44] 2019 USA P ML/CV Develop a delta-radiomic process Retrospective CT images
based on machine learning to study
predict the treatment response of
pancreatic cancer
Shan et al. [45] 2019 China L ML/CV A Prediction model based on Retrospective CT images
peritumoral radiomics signatures study
from CT - investigate its efficiency
in predicting early recurrence of
HCC after curative treatment
[46]
Chen et al. 2020 China L CV/ML Establish a radiomics-based Retrospective MRI images
clinical model for preoperative study
prediction of PHLF in HCC
[47]
Han et al. 2020 South P ML Risk prediction model for POPF Retrospective Patient factors
Korea using AI study
Kambakamba 2020 Switzerland P ML The potential of machine learning- Retrospective CT images
et al. [48] based approaches to describe the study
pancreatic texture and to predict
POPF
[49]
Merath et al. 2020 USA L/P ML Assess ML algorithm to predict the Retrospective Patient factors
patient risk of developing study
complications following liver,
pancreatic or colorectal surgery
[50]
Saillard et al. 2020 France L DL Evaluate the effectiveness of AI Development Histology
algorithms to predict survival and testing of AI images
following HCC resection models
[51]
Cesaretti et al. 2020 France L ML/DL/CV Automatizing liver-graft Prospective Surgery images