Page 53 - Read Online

Shapey et al. Art Int Surg 2023;3:1-13 https://dx.doi.org/10.20517/ais.2022.31 Page 11

bilirubin: 0.584, Fibrosis index based on the 4-factor -4: 0.665, and aspartate transaminase-platelet ratio
[50]
index .
In all three studies, generalisability of the ML models outside of a hepatitis B endemic population remains to
[47]
be seen . This is important, because HCC associated with hepatitis C predominates in Western
populations, which also tend to be older and more obese .
[51]
CONCLUSION
ML shows great promise in substantially increasing the performance of statistical models to predict
postoperative complications following hepatobiliary and pancreatic surgery. The accuracy, validity and
integrity of data that are input into ML predictive models are central to its future success. Future studies
[52]
should follow the TRIPOD-AI guidance that is currently in development . ML has the potential to
improve outcomes following hepato-biliary and pancreatic surgery by reducing errors through highlighting
known risks of complications using supervised learning and by gaining greater insights through identifying
previously under-appreciated aspects of care using unsupervised learning. The success or failure of ML to
enhance clinical care will not be determined by computer science. Rather, it will be determined at a human
level through our willingness to integrate the compassion of clinical care with the objectivity of data science,
through our acceptance and correction of our own errors in clinical practice and data coding, and through
the cultures that dominate our workplace environments and shape our attitude towards life-long learning.

DECLARATIONS
Authors’ contributions
Concept and design of the paper, data collection, and authorship: Shapey IM, Sultan M

Availability of data and materials
Not applicable.

Financial support and sponsorship
None.

Conflicts of interest
Both authors declared that there are no conflicts of interest.

Ethical approval and consent to participate
Not applicable.

Consent for publication
Not applicable.

Copyright
© The Author(s) 2023.

REFERENCES
1. Versteijne E, van Dam JL, Suker M, et al. Neoadjuvant chemoradiotherapy versus upfront surgery for resectable and borderline
resectable pancreatic cancer: long-term results of the dutch randomized PREOPANC trial. J Clin Oncol 2022;40:1220-30. DOI
PubMed
2. van der Gaag NA, Rauws EA, van Eijck CH, et al. Preoperative biliary drainage for cancer of the head of the pancreas. N Engl J Med
2010;362:129-37. DOI PubMed
3. Hackert T, Hinz U, Fritz S, et al. Enucleation in pancreatic surgery: indications, technique, and outcome compared to standard