A machine learning analysis of difficulty scoring systems for laparoscopic liver surgery.
Difficulty scoring system
Laparoscopic liver resection
Machine learning
Patient selection
Textbook outcome
Journal
Surgical endoscopy
ISSN: 1432-2218
Titre abrégé: Surg Endosc
Pays: Germany
ID NLM: 8806653
Informations de publication
Date de publication:
12 2022
12 2022
Historique:
received:
30
08
2021
accepted:
27
04
2022
pubmed:
24
5
2022
medline:
16
11
2022
entrez:
23
5
2022
Statut:
ppublish
Résumé
In the last decade, several difficulty scoring systems (DSS) have been proposed to predict technical difficulty in laparoscopic liver resections (LLR). The present study aimed to investigate the ability of four DSS for LLR to predict operative, short-term, and textbook outcomes. Patients who underwent LLR at a single tertiary referral center from January 2014 to June 2020 were included in the present study. Four DSS for LLR (Halls, Hasegawa, Kawaguchi, and Iwate) were investigated to test their ability to predict operative and postoperative complications. Machine learning algorithms were used to identify the most important DSS associated with operative and short-term outcomes. A total of 346 patients were included in the analysis, 28 (8.1%) patients were converted to open surgery. A total of 13 patients (3.7%) had severe (Clavien-Dindo ≥ 3) complications; the incidence of prolonged length of stay (> 5 days) was 39.3% (n = 136). No patients died within 90 days after the surgery. According to Halls, Hasegawa, Kawaguchi, and Iwate scores, 65 (18.8%), 59 (17.1%), 57 (16.5%), and 112 (32.4%) patients underwent high difficulty LLR, respectively. In accordance with a random forest algorithm, the Kawaguchi DSS predicted prolonged length of stay, high blood loss, and conversions and was the best performing DSS in predicting postoperative outcomes. Iwate DSS was the most important variable associated with operative time, while Halls score was the most important DSS predicting textbook outcomes. No one of the DSS investigated was associated with the occurrence of complication. According to our results DDS are significantly related to surgical complexity and short-term outcomes, Kawaguchi and Iwate DSS showed the best performance in predicting operative outcomes, while Halls score was the most important variable in predicting textbook outcome. Interestingly, none of the DSS showed any correlation with or importance in predicting overall and severe postoperative complications.
Identifiants
pubmed: 35604481
doi: 10.1007/s00464-022-09322-7
pii: 10.1007/s00464-022-09322-7
pmc: PMC9652257
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
8869-8880Informations de copyright
© 2022. The Author(s).
Références
Halls MC, Alseidi A, Berardi G et al (2019) A comparison of the learning curves of laparoscopic liver surgeons in differing stages of the ideal paradigm of surgical innovation: standing on the shoulders of pioneers. Ann Surg 269:221–228
doi: 10.1097/SLA.0000000000002996
pubmed: 30080729
Hallet J, Pessaux P, Beyfuss KA et al (2019) Critical appraisal of predictive tools to assess the difficulty of laparoscopic liver resection: a systematic review. Surg Endosc 33:366–376
doi: 10.1007/s00464-018-6479-3
pubmed: 30350105
Halls MC, Cherqui D, Taylor MA et al (2018) Are the current difficulty scores for laparoscopic liver surgery telling the whole story? An international survey and recommendations for the future. HPB (Oxford) 20:231–236
doi: 10.1016/j.hpb.2017.08.028
Wakabayashi G (2016) What has changed after the Morioka consensus conference 2014 on laparoscopic liver resection? Hepatobiliary Surg Nutr 5:281–289
doi: 10.21037/hbsn.2016.03.03
pubmed: 27500140
pmcid: 4960417
Dimick JB, Staiger DO, Hall BL et al (2013) Composite measures for profiling hospitals on surgical morbidity. Ann Surg 257:67–72
doi: 10.1097/SLA.0b013e31827b6be6
pubmed: 23235395
Merath K, Chen Q, Bagante F et al (2020) Textbook outcomes among medicare patients undergoing hepatopancreatic surgery. Ann Surg 271:1116–1123
doi: 10.1097/SLA.0000000000003105
pubmed: 30499800
Halls MC, Berardi G, Cipriani F et al (2018) Development and validation of a difficulty score to predict intraoperative complications during laparoscopic liver resection. Br J Surg 105:1182–1191
doi: 10.1002/bjs.10821
pubmed: 29737513
Hasegawa Y, Wakabayashi G, Nitta H et al (2017) A novel model for prediction of pure laparoscopic liver resection surgical difficulty. Surg Endosc 31:5356–5363
doi: 10.1007/s00464-017-5616-8
pubmed: 28593408
Kawaguchi Y, Fuks D, Kokudo N et al (2018) Difficulty of laparoscopic liver resection: proposal for a new classification. Ann Surg 267:13–17
doi: 10.1097/SLA.0000000000002176
pubmed: 28187043
Strasberg SM (2005) Nomenclature of hepatic anatomy and resections: a review of the Brisbane 2000 system. J Hepatobiliary Pancreat Surg 12:351–355
doi: 10.1007/s00534-005-0999-7
pubmed: 16258801
Kazaryan AM, Røsok BI, Edwin B (2013) Morbidity assessment in surgery: refinement proposal based on a concept of perioperative adverse events. ISRN Surg 2013:625093
doi: 10.1155/2013/625093
pubmed: 23762627
pmcid: 3671541
Clavien PA, Barkun J, de Oliveira ML et al (2009) The Clavien-Dindo classification of surgical complications: five-year experience. Ann Surg 250:187–196
doi: 10.1097/SLA.0b013e3181b13ca2
pubmed: 19638912
Koch M, Garden OJ, Padbury R et al (2011) Bile leakage after hepatobiliary and pancreatic surgery: a definition and grading of severity by the International Study Group of Liver Surgery. Surgery 149:680–688
doi: 10.1016/j.surg.2010.12.002
pubmed: 21316725
Rahbari NN, Garden OJ, Padbury R et al (2011) Posthepatectomy liver failure: a definition and grading by the International Study Group of Liver Surgery (ISGLS). Surgery 149:713–724
doi: 10.1016/j.surg.2010.10.001
pubmed: 21236455
Buri M, Hothorn T (2020) Model-based random forests for ordinal regression. Int J Biostat. https://doi.org/10.1515/ijb-2019-0063
doi: 10.1515/ijb-2019-0063
pubmed: 32764162
Aldrighetti L, Ratti F, Cillo U et al (2017) Diffusion, outcomes and implementation of minimally invasive liver surgery: a snapshot from the I Go MILS (Italian Group of Minimally Invasive Liver Surgery) Registry. Updates Surg 69:271–283
doi: 10.1007/s13304-017-0489-x
pubmed: 28861759
Ciria R, Gomez-Luque I, Ocaña S et al (2019) A systematic review and meta-analysis comparing the short- and long-term outcomes for laparoscopic and open liver resections for hepatocellular carcinoma: updated results from the european guidelines meeting on laparoscopic liver surgery, southampton, UK, 2017. Ann Surg Oncol 26:252–263
doi: 10.1245/s10434-018-6926-3
pubmed: 30390167
Tanaka S, Kawaguchi Y, Kubo S et al (2019) Validation of index-based IWATE criteria as an improved difficulty scoring system for laparoscopic liver resection. Surgery 165:731–740
doi: 10.1016/j.surg.2018.10.012
pubmed: 30446171
Lee SY, Goh BKP, Sepideh G et al (2019) Laparoscopic liver resection difficulty score-a validation study. J Gastrointest Surg 23:545–555
doi: 10.1007/s11605-018-4036-y
pubmed: 30421119
Im C, Cho JY, Han H-S et al (2017) Validation of difficulty scoring system for laparoscopic liver resection in patients who underwent laparoscopic left lateral sectionectomy. Surg Endosc 31:430–436
doi: 10.1007/s00464-016-4994-7
pubmed: 27287898
Uchida H, Iwashita Y, Saga K et al (2016) Clinical utility of the difficulty scoring system for predicting surgical time of laparoscopic liver resection. J Laparoendosc Adv Surg Tech A 26:702–706
doi: 10.1089/lap.2016.0135
pubmed: 27352010
Ivanecz A, Plahuta I, Magdalenić T et al (2020) Evaluation of the iwate model for predicting the difficulty of laparoscopic liver resection: does tumor size matter? J Gastrointest Surg. https://doi.org/10.1007/s11605-020-04657-9
doi: 10.1007/s11605-020-04657-9
pubmed: 32495139
Ivanecz A, Plahuta I, Magdalenić T et al (2019) The external validation of a difficulty scoring system for predicting the risk of intraoperative complications during laparoscopic liver resection. BMC Surg 19:179
doi: 10.1186/s12893-019-0645-y
pubmed: 31775813
pmcid: 6882247
Russolillo N, Maina C, Fleres F et al (2020) Comparison and validation of three difficulty scoring systems in laparoscopic liver surgery: a retrospective analysis on 300 cases. Surg Endosc 34:5484–5494
doi: 10.1007/s00464-019-07345-1
pubmed: 31950272
Goh BKP, Prieto M, Syn N et al (2021) Validation and comparison of the Iwate, IMM, Southampton and Hasegawa difficulty scoring systems for primary laparoscopic hepatectomies. HPB (Oxford) 23:770–776
doi: 10.1016/j.hpb.2020.09.015
Tsilimigras DI, Mehta R, Merath K et al (2020) Hospital variation in textbook outcomes following curative-intent resection of hepatocellular carcinoma: an international multi-institutional analysis. HPB (Oxford) 22:1305–1313
doi: 10.1016/j.hpb.2019.12.005
Görgec B, Benedetti Cacciaguerra A, Lanari J et al (2021) Assessment of textbook outcome in laparoscopic and open liver surgery. JAMA Surg 156:e212064
doi: 10.1001/jamasurg.2021.2064
pubmed: 34076671
pmcid: 8173471
Kawaguchi Y, Tanaka S, Fuks D et al (2020) Validation and performance of three-level procedure-based classification for laparoscopic liver resection. Surg Endosc 34:2056–2066
doi: 10.1007/s00464-019-06986-6
pubmed: 31338665