Data analytics and artificial intelligence in predicting length of stay, readmission, and mortality: a population-based study of surgical management of colorectal cancer.
Artificial intelligence
Colorectal cancer
Colorectal surgery
Data analytics
Length of stay
Machine learning
Mortality
Prediction
Predictor variables
Readmission
Journal
Discover. Oncology
ISSN: 2730-6011
Titre abrégé: Discov Oncol
Pays: United States
ID NLM: 101775142
Informations de publication
Date de publication:
28 Feb 2022
28 Feb 2022
Historique:
received:
19
12
2021
accepted:
07
02
2022
entrez:
28
2
2022
pubmed:
1
3
2022
medline:
1
3
2022
Statut:
epublish
Résumé
Data analytics and artificial intelligence (AI) have been used to predict patient outcomes after colorectal cancer surgery. A prospectively maintained colorectal cancer database was used, covering 4336 patients who underwent colorectal cancer surgery between 2003 and 2019. The 47 patient parameters included demographics, peri- and post-operative outcomes, surgical approaches, complications, and mortality. Data analytics were used to compare the importance of each variable and AI prediction models were built for length of stay (LOS), readmission, and mortality. Accuracies of at least 80% have been achieved. The significant predictors of LOS were age, ASA grade, operative time, presence or absence of a stoma, robotic or laparoscopic approach to surgery, and complications. The model with support vector regression (SVR) algorithms predicted the LOS with an accuracy of 83% and mean absolute error (MAE) of 9.69 days. The significant predictors of readmission were age, laparoscopic procedure, stoma performed, preoperative nodal (N) stage, operation time, operation mode, previous surgery type, LOS, and the specific procedure. A BI-LSTM model predicted readmission with 87.5% accuracy, 84% sensitivity, and 90% specificity. The significant predictors of mortality were age, ASA grade, BMI, the formation of a stoma, preoperative TNM staging, neoadjuvant chemotherapy, curative resection, and LOS. Classification predictive modelling predicted three different colorectal cancer mortality measures (overall mortality, and 31- and 91-days mortality) with 80-96% accuracy, 84-93% sensitivity, and 75-100% specificity. A model using all variables performed only slightly better than one that used just the most significant ones.
Identifiants
pubmed: 35226196
doi: 10.1007/s12672-022-00472-7
pii: 10.1007/s12672-022-00472-7
pmc: PMC8885960
doi:
Types de publication
Journal Article
Langues
eng
Pagination
11Subventions
Organisme : University of Portsmouth
ID : Thematic Research & Innovation Fund (TRIF)
Informations de copyright
© 2022. The Author(s).
Références
Eur J Surg Oncol. 2017 Jul;43(7):1312-1323
pubmed: 28342688
Ann Intern Med. 2010 Dec 7;153(11):757-8
pubmed: 21135299
Medicine (Baltimore). 2016 Nov;95(47):e5064
pubmed: 27893655
Br J Surg. 1998 Sep;85(9):1217-20
pubmed: 9752863
J Gastrointest Surg. 2015 Sep;19(9):1684-90
pubmed: 26105552
Arch Surg. 2005 Mar;140(3):278-83, discussion 284
pubmed: 15781793
Eur Respir J. 2011 Dec;38(6):1294-300
pubmed: 21565913
CA Cancer J Clin. 2018 Nov;68(6):394-424
pubmed: 30207593
Sci Rep. 2017 Aug 7;7(1):7402
pubmed: 28784991
Ann Intern Med. 2011 Oct 18;155(8):520-8
pubmed: 22007045
Sci Rep. 2020 Feb 13;10(1):2519
pubmed: 32054897
Health Econ Rev. 2018 Jun 14;8(1):12
pubmed: 29904805
Lancet Psychiatry. 2016 Jan;3(1):13-15
pubmed: 26772057
Aust N Z J Public Health. 2020 Feb;44(1):73-82
pubmed: 31617657
Br J Surg. 2014 Feb;101(3):239-45
pubmed: 24281922
IEEE Trans Inf Technol Biomed. 2010 Jul;14(4):1114-20
pubmed: 20071261
BMC Health Serv Res. 2012 Mar 26;12:77
pubmed: 22448728
BMJ. 2003 Nov 22;327(7425):1196-201
pubmed: 14630754
J Am Coll Surg. 2012 Apr;214(4):390-8; discussion 398-9
pubmed: 22289517
Tech Coloproctol. 2016 Aug;20(8):567-76
pubmed: 27422532
Int J Colorectal Dis. 2020 Aug;35(8):1529-1535
pubmed: 32377912
Int J Surg. 2010;8(8):628-32
pubmed: 20691293
Biochem J. 2018 Mar 15;475(5):1019-1035
pubmed: 29437994
Dig Dis Sci. 2017 Oct;62(10):2719-2727
pubmed: 28836087
J Natl Cancer Inst. 2011 Jan 19;103(2):117-28
pubmed: 21228314
J Surg Res. 2016 Jan;200(1):200-7
pubmed: 26216748
Ann Coloproctol. 2020 Jun;36(3):186-191
pubmed: 32054242
Oncotarget. 2015 Apr 30;6(12):9908-23
pubmed: 25839161
J Am Geriatr Soc. 2013 Jul;61(7):1175-81
pubmed: 23730901
Comput Struct Biotechnol J. 2014 Nov 15;13:8-17
pubmed: 25750696
Br J Surg. 1991 Mar;78(3):355-60
pubmed: 2021856
Br J Surg. 2004 Sep;91(9):1174-82
pubmed: 15449270
J Gastrointest Oncol. 2015 Dec;6(6):613-7
pubmed: 26697192
J Int Med Res. 2017 Apr;45(2):691-705
pubmed: 28173723
Dis Colon Rectum. 2004 Dec;47(12):2015-24
pubmed: 15657649
Dis Colon Rectum. 2004 Sep;47(9):1435-41
pubmed: 15486738
Med Care. 1991 Apr;29(4):377-94
pubmed: 1902276
Gastroenterol Clin Biol. 2005 May;29(5):509-14
pubmed: 15980743
Lancet Oncol. 2007 Apr;8(4):317-22
pubmed: 17395105
J Clin Nurs. 2009 Sep;18(18):2539-46
pubmed: 19374695
Ann Surg Oncol. 2013 Oct;20(11):3370-6
pubmed: 23732859
BJS Open. 2020 Sep 28;:
pubmed: 32985127
Ann Surg. 2014 May;259(5):844-9
pubmed: 24717374
CA Cancer J Clin. 2020 May;70(3):145-164
pubmed: 32133645
Colorectal Dis. 2014 Aug;16(8):631-9
pubmed: 24506067