Predicting Outcomes in Patients Undergoing Pancreatectomy Using Wearable Technology and Machine Learning: Prospective Cohort Study.
activity
machine learning
pancreatectomy
pancreatic cancer
remote monitoring
telemonitoring
wearable technology
Journal
Journal of medical Internet research
ISSN: 1438-8871
Titre abrégé: J Med Internet Res
Pays: Canada
ID NLM: 100959882
Informations de publication
Date de publication:
18 03 2021
18 03 2021
Historique:
received:
17
08
2020
accepted:
17
02
2021
revised:
18
11
2020
entrez:
18
3
2021
pubmed:
19
3
2021
medline:
30
9
2021
Statut:
epublish
Résumé
Pancreatic cancer is the third leading cause of cancer-related deaths, and although pancreatectomy is currently the only curative treatment, it is associated with significant morbidity. The objective of this study was to evaluate the utility of wearable telemonitoring technologies to predict treatment outcomes using patient activity metrics and machine learning. In this prospective, single-center, single-cohort study, patients scheduled for pancreatectomy were provided with a wearable telemonitoring device to be worn prior to surgery. Patient clinical data were collected and all patients were evaluated using the American College of Surgeons National Surgical Quality Improvement Program surgical risk calculator (ACS-NSQIP SRC). Machine learning models were developed to predict whether patients would have a textbook outcome and compared with the ACS-NSQIP SRC using area under the receiver operating characteristic (AUROC) curves. Between February 2019 and February 2020, 48 patients completed the study. Patient activity metrics were collected over an average of 27.8 days before surgery. Patients took an average of 4162.1 (SD 4052.6) steps per day and had an average heart rate of 75.6 (SD 14.8) beats per minute. Twenty-eight (58%) patients had a textbook outcome after pancreatectomy. The group of 20 (42%) patients who did not have a textbook outcome included 14 patients with severe complications and 11 patients requiring readmission. The ACS-NSQIP SRC had an AUROC curve of 0.6333 to predict failure to achieve a textbook outcome, while our model combining patient clinical characteristics and patient activity data achieved the highest performance with an AUROC curve of 0.7875. Machine learning models outperformed ACS-NSQIP SRC estimates in predicting textbook outcomes after pancreatectomy. The highest performance was observed when machine learning models incorporated patient clinical characteristics and activity metrics.
Sections du résumé
BACKGROUND
Pancreatic cancer is the third leading cause of cancer-related deaths, and although pancreatectomy is currently the only curative treatment, it is associated with significant morbidity.
OBJECTIVE
The objective of this study was to evaluate the utility of wearable telemonitoring technologies to predict treatment outcomes using patient activity metrics and machine learning.
METHODS
In this prospective, single-center, single-cohort study, patients scheduled for pancreatectomy were provided with a wearable telemonitoring device to be worn prior to surgery. Patient clinical data were collected and all patients were evaluated using the American College of Surgeons National Surgical Quality Improvement Program surgical risk calculator (ACS-NSQIP SRC). Machine learning models were developed to predict whether patients would have a textbook outcome and compared with the ACS-NSQIP SRC using area under the receiver operating characteristic (AUROC) curves.
RESULTS
Between February 2019 and February 2020, 48 patients completed the study. Patient activity metrics were collected over an average of 27.8 days before surgery. Patients took an average of 4162.1 (SD 4052.6) steps per day and had an average heart rate of 75.6 (SD 14.8) beats per minute. Twenty-eight (58%) patients had a textbook outcome after pancreatectomy. The group of 20 (42%) patients who did not have a textbook outcome included 14 patients with severe complications and 11 patients requiring readmission. The ACS-NSQIP SRC had an AUROC curve of 0.6333 to predict failure to achieve a textbook outcome, while our model combining patient clinical characteristics and patient activity data achieved the highest performance with an AUROC curve of 0.7875.
CONCLUSIONS
Machine learning models outperformed ACS-NSQIP SRC estimates in predicting textbook outcomes after pancreatectomy. The highest performance was observed when machine learning models incorporated patient clinical characteristics and activity metrics.
Identifiants
pubmed: 33734096
pii: v23i3e23595
doi: 10.2196/23595
pmc: PMC8074869
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e23595Subventions
Organisme : NCI NIH HHS
ID : P30 CA091842
Pays : United States
Organisme : NCI NIH HHS
ID : P50 CA196510
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR000448
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR002345
Pays : United States
Informations de copyright
©Heidy Cos, Dingwen Li, Gregory Williams, Jeffrey Chininis, Ruixuan Dai, Jingwen Zhang, Rohit Srivastava, Lacey Raper, Dominic Sanford, William Hawkins, Chenyang Lu, Chet W Hammill. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 18.03.2021.
Références
J Am Coll Surg. 2013 Nov;217(5):833-42.e1-3
pubmed: 24055383
J Clin Oncol. 2020 Jun 1;38(16):1763-1773
pubmed: 32105518
Eur J Surg Oncol. 2018 Jul;44(7):1078-1082
pubmed: 29685757
PLoS One. 2018 Jul 20;13(7):e0201016
pubmed: 30028888
Chronobiol Int. 2017;34(8):1042-1056
pubmed: 28650674
Ann Surg. 2011 Dec;254(6):907-13
pubmed: 21562405
JAMA Surg. 2016 Aug 17;151(8):e161137
pubmed: 27275632
NPJ Digit Med. 2018 Jul 5;1:27
pubmed: 31304309
Langenbecks Arch Surg. 2017 Dec;402(8):1175-1185
pubmed: 28710540
Postgrad Med. 1989 Mar;85(4):85-6, 89-92, 94
pubmed: 2648367
J Med Internet Res. 2017 Dec 19;19(12):e420
pubmed: 29258977
Gigascience. 2017 May 1;6(5):1-9
pubmed: 28327985
Ann Surg. 2009 Aug;250(2):177-86
pubmed: 19638919
World J Surg. 2019 Jul;43(7):1661-1668
pubmed: 30788536
Support Care Cancer. 2018 Apr;26(4):1019-1028
pubmed: 29243164
Eur J Epidemiol. 2019 May;34(5):463-470
pubmed: 30569368
Ann Surg. 2013 Jun;257(6):999-1004
pubmed: 23665968
Am J Surg. 2012 Sep;204(3):332-8
pubmed: 22464011
Rev Esp Cardiol (Engl Ed). 2016 Jun;69(6):629
pubmed: 27095531
Ann Surg. 2020 Jan;271(1):155-162
pubmed: 31274651
HPB (Oxford). 2017 Dec;19(12):1104-1111
pubmed: 28890310
J Gastrointest Surg. 2009 Oct;13(10):1798-805
pubmed: 19506975
Hepatobiliary Surg Nutr. 2021 Jan;10(1):20-30
pubmed: 33575287
Nutrients. 2017 Mar 07;9(3):
pubmed: 28272344
PLoS One. 2014 Jan 24;9(1):e86863
pubmed: 24475186
Br J Anaesth. 2010 Sep;105(3):297-303
pubmed: 20573634