Treffer: Machine Learning to Calculate Heparin Dose in COVID-19 Patients with Active Cancer.

Title:
Machine Learning to Calculate Heparin Dose in COVID-19 Patients with Active Cancer.
Authors:
Imbalzano E; Department of Clinical and Experimental Medicine, University of Messina, 98122 Messina, Italy., Orlando L; Department of Clinical and Experimental Medicine, University of Messina, 98122 Messina, Italy., Sciacqua A; Department of Medical and Surgical Sciences, University Magna Græcia of Catanzaro, 88100 Catanzaro, Italy., Nato G; Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy., Dentali F; Department of Medicine and Surgery, Insubria University, 21100 Varese, Italy., Nassisi V; Department of Clinical and Experimental Medicine, University of Messina, 98122 Messina, Italy., Russo V; Department of Medical Translational Sciences, Division of Cardiology, Monaldi Hospital, University of Campania 'Luigi Vanvitelli', 80100 Naples, Italy., Camporese G; Unit of Angiology, Department of Cardiac, Thoracic and Vascular Sciences, Padua University Hospital, 35100 Padua, Italy., Bagnato G; Department of Clinical and Experimental Medicine, University of Messina, 98122 Messina, Italy., Cicero AFG; IRCCS Policlinico S. Orsola-Malpighi, Hypertension and Cardiovascular Risk Research Center, DIMEC, University of Bologna, 40126 Bologna, Italy., Dattilo G; Department of Clinical and Experimental Medicine, University of Messina, 98122 Messina, Italy., Vatrano M; UTIC and Cardiology, Hospital 'Pugliese-Ciaccio' of Catanzaro, 88100 Catanzaro, Italy., Versace AG; Department of Clinical and Experimental Medicine, University of Messina, 98122 Messina, Italy., Squadrito G; Department of Clinical and Experimental Medicine, University of Messina, 98122 Messina, Italy., Di Micco P; Department of Medicine, BuonconsiglioFatebenefratelli Hospital, 80100 Naples, Italy.
Source:
Journal of clinical medicine [J Clin Med] 2021 Dec 31; Vol. 11 (1). Date of Electronic Publication: 2021 Dec 31.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: MDPI AG Country of Publication: Switzerland NLM ID: 101606588 Publication Model: Electronic Cited Medium: Print ISSN: 2077-0383 (Print) Linking ISSN: 20770383 NLM ISO Abbreviation: J Clin Med Subsets: PubMed not MEDLINE
Imprint Name(s):
Original Publication: Basel, Switzerland : MDPI AG, [2012]-
References:
Sci Rep. 2021 Jul 9;11(1):14250. (PMID: 34244563)
Comput Biol Med. 2020 Sep;124:103949. (PMID: 32798922)
Transplantation. 2020 Nov;104(11):e329-e331. (PMID: 33122591)
Lancet Psychiatry. 2016 Mar;3(3):243-50. (PMID: 26803397)
Am J Cardiol. 2021 Feb 15;141:140-146. (PMID: 33217345)
Dimens Crit Care Nurs. 2015 Jan-Feb;34(1):3-9. (PMID: 25470260)
Bioinformatics. 2011 May 15;27(10):1384-9. (PMID: 21450715)
Pathol Res Pract. 2020 Sep;216(9):153086. (PMID: 32825954)
Semin Thromb Hemost. 2019 Jun;45(4):354-372. (PMID: 31108555)
J Thromb Haemost. 2020 May;18(5):1094-1099. (PMID: 32220112)
Circulation. 2020 Jul 14;142(2):184-186. (PMID: 32330083)
Eur J Case Rep Intern Med. 2020 Apr 08;7(5):001646. (PMID: 32399449)
Ann Palliat Med. 2020 Sep;9(5):3373-3378. (PMID: 33065788)
Viruses. 2021 Aug 30;13(9):. (PMID: 34578301)
J Clin Med. 2021 Jun 21;10(12):. (PMID: 34205536)
N Engl J Med. 2000 Dec 21;343(25):1846-50. (PMID: 11117976)
J Thromb Haemost. 2020 Apr;18(4):844-847. (PMID: 32073213)
Eur Heart J. 2021 Jun 14;42(23):2299-2307. (PMID: 33769475)
Life Sci. 2020 Nov 1;260:118482. (PMID: 32971105)
J Thromb Haemost. 2006 Mar;4(3):529-35. (PMID: 16460435)
J Thromb Haemost. 2018 Sep;16(9):1891-1894. (PMID: 30027649)
Circ Res. 2017 Oct 13;121(9):1092-1101. (PMID: 28794054)
J Am Coll Cardiol. 2020 Aug 25;76(8):930-941. (PMID: 32819467)
Indian Heart J. 2021 Jan-Feb;73(1):91-98. (PMID: 33714416)
N Engl J Med. 1999 Sep 9;341(11):793-800. (PMID: 10477777)
JAMA Netw Open. 2019 May 3;2(5):e193721. (PMID: 31074823)
Arch Intern Med. 2004 Jan 26;164(2):190-4. (PMID: 14744843)
Adv Biol Regul. 2020 Aug;77:100739. (PMID: 32773105)
Thromb Haemost. 2020 Aug;120(8):1230-1232. (PMID: 32349132)
Acta Oncol. 2021 Jan;60(1):13-19. (PMID: 33131376)
Lancet Oncol. 2020 Jul;21(7):914-922. (PMID: 32539942)
PLoS One. 2020 Jun 25;15(6):e0233791. (PMID: 32584909)
Int J Infect Dis. 2021 Apr;105:551-559. (PMID: 33711519)
Tumori. 2020 Aug;106(4):271-272. (PMID: 32508257)
Semin Thromb Hemost. 1978 Summer;5(1):1-26. (PMID: 705351)
Cancer. 2021 Feb 1;127(3):437-448. (PMID: 33136293)
Contributed Indexing:
Keywords: SARS-CoV-2; anticoagulation; artificial intelligence; heparin; machine-learning
Entry Date(s):
Date Created: 20220111 Latest Revision: 20220114
Update Code:
20250114
PubMed Central ID:
PMC8746167
DOI:
10.3390/jcm11010219
PMID:
35011959
Database:
MEDLINE

Weitere Informationen

To realize a machine learning (ML) model to estimate the dose of low molecular weight heparin to be administered, preventing thromboembolism events in COVID-19 patients with active cancer. Methods: We used a dataset comprising 131 patients with active cancer and COVID-19. We considered five ML models: logistic regression, decision tree, random forest, support vector machine and Gaussian naive Bayes. We decided to implement the logistic regression model for our study. A model with 19 variables was analyzed. Data were randomly split into training (70%) and testing (30%) sets. Model performance was assessed by confusion matrix metrics on the testing data for each model as positive predictive value, sensitivity and F1-score. Results: We showed that the five selected models outperformed classical statistical methods of predictive validity and logistic regression was the most effective, being able to classify with an accuracy of 81%. The most relevant result was finding a patient-proof where python function was able to obtain the exact dose of low weight molecular heparin to be administered and thereby to prevent the occurrence of VTE. Conclusions: The world of machine learning and artificial intelligence is constantly developing. The identification of a specific LMWH dose for preventing VTE in very high-risk populations, such as the COVID-19 and active cancer population, might improve with the use of new training ML-based algorithms. Larger studies are needed to confirm our exploratory results.