Using a decision tree algorithm to distinguish between repeated supra-therapeutic and acute acetaminophen exposures.
APAP
Acute acetaminophen poisoning
Decision Tree
NPDS
Repeated supra-therapeutic ingestion
Journal
BMC medical informatics and decision making
ISSN: 1472-6947
Titre abrégé: BMC Med Inform Decis Mak
Pays: England
ID NLM: 101088682
Informations de publication
Date de publication:
01 06 2023
01 06 2023
Historique:
received:
16
03
2022
accepted:
04
05
2023
medline:
5
6
2023
pubmed:
2
6
2023
entrez:
1
6
2023
Statut:
epublish
Résumé
This study aimed to compare clinical and laboratory characteristics of supra-therapeutic (RSTI) and acute acetaminophen exposures using a predictive decision tree (DT) algorithm. We conducted a retrospective cohort study using the National Poison Data System (NPDS). All patients with RSTI acetaminophen exposure (n = 4,522) between January 2012 and December 2017 were included. Additionally, 4,522 randomly selected acute acetaminophen ingestion cases were included. After that, the DT machine learning algorithm was applied to differentiate acute acetaminophen exposure from supratherapeutic exposures. The DT model had accuracy, precision, recall, and F1-scores of 0.75, respectively. Age was the most relevant variable in predicting the type of acetaminophen exposure, whether RSTI or acute. Serum aminotransferase concentrations, abdominal pain, drowsiness/lethargy, and nausea/vomiting were the other most important factors distinguishing between RST and acute acetaminophen exposure. DT models can potentially aid in distinguishing between acute and RSTI of acetaminophen. Further validation is needed to assess the clinical utility of this model.
Sections du résumé
BACKGROUND
This study aimed to compare clinical and laboratory characteristics of supra-therapeutic (RSTI) and acute acetaminophen exposures using a predictive decision tree (DT) algorithm.
METHODS
We conducted a retrospective cohort study using the National Poison Data System (NPDS). All patients with RSTI acetaminophen exposure (n = 4,522) between January 2012 and December 2017 were included. Additionally, 4,522 randomly selected acute acetaminophen ingestion cases were included. After that, the DT machine learning algorithm was applied to differentiate acute acetaminophen exposure from supratherapeutic exposures.
RESULTS
The DT model had accuracy, precision, recall, and F1-scores of 0.75, respectively. Age was the most relevant variable in predicting the type of acetaminophen exposure, whether RSTI or acute. Serum aminotransferase concentrations, abdominal pain, drowsiness/lethargy, and nausea/vomiting were the other most important factors distinguishing between RST and acute acetaminophen exposure.
CONCLUSION
DT models can potentially aid in distinguishing between acute and RSTI of acetaminophen. Further validation is needed to assess the clinical utility of this model.
Identifiants
pubmed: 37264381
doi: 10.1186/s12911-023-02188-2
pii: 10.1186/s12911-023-02188-2
pmc: PMC10233916
doi:
Substances chimiques
Acetaminophen
362O9ITL9D
Analgesics, Non-Narcotic
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
102Informations de copyright
© 2023. The Author(s).
Références
Med J Aust. 2015 Sep 7;203(5):215-8
pubmed: 26852051
Daru. 2019 Dec;27(2):839-851
pubmed: 31713183
Drug Chem Toxicol. 2022 Jun 7;:1-7
pubmed: 35670081
Clin Liver Dis. 2013 Nov;17(4):587-607, viii
pubmed: 24099020
J Med Toxicol. 2007 Dec;3(4):152-6
pubmed: 18072168
Postgrad Med J. 2005 Apr;81(954):204-16
pubmed: 15811881
J Toxicol Clin Toxicol. 1996;34(2):163-7
pubmed: 8618249
Nurse Pract. 2019 Nov;44(11):42-47
pubmed: 31651762
J Toxicol Clin Toxicol. 1999;37(1):35-42
pubmed: 10078158
Drug Chem Toxicol. 2022 Mar;45(2):878-885
pubmed: 32588664
J Biomed Inform. 2019 Jun;94:103185
pubmed: 31028874
Clin Toxicol (Phila). 2011 Feb;49(2):108-12
pubmed: 21370947
Pharm Res. 2013 Sep;30(9):2174-87
pubmed: 23462933
BMC Med Res Methodol. 2019 Mar 19;19(1):64
pubmed: 30890124
BMJ Open. 2016 Dec 1;6(12):e013336
pubmed: 27909038
Circulation. 2015 Nov 17;132(20):1920-30
pubmed: 26572668
J Clin Transl Hepatol. 2016 Jun 28;4(2):131-42
pubmed: 27350943
J Pediatr. 1997 Feb;130(2):300-4
pubmed: 9042136
Clin Toxicol (Phila). 2019 Aug;57(8):703-711
pubmed: 30789042
Hepatology. 2005 Dec;42(6):1364-72
pubmed: 16317692
J Med Syst. 2002 Oct;26(5):445-63
pubmed: 12182209
Pharmacoepidemiol Drug Saf. 2010 May;19(5):511-7
pubmed: 20333776
BMC Pharmacol Toxicol. 2016 Jul 14;17(1):30
pubmed: 27411502
Clin Toxicol (Phila). 2018 Mar;56(3):199-203
pubmed: 28812380
Cleve Clin J Med. 2010 Jan;77(1):19-27
pubmed: 20048026
Pediatr Emerg Care. 1992 Dec;8(6):345-6
pubmed: 1360651
J Toxicol Clin Toxicol. 1998;36(1-2):19-25
pubmed: 9541036
Toxics. 2018 Sep 29;6(4):
pubmed: 30274302
Arch Toxicol. 2015 Feb;89(2):193-9
pubmed: 25537186
Br J Clin Pharmacol. 2012 Feb;73(2):285-94
pubmed: 22106945
Clin J Am Soc Nephrol. 2006 May;1(3):441-7
pubmed: 17699243
Ann Emerg Med. 2004 Oct;44(4):393-8
pubmed: 15459622
Clin Toxicol (Phila). 2006;44(1):1-18
pubmed: 16496488