PMID- 33835524
OWN - NLM
STAT- MEDLINE
DCOM- 20211207
LR  - 20230918
IS  - 1365-2125 (Electronic)
IS  - 0306-5251 (Linking)
VI  - 87
IP  - 11
DP  - 2021 Nov
TI  - Systematic review of machine learning models for personalised dosing of heparin.
PG  - 4124-4139
LID - 10.1111/bcp.14852 [doi]
AB  - AIM: To identify and critically appraise studies of prediction models, developed 
      using machine learning (ML) methods, for determining the optimal dosing of 
      unfractionated heparin (UFH). METHODS: Embase, PubMed, CINAHL, Web of Science, 
      International Pharmaceutical Abstracts and IEEE Xplore databases were searched 
      from inception to 31 January 2020 to identify relevant studies using key search 
      terms synonymous with artificial intelligence or ML, 'prediction', 'dose', 
      'activated partial thromboplastin time (aPTT)' and 'UFH.' Studies had to have 
      used ML methods for developing models that predicted optimal dose of UFH or 
      target therapeutic aPTT levels in the hospital setting. The CHARMS Checklist was 
      used to assess quality and risk of bias of included studies. RESULTS: Of 8393 
      retrieved abstracts, 61 underwent full text review and eight studies met 
      inclusion criteria. Four studies described models for predicting aPTT, three 
      studies described models predicting optimal dose of heparin during dialysis and 
      one study described a model that used surrogate outcomes of clotting and bleeding 
      to predict a therapeutic aPTT. Studies varied widely in reporting of study 
      participants, feature characterisation and selection, handling of missing data, 
      sample size calculations and the intended clinical application of the model. Only 
      one study conducted an external validation and no studies evaluated model impacts 
      in clinical practice. CONCLUSION: Studies of ML models for UFH dosing are few and 
      none report a model ready for routine clinical use. Existing studies are limited 
      by low methodological quality, inadequate reporting of study factors and absence 
      of external validation and impact analysis.
CI  - (c) 2021 British Pharmacological Society.
FAU - Falconer, Nazanin
AU  - Falconer N
AUID- ORCID: 0000-0003-4682-7890
AD  - Department of Pharmacy, Princess Alexandra Hospital, Brisbane, Queensland, 4102, 
      Australia.
AD  - School of Pharmacy, The University of Queensland, Brisbane, Queensland, 4102, 
      Australia.
AD  - Centre for Health Services Research, The University of Queensland, Level two, 
      Building 33, Princess Alexandra Hospital, Brisbane, 4102, Australia.
FAU - Abdel-Hafez, Ahmad
AU  - Abdel-Hafez A
AD  - Clinical Informatics, Princess Alexandra Hospital, Brisbane, Queensland, 4102, 
      Australia.
FAU - Scott, Ian A
AU  - Scott IA
AD  - Department of Internal Medicine and Clinical Epidemiology, Princess Alexandra 
      Hospital, Brisbane, Queensland, Australia.
AD  - School of Clinical Medicine, Faculty of Medicine, The University of Queensland, 
      4102, Australia.
FAU - Marxen, Sven
AU  - Marxen S
AD  - Department of Pharmacy, Logan and Beaudesert Hospitals, Meadowbrook, Metro South 
      Health, Brisbane, QLD, 4131, Australia.
FAU - Canaris, Stephen
AU  - Canaris S
AD  - Clinical Informatics, Princess Alexandra Hospital, Brisbane, Queensland, 4102, 
      Australia.
FAU - Barras, Michael
AU  - Barras M
AD  - Department of Pharmacy, Princess Alexandra Hospital, Brisbane, Queensland, 4102, 
      Australia.
AD  - School of Pharmacy, The University of Queensland, Brisbane, Queensland, 4102, 
      Australia.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
PT  - Review
PT  - Systematic Review
DEP - 20210514
PL  - England
TA  - Br J Clin Pharmacol
JT  - British journal of clinical pharmacology
JID - 7503323
RN  - 0 (Anticoagulants)
RN  - 9005-49-6 (Heparin)
SB  - IM
MH  - Anticoagulants
MH  - *Artificial Intelligence
MH  - *Heparin/adverse effects
MH  - Humans
MH  - Machine Learning
MH  - Partial Thromboplastin Time
OTO - NOTNLM
OT  - UFH
OT  - dose prediction
OT  - machine learning algorithm
OT  - predictive model
OT  - unfractionated heparin
EDAT- 2021/04/10 06:00
MHDA- 2021/12/15 06:00
CRDT- 2021/04/09 12:58
PHST- 2021/03/25 00:00 [revised]
PHST- 2020/12/22 00:00 [received]
PHST- 2021/03/29 00:00 [accepted]
PHST- 2021/04/10 06:00 [pubmed]
PHST- 2021/12/15 06:00 [medline]
PHST- 2021/04/09 12:58 [entrez]
AID - 10.1111/bcp.14852 [doi]
PST - ppublish
SO  - Br J Clin Pharmacol. 2021 Nov;87(11):4124-4139. doi: 10.1111/bcp.14852. Epub 2021 
      May 14.