PMID- 31891645
OWN - NLM
STAT- MEDLINE
DCOM- 20200402
LR  - 20200402
IS  - 1932-6203 (Electronic)
IS  - 1932-6203 (Linking)
VI  - 14
IP  - 12
DP  - 2019
TI  - Applications of machine learning in decision analysis for dose management for 
      dofetilide.
PG  - e0227324
LID - 10.1371/journal.pone.0227324 [doi]
LID - e0227324
AB  - BACKGROUND: Initiation of the antiarrhythmic medication dofetilide requires an 
      FDA-mandated 3 days of telemetry monitoring due to heightened risk of toxicity 
      within this time period. Although a recommended dose management algorithm for 
      dofetilide exists, there is a range of real-world approaches to dosing the 
      medication. METHODS AND RESULTS: In this multicenter investigation, clinical data 
      from the Antiarrhythmic Drug Genetic (AADGEN) study was examined for 354 patients 
      undergoing dofetilide initiation. Univariate logistic regression identified a 
      starting dofetilide dose of 500 mcg (OR 5.0, 95%CI 2.5-10.0, p<0.001) and sinus 
      rhythm at the start of dofetilide loading (OR 2.8, 95%CI 1.8-4.2, p<0.001) as 
      strong positive predictors of successful loading. Any dose-adjustment during 
      loading (OR 0.19, 95%CI 0.12-0.31, p<0.001) and a history coronary artery disease 
      (OR 0.33, 95%CI 0.19-0.59, p<0.001) were strong negative predictors of successful 
      dofetilide loading. Based on the observation that any dose adjustment was a 
      significant negative predictor of successful initiation, we applied multiple 
      supervised approaches to attempt to predict the dose adjustment decision, but 
      none of these approaches identified dose adjustments better than a probabilistic 
      guess. Principal component analysis and cluster analysis identified 8 clusters as 
      a reasonable data reduction method. These 8 clusters were then used to define 
      patient states in a tabular reinforcement learning model trained on 80% of dosing 
      decisions. Testing of this model on the remaining 20% of dosing decisions 
      revealed good accuracy of the reinforcement learning model, with only 16/410 
      (3.9%) instances of disagreement. CONCLUSIONS: Dose adjustments are a strong 
      determinant of whether patients are able to successfully initiate dofetilide. A 
      reinforcement learning algorithm informed by unsupervised learning was able to 
      predict dosing decisions with 96.1% accuracy. Future studies will apply this 
      algorithm prospectively as a data-driven decision aid.
FAU - Levy, Andrew E
AU  - Levy AE
AUID- ORCID: 0000-0002-9076-9619
AD  - Division of Cardiology, University of Colorado Anschutz Medical Campus, Aurora, 
      CO, United States of America.
FAU - Biswas, Minakshi
AU  - Biswas M
AD  - Division of Cardiology, University of Colorado Anschutz Medical Campus, Aurora, 
      CO, United States of America.
FAU - Weber, Rachel
AU  - Weber R
AD  - Division of Biostatistics and Informatics, Colorado School of Public Health, 
      Aurora, CO, United States of America.
FAU - Tarakji, Khaldoun
AU  - Tarakji K
AD  - Center for Atrial Fibrillation, Section of Cardiac Pacing and Electrophysiology, 
      Cleveland Clinic Foundation, Cleveland, OH, United States of America.
FAU - Chung, Mina
AU  - Chung M
AD  - Center for Atrial Fibrillation, Section of Cardiac Pacing and Electrophysiology, 
      Cleveland Clinic Foundation, Cleveland, OH, United States of America.
FAU - Noseworthy, Peter A
AU  - Noseworthy PA
AD  - Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, 
      Mayo Clinic, Rochester, MN, United States of America.
FAU - Newton-Cheh, Christopher
AU  - Newton-Cheh C
AD  - Cardiovascular Research Center, Department of Medicine, Massachusetts General 
      Hospital and Harvard Medical School, Boston, MA, United States of America.
FAU - Rosenberg, Michael A
AU  - Rosenberg MA
AUID- ORCID: 0000-0002-6708-1648
AD  - Division of Cardiology, University of Colorado Anschutz Medical Campus, Aurora, 
      CO, United States of America.
AD  - Colorado Center for Personalized Medicine, University of Colorado Anschutz 
      Medical Campus, Aurora, CO, United States of America.
LA  - eng
GR  - K23 HL127296/HL/NHLBI NIH HHS/United States
GR  - L30 HL123413/HL/NHLBI NIH HHS/United States
GR  - R01 HL143070/HL/NHLBI NIH HHS/United States
GR  - T32 HL007822/HL/NHLBI NIH HHS/United States
PT  - Journal Article
PT  - Multicenter Study
PT  - Research Support, N.I.H., Extramural
DEP - 20191231
PL  - United States
TA  - PLoS One
JT  - PloS one
JID - 101285081
RN  - 0 (Anti-Arrhythmia Agents)
RN  - 0 (Phenethylamines)
RN  - 0 (Sulfonamides)
RN  - R4Z9X1N2ND (dofetilide)
SB  - IM
MH  - Aged
MH  - Anti-Arrhythmia Agents/*administration & dosage
MH  - *Decision Support Techniques
MH  - Dose-Response Relationship, Drug
MH  - Female
MH  - Humans
MH  - *Machine Learning
MH  - Male
MH  - Middle Aged
MH  - Phenethylamines/*administration & dosage
MH  - Sulfonamides/*administration & dosage
PMC - PMC6938356
COIS- The authors have declared that no competing interests exist.
EDAT- 2020/01/01 06:00
MHDA- 2020/04/03 06:00
PMCR- 2019/12/31
CRDT- 2020/01/01 06:00
PHST- 2019/06/25 00:00 [received]
PHST- 2019/12/17 00:00 [accepted]
PHST- 2020/01/01 06:00 [entrez]
PHST- 2020/01/01 06:00 [pubmed]
PHST- 2020/04/03 06:00 [medline]
PHST- 2019/12/31 00:00 [pmc-release]
AID - PONE-D-19-17964 [pii]
AID - 10.1371/journal.pone.0227324 [doi]
PST - epublish
SO  - PLoS One. 2019 Dec 31;14(12):e0227324. doi: 10.1371/journal.pone.0227324. 
      eCollection 2019.