PMID- 34677211
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20211026
IS  - 2306-5354 (Print)
IS  - 2306-5354 (Electronic)
IS  - 2306-5354 (Linking)
VI  - 8
IP  - 10
DP  - 2021 Oct 3
TI  - Extracting Features from Poincare Plots to Distinguish Congestive Heart Failure 
      Patients According to NYHA Classes.
LID - 10.3390/bioengineering8100138 [doi]
LID - 138
AB  - Heart-rate variability has proved a valid tool in prognosis definition of 
      patients with congestive heart failure (CHF). Previous research has documented 
      Poincare plot analysis as a valuable approach to study heart-rate variability 
      performance among different subjects. In this paper, we explored the possibility 
      to feed machine-learning (ML) algorithms using unconventional quantitative 
      parameters extracted from Poincare plots (generated from 24-h electrocardiogram 
      recordings) to classify patients with CHF belonging to different New York Heart 
      Association (NYHA) classes. We performed in sequence the following 
      investigations: first, a statistical analysis was carried out on 9 morphological 
      parameters, automatically measured from Poincare plots. Subsequently, a feature 
      selection through a wrapper with a 10-fold cross-validation method was performed 
      to find the best subset of features which maximized the classification accuracy 
      for each considered ML algorithm. Finally, patient classification was assessed 
      through a ML analysis using AdaBoost of Decision Tree, k-Nearest Neighbors and 
      Naive Bayes algorithms. A univariate statistical analysis proved 5 out of 9 
      parameters presented statistically significant differences among patients of 
      distinct NYHA classes; similarly, a multivariate logistic regression confirmed 
      the importance of the parameter rhoy in the separability between low-risk and 
      high-risk classes. The ML analysis achieved promising results in terms of 
      evaluation metrics (especially the Naive Bayes algorithm), with accuracies 
      greater than 80% and Area Under the Receiver Operating Curve indices greater than 
      0.7 for the overall three algorithms. The study indicates the proposed features 
      have a predictive power to discriminate the NYHA classes, to which the features 
      seem evenly correlated. Despite the NYHA classification being subjective and 
      easily recognized by cardiologists, the potential relevance in the clinical 
      cardiology of the proposed features and the promising ML results implies the 
      methodology could be a valuable approach to automatically classify CHF. Future 
      investigations on enriched datasets may further confirm the presented evidence.
FAU - D'Addio, Giovanni
AU  - D'Addio G
AD  - Institute of Care and Scientific Research Maugeri, 27100 Pavia, Italy.
FAU - Donisi, Leandro
AU  - Donisi L
AUID- ORCID: 0000-0002-9746-2265
AD  - Institute of Care and Scientific Research Maugeri, 27100 Pavia, Italy.
AD  - Department of Advanced Biomedical Sciences, University of Naples Federico II, 
      80131 Naples, Italy.
FAU - Cesarelli, Giuseppe
AU  - Cesarelli G
AUID- ORCID: 0000-0001-8303-5900
AD  - Institute of Care and Scientific Research Maugeri, 27100 Pavia, Italy.
AD  - Department of Chemical, Material and Production Engineering, University of Naples 
      Federico II, 80125 Naples, Italy.
FAU - Amitrano, Federica
AU  - Amitrano F
AUID- ORCID: 0000-0001-6890-6165
AD  - Institute of Care and Scientific Research Maugeri, 27100 Pavia, Italy.
AD  - Department of Information Technology and Electrical Engineering, University of 
      Naples Federico II, 80125 Naples, Italy.
FAU - Coccia, Armando
AU  - Coccia A
AUID- ORCID: 0000-0001-5921-452X
AD  - Institute of Care and Scientific Research Maugeri, 27100 Pavia, Italy.
AD  - Department of Information Technology and Electrical Engineering, University of 
      Naples Federico II, 80125 Naples, Italy.
FAU - La Rovere, Maria Teresa
AU  - La Rovere MT
AUID- ORCID: 0000-0002-1884-5058
AD  - Institute of Care and Scientific Research Maugeri, 27100 Pavia, Italy.
FAU - Ricciardi, Carlo
AU  - Ricciardi C
AUID- ORCID: 0000-0001-7290-6432
AD  - Institute of Care and Scientific Research Maugeri, 27100 Pavia, Italy.
AD  - Department of Information Technology and Electrical Engineering, University of 
      Naples Federico II, 80125 Naples, Italy.
LA  - eng
PT  - Journal Article
DEP - 20211003
PL  - Switzerland
TA  - Bioengineering (Basel)
JT  - Bioengineering (Basel, Switzerland)
JID - 101676056
PMC - PMC8533203
OTO - NOTNLM
OT  - NYHA classification
OT  - Poincare plot analysis
OT  - congestive heart failure
OT  - heart-rate variability
OT  - machine learning
COIS- The authors declare no conflict of interest.
EDAT- 2021/10/23 06:00
MHDA- 2021/10/23 06:01
PMCR- 2021/10/03
CRDT- 2021/10/22 12:17
PHST- 2021/08/11 00:00 [received]
PHST- 2021/09/29 00:00 [revised]
PHST- 2021/09/30 00:00 [accepted]
PHST- 2021/10/22 12:17 [entrez]
PHST- 2021/10/23 06:00 [pubmed]
PHST- 2021/10/23 06:01 [medline]
PHST- 2021/10/03 00:00 [pmc-release]
AID - bioengineering8100138 [pii]
AID - bioengineering-08-00138 [pii]
AID - 10.3390/bioengineering8100138 [doi]
PST - epublish
SO  - Bioengineering (Basel). 2021 Oct 3;8(10):138. doi: 10.3390/bioengineering8100138.