Classification of fever patterns using a single extracted entropy feature: A feasibility study based on Sample Entropy

David Cuesta-Frau; Pau Miró-Martínez; Sandra Oltra-Crespo; Antonio Molina-Picó; Pradeepa H. Dakappa; Chakrapani Mahabala; Borja Vargas; Paula González; David Cuesta-Frau; Pau Miró-Martínez; Sandra Oltra-Crespo; Antonio Molina-Picó; Pradeepa H. Dakappa; Chakrapani Mahabala; Borja Vargas; Paula González

doi:10.3934/mbe.2020013

Mathematical Biosciences and Engineering

2020, Volume 17, Issue 1: 235-249. doi: 10.3934/mbe.2020013

Previous Article Next Article

Research article Special Issues

Classification of fever patterns using a single extracted entropy feature: A feasibility study based on Sample Entropy

1.
Technological Institute of Informatics(ITI), Universitat Politècnica de València, Campus Alcoi, Plaza Ferrándiz y Carbonell, 2, 03801, Alcoi, Spain
2.
Innovatec Sensorización y Comunicación S. L., Avda. Elx, 3, 03801, Alcoi, Spain
3.
Department of Statistics, Universitat Politècnica de València, Campus Alcoi, Plaza Ferrándiz y Carbonell, 2, 03801, Alcoi, Spain
4.
Department of Pharmacology, MVJ Medical College and Research Hospital, Dandupalya, Hoskote, Karnataka, India
5.
Department of General Medicine, Kasturba Medical College, Mangalore, Manipal Academy of Higher Education, Manipal, Karnataka, India
6.
Department of Internal Medicine, Móstoles Teaching Hospital, Móstoles, 28935, Madrid, Spain

Received: 26 June 2019 Accepted: 22 September 2019 Published: 30 September 2019

Fever is a common symptom of many diseases. Fever temporal patterns can be different depending on the specific pathology. Differentiation of diseases based on multiple mathematical features and visual observations has been recently studied in the scientific literature. However, the classification of diseases using a single mathematical feature has not been tried yet. The aim of the present study is to assess the feasibility of classifying diseases based on fever patterns using a single mathematical feature, specifically an entropy measure, Sample Entropy. This was an observational study. Analysis was carried out using 103 patients, 24 hour continuous tympanic temperature data. Sample Entropy feature was extracted from temperature data of patients. Grouping of diseases (infectious, tuberculosis, non-tuberculosis, and dengue fever) was made based on physicians diagnosis and laboratory findings. The quantitative results confirm the feasibility of the approach proposed, with an overall classification accuracy close to 70%, and the capability of finding significant differences for all the classes studied. %An abstract is a brief of the paper; the abstract should not contain references, the text of the abstract section should be in 12 point normal Times New Roman.
- fever,
- time series classification,
- tuberculosis,
- dengue,
- diagnostic aids,
- Sample entropy,
- Trace segmentation
Citation: David Cuesta-Frau, Pau Miró-Martínez, Sandra Oltra-Crespo, Antonio Molina-Picó, Pradeepa H. Dakappa, Chakrapani Mahabala, Borja Vargas, Paula González. Classification of fever patterns using a single extracted entropy feature: A feasibility study based on Sample Entropy[J]. Mathematical Biosciences and Engineering, 2020, 17(1): 235-249. doi: 10.3934/mbe.2020013

Related Papers:

Abstract

Fever is a common symptom of many diseases. Fever temporal patterns can be different depending on the specific pathology. Differentiation of diseases based on multiple mathematical features and visual observations has been recently studied in the scientific literature. However, the classification of diseases using a single mathematical feature has not been tried yet. The aim of the present study is to assess the feasibility of classifying diseases based on fever patterns using a single mathematical feature, specifically an entropy measure, Sample Entropy. This was an observational study. Analysis was carried out using 103 patients, 24 hour continuous tympanic temperature data. Sample Entropy feature was extracted from temperature data of patients. Grouping of diseases (infectious, tuberculosis, non-tuberculosis, and dengue fever) was made based on physicians diagnosis and laboratory findings. The quantitative results confirm the feasibility of the approach proposed, with an overall classification accuracy close to 70%, and the capability of finding significant differences for all the classes studied. %An abstract is a brief of the paper; the abstract should not contain references, the text of the abstract section should be in 12 point normal Times New Roman.

References

[1]	D. Ogoina, Fever, fever patterns and diseases called fever-A review, J. Infect. Public Heal., 4 (2011), 108-124.
[2]	G. Kelly, Body temperature variability (part 1): A review of the history of body temperature and its variability due to site selection, biological rhythms, fitness, and aging, Altern. Med. Rev., 11 (2007), 278-293.
[3]	G. Kelly, Body temperature variability (part 2): Masking influences of body temperature variability and a review of body temperature variability in disease, Altern. Med. Rev., 12 (2007), 49-62.
[4]	T. E. Fletcher, C. P. Bleeker-Rovers and N. J. Beeching, Fever, Medicine, 45 (2017), 177-183, Acute Medicine Part 2 of 2.
[5]	T. Susilawati and W. McBride, Acute undifferentiated fever in Asia: A review of the literature,SE Asian J. Trop. Med. Public Health, 45 (2014), 719-726.
[6]	W. Chen, Thermometry and interpretation of body temperature, Biomed. Eng. Lett., 9 (2019), 3-17.
[7]	M. Varela-Entrecanales, D. Cuesta-Frau, J. A. Madrid, et al., Holter monitoring of central and peripheral temperature: Possible uses and feasibility study in outpatient settings, J. Clin. Monit. Comput., 23 (2009), 209-216.
[8]	D. Cuesta-Frau, P. Miró-Martínez, S. Oltra-Crespo, et al., Model selection for body temperature signal classification using both amplitude and ordinality-based entropy measures, Entropy, 20 (2018).
[9]	J. Jordán-Núnez, P. Miró-Martínez, B. Vargas, et al., Statistical models for fever forecasting based on advanced body temperature monitoring, J. Crit. Care, 37 (2017), 136-140.
[10]	A. M Drewry, B. Fuller, T. Bailey, et al., Body temperature patterns as a predictor of hospitalacquired sepsis in afebrile adult intensive care unit patients: A case-control study, Crit. Care, 17 (2013), R200.
[11]	V. Papaioannou, I. Chouvarda, N. Maglaveras, et al., Temperature variability analysis using Wavelets and Multiscale Entropy in patients with systemic inflammatory response syndrome, sepsis, and septic shock, Crit. Care, 16 (2012), R51.
[12]	V. E. Papaioannou, I. G. Chouvarda, N. K. Maglaveras, et al., Temperature Multiscale Entropy analysis: A promising marker for early prediction of mortality in septic patients, Physiol. Meas.,34 (2013), 1449.
[13]	D. Cuesta-Frau, M. Varela, P. Miró-Martínez, et al., Predicting survival in critical patients by use of body temperature regularity measurement based on Approximate Entropy, Medical & Biological Engineering & Computing, 45 (2007), 671-678.
[14]	P. H. Dakappa, K. Prasad, S. B. Rao, et al., Classification of infectious and noninfectious diseases using artificial neural networks from 24-hour continuous tympanic temperature data of patients with undifferentiated fever, Crit. Rev. Bio. Eng., 46 (2018), 173-183.
[15]	P. H. Dakappa, K. Prasad, S. B. Rao, et al., A Predictive Model to Classify Undifferentiated Fever Cases Based on Twenty-Four-Hour Continuous Tympanic Temperature Recording, J. Healthc. Eng., 2017 (2017), 6, URL 10.1155/2017/5707162.
[16]	M. Aboy, D. Cuesta-Frau, D. Austin, et al., Characterization of Sample Entropy in the context of biomedical signal analysis, in 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2007, 5942-5945.
[17]	J. Richman and J. R. Moorman, Physiological time-series analysis using Approximate Entropy and Sample Entropy, Am. J. Physiol. Heart Circ. Physiol., 278 (2000), H2039-2049.
[18]	S. M. Pincus, Approximate Entropy as a measure of system complexity, Proceed. Nat. Aca. Sci.,88 (1991), 2297-2301.
[19]	W. Chen, J. Zhuang, W. Yu, et al., Measuring complexity using FuzzyEn, ApEn, and SampEn,Med. Eng. Phys., 31 (2009), 61-68.
[20]	E. Cirugeda-Roldán, D. Cuesta-Frau, P. Miró-Martínez, et al., A new algorithm for quadratic Sample Entropy optimization for very short biomedical signals: Application to blood pressure records, Comput. Meth. Prog. Bio., 114 (2014), 231-239.
[21]	D. E. Lake and J. R. Moorman, Accurate estimation of entropy in very short physiological time series: The problem of atrial fibrillation detection in implanted ventricular devices, Am. J. Physiol.-Heart C., 300 (2011), H319-H325, PMID: 21037227.
[22]	S. Simons, P. Espino and D. Abásolo, Fuzzy entropy analysis of the electroencephalogram in patients with Alzheimer's disease: Is the method superior to Sample Entropy?, Entropy, 20 (2018).
[23]	D. Cuesta-Frau, P. Miro-Miró-Martínez, J. Jordán-Núnez, et al., Noisy EEG signals classification based on entropy metrics. Performance assessment using first and second generation statistics, Comput. Biol. Med., 87 (2017), 141-151.
[24]	D. Cuesta-Frau, D. Novák, V. Burda, et al., Characterization of artifact influence on the classification of glucose time series using sample entropy statistics, Entropy, 20 (2018).
[25]	D. Cuesta-Frau, D. Novák, V. Burda, et al., Influence of Duodenal-Jejunal Implantation on Glucose Dynamics: A Pilot Study Using Different Nonlinear Methods, Complexity, 2019 (2019), 10.
[26]	A. Lubetzky, D. Harel and E. Lubetzky, On the effects of signal processing on Sample Entropy for postural control, PLOS ONE, 13 (2018), e0193460.
[27]	H. Azami and J. Escudero, Coarse-graining approaches in univariate Multiscale Sample and Dispersion Entropy, Entropy, 20(2018), 138.
[28]	J. McCamley, W. Denton, A. Arnold, et al., On the calculation of Sample Entropy using continuous and discrete human gait data, Entropy, 20 (2018), 764.
[29]	D. Cuesta-Frau, M. Varela-Entrecanales, A. Molina-Picó, et al., Patterns with equal values in Permutation Entropy: Do they really matter for biosignal classification?, Complexity, 2018 (2018), 1-15.
[30]	D. Cuesta-Frau, J. C. Pérez-Cortés and G. Andreu-García, Clustering of electrocardiograph signals in computer-aided Holter analysis, Comput. Meth. Prog. Bio., 72 (2003), 179-196.
[31]	D. Cuesta-Frau, J. C. Pérez-Cortés and G. Andreu-García, et al., Feature extraction methods applied to the clustering of electrocardiographic signals. a comparative study, in 16 Th International Conference on Pattern Recognition IEEE Computer Society, 3 (2002), 961-964.
[32]	P. H. Dakappa, S. B. Rao, B. Ganaraja, et al., Unique temperature patterns in 24-h continuous tympanic temperature in tuberculosis, Trop. Doct., 0049475519829600, PMID: 30782109.
[33]	A. A. Rabinstein and K. Sandhu, Non-infectious fever in the neurological intensive care unit: Incidence, causes and predictors, J. Neurol. Neurosurg. Psychiat., 78 (2007), 1278-1280.
[34]	J. M. Yentes, N. Hunt, K. K. Schmid, et al., The appropriate use of Approximate Entropy and Sample Entropy with short data sets, An. Biomed. Eng., 41 (2013), 349-365.
[35]	A. Romanovsky, C. Simons and V. Kulchitsky, "biphasic" fevers often consist of more than two phases, Am. J. Physiol., 275 (1998), R323-331.

Reader Comments

Your name:*

Email:*
© 2020 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)