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

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

doi:10.3934/mbe.2020013

Cited by 11 publications

(24 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using SampEn, the highest performance was achieved using

, and

0.25–0.50, yielding MCC = 0.6347, sensitivity = 0.81 and specificity = 0.87. This was also a good performance that confirms the suitability of SampEn to this task, as demonstrated in [ 17 ].…”

Section: Experiments and Resultssupporting

confidence: 84%

“…These records have not been used in any other prior study yet, although they were acquired in the same clinical setting as the dataset used in [ 17 ]. The clinical contributors of this paper from Kasturba Medical College (India) are conducting an ongoing effort of recording body temperature data from a disparity of pathologies: dengue, malaria, tuberculosis, leptospirosis, thyroiditis, enteric fever, pyogenic sepsis, and others, and when a significant number of records of each type becomes available, we study their properties and the best methods to yield a differential diagnosis based solely on time series analysis, as was the case in [ 17 , 18 , 19 , 20 ] and in the present paper.…”

Section: Materials and Methodsmentioning

confidence: 99%

“…For comparative purposes, SampEn was also computed in the experiments. This measure is one of the most successful methods for time series classification [ 24 , 25 , 26 , 27 ], including temperature records [ 17 ], and it is therefore a good cornerstone on which to build the conclusions for SlopEn.…”

Section: Materials and Methodsmentioning

confidence: 99%

“…It also takes advantage of the recent progress made on the two previous key issues described: the analysis of continuous body temperature time series, and the application of entropy measures [ 16 ]. For instance, the work [ 17 ] used SampEn to find differences between dengue, tuberculosis, and other non-infectious and non tubercular bacterial infections. The classification accuracy achieved spanned from 0.60 up to 0.77, depending on the diseases under comparison.…”

Section: Introductionmentioning

confidence: 99%

“…This paper proposes a scheme for assessing the differences between body temperature records coming from a variety of pathological backgrounds, as in [ 17 ]. The analysis was based on body temperature records of 24 h, 1 min sampling period, from patients that specifically developed a fever due to malaria or dengue diseases.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Fever Time Series Analysis Using Slope Entropy. Application to Early Unobtrusive Differential Diagnosis

Cuesta–Frau

Dakappa²,

Chakrapani

et al. 2020

Entropy

Self Cite

View full text Add to dashboard Cite

Fever is a readily measurable physiological response that has been used in medicine for centuries. However, the information provided has been greatly limited by a plain thresholding approach, overlooking the additional information provided by temporal variations and temperature values below such threshold that are also representative of the subject status. In this paper, we propose to utilize continuous body temperature time series of patients that developed a fever, in order to apply a method capable of diagnosing the specific underlying fever cause only by means of a pattern relative frequency analysis. This analysis was based on a recently proposed measure, Slope Entropy, applied to a variety of records coming from dengue and malaria patients, among other fever diseases. After an input parameter customization, a classification analysis of malaria and dengue records took place, quantified by the Matthews Correlation Coefficient. This classification yielded a high accuracy, with more than 90% of the records correctly labelled in some cases, demonstrating the feasibility of the approach proposed. This approach, after further studies, or combined with more measures such as Sample Entropy, is certainly very promising in becoming an early diagnosis tool based solely on body temperature temporal patterns, which is of great interest in the current Covid-19 pandemic scenario.

show abstract

“…Using SampEn, the highest performance was achieved using

, and

0.25–0.50, yielding MCC = 0.6347, sensitivity = 0.81 and specificity = 0.87. This was also a good performance that confirms the suitability of SampEn to this task, as demonstrated in [ 17 ].…”

Section: Experiments and Resultssupporting

confidence: 84%