1. |
- Gavrilis, Dimitris, et al.
(author)
-
A One-Class Approach to Cardiotocogram Assessment
- 2015
-
In: 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. - Piscataway, NJ : IEEE Communications Society. - 9781424492718 ; , s. 518-521
-
Conference paper (peer-reviewed)abstract
- Cardiotocogram (CTG) is the most widely used means for the assessment of fetal condition. CTG consists of two traces one depicting the Fetal Heart Rate (FHR), and the other the Uterine Contractions (UC) activity. Many automatic methods have been proposed for the interpretation of the CTG. Most of them rely either on a binary classification approach or on a multiclass approach to come up with a decision about the class that the tracing belongs to. This work investigates the use of a one-class approach to the assessment of CTGs building a model only for the healthy data. The preliminary results are promising indicating that normal traces could be used as part of an automatic system that can detect deviations from normality.
|
|
2. |
- Mastinu, Enzo, 1987, et al.
(author)
-
Analog Front-Ends comparison: on the way to a portable, lowpower and low-cost EMG controller based on Pattern Recognition
- 2015
-
In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. - 1557-170X. - 9781424492718 ; 2015-November, s. 2111-2114
-
Conference paper (peer-reviewed)abstract
- Compact and low-noise Analog Front-Ends (AFEs)are becoming increasingly important for the acquisition ofbioelectric signals in portable system. In this work, we comparetwo popular AFEs available on the market, namely theADS1299 (Texas Instruments) and the RHA2216 (IntanTechnologies). This work develops towards the identification ofsuitable acquisition modules to design an affordable, reliableand portable device for electromyography (EMG) acquisitionand prosthetic control. Device features such as Common ModeRejection (CMR), Input Referred Noise (IRN) and Signal toNoise Ratio (SNR) were evaluated, as well as the resultingaccuracy in myoelectric pattern recognition (MPR) for thedecoding of motion intention. Results reported better noiseperformances and higher MPR accuracy for the ADS1299 andsimilar SNR values for both devices.
|
|
3. |
- Ortiz Catalan, Max Jair, 1982, et al.
(author)
-
Offline Accuracy: A Potentially Misleading Metric in Myoelectric Pattern Recognition for Prosthetic Control.
- 2015
-
In: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy, 15-19 August 2015. - 1557-170X. - 9781424492718 ; , s. 1140-1143
-
Conference paper (peer-reviewed)abstract
- Offline accuracy has been the preferred performance measure in myoelectric pattern recognition (MPR) for the prediction of motion volition. In this study, different metrics relating the fundamental binary prediction outcomes were analyzed. Our results indicate that global accuracy is biased by 1) the unbalanced number of possible true positive and negative outcomes, and 2) the almost perfect specificity and negative predicted value, which were consistently found across algorithms, topologies, and movements (individual and simultaneous). Therefore, class-specific accuracy is advisable instead. Additionally, we propose the use of precision (positive predictive value) and sensitivity (recall) as a complement to accuracy to better describe the discrimination capabilities of MPR algorithms, as these consider the effect of false predictions. However, all the studied offline metrics failed to predict real-time decoding, and therefore real-time testing continue to be necessary to truly evaluate the clinical usability of MPR.
|
|
4. |
- Sambo, Francesco, et al.
(author)
-
A Bayesian Network analysis of the probabilistic relations between risk factors in the predisposition to type 2 diabetes
- 2015
-
In: 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). - 1557-170X. - 9781424492718 ; 2015, s. 22-2119
-
Conference paper (peer-reviewed)abstract
- In order to better understand the relations between different risk factors in the predisposition to type 2 diabetes, we present a Bayesian Network analysis of a large dataset, composed of three European population studies. Our results show, together with a key role of metabolic syndrome and of glucose after 2 hours of an Oral Glucose Tolerance Test, the importance of education, measured as the number of years of study, in the predisposition to type 2 diabetes.
|
|
5. |
- Seoane, Fernando, et al.
(author)
-
Slightly superior performance of bioimpedance spectroscopy over single frequency regression equations for assessment of total body water.
- 2015
-
In: Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE. 25-29 Aug. 2015, Milan, Italy.. - : IEEE. - 1094-687X .- 1558-4615. - 9781424492718 - 9781424492701 ; 2015, s. 3707-10
-
Conference paper (peer-reviewed)abstract
- Electrical bioimpedance has been used for several decades to assess body fluid distribution and body composition by using single frequency and bioimpedance spectroscopic (BIS) techniques. It remains uncertain whether BIS methods have better performance compare to single frequency regression equations. In this work the performance of two BIS methods and four different 50 kHz single frequency prediction equations was studied in a data set of wrist-to-ankle tetrapolar BIS measurements (5-1000 kHz) together with reference values of total body water obtained by tritium dilution in 92 patients. Data were compared using regression techniques and Bland-Altman plots. The results of this study showed that all methods produced similarly high correlation and concordance coefficients, indicating good accuracy as a method. Limits of agreement analysis indicated that the population level performance of Sun's prediction equations was very similar to the performance of both BIS methods. However, BIS methods in practice have slightly better predictive performance than the single-frequency equations as judged by higher correlation and the limits of agreement from the Bland-Altman analysis. In any case, the authors believe that an accurate evaluation of performance of the methods cannot be done as long as the evaluation is done using Bland-Altman analysis, the commonly accepted technique for this kind of performance comparisons.
|
|