Limits...
Pain Intensity Recognition Rates via Biopotential Feature Patterns with Support Vector Machines.

Gruss S, Treister R, Werner P, Traue HC, Crawcour S, Andrade A, Walter S - PLoS ONE (2015)

Bottom Line: The clinically used methods of pain diagnosis do not allow for objective and robust measurement, and physicians must rely on the patient's report on the pain sensation.We achieved classification rates of 90.94% for baseline vs. pain tolerance threshold and 79.29% for baseline vs. pain threshold.The machine learning measurement of pain in patients could provide valuable information for a clinical team and thus support the treatment assessment.

View Article: PubMed Central - PubMed

Affiliation: University of Ulm, Medical Psychology, Department of Psychosomatic Medicine and Psychotherapy, Ulm, Germany.

ABSTRACT

Background: The clinically used methods of pain diagnosis do not allow for objective and robust measurement, and physicians must rely on the patient's report on the pain sensation. Verbal scales, visual analog scales (VAS) or numeric rating scales (NRS) count among the most common tools, which are restricted to patients with normal mental abilities. There also exist instruments for pain assessment in people with verbal and / or cognitive impairments and instruments for pain assessment in people who are sedated and automated ventilated. However, all these diagnostic methods either have limited reliability and validity or are very time-consuming. In contrast, biopotentials can be automatically analyzed with machine learning algorithms to provide a surrogate measure of pain intensity.

Methods: In this context, we created a database of biopotentials to advance an automated pain recognition system, determine its theoretical testing quality, and optimize its performance. Eighty-five participants were subjected to painful heat stimuli (baseline, pain threshold, two intermediate thresholds, and pain tolerance threshold) under controlled conditions and the signals of electromyography, skin conductance level, and electrocardiography were collected. A total of 159 features were extracted from the mathematical groupings of amplitude, frequency, stationarity, entropy, linearity, variability, and similarity.

Results: We achieved classification rates of 90.94% for baseline vs. pain tolerance threshold and 79.29% for baseline vs. pain threshold. The most selected pain features stemmed from the amplitude and similarity group and were derived from facial electromyography.

Conclusion: The machine learning measurement of pain in patients could provide valuable information for a clinical team and thus support the treatment assessment.

No MeSH data available.


Related in: MedlinePlus

Support Vector Machine learning architecture.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4608770&req=5

pone.0140330.g005: Support Vector Machine learning architecture.

Mentions: We conducted the Support Vector Machine classification tasks in conjunction with the previously mentioned feature selection method on varying data sets and different biopotentials. SVMs were trained on 75% of the data (total number of training samples = 6375) tested on the remaining 25% of data (total number of test samples = 2125) (see Fig 5). The number of hereby-obtained optimal features ranges from 5 to 22 (depending on learning task).


Pain Intensity Recognition Rates via Biopotential Feature Patterns with Support Vector Machines.

Gruss S, Treister R, Werner P, Traue HC, Crawcour S, Andrade A, Walter S - PLoS ONE (2015)

Support Vector Machine learning architecture.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4608770&req=5

pone.0140330.g005: Support Vector Machine learning architecture.
Mentions: We conducted the Support Vector Machine classification tasks in conjunction with the previously mentioned feature selection method on varying data sets and different biopotentials. SVMs were trained on 75% of the data (total number of training samples = 6375) tested on the remaining 25% of data (total number of test samples = 2125) (see Fig 5). The number of hereby-obtained optimal features ranges from 5 to 22 (depending on learning task).

Bottom Line: The clinically used methods of pain diagnosis do not allow for objective and robust measurement, and physicians must rely on the patient's report on the pain sensation.We achieved classification rates of 90.94% for baseline vs. pain tolerance threshold and 79.29% for baseline vs. pain threshold.The machine learning measurement of pain in patients could provide valuable information for a clinical team and thus support the treatment assessment.

View Article: PubMed Central - PubMed

Affiliation: University of Ulm, Medical Psychology, Department of Psychosomatic Medicine and Psychotherapy, Ulm, Germany.

ABSTRACT

Background: The clinically used methods of pain diagnosis do not allow for objective and robust measurement, and physicians must rely on the patient's report on the pain sensation. Verbal scales, visual analog scales (VAS) or numeric rating scales (NRS) count among the most common tools, which are restricted to patients with normal mental abilities. There also exist instruments for pain assessment in people with verbal and / or cognitive impairments and instruments for pain assessment in people who are sedated and automated ventilated. However, all these diagnostic methods either have limited reliability and validity or are very time-consuming. In contrast, biopotentials can be automatically analyzed with machine learning algorithms to provide a surrogate measure of pain intensity.

Methods: In this context, we created a database of biopotentials to advance an automated pain recognition system, determine its theoretical testing quality, and optimize its performance. Eighty-five participants were subjected to painful heat stimuli (baseline, pain threshold, two intermediate thresholds, and pain tolerance threshold) under controlled conditions and the signals of electromyography, skin conductance level, and electrocardiography were collected. A total of 159 features were extracted from the mathematical groupings of amplitude, frequency, stationarity, entropy, linearity, variability, and similarity.

Results: We achieved classification rates of 90.94% for baseline vs. pain tolerance threshold and 79.29% for baseline vs. pain threshold. The most selected pain features stemmed from the amplitude and similarity group and were derived from facial electromyography.

Conclusion: The machine learning measurement of pain in patients could provide valuable information for a clinical team and thus support the treatment assessment.

No MeSH data available.


Related in: MedlinePlus