Cost-Saving Early Diagnosis of Functional Pain in Nonmalignant Pain: A Noninferiority Study of Diagnostic Accuracy

Chronic Pain Diagnosis Using Machine Learning, Questionnaires, and QST: A Sensitivity Experiment

In the last decade, machine learning has been widely used in different fields, especially because of its capacity to work with complex data. With the support of machine learning techniques, different studies have been using data-driven approaches to better understand some syndromes like mild cognitive impairment, Alzheimer’s disease, schizophrenia, and chronic pain. Chronic pain is a complex disease that can recurrently be misdiagnosed due to its comorbidities with other syndromes with which it shares symptoms. Within that context, several studies have been suggesting different machine learning algorithms to classify or predict chronic pain conditions. Those algorithms were fed with a diversity of data types, from self-report data based on questionnaires to the most advanced brain imaging techniques. In this study, we assessed the sensitivity of different algorithms and datasets classifying chronic pain syndromes. Together with this assessment, we highlighted important methodological steps that should be taken into account when an experiment using machine learning is conducted. The best results were obtained by ensemble-based algorithms and the dataset containing the greatest diversity of information, resulting in area under the receiver operating curve (AUC) values of around 0.85. In addition, the performance of the algorithms is strongly related to the hyper-parameters. Thus, a good strategy for hyper-parameter optimization should be used to extract the most from the algorithm. These findings support the notion that machine learning can be a powerful tool to better understand chronic pain conditions.

Age and Gender as Factors of Pressure Sensitivity of Pain-Free Persons: Are They Meaningful?

Purpose

Prior findings suggest that women and elderly persons are more sensitive to pressure than men and younger persons; however, the magnitudes of these differences are substantially inconsistent. We answered the question whether the higher sensitivity of women and elderly persons is quantitatively meaningful. Specifically, we investigated if it is large enough to hamper the diagnosis, classification and follow-up of pain conditions by clinicians.

Materials and Methods

From each age stratum (18–20, 21–30, 31–40, 41–50, 51–60, 61–70, 71–80, and >80 years), 40 pain-free women and 40 pain-free men were recruited. They rated the intensity of pressure of ten Newtons over ten seconds on an analogue zero to ten rating scale. The pressure was applied on their middle fingers and ear lobes with a threshold algometer. Centile curves visualized the sex- and age-dependent fluctuation of pressure sensitivity.

Results

Over the entire age range from 20 to 80 years, the median curves fluctuated within the interval of less than two points. The distance between the median curves of men and women was also less than two points. On the average, the median difference was half a point on the finger (p = 0.249) and the ear lobe (p = 0.083).

Conclusion

Less than two points is below the minimal clinically important difference for a zero to ten analogue pain rating scale; differences smaller than one point are even below the resolution of the scale. Sex differences and age fluctuations of pressure sensitivity are negligible.

Using Deep Learning and Resting-State fMRI to Classify Chronic Pain Conditions

Chronic pain is known as a complex disease due to its comorbidities with other symptoms and the lack of effective treatments. As a consequence, chronic pain seems to be under-diagnosed in more than 75% of patients. At the same time, the advance in brain imaging, the popularization of machine learning techniques and the development of new diagnostic tools based on these technologies have shown that these tools could be an option in supporting decision-making of healthcare professionals. In this study, we computed functional brain connectivity using resting-state fMRI data from one hundred and fifty participants to assess the performance of different machine learning models, including deep learning (DL) neural networks in classifying chronic pain patients and pain-free controls. The best result was obtained by training a convolutional neural network fed with data preprocessed using the MSDL probabilistic atlas and using the dynamic time warping (DTW) as connectivity measure. DL models had a better performance compared to other less costly models such as support vector machine (SVM) and RFC, with balanced accuracy ranged from 69 to 86%, while the area under the curve (ROC) ranged from 0.84 to 0.93. Also, DTW overperformed correlation as connectivity measure. These findings support the notion that resting-state fMRI data could be used as a potential biomarker of chronic pain conditions.

Rethinking the criteria for fibromyalgia in 2019: the ABC indicators

PURPOSE

Diagnostic criteria for fibromyalgia have been subject to debate and controversy for many years. The preliminary diagnostic criteria introduced in 2010 and 2011 have been criticized for different reasons, including questionable diagnostic specificity and a lack of an etiopathogenetic foundation. The "ABC indicators" presented in this study reflect a further development of the 2011 criteria and refer to (A) algesia, (B) bilateral, axial-symmetric pain distribution, and (C) chronic distress.

PATIENTS AND METHODS

We compared the diagnostic performance of the ABC indicators with that of the 2011 criteria by analyzing the data of 409 inpatients with chronic functional pain divided into two subgroups of pain patients: Those with whole-body pain and those with pain not involving the whole body. Under the premise that FM phenotypically represents a whole-body pain disorder, sensitivity, specificity, correct classification and diagnostic odds ratios were calculated.

RESULTS

The 2011 criteria demonstrated a specificity of 68.1%, a sensitivity of 75.5%, a correct classification of 71.0% and a diagnostic odds ratio of 6.56 (CI: 4.17-10.31). The ABC indicators achieved a specificity of 88.3%, a sensitivity of 62.3%, a correct classification of 78.6%, and a diagnostic odds ratio of 12.47 (CI: 7.30-21.28).

CONCLUSION

The ABC fibromyalgia indicators demonstrated better specificity, lower sensitivity, and better overall diagnostic effectiveness than the original 2011 criteria.