Stress is a factor that affects many people today and is responsible for many of the causes of poor quality of life. For this reason, it is necessary to be able to determine whether a person is stressed or not. Therefore, it is necessary to develop tools that are non-invasive, innocuous, and easy to use. This paper describes a methodology for classifying stress in humans by automatically detecting facial regions of interest in thermal images using machine learning during a short Trier Social Stress Test. Five regions of interest, namely the nose, right cheek, left cheek, forehead, and chin, are automatically detected. The temperature of each of these regions is then extracted and used as input to a classifier, specifically a Support Vector Machine, which outputs three states: baseline, stressed, and relaxed. The proposal was developed and tested on thermal images of 25 participants who were subjected to a stress-inducing protocol followed by relaxation techniques. After testing the developed methodology, an accuracy of 95.4% and an error rate of 4.5% were obtained. The methodology proposed in this study allows the automatic classification of a person’s stress state based on a thermal image of the face. This represents an innovative tool applicable to specialists. Furthermore, due to its robustness, it is also suitable for online applications.

Background: Recent research has evaluated psychological and biological characteristics associated with pain in survivors of breast cancer (BC). Few studies consider their relationship with inflammatory activity. Voluntary facial expressions modify the autonomic activity and this may be useful in the hospital environment for clinical biopsychosocial assessment of pain. Methods: This research compared a BC survivors group under integral treatment (Oncology, Psychology, Nutrition) with a control group to assess the intensity of pain, behavioral interference, anxiety, depression, temperament-expression, anger control, social isolation, emotional regulation, and alexithymia and inflammatory activity, with salivary interleukin 6 (IL-6). Then, a psychophysiological evaluation through repeated measures of facial infrared thermal imaging (IRT) and hands in baseline—positive facial expression (joy)—negative facial expression (pain)—relaxation (diaphragmatic breathing). Results: The results showed changes in the IRT (p < 0.05) during the execution of facial expressions in the chin, perinasal, periorbital, frontal, nose, and fingers areas in both groups. No differences were found in the IL-6 level among the aforementioned groups, but an association with baseline nasal temperature (p < 0.001) was observable. The BC group had higher alexithymia score (p < 0.01) but lower social isolation (p < 0.05), in comparison to the control group. Conclusions: In the low- and medium-concentration groups of IL-6, the psychophysiological intervention proposed in this study has a greater effect than on the high concentration group of IL-6. This will be considered in the design of psychological and psychosocial interventions for the treatment of pain.

Background: Pain is a frequent symptom in cancer patients (CP), and its multidimensional assessment is essential for a comprehensive approach and to establish clinical prognoses. The Short-Form McGill Pain Questionnaire (SF-MPQ) is an internationally recognized tool for the multidimensional assessment of pain, both in clinical and research settings. However, no studies have been reported in Latin America that determine its psychometric properties in CP and chronic pain. Objectives: To determine the psychometric properties of the SF-MPQ in adult Mexican cancer patients with chronic pain. Methods: An instrumental design was used with a non-probabilistic convenience sample of 222 cancer patients treated at the pain clinic of a tertiary care hospital. Analyses were conducted to evaluate factorial structure (exploratory and confirmatory factor analysis [CFA]), reliability (internal consistency), measurement invariance, and criterion validity (concurrent and divergent). Results: CFA verified a 9-item structure divided into 2 factors: (1) Affective-Nociceptive and (2) Neuropathic. A global Cronbach’s alpha coefficient of .82 and a global McDonald’s Omega index of .82 were identified. Configural, metric, and scalar invariance (ΔCFI ≤ .01; ΔRMSEA ≤ .015) were confirmed regarding the sex variable. Finally, the SF-MPQ showed a positive correlation with the Numerical Rating Scale (rho = .436, p< .01) and a negative correlation with the EORTC-QLQ C30 (rho = −.396, p< .01). Significance of results: The Mexican version of the SF-MPQ presented adequate psychometric properties and fit indices, making it a valid and reliable instrument for use in clinical and research settings in Mexico. Its use is recommended for the comprehensive assessment of pain in oncology in Mexico, as it allows for the understanding of pain characteristics beyond intensity, guiding the establishment of clinical prognoses.

This work presents a methodology for automatic colour allocation in thermographic images which is based on two thermograms, one with an Iron colour palette for segmentation and the other in grayscale for thermal analysis through the thermal matrix. With the fusion of both procedures, a palette of colours image is obtained. The colour palette allows characterising the thermography in a controlled manner and gain a better interpretation of the colours. Likewise, the colour palette permits to work in temperature level. With this proposed methodology, it is possible to assign any colour desired. An experiment to induce human emotions (joy, disgust, anger, fear, and sadness) was carried out to prove the application of this proposed method. In a quantitative way, a thermal index of emotions that shows the emotion concerning the baseline was obtained, which correlates with the colours assigned to the new image. Each emotion was associated with one colour. The results attained from both the thermal index of emotions and the hue allocation show the applicability and validation of the proposed palette; thus, it could be employed in any application of thermographic analysis.

Pain is a relevant public health problem and is one of the most common symptoms in cancer patients. Identifying psychosocial factors related to cancer pain would allow the development of specific multidisciplinary treatments to mitigate the impact of pain and help improve the patients’ quality of life. Objective: To analyze a literature search of psychosocial variables related to cancer pain. Method: A literature search was conducted on publications made between 2016 and 2021 using the PICO strategy within the Pubmed and PsycINFO databases. We revised 22 studies that met the inclusion criteria in full text. Results: Pain intensity is a predictor of quality of life (and its various dimensions) and interferes with various key aspects of daily life. Patients with symptoms of anxiety and depression are more likely to report greater intensity of pain. Likewise, greater intensity of pain relates to lower self-rated health, less social support, more suffering, and greater pain catastrophizing. Conclusion: The identification of psychosocial variables associated with cancer pain requires the establishment of intervention objectives for future research including non-pharmacological treatment for the modulation of pain perception and the improvement in the quality of life of cancer patients in Mexico. El dolor es un importante problema de salud pública y uno de los síntomas más comunes en los pacientes con cáncer. Identificar los factores psicosociales relacionados con el dolor que genera esta enfermedad permitiría desarrollar tratamientos multidisciplinarios específicos con los que mitigar su impacto y así contribuir a mejorar la calidad de vida de los pacientes. Objetivo: Efectuar una búsqueda de la literatura de variables psicosociales relacionadas con dolor por cáncer. Método: Se llevó a cabo una búsqueda en las bases de datos Pubmed y PsycINFO de la literatura publicada entre los años 2016 y 2021 mediante la estrategia PICO. Resultados: Se revisaron en texto completo 22 estudios que cumplieron los criterios de inclusión. La intensidad de dolor es un predictor de calidad de vida y de sus diversas dimensiones y de la inferencia de dolor, esto es, grado en que interfiere con varios aspectos de la vida diaria. Los pacientes con síntomas de ansiedad y depresión tienen mayor probabilidad de sufrir una mayor intensidad del dolor, la que a su vez está relacionada con una salud autoevaluada más pobre, un menor apoyo social y un mayor sufrimiento y catastrofización del dolor. Conclusión: La identificación de las variables psicosociales asociadas con el dolor oncológico supone el establecimiento de objetivos de intervención para futuras investigaciones en el tratamiento no farmacológico para modular la percepción de dolor y mejorar la calidad de vida de los pacientes con cáncer en México. Recibido: 28/07/2022 Aceptado: 19/09/2023