A Critical Review About the Application of Artificial Intelligence in Pain Assessment

Mostafa Farghal
Faculty of Veterinary Medicine, University of Calgary, Calgary, Alberta, Canada
Faculty of Veterinary Medicine, Minia University, Minia, Egypt
Correspondence to: Mostafa Farghal, mostafa.farhgal@ucalgary.ca

DOI: https://doi.org/10.70389/PJAI.100002

Additional information

• Ethical approval: N/a
• Consent: N/a
• Funding: No industry funding
• Conflicts of interest: N/a
• Author contribution: Mostafa Farghal – Conceptualization, Writing – original draft, review and editing
• Guarantor: Mostafa Farghal
• Provenance and peer-review:
  Commissioned and externally peer-reviewed
• Data availability statement: N/a

Keywords: automated pain assessment, machine learning, facial expressions, electrodermal activity, electroencephalography

Peer-review
Received: 24 September 2024
Accepted: 26 September 2024
Published: 10 October 2024

Introduction

Pain is defined as an unpleasant sensory and emotional experience associated with, or resembling that associated with, actual or potential tissue damage. It is considered a personal experience, which is influenced to varying degrees by psychological, social, and biological factors.¹ Pain has many consequences for human health, including sleep disturbance, reduced physical activities, limited daily social activities, mental problems, and reduced life quality.^2–4 Pain was reported to increase hospitalization, visits to emergency departments, and financial burden.^5,6 Therefore, pain assessment and treatment not only improve patient outcomes but also improve the use of the healthcare sector.⁶

Pain assessment is a crucial step for effective pain management; however, accurate pain assessment, particularly determining its intensity, could be a challenging task.⁷ Fast and accurate pain assessment can avoid transformation of acute pain into chronic pain, which results in psychological or physiological suffering.⁸ The current tools for pain assessment in humans, including self-reports (self-report is considered the gold standard), visual analog scale (VAS), numerical rating scale (NRS), and facial expressions have limitations such as their subjective nature, being inappropriate for noncommunicative patients, dependence on human judgment, and influence by observer bias and gender.⁹ Therefore, the need for a pain assessment tool that can precisely identify pain and its intensity still exists.¹⁰ Artificial intelligence (AI) was proposed to address the challenges in the current pain assessment tools by providing accurate and objective pain assessment. However, a gap between AI development and AI applications exists.¹¹

AI refers to the analysis of large datasets utilizing computational algorithms to organize, predict, and influence future behaviors or outcomes.¹² Also, it refers to the notion that computers could be taught pattern recognition with little or no human interference.¹³ Machine learning (ML), computer vision, natural language processing (NLP), and fuzzy logic are considered subsets of AI, applied in different medical fields.¹⁴ Generally, AI was implemented in pain research for three main purposes: pain assessment,^15–17 pain prediction and aiding clinical decision making,^18–20 and self-management of pain through developing AI-based mobile applications.^21–23 In the last few years, AI models were integrated with several pain assessment tools, including facial expressions, body/head movements, language analysis, electrodermal activity, and electroencephalography (EEG), to enhance pain assessment.²⁴ Nevertheless, little is known about the range of applications of these AI-based tools for pain assessment across populations (infants vs. adults) and conditions (research vs. clinical conditions).

We would like to clarify that this paper does not delve into the technical working of AI nor provide in-depth knowledge of AI models, subsets, and classifiers, as these topics are beyond its scope. Therefore, a basic knowledge of AI terminology is required to understand this paper. Comprehensive and simple explanations of AI terms and their subsets can be found elsewhere.^25,26 The primary objectives of this paper are: (1) to provide an overview of common applications of AI in the field of pain assessment and (2) to demonstrate the challenges for using AI-powered pain assessment tools by clinicians.

The Application of AI in Medicine

The adoption of AI in various medical fields is rapidly expanding. AI contributes to outcome optimization, cost reductions, new product development, and improved decision-making.²⁷ It has been applied in identifying diseases, predicting prognosis, analyzing health examinations, laboratory results, and imaging, and linking these findings to specific diseases.²⁸ Simply, AI-empowered tools can analyze patient records to identify their patterns and risk factors that may indicate the presence of a specific disease. Additionally, AI-empowered tools can help with selecting treatment options to support favorable outcomes.¹²

The decision-making process could be significantly enhanced by the AI application through analysis of big datasets. Current clinical decision-making relies on physicians’ knowledge and experience, a process that can be considered slow due to managing a vast amount of information. AI enables fast and precise analysis of big data at both national and international levels, ultimately improving clinical decision-making globally.²⁹ Moreover, AI algorithms can help in opioid monitoring and risk reduction through analyzing patterns in electronic health records and identifying patients at risk of opioid misuse or when opioid use is appropriate.^30,31 Another application for AI is tailoring interventions to individual needs. Many chronic pain patients suffer from conditions such as anxiety and depression, making it crucial to address these problems.¹² AI could assist in developing personalized psychological treatment protocols through identifying patterns in patients’ behaviors. For example, AI could improve cognitive behavioral therapy for chronic pain by tailoring interventions to individual needs based on their insights.¹²

Applications of AI in Pain Assessment

AI has become prevalent in the field of pain assessment. AI has the potential to help clinicians in pain assessment through offering enhanced diagnostic capabilities and ultimately get better outcomes.²⁷ By integrating data from various sources, such as patient monitor sensors, electronic health records, and facial expressions, AI can accurately assess pain and its intensities.^29,30 The gold standard of pain assessment, self-reports, is not possible in neonates and adult patients unable to communicate due to various reasons, including unconsciousness, installing medical devices, medications, cognitive disabilities, and dementia.³² Therefore, automated pain assessment has been receiving much attention in the last few years.

Several behaviors or tools, including, but not limited to, facial expressions, body and head movements, language, electrodermal activity, and EEG, have been powered by AI to enhance pain assessment.^31,33,34 Some of these tools are appropriate for pain assessment in adults, while others are appropriate for pain assessment in infants. These tools vary in terms of accuracy, sensitivity, specificity, and applications under research or clinical conditions.³⁴ The following sections investigate five common pain assessment tools empowered with AI algorithms, which are: analysis of facial expressions, analysis of body and head movements, analysis of language, electrodermal activity, and EEG.

AI-Powered Analysis of Facial Expressions

Facial expressions refer to the changes in the muscles of the face, known as action units, to pain stimulation such as brow lowering, eye closure, orbital tightening, and levator muscle contraction.^35,36 The facial action coding system (FACS) is a manual method for describing and analyzing observable changes in facial muscles,^14,33 which has been used to study the facial expressions of pain in a variety of populations, including healthy individuals, individuals with psychiatric or neurological disorders, and individuals with chronic pain conditions.³⁷ It is reported that facial expressions of pain are consistent across ages, genders, different types of pain, and mental states and correlate with self-report of pain.³⁸ However, facial expressions of pain have several limitations, such as the impact of observer bias, gender bias, the need for training, and population differences.^9,39

The Prkachin and Solomon Pain Intensity scale is a validated facial expression-based pain scale,⁴⁰ which is commonly used in pain studies.^9,17,41 It has a significant correlation with self-reported pain and is considered the gold standard for measuring pain intensity.^32,42 It is characterized by being simple, has a total score for facial expressions, and is widely accepted as a pain assessment measure.⁴⁰ However, it has several limitations, such as pain underestimation on some occasions, it does not reflect pain intensity in all cases, and it is difficult to use when facial muscles are disabled, such as in the case of Parkinson’s patients.⁴³

AI can automatically identify the features in each video frame and changes over time through the training of a classifier to recognize the pain-related facial expressions.^44,45 Briefly, ML models are loaded with a huge dataset and then analyze and classify these data to identify pain-related patterns.³⁹ These models have the capability to identify pain and pain intensities.^9,46 AI avoids the risk of bias by human observers in pain assessment,^47–49 and gender bias, whereas females were reported to overscore pain due to their empathic nature.^50,51 Mobile applications were developed using AI to assess pain from a patient’s facial expression, such as the PainCheck app (Fig. 1), which is applied specifically in older nonverbal patients.⁵²

In adult patients, the accuracy of AI-based pain detection through facial expressions varied widely depending on the model; it ranged from 51.7% to 95.57%,^53,54 with varying levels of accuracy in between 53%, 83.1%, and 92.26%.^9,41,46 Also, AI was more accurate in pain identification than human observers,^55,56 but similar to the accuracy of nurses in another study.⁴⁹ Moreover, the sensitivity and specificity of these models varied. For example, the sensitivity was 77.5% and 89.7%, and the specificity was 45% and 61.5% for two AI models in two different studies.^9,46 These variations could be related to many factors, such as AI algorithms, feature extraction tools, or type of painful stimulation used (heat and electrical stimulation, arm movement, shoulder pain, postoperative pain), cross-validation techniques, and video or image quality.⁵⁷

In infants, manual pain assessment relies on using various scales such as the neonatal infant pain scale, the neonatal facial coding system, the neonatal pain, agitation, and sedation scale, as well as the Faces Pain Scale-Revised, which have proven to be reliable, valid, and accurate.^34,58 These scales have several limitations, including a lack of continuous pain assessment, observer bias, being time-consuming, and requiring trained personnel.^34,59,60 Several AI-based models were developed for pain assessment in infants. These models demonstrated varying levels of accuracy from 80% to 96% across several studies.^49,61–63 The model built by Sikka et al.⁴⁹ demonstrated good-to-excellent accuracy (0.84–0.94) in both ongoing and transient pain conditions. The model was equivalent to nurses in pain detection and to parents in estimating pain severity. Heiderich et al.⁶⁴ reviewed 15 articles about AI-based pain assessment using facial expressions in neonates; the models varied in their accuracy, sensitivity, and specificity, and the author concluded that AI was not effective enough to replace the human eye for pain assessment in neonates. AI-based pain detection through facial expressions in infants is still a promising area and needs more advancements.

AI-Powered Analysis of Head and Body Movements

While body and head movements have been used to identify emotional states in humans,⁶⁵ they also have proven to be effective in pain assessment, albeit not receiving much attention compared to other indicators such as facial expressions.^66,67 Behaviors such as head aversion, downward gaze, and leaning the body forward have been identified as indicative of pain in adult patients.⁶⁸ Head orientation and posture leaning downward or toward the pain area are considered reliable signs of pain in both infants and adults.⁶⁹ Zamzmi et al.³⁴ have considered head shaking, arms and leg extension, and splaying fingers to be pain-related behaviors in infants, despite the fact that they were primarily used to diagnose diseases.^70–72

ML models based on body and head movements were developed to assess pain, achieving an accuracy of 87.5% in infants and 92% in adults.^73,74 While ML models of body and head movements showed promising results in pain assessment, their application could be limited to nonverbal population, such as infants or adults who cannot communicate verbally,⁶⁹ as self-reported pain remains the gold standard for verbal adults. However, in certain conditions where body movements are restricted, alternative pain assessment tools such as other manual pain scales or AI-based facial expression models may be prioritized. Werner et al.⁶⁹ used AI to assess pain in human adults, achieving good reliability and high accuracy, but the study findings were not fully applicable under clinical conditions due to several limitations, including confounding factors, the absence of a control group, and the use of an artificial rather than natural pain source.

AI-Powered Language Analysis

AI has been applied to analyze patients’ language as an indicator of pain, focusing on language feature extraction and classification.¹⁴ NLP, a subset of AI, represents an advanced step in automatic pain assessment through language analysis. NLP uses linguistics and computer science to extract, interpret, and retrieve data from unstructured spoken and written words.⁷⁵ The integration of AI, linguistics, and computer science represents the foundation for NLP.¹⁴ NLP is capable of performing tasks such as language translation, text summarization, and sentiment analysis with a wide range of applications, including chatbots, language-enabled applications, and virtual assistants.¹⁴ In the medical field, NLP has been applied to enhance computerized clinical decision support systems and improve healthcare management through analysis of patient feedback.^68,76

In pain research, NLP has been employed to extract and analyze key information from text data such as electronic medical records and patient-reported outcomes, identifying location, intensity, and duration of pain.⁷⁷ This is beneficial to understand the patient’s experience of pain and identify patterns in pain management. Chaturvedi et al.⁷⁸ validated a lexicon comprising 382 terms, which facilitates the extraction of pain-related information from electronic databases. Similarly, Naseri et al.⁷⁹ proposed an AI method to automatically identify and categorize pain reported by physicians in clinical notes, even when the pain is not documented through structured data entry.

Sentiment analysis is another significant application for NLP in pain research, which combines ML algorithms with NLP processes to classify text as positive, neutral, or negative.⁸⁰ This method has been used to analyze language in patient-reported outcomes, online patient forums, and patient surveys, providing insights regarding patients’ emotions and opinions about their pain and treatment.¹⁴ Additionally, facial expression analysis was integrated with language analysis for pain assessment, resulting in the development of software named “the ELAN tool” (Fig. 2).⁸¹

Interestingly, infants’ cries have been used to assess various emotions, including pain, hunger, and discomfort.³⁴ AI models have been developed to analyze infant cries and identify pain, achieving varying levels of accuracy. These models have demonstrated accuracies ranging from 30.56% and 83.33%⁸² to 92%⁸³ and as high as 97.83%.⁸⁴ While AI-based language analysis offers a valuable pain assessment tool under research settings; its application could be limited to analyzing big data on a large scale and providing general assessments and recommendations. Also, other common methods of pain assessment, such visual analog or numerical rating scales, are easier to use and not time-consuming under clinical settings compared to language analysis.⁸⁵

AI-Powered Analysis of Electrodermal Activity

Electrodermal activity (EDA) or galvanic skin response has been used to identify and quantify pain intensity, especially for poorly communicating individuals.³² EDA refers to the changes in skin conductivity or skin resistance due to moisture secretion. When humans are exposed to stimuli, sweat glands are induced to secrete moisture, termed emotional sweating, which changes the skin conductivity.⁸⁶ EDA was integrated into ML devices such as the BITalino® multichannel platform (Fig. 3). It is an open-source biosignal platform compatible with easy-to-use software such as OpenSignals that can be used for obtaining data from EDA, electrocardiography, electromyography, and EEG.¹⁴

ML models using EDA were built to predict pain intensity in postoperative adult patients,⁸⁷ with an accuracy of >80%, but the accuracy decreased to <60%, when the pain level increased. AI models based on EDA were built and validated for pain assessment in infants.^88,89 Moreover, the ML model was able to differentiate between nonpainful and moderate-to-severe painful states under clinical conditions in infants.⁹⁰ Employing AI-empowered EDA has proven applicable for pain assessment in both infants and adults unable to communicate.⁸⁷ The use of EDA for pain assessment faces some challenges, such as that it requires specific equipment, such as a BITalino® device, needs a specialist to operate this device, and is time-consuming. These limitations could restrict the use of AI-empowered EDA for pain assessment.

AI-Powered Electroencephalography

Electroencephalography, a non-invasive neuroimaging method capable of measuring the electrical voltage changes on the patient’s scalp caused by the activity in the cortex, has the potential to monitor brain activities under different conditions.⁹¹ Pain causes changes in EEG patterns; therefore, EEG can be used as a useful tool for pain assessment.⁹¹ EEG can detect the functional and structural changes associated with chronic pain.⁹² In particular, the neuronal activities in the sensorimotor cortex, including increased gamma and theta oscillations, have been linked to painful states.⁹³ In addition, gamma-band oscillations have been identified as a predictor of acute thermal pain.⁹⁴

AI has been applied for EEG-based pain detection by Chen et al.,⁹⁵ who validated an ML model capable of distinguishing between nonpainful and painful states, achieving an accuracy of 81%. Other ML models for EEG pain detection in adults achieved even higher accuracy, such as 97.07% and 96.89%.^96,97 However, these studies acknowledged that the application of these models under clinical conditions has not been investigated yet. In another study by Elsayed et al.,⁹⁸ ML models were used to analyze pain-related brain signals and classify them into four pain intensity levels (no pain, low pain, moderate pain, and high pain), achieving an accuracy of 94.83%. This analysis referred to a direct correlation between the pain intensity and the alpha frequency band power.

In addition, EEG can play a vital role in advancing the understanding of pain. In a study by Tayeb et al.,⁹⁹ EEG source localization was combined with ML techniques to decode pain perception for a real-time reflex system, demonstrated in a single-subject case study. Moreover, EEG has proven to be accurate, non-invasive, and effective for pain assessment in newborn infants.¹⁰⁰ However, its application for pain assessment under clinical settings could be limited due to the need for specialized equipment, trained personnel, and the inconsistencies in cortical activation patterns.^101–103 As a result, EEG may be most useful for objective pain assessment in nonverbal patients who are unable to self-report or within a research setting.¹⁰⁴

We would like to note that heart rate variability, despite its common use in pain assessment, has not been discussed in this paper due to the presence of conflicting evidence about its capability for pain assessment. Bandeira et al.¹⁰⁵ screened 2,873 papers about the use of heart rate variability for assessing pain in low back pain patients and revealed limited evidence about the association of heart rate variability with chronic pain. Furthermore, Rampazo et al.¹⁰⁶ screened 4,893 papers about pain assessment using heart rate variability in musculoskeletal pain patients and reported heterogeneous and moderate quality evidence about this association. We acknowledge the limitations of this review. First, it does not provide a comprehensive overview of AI applications in pain assessment. Instead, it focuses only on commonly used tools enhanced by AI for pain assessment. Second, the performance of most AI models discussed here has been evaluated under research settings, with little evidence regarding their performance under clinical practice.

Conclusion

AI has a broad range of applications in the medical sector, particularly in the field of pain assessment. Recently, traditional tools for evaluating pain, such as analyzing facial expressions, body and head movements, language, electrodermal activity, and EEG, are powered with AI to offer more objective and accurate pain assessment. Numerous AI models have been developed based on these tools with varying levels of accuracy, specificity, and sensitivity, but their applications are often limited to specific populations, such as infants or people unable to self-report or under research settings. The implementation of AI-empowered pain assessment tools in clinical conditions remains a developing area with the potential for greater integration. References

References

1. ISAP. International Association for the Study of Pain (ISAP). 2021 [cited 2024 Sep 14]; Available from: http://www.isap-pain.org
 
2. Cheatle MD, Foster S, Pinkett A, Lesneski M, Qu D, Dhingra L. Assessing and managing sleep disturbance in patients with chronic pain. Anesthesiol Clin. 2016 Jun;34(2):379-93.
https://doi.org/10.1016/j.anclin.2016.01.007
 
3. Hooten WM. Chronic pain and mental health disorders: shared neural mechanisms, epidemiology, and treatment. Mayo Clin Proc. 2016 Jul;91(7):955-70.
https://doi.org/10.1016/j.mayocp.2016.04.029
 
4. Yong RJ, Mullins PM, Bhattacharyya N. Prevalence of chronic pain among adults in the United States. Pain. 2022 Feb 1;163(2):e328-32.
https://doi.org/10.1097/j.pain.0000000000002291
 
5. Clewley D, Rhon D, Flynn T, Koppenhaver S, Cook C. Health seeking behavior as a predictor of healthcare utilization in a population of patients with spinal pain. PLoS ONE. 2018;13(8):e0201348.
https://doi.org/10.1371/journal.pone.0201348
 
6. Romanelli RJ, Shah SN, Ikeda L, Lynch B, Craig TL, Cappelleri JC, et al. Patient characteristics and healthcare utilization of a chronic pain population within an integrated healthcare system. Am J Manag Care. 2017 Feb 1;23(2):e50-6.
 
7. Thong ISK, Jensen MP, Miró J, Tan G. The validity of pain intensity measures: what do the NRS, VAS, VRS, and FPS-R measure? Scand J Pain. 2018 Jan 26;18(1):99-107.
https://doi.org/10.1515/sjpain-2018-0012
 
8. McGreevy K, Bottros MM, Raja SN. Preventing chronic pain following acute pain: risk factors, preventive strategies, and their efficacy. Eur J Pain Suppl. 2011 Nov 11;5(2):365-72.
https://doi.org/10.1016/j.eujps.2011.08.013
 
9. Bargshady G, Zhou X, Deo RC, Soar J, Whittaker F, Wang H. Ensemble neural network approach detecting pain intensity from facial expressions. Artif Intell Med. 2020 Sep;109:101954.
https://doi.org/10.1016/j.artmed.2020.101954
 
10. Gregory J, McGowan L. An examination of the prevalence of acute pain for hospitalised adult patients: a systematic review. J Clin Nurs. 2016 Mar;25(5-6):583-98.
https://doi.org/10.1111/jocn.13094
 
11. Aristidou A, Jena R, Topol EJ. Bridging the chasm between AI and clinical implementation. Lancet Lond Engl. 2022 Feb 12;399(10325):620.
https://doi.org/10.1016/S0140-6736(22)00235-5
 
12. Hagedorn JM, George TK, Aiyer R, Schmidt K, Halamka J, D’Souza RS. Artificial intelligence and pain medicine: an introduction. J Pain Res. 2024;17:509-18.
https://doi.org/10.2147/JPR.S429594
 
13. Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism [Internet]. 2017 Apr 1 [cited 2024 Sep 10];69:S36-40. Available from: https://www.sciencedirect.com/science/article/pii/S002604951730015X
https://doi.org/10.1016/j.metabol.2017.01.011
 
14. Cascella M, Schiavo D, Cuomo A, Ottaiano A, Perri F, Patrone R, et al. Artificial intelligence for automatic pain assessment: research methods and perspectives. Pain Res Manag [Internet]. 2023 [cited 2024 Sep 10];2023(1):6018736. Available from: https://onlinelibrary.wiley.com/doi/abs/10.1155/2023/6018736
https://doi.org/10.1155/2023/6018736
 
15. Dutta P, Nachamai M. Facial pain expression recognition in real-time videos. J Healthc Eng. 2018;2018:7961427.
https://doi.org/10.1155/2018/7961427
 
16. Kharghanian R, Peiravi A, Moradi F. Pain detection from facial images using unsupervised feature learning approach. Annu Int Conf IEEE Eng Med Biol Soc IEEE Eng Med Biol Soc Annu Int Conf. 2016 Aug;2016:419-22.
https://doi.org/10.1109/EMBC.2016.7590729
 
17. Lucey P, Cohn JF, Matthews I, Lucey S, Sridharan S, Howlett J, et al. Automatically detecting pain in video through facial action units. IEEE Trans Syst Man Cybern Part B Cybern Publ IEEE Syst Man Cybern Soc. 2011 Jun;41(3):664-74.
https://doi.org/10.1109/TSMCB.2010.2082525
 
18. Honcu P, Zach P, Mrzilkova J, Jandova D, Musil V, Celko AM. Computer kinesiology: new diagnostic and therapeutic tool for lower back pain treatment (pilot study). BioMed Res Int. 2020;2020:2987696.
https://doi.org/10.1155/2020/2987696
 
19. Lötsch J, Sipilä R, Dimova V, Kalso E. Machine-learned selection of psychological questionnaire items relevant to the development of persistent pain after breast cancer surgery. Br J Anaesth. 2018 Nov;121(5):1123-32.
https://doi.org/10.1016/j.bja.2018.06.007
 
20. Nickerson P, Tighe P, Shickel B, Rashidi P. Deep neural network architectures for forecasting analgesic response. Annu Int Conf IEEE Eng Med Biol Soc IEEE Eng Med Biol Soc Annu Int Conf. 2016 Aug;2016:2966-9.
https://doi.org/10.1109/EMBC.2016.7591352
 
21. Lo WLA, Lei D, Li L, Huang DF, Tong KF. The perceived benefits of an artificial intelligence-embedded mobile app implementing evidence-based guidelines for the self-management of chronic neck and back pain: observational study. JMIR MHealth UHealth. 2018 Nov 26;6(11):e198.
https://doi.org/10.2196/mhealth.8127
 
22. Rabbi M, Aung MS, Gay G, Reid MC, Choudhury T. Feasibility and acceptability of mobile phone-based auto-personalized physical activity recommendations for chronic pain self-management: pilot study on adults. J Med Internet Res. 2018 Oct 26;20(10):e10147.
https://doi.org/10.2196/10147
 
23. Sandal LF, Øverås CK, Nordstoga AL, Wood K, Bach K, Hartvigsen J, et al. A digital decision support system (selfBACK) for improved self-management of low back pain: a pilot study with 6-week follow-up. Pilot Feasibility Stud. 2020;6:72.
https://doi.org/10.1186/s40814-020-00604-2
 
24. Zhang M, Zhu L, Lin SY, Herr K, Chi CL, Demir I, et al. Using artificial intelligence to improve pain assessment and pain management: a scoping review. J Am Med Inform Assoc. 2023 Feb 16;30(3):570-87.
https://doi.org/10.1093/jamia/ocac231
 
25. Deo RC. Machine learning in medicine. Circulation. 2015 Nov 17;132(20):1920-30.
https://doi.org/10.1161/CIRCULATIONAHA.115.001593
 
26. Witten IH, Frank E, Hall MA, editors. Front matter. In Data Mining: Practical Machine Learning Tools and Techniques. 3rd ed. [Internet]. Boston: Morgan Kaufmann; 2011 [cited 2024 Sep 16]. p. i-iii. (The Morgan Kaufmann Series in Data Management Systems). Available from: https://www.sciencedirect.com/science/article/pii/B9780123748560000183
 
27. Khalifa M, Albadawy M, Iqbal U. Advancing clinical decision support: the role of artificial intelligence across six domains. Comput Methods Programs Biomed Update [Internet]. 2024 Jan 1 [cited 2024 Sep 17];5:100142. Available from: https://www.sciencedirect.com/science/article/pii/S2666990024000090
https://doi.org/10.1016/j.cmpbup.2024.100142
 
28. Thieme A, Hanratty M, Lyons M, Palacios J, Marques RF, Morrison C, et al. Designing human-centered AI for mental health: developing clinically relevant applications for online CBT treatment. ACM Trans Comput Hum Interact [Internet]. 2023 Mar 17 [cited 2024 Sep 18];30(2):27:1-27:50. Available from: https://dl.acm.org/doi/10.1145/3564752
https://doi.org/10.1145/3564752
 
29. Wang J. The power of AI-assisted diagnosis. EAI Endorsed Trans E-Learn [Internet]. 2022 [cited 2024 Sep 17];8(4):e3-e3. Available from: https://publications.eai.eu/index.php/el/article/view/3772
https://doi.org/10.4108/eetel.3772
 
30. De Sario GD, Haider CR, Maita KC, Torres-Guzman RA, Emam OS, Avila FR, et al. Using AI to detect pain through facial expressions: a review. Bioengineering [Internet]. 2023 May [cited 2024 Sep 17];10(5):548. Available from: https://www.mdpi.com/2306-5354/10/5/548
https://doi.org/10.3390/bioengineering10050548
 
31. Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol [Internet]. 2017 Dec 1 [cited 2024 Sep 18];2(4):230. Available from: https://svn.bmj.com/content/2/4/230
https://doi.org/10.1136/svn-2017-000101
 
32. Herr K, Coyne PJ, McCaffery M, Manworren R, Merkel S. Pain assessment in the patient unable to self-report: position statement with clinical practice recommendations. Pain Manag Nurs [Internet]. 2011 Dec 1 [cited 2024 Sep 12];12(4):230-50. Available from: https://www.painmanagementnursing.org/article/S1524-9042(11)00188-3/abstract
https://doi.org/10.1016/j.pmn.2011.10.002
 
33. Waller BM, Julle-Daniere E, Micheletta J. Measuring the evolution of facial ‘expression’ using multi-species FACS. Neurosci Biobehav Rev [Internet]. 2020 Jun [cited 2022 Feb 9];113:1-11. Available from: https://linkinghub.elsevier.com/retrieve/pii/S0149763419302404
https://doi.org/10.1016/j.neubiorev.2020.02.031
 
34. Zamzmi G, Kasturi R, Goldgof D, Zhi R, Ashmeade T, Sun Y. A review of automated pain assessment in infants: features, classification tasks, and databases. IEEE Rev Biomed Eng. 2018;11:77-96.
https://doi.org/10.1109/RBME.2017.2777907
 
35. Prkachin KM. The consistency of facial expressions of pain: a comparison across modalities. Pain [Internet]. 1992 Dec 1 [cited 2023 Sep 18];51(3):297-306. Available from: https://www.sciencedirect.com/science/article/pii/030439599290213U
https://doi.org/10.1016/0304-3959(92)90213-U
 
36. Prkachin KM. Assessing pain by facial expression: facial expression as nexus. Pain Res Manag J Can Pain Soc [Internet]. 2009 [cited 2023 Jan 12];14(1):53-8. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2706565/
https://doi.org/10.1155/2009/542964
 
37. Priebe JA, Kunz M, Morcinek C, Rieckmann P, Lautenbacher S. Does Parkinson’s disease lead to alterations in the facial expression of pain? J Neurol Sci. 2015 Dec 15;359(1-2):226-35.
https://doi.org/10.1016/j.jns.2015.10.056
 
38. Chambers CT, Mogil JS. Ontogeny and phylogeny of facial expression of pain. Pain. 2015 May;156(5):798-9.
https://doi.org/10.1097/j.pain.0000000000000133
 
39. Craig KD, Prkachin KM, Grunau RE. The facial expression of pain. In Handbook of Pain Assessment. 3rd ed. New York, NY: The Guilford Press; 2011. p. 117-33.
 
40. Prkachin KM, Solomon PE. The structure, reliability and validity of pain expression: evidence from patients with shoulder pain. Pain [Internet]. 2008 Oct 15 [cited 2024 Sep 12];139(2):267. Available from:
https://doi.org/10.1016/j.pain.2008.04.010
 https://journals.lww.com/pain/abstract/2008/10150/the_structure,_reliability_and_validity
_of_pain.6.aspx
 
41. Rodriguez P, Cucurull G, Gonzalez J, Gonfaus JM, Nasrollahi K, Moeslund TB, et al. Deep pain: exploiting long short-term memory networks for facial expression classification. IEEE Trans Cybern. 2022 May;52(5):3314-24.
https://doi.org/10.1109/TCYB.2017.2662199
 
42. Craig KD. The social communication model of pain. Can Psychol Psychol Can. 2009;50(1):22-32.
https://doi.org/10.1037/a0014772
 
43. Prkachin KM, Craig KD. Expressing pain: the communication and interpretation of facial pain signals. J Nonverbal Behav [Internet]. 1995 Dec 1 [cited 2024 Sep 12];19(4):191-205. Available from:
https://doi.org/10.1007/BF02173080
 
44. Lucey P, Cohn J, Lucey S, Matthews I, Sridharan S, Prkachin KM. Automatically detecting pain using facial actions. Int Conf Affect Comput Intell Interact Workshop Proc ACII Conf. 2009 Dec 8;2009:1-8.
https://doi.org/10.1109/ACII.2009.5349321
 
45. Prkachin KM, Hammal Z. Computer mediated automatic detection of pain-related behavior: prospect, progress, perils. Front Pain Res Lausanne Switz. 2021;2:788606.
https://doi.org/10.3389/fpain.2021.788606
 
46. Fontaine D, Vielzeuf V, Genestier P, Limeux P, Santucci-Sivilotto S, Mory E, et al. Artificial intelligence to evaluate postoperative pain based on facial expression recognition. Eur J Pain [Internet]. 2022 [cited 2024 Sep 12];26(6):1282-91. Available from: https://onlinelibrary.wiley.com/doi/abs/10.1002/ejp.1948
https://doi.org/10.1002/ejp.1948
 
47. Craig KD. Social communication model of pain. Pain [Internet]. 2015 Jul [cited 2024 Sep 12];156(7):1198. Available from: https://journals.lww.com/pain/fulltext/2015/07000/social_communication_model_of_pain.7.aspx
https://doi.org/10.1097/j.pain.0000000000000185
 
48. Kaseweter KA, Drwecki BB, Prkachin KM. Racial differences in pain treatment and empathy in a Canadian sample. Pain Res Manag [Internet]. 2012 [cited 2024 Sep 12];17(6):803474. Available from: https://onlinelibrary.wiley.com/doi/abs/10.1155/2012/803474
https://doi.org/10.1155/2012/803474
 
49. Sikka K, Ahmed AA, Diaz D, Goodwin MS, Craig KD, Bartlett MS, et al. Automated assessment of children’s postoperative pain using computer vision. Pediatrics. 2015 Jul;136(1):e124-131.
https://doi.org/10.1542/peds.2015-0029
 
50. Keogh E. Sex and gender differences in pain: past, present, and future. Pain. 2022 Nov 1;163(Suppl 1):S108-16.
https://doi.org/10.1097/j.pain.0000000000002738
 
51. Zhang L, Losin EAR, Ashar YK, Koban L, Wager TD. Gender biases in estimation of others’ p ain. J Pain. 2021 Sep;22(9):1048-59.
https://doi.org/10.1016/j.jpain.2021.03.001
 
52. PainCheck [Internet]. 2024 [cited 2024 Sep 20]. Available from: https://www.painchek.com/product/.
 
53. Othman E, Werner P, Saxen F, Al-Hamadi A, Gruss S, Walter S. Automatic vs. human recognition of pain intensity from facial expression on the X-ITE pain database. Sensors [Internet]. 2021 Jan [cited 2024 Sep 12];21(9):3273. Available from: https://www.mdpi.com/1424-8220/21/9/3273
https://doi.org/10.3390/s21093273
 
54. Barua PD, Baygin N, Dogan S, Baygin M, Arunkumar N, Fujita H, et al. Automated detection of pain levels using deep feature extraction from shutter blinds-based dynamic-sized horizontal patches with facial images. Sci Rep [Internet]. 2022 Oct 14 [cited 2024 Sep 12];12(1):17297. Available from: https://www.nature.com/articles/s41598-022-21380-4
https://doi.org/10.1038/s41598-022-21380-4
 
55. Bartlett MS, Littlewort GC, Frank MG, Lee K. Automatic decoding of facial movements reveals deceptive pain expressions. Curr Biol [Internet]. 2014 Mar 31 [cited 2024 Sep 12];24(7):738-43. Available from: https://www.cell.com/current-biology/abstract/S0960-9822(14)00147-X
https://doi.org/10.1016/j.cub.2014.02.009
 
56. Littlewort GC, Bartlett MS, Lee K. Automatic coding of facial expressions displayed during posed and genuine pain. Image Vis Comput [Internet]. 2009 Nov 1 [cited 2024 Sep 12];27(12):1797-803. Available from: https://www.sciencedirect.com/science/article/pii/S0262885609000055
https://doi.org/10.1016/j.imavis.2008.12.010
 
57. Badi Mame A, Tapamo JR. A Comparative study of local descriptors and classifiers for facial expression recognition. Appl Sci [Internet]. 2022 Jan [cited 2024 Sep 12];12(23):12156. Available from: https://www.mdpi.com/2076-3417/12/23/12156
https://doi.org/10.3390/app122312156
 
58. Hicks CL, von Baeyer CL, Spafford PA, van Korlaar I, Goodenough B. The Faces Pain Scale-revised: toward a common metric in pediatric pain measurement. Pain [Internet]. 2001 Aug [cited 2024 Sep 18];93(2):173. Available from: https://journals.lww.com/pain/abstract/2001/08000/the_faces_pain_scale revised tow ard_a_common.11.aspx
https://doi.org/10.1016/S0304-3959(01)00314-1
 
59. Miller C, Newton SE. Pain perception and expression: the influence of gender, personal self-efficacy, and lifespan socialization. Pain Manag Nurs [Internet]. 2006 Dec 1 [cited 2024 Sep 21];7(4):148-52. Available from: https://www.sciencedirect.com/science/article/pii/S1524904206001482
https://doi.org/10.1016/j.pmn.2006.09.004
 
60. Samolsky Dekel BG, Gori A, Vasarri A, Sorella C, Di Nino G, Melotti RM. The influence of medical evidence moderators on pain rating agreement between inpatients and nurses. Pain Res Manag. 2015 Sep;10:17103.
 
61. Brahnam S, Chuang CF, Shih FY, Slack MR. Machine recognition and representation of neonatal facial displays of acute pain. Artif Intell Med. 2006 Mar;36(3):211-22.
https://doi.org/10.1016/j.artmed.2004.12.003
 
62. Brahnam S, Chuang CF, Sexton RS, Shih FY. Machine assessment of neonatal facial expressions of acute pain. Decis Support Syst [Internet]. 2007 Aug [cited 2024 Sep 13];43(4):1242-54. Available from: https://linkinghub.elsevier.com/retrieve/pii/S0167923606000261
https://doi.org/10.1016/j.dss.2006.02.004
 
63. Zamzami G, Ruiz G, Goldgof D, Kasturi R, Yu Sun, Ashmeade T. Pain assessment in infants: towards spotting pain expression based on infants’ facial strain. 2015 11th IEEE Int Conf Workshop Autom Face Gesture Recognit FG [Internet]. 2015 May [cited 2024 Sep 13];1-5. Available from: http://ieeexplore.ieee.org/document/7284857/
https://doi.org/10.1109/FG.2015.7284857
 
64. Heiderich TM, Carlini LP, Buzuti LF, Balda R de CX, Barros MCM, Guinsburg R, et al. Face-based automatic pain assessment: challenges and perspectives in neonatal intensive care units. J Pediatr (Rio J) [Internet]. 2023 Jun 15 [cited 2024 Sep 21];99(6):546-60. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10594024/
https://doi.org/10.1016/j.jped.2023.05.005
 
65. Castellano G, Villalba SD, Camurri A. Recognising human emotions from body movement and gesture dynamics. Lect Notes Comput Sci Subser Lect Notes Artif Intell Lect Notes Bioinforma. 2007;4738 LNCS:71-82.
https://doi.org/10.1007/978-3-540-74889-2_7
 
66. Castellano G, Kessous L, Caridakis G. Emotion recognition through multiple modalities: face, body gesture, speech. In Peter C, Beale R, editors. Affect and Emotion in Human-Computer Interaction: From Theory to Applications [Internet]. Berlin, Heidelberg: Springer; 2008 [cited 2024 Sep 16]. p. 92-103. Available from: https://doi.org/10.1007/978-3-540-85099-1_8
https://doi.org/10.1007/978-3-540-85099-1_8
 
67. Semwal A, Londhe ND. Head Movement Dynamics Based Pain Detection using Spatio-Temporal Network. 2021. p. 204-9.
https://doi.org/10.1109/SPIN52536.2021.9566047
 
68. Cascella M, Montomoli J, Bellini V, Bignami E. Evaluating the feasibility of ChatGPT in healthcare: An analysis of multiple clinical and research scenarios. J Med Syst [Internet]. 2023 Mar 4 [cited 2024 Sep 10];47(1):33. Available from: https://link.springer.com/10.1007/s10916-023-01925-4
https://doi.org/10.1007/s10916-023-01925-4
 
69. Werner P, Al-Hamadi A, Limbrecht-Ecklundt K, Walter S, Traue HC. Head movements and postures as pain behavior. PLoS ONE. 2018;13(2):e0192767.
https://doi.org/10.1371/journal.pone.0192767
 
70. Conover M. Using accelerometers to quantify infant general movements as a tool for assessing motility to assist in making a diagnosis of cerebral palsy. 2003 [cited 2024 Sep 13]. Available from: https://www.semanticscholar.org/paper/Using-Accelerometers-to-Quantify-Infant-General-as-Conover/eecc8830519c387a028b8c2015876bcdf5268c5a
 
71. Marcroft C, Khan A, Embleton ND, Trenell M, Plötz T. Movement recognition technology as a method of assessing spontaneous general movements in high-risk infants. Front Neurol. 2014;5:284.
https://doi.org/10.3389/fneur.2014.00284
 
72. Meinecke L, Breitbach-Faller N, Bartz C, Damen R, Rau G, Disselhorst-Klug C. Movement analysis in the early detection of newborns at risk for developing spasticity due to infantile cerebral palsy. Hum Mov Sci. 2006 Apr;25(2):125-44.
https://doi.org/10.1016/j.humov.2005.09.012
 
73. Zamzmi G, Pai CY, Goldgof D, Kasturi R, Sun Y, Ashmeade T. Automated pain assessment in neonates. In Sharma P, Bianchi FM, editors. Image Analysis. Cham: Springer International Publishing; 2017. p. 350-61.
https://doi.org/10.1007/978-3-319-59129-2_30
 
74. Semwal A, Londhe ND. Head movement dynamics based pain detection using spatio-temporal network. In 2021 8th International Conference on Signal Processing and Integrated Networks (SPIN) [Internet]. 2021 [cited 2024 Sep 16]. p. 204-9. Available from: https://ieeexplore.ieee.org/document/9566047/?arnumber=9566047
https://doi.org/10.1109/SPIN52536.2021.9566047
 
75. Liu K, Hogan WR, Crowley RS. Natural language processing methods and systems for biomedical ontology learning. J Biomed Inform [Internet]. 2011 Feb 1 [cited 2024 Sep 10];44(1):163-79. Available from: https://www.sciencedirect.com/science/article/pii/S153204641000105X
https://doi.org/10.1016/j.jbi.2010.07.006
 
76. Voytovich L, Greenberg C. Natural language processing: practical applications in medicine and investigation of contextual autocomplete. In Staartjes VE, Regli L, Serra C, editors. Machine Learning in Clinical Neuroscience. Cham: Springer International Publishing; 2022. p. 207-14.
https://doi.org/10.1007/978-3-030-85292-4_24
 
77. Carlson LA, Hooten WM. Pain-linguistics and natural language processing. Mayo Clin Proc Innov Qual Outcomes. 2020 Jun;4(3):346-7.
https://doi.org/10.1016/j.mayocpiqo.2020.01.005
 
78. Chaturvedi J, Mascio A, Velupillai SU, Roberts A. Development of a lexicon for pain. Front Digit Health. 2021;3:778305.
https://doi.org/10.3389/fdgth.2021.778305
 
79. Naseri H, Kafi K, Skamene S, Tolba M, Faye MD, Ramia P, et al. Development of a generalizable natural language processing pipeline to extract physician-reported pain from clinical reports: generated using publicly-available datasets and tested on institutional clinical reports for cancer patients with bone metastases. J Biomed Inform [Internet]. 2021 Aug [cited 2024 Sep 10];120:103864. Available from: https://linkinghub.elsevier.com/retrieve/pii/S1532046421001933
https://doi.org/10.1016/j.jbi.2021.103864
 
80. Nguyen TB, Nguyen DDK, Le Nguyen BN, Le T. A machine learning-based anomaly packets detection for smart home. In Proceedings of the 12th International Symposium on Information and Communication Technology [Internet]. New York, NY, USA: Association for Computing Machinery; 2023 [cited 2024 Sep 10]. p. 816-23. (SOICT ’23). Available from: https://doi.org/10.1145/3628797.3628930
https://doi.org/10.1145/3628797.3628930
 
81. ELAN. ELAN (Version 6.8) [Computer software]. Nijmegen: Max Planck Institute for Psycholinguistics; 2024 [cited 2024 Sep 13]. Available from https://archive.mpi.nl/tla/elan
 
82. Vempada RR, Siva Ayyappa Kumar B, Rao KS. Characterization of infant cries using spectral and prosodic features. 2012 Natl Conf Commun NCC [Internet]. 2012 Feb [cited 2024 Sep 13];1-5. Available from: http://ieeexplore.ieee.org/document/6176851/
https://doi.org/10.1109/NCC.2012.6176851
 
83. Petroni M, Malowany AS, Johnston CC, Stevens BJ. Identification of pain from infant cry vocalizations using artificial neural networks (ANNs). In Rogers SK, Ruck DW, editors. Orlando, FL; 1995 [cited 2024 Sep 13]. p. 729-38. Available from: http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1001007
https://doi.org/10.1117/12.205186
 
84. Barajas-Montiel SE, Reyes-García CA. Fuzzy support vector machines for automatic infant cry recognition. In Huang DS, Li K, Irwin GW, editors. Intelligent Computing in Signal Processing and Pattern Recognition: International Conference on Intelligent Computing, ICIC 2006 Kunming, China, August 16-19, 2006 [Internet]. Berlin, Heidelberg: Springer 2006 [cited 2024 Sep 13]. p. 876-81. Available from: https://doi.org/10.1007/978-3-540-37258-5_107
https://doi.org/10.1007/978-3-540-37258-5_107
 
85. Heller GZ, Manuguerra M, Chow R. How to analyze the Visual Analogue Scale: myths, truths and clinical relevance. Scand J Pain [Internet]. 2016 Oct 1 [cited 2024 Sep 13];13(1):67-75. Available from: https://www.degruyter.com/document/doi/10.1016/j.sjpain.2016.06.012/html
https://doi.org/10.1016/j.sjpain.2016.06.012
 
86. Galvanic Skin Response (GSR): The Complete Pocket Guide-iMotions [Internet]. 2020 [cited 2024 Sep 16]. Available from: https://imotions.com/blog/learning/research- fundamentals/galvanic-skin-response/
 
87. Aqajari SAH, Cao R, Kasaeyan Naeini E, Calderon MD, Zheng K, Dutt N, et al. Pain assessment tool with electrodermal activity for postoperative patients: method validation study. JMIR MHealth UHealth [Internet]. 2021 May 5 [cited 2024 Sep 16];9(5):e25258. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8135033/
https://doi.org/10.2196/25258
 
88. Eriksson M, Storm H, Fremming A, Schollin J. Skin conductance compared to a combined behavioural and physiological pain measure in newborn infants. Acta Paediatr Oslo Nor 1992. 2008 Jan;97(1):27-30.
https://doi.org/10.1111/j.1651-2227.2007.00586.x
 
89. Munsters J, Wallström L, Agren J, Norsted T, Sindelar R. Skin conductance measurements as pain assessment in newborn infants born at 22-27 weeks gestational age at different postnatal age. Early Hum Dev. 2012 Jan;88(1):21-6.
https://doi.org/10.1016/j.earlhumdev.2011.06.010
 
90. Susam BT, Akcakaya M, Nezamfar H, Diaz D, Xu X, de Sa VR, et al. Automated pain assessment using electrodermal activity data and machine learning. Annu Int Conf IEEE Eng Med Biol Soc IEEE Eng Med Biol Soc Annu Int Conf. 2018 Jul;2018:372-5.
https://doi.org/10.1109/EMBC.2018.8512389
 
91. Madeo D, Castellani E, Mocenni C, Santarcangelo EL. Pain perception and EEG dynamics: does hypnotizability account for the efficacy of the suggestions of analgesia? Physiol Behav. 2015 Jun 1;145:57-63.
https://doi.org/10.1016/j.physbeh.2015.03.040
 
92. Levitt J, Saab CY. What does a pain ‘biomarker’ mean and can a machine be taught to measure pain? Neurosci Lett [Internet]. 2019 May 29 [cited 2024 Sep 11];702:40-3. Available from: https://www.sciencedirect.com/science/article/pii/S0304394018308243
https://doi.org/10.1016/j.neulet.2018.11.038
 
93. Misra G, Wang WE, Archer DB, Roy A, Coombes SA. Automated classification of pain perception using high-density electroencephalography data. J Neurophysiol. 2017 Feb 1;117(2):786-95.
https://doi.org/10.1152/jn.00650.2016
 
94. Savignac C, Ocay DD, Mahdid Y, Blain-Moraes S, Ferland CE. Clinical use of electroencephalography in the assessment of acute thermal pain: a narrative review based on articles from 2009 to 2019. Clin EEG Neurosci [Internet]. 2022 Mar 1 [cited 2024 Sep 11];53(2):124-32. Available from: https://doi.org/10.1177/15500594211026280
https://doi.org/10.1177/15500594211026280
 
95. Chen D, Zhang H, Kavitha PT, Loy FL, Ng SH, Wang C, et al. Scalp EEG-based pain detection using convolutional neural network. IEEE Trans Neural Syst Rehabil Eng [Internet]. 2022 [cited 2024 Sep 11];30:274-85. Available from: https://ieeexplore.ieee.org/document/9696316
https://doi.org/10.1109/TNSRE.2022.3147673
 
96. Vijayakumar V, Case M, Shirinpour S, He B. Quantifying and characterizing tonic thermal pain across subjects from EEG data using random forest models. IEEE Trans Biomed Eng [Internet]. 2017 Dec [cited 2024 Sep 16];64(12):2988-96. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5718188/
https://doi.org/10.1109/TBME.2017.2756870
 
97. Alazrai R, Momani M, Khudair HA, Daoud MI. EEG-based tonic cold pain recognition system using wavelet transform. Neural Comput Appl [Internet]. 2019 Jul 1 [cited 2024 Sep 16];31(7):3187-200. Available from: https://doi.org/10.1007/s00521-017-3263-6
https://doi.org/10.1007/s00521-017-3263-6
 
98. Elsayed M, Sim KS, Tan SC. A novel approach to objectively quantify the subjective perception of pain through electroencephalogram signal analysis. IEEE Access [Internet]. 2020 [cited 2024 Sep 11];8:199920-30. Available from: https://ieeexplore.ieee.org/document/9229386/
https://doi.org/10.1109/ACCESS.2020.3032153
 
99. Tayeb Z, Bose R, Dragomir A, Osborn LE, Thakor NV, Cheng G. Decoding of pain perception using EEG signals for a real-time reflex system in prostheses: a case study. Sci Rep. 2020 Mar 27;10(1):5606.
https://doi.org/10.1038/s41598-020-62525-7
 
100. Olsson E, Ahl H, Bengtsson K, Vejayaram DN, Norman E, Bruschettini M, et al. The use and reporting of neonatal pain scales: a systematic review of randomized trials. Pain [Internet]. 2021 Feb [cited 2024 Sep 19];162(2):353. Available from: https://journals.lww.com/pain/Fulltext/2021/02000/The_use_and_reporting_of_neonatal_p ain_scales a.4.aspx
https://doi.org/10.1097/j.pain.0000000000002046
 
101. Cao S, Fu D, Yang X, Wermter S, Liu X, Wu H. Pain recognition and pain empathy from a human-centered AI perspective. iScience [Internet]. 2024 Aug 16 [cited 2024 Sep 16];27(8):110570. Available from: https://www.sciencedirect.com/science/article/pii/S2589004224017954
https://doi.org/10.1016/j.isci.2024.110570
 
102. Lopes da Silva F. EEG and MEG: relevance to neuroscience. Neuron. 2013 Dec 4;80(5):1112-28.
https://doi.org/10.1016/j.neuron.2013.10.017
 
103. Zis P, Liampas A, Artemiadis A, Tsalamandris G, Neophytou P, Unwin Z, et al. EEG recordings as biomarkers of pain perception: where do we stand and where to go? Pain Ther [Internet]. 2022 Jun 1 [cited 2024 Sep 19];11(2):369-80. Available from: https://doi.org/10.1007/s40122-022-00372-2
https://doi.org/10.1007/s40122-022-00372-2
 
104. Wu F, Mai W, Tang Y, Liu Q, Chen J, Guo Z. Learning spatial-spectral-temporal EEG representations with deep attentive-recurrent-convolutional neural networks for pain intensity assessment. Neuroscience [Internet]. 2022 Jan 15 [cited 2024 Sep 19];481:144-55. Available from: https://www.sciencedirect.com/science/article/pii/S0306452221006011
https://doi.org/10.1016/j.neuroscience.2021.11.034
 
105. Bandeira PM, Reis FJJ, Sequeira VCC, Chaves ACS, Fernandes O, Arruda-Sanchez T. Heart rate variability in patients with low back pain: a systematic review. Scand J Pain. 2021 Jul 27;21(3):426-33.
https://doi.org/10.1515/sjpain-2021-0006
 
106. Rampazo ÉP, Rehder-Santos P, Catai AM, Liebano RE. Heart rate variability in adults with chronic musculoskeletal pain: a systematic review. Pain Pract Off J World Inst Pain. 2024 Jan;24(1):211-30.
https://doi.org/10.1111/papr.13294

Cite this article as:
Farghal M. A Critical Review About the Application of Artificial Intelligence in Pain Assessment. Premier Journal of Artificial Intelligence 2024:1;100002

Export to Endnote Export to Mendeley