Development of a binary classifier model from extended facial codes toward video-based pain recognition in cancer patients.

OBJECTIVES: The Automatic Pain Assessment (APA) relies on the exploitation of objective methods to evaluate the severity of pain and other pain-related characteristics. Facial expressions are the most investigated pain behavior features for APA. We constructed a binary classifier model for discriminating between the absence and presence of pain through video analysis. METHODS: A brief interview lasting approximately two-minute was conducted with cancer patients, and video recordings were taken during the session. The Delaware Pain Database and UNBC-McMaster Shoulder Pain dataset were used for training. A set of 17 Action Units (AUs) was adopted. For each image, the OpenFace toolkit was used to extract the considered AUs. The collected data were grouped and split into train and test sets: 80 % of the data was used as a training set and the remaining 20 % as the validation set. For continuous estimation, the entire patient video with frame prediction values of 0 (no pain) or 1 (pain), was imported into an annotator (ELAN 6.4). The developed Neural Network classifier consists of two dense layers. The first layer contains 17 nodes associated with the facial AUs extracted by OpenFace for each image. The output layer is a classification label of "pain" (1) or "no pain" (0). RESULTS: The classifier obtained an accuracy of ∼94 % after about 400 training epochs. The Area Under the ROC curve (AUROC) value was approximately 0.98. CONCLUSIONS: This study demonstrated that the use of a binary classifier model developed from selected AUs can be an effective tool for evaluating cancer pain. The implementation of an APA classifier can be useful for detecting potential pain fluctuations. In the context of APA research, further investigations are necessary to refine the process and particularly to combine this data with multi-parameter analyses such as speech analysis, text analysis, and data obtained from physiological parameters.

Artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives.

Although proper pain evaluation is mandatory for establishing the appropriate therapy, self-reported pain level assessment has several limitations. Data-driven artificial intelligence (AI) methods can be employed for research on automatic pain assessment (APA). The goal is the development of objective, standardized, and generalizable instruments useful for pain assessment in different clinical contexts. The purpose of this article is to discuss the state of the art of research and perspectives on APA applications in both research and clinical scenarios. Principles of AI functioning will be addressed. For narrative purposes, AI-based methods are grouped into behavioral-based approaches and neurophysiology-based pain detection methods. Since pain is generally accompanied by spontaneous facial behaviors, several approaches for APA are based on image classification and feature extraction. Language features through natural language strategies, body postures, and respiratory-derived elements are other investigated behavioral-based approaches. Neurophysiology-based pain detection is obtained through electroencephalography, electromyography, electrodermal activity, and other biosignals. Recent approaches involve multimode strategies by combining behaviors with neurophysiological findings. Concerning methods, early studies were conducted by machine learning algorithms such as support vector machine, decision tree, and random forest classifiers. More recently, artificial neural networks such as convolutional and recurrent neural network algorithms are implemented, even in combination. Collaboration programs involving clinicians and computer scientists must be aimed at structuring and processing robust datasets that can be used in various settings, from acute to different chronic pain conditions. Finally, it is crucial to apply the concepts of explainability and ethics when examining AI applications for pain research and management.

Bibliometric Network Analysis on Rapid-Onset Opioids for Breakthrough Cancer Pain Treatment.

BACKGROUND AND OBJECTIVES: Proper breakthrough cancer pain (BTcP) management is of pivotal importance. Although rapid-acting, oral and nasal transmucosal, fentanyl formulations (rapid-onset opioids, ROOs) are licensed for BTcP treatment, not all guidelines recommend their use. Presumably, some research gaps need to be bridged to produce solid evidence. We present a bibliometric network analysis on ROOs for BTcP treatment. METHODS: Documents were retrieved from the Web of Science (WOS) online database. The string was "rapid onset opioids" or "transmucosal fentanyl" and "breakthrough cancer pain". Year of publication, journal metrics (impact factor and quartile), title, document type, topic, and clinical setting (in-patients, outpatients, and palliative care) were extracted. The software tool VOSviewer (version 1.6.17) was used to analyze the semantic network analyzes, bibliographic coupling, journals analysis, and research networks. RESULTS: 502 articles were found in WOS. A declining trend in published articles from 2014 to 2021 was observed. Approximately 50% of documents regard top quartile (Q1) journals. Most articles focused on ROOs efficacy, but abuse and misuse issues are poorly addressed. With respect to article type, we calculated 132 clinical investigations. The semantic network analysis found interconnections between the terms "breakthrough cancer pain," "opioids," and "cancers." The top co-cited article was published in 2000 and addressed pain assessment. The largest number of partnerships regarded the United States, Italy, and England. CONCLUSION: In this research area, most articles are published in top-ranked journals. Nevertheless, paramount topics should be better addressed, and the implementation of research networks is needed.

A Delphi Consensus Approach for the Management of Chronic Pain during and after the COVID-19 Era.

Due to a lack of published evidence on the topic, a modified Delphi approach was used to develop recommendations useful for chronic pain management during and after the COVID-19 pandemic. Focusing on the available literature and personal clinical expertise, an Italian board of nine professionals from different disciplines identified four main topics: prevention of chronic pain, treatment of chronic pain, consequences of inadequate treatment, and perspectives. They elaborated a semi-structured questionnaire. A multidisciplinary panel of experts in the field of pain management was requested to comment on the statements. Based on the answers provided, a structured questionnaire was prepared (Round 1). It included 21 statements divided into three categories (organizational issues; diagnosis and therapies; telemedicine and future perspectives). A five-point Likert scale was adopted. The threshold for consensus was set at a minimum of 70% of the number of respondents (level of agreement ≥ 4, Agree or Strongly Agree). A final questionnaire with rephrasing of the statements that did not reach the consensus threshold was elaborated (Round 2). A total of 29 clinicians were included in the panel. Twenty clinicians (69%) responded in both the first and second round. After two rounds, consensus (≥70%) was achieved in 20 out of 21 statements. The lack of consensus was recorded for the statement regarding the management of post-COVID pain (55%; Median 4; IQR 2.3). Another statement on telemedicine reached the threshold in the first round (70%), but the value was not confirmed in Round 2 (65%; Median 4; IQR 2). Most of the proposed items reached consensus, suggesting the need to make organizational changes, the structuring of careful diagnostic and therapeutic pathways, and the application of new technologies in pain medicine. Long-COVID-19 care is an issue that needs further research. Remote assistance for chronic pain must be regulated.