Search for: All records

Physicians are challenged in treating pain patients due to the lack of quantifiable, objective methods of measuring pain in the clinic; pain sensation is multifaceted and subjective to each individual. There is a critical need for point-of-care quantification of accessible biomarkers to provide objective analyses beyond the subjective pain scales currently employed in clinical care settings. In the present study, we employed an animal model to test the hypothesis that circulating regulators of the inflammatory response directly associate with an objective behavioral response to inflammatory pain. Upon induction of localized paw inflammation, we measured the systemic protein expression of cytokines, and activity levels of matrix metalloproteinases (MMPs) that are known to participate in the inflammatory response at the site of injury and investigated their relationship to the behavioral response across a 24 h period. Intraplantar injection with 1% λ-carrageenan induced a significant increase in paw thickness across this timespan with maximal effects observed at the 8 h timepoint when locomotor activity was also impaired. Expression of the chemokines C-X-C motif chemokine ligand 1 (CXCL1) and C-C motif chemokine ligand 2 (CCL2) positively correlated with paw inflammation and negatively correlated with locomotor activity at 8 h. The ratio of MMP9 to MMP2 activity negatively correlated with paw inflammation at the 8 h timepoint. We postulate that the CXCL1 and CCL2 as well as the ratio of MMP9 to MMP2 activity may serve as predictive biomarkers for the timecourse of inflammation-associated locomotor impairment. These data define opportunities for the future development of a point-of-care device to objectively quantify biomarkers for inflammatory pain states. 

Cyber-Physical-Human Systems (CPHS) interconnect humans, physical plants and cyber infrastructure across space and time. Industrial processes, electromechanical systems operations and medical diagnosis are some examples where one can see the intersection of humans, physical and cyber components. Emergence of Artificial Intelligence (AI) based computational models, controllers and decision support engines have improved the efficiency and cost effectiveness of such systems and processes. These CPHS typically involve a collaborative decision environment, comprising of AI-based models and human experts. Active Learning (AL) is a category of AI algorithms which aims to learn an efficient decision model by combining domain expertise of the human expert and computational capabilities of the AI model. Given the indispensable role of humans and lack of understanding about human behavior in collaborative decision environments, modeling and prediction of behavioral biases is a critical need. This paper, for the first time, introduces different behavioral biases within an AL context and investigates their impacts on the performance of AL strategies. The modelling of behavioral biases is demonstrated using experiments conducted on a real-world pancreatic cancer dataset. It is observed that classification accuracy of the decision model reduces by at least 20% in case of all the behavioral biases.