ENURSING LLC — Department of Health and Human Services SBIR Phase I: NIDA

Description

Abstract Our goal is to develop a product that will objectively measure pain using computer vision and machine learning technologies together with tablet based self reported pain data from patients for research or clinical purposesOur device will be low cost because it will consist of one or two cameras to record the video and a computer to analyze the video in almost real timeThe software of the device will be portable to ordinary personal computers and tabletsand it will be able to simultaneously control multiple cameras that capture facial pain expressionwhich is an important modality for detecting painespecially when the patientandapos s verbal ability to communicate is impairedNon verbal facial pain behaviors provide important cues to estimate the level of pain and self reported tablet based pain data discriminate the type of painnociceptiveneuropathicUsed togetherthese two data sources could contribute to appropriate use of opioidsFacial muscle based action unitsAUswhich are defined by the Facial Action Coding SystemFACShave been widely studied and are highly reliable as a method for detecting facial expressions including valid detection of painUnfortunatelyuse of FACS is time consuming making its clinical use prohibitiveAn automated system for capturing facial images and detecting pain related AUsas proposed herewould be highly beneficial for efficient and practical pain monitoringPreliminary work based on a unique video dataset captured by MPI Wilkie led to a highly promising method to detect AUs related to facial pain expressionBuilding on our existing researchwe will enhance the performance of the automated method to detect pain related AUs and then integrate this information with patientsandaposself reported pain data to objectively measure pain intensityWe will develop an almost realtime AU detection system under clinical settings using a deep learning based facial video analysis softwareThe likelihood scores for the presence of different AUs in the video together with the patient reported data will be fed to a second machine learning modulewhich will then estimate the existence and the intensity of pain in an automated mannerThe software will have the option of human verificationWe will estimate the accuracy of the proposed system by extensive tests on two existing facial pain image datasets in the Phase I of this SBIR projectOne of these datasets is the Wilkie video datasetwhich has patient reported data together with the ground truth scores from certified human FACS codersWe envision that when we move on to Phase II activitieseNursing llc will create a device that will be ready for testing in a suitable population to show data suitable for FDA approval Narrative Automated detection of pain from facial expressions and patient reported data can greatly benefit patient care efficiency and provide practical pain monitoring in a variety of clinical settingsWe will develop and test an advanced video analysis and machine learning based system to objectively measure pain for research and clinical purposesThis new tool has the potential to help rectify the poor pain outcomes that still plague Americans with opioid addictioncancer and other health conditions in many health care settings