Intelligent ICU for Autonomous Patient Monitoring Using Pervasive Sensing and Deep Learning

Abstract

Currently, many critical care indices are not captured automatically at a granular level, rather are repetitively assessed by overburdened nurses. In this pilot study, we examined the feasibility of using pervasive sensing technology and artificial intelligence for autonomous and granular monitoring in the Intensive Care Unit (ICU). As an exemplary prevalent condition, we characterized delirious patients and their environment. We used wearable sensors, light and sound sensors, and a camera to collect data on patients and their environment. We analyzed collected data to detect and recognize patient’s face, their postures, facial action units and expressions, head pose variation, extremity movements, sound pressure levels, light intensity level, and visitation frequency. We found that facial expressions, functional status entailing extremity movement and postures, and environmental factors including the visitation frequency, light and sound pressure levels at night were significantly different between the delirious and non-delirious patients. Our results showed that granular and autonomous monitoring of critically ill patients and their environment is feasible using a noninvasive system, and we demonstrated its potential for characterizing critical care patients and environmental factors.

The impact of environmental risk factors on delirium and benefits of noise and light modifications: a scoping review

“…During the full-text review of these 194 articles, 157 were excluded. In total 37 studies were included: 21 assessed association between environmental risk factors and delirium 13,19,20,[30][31][32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47] , and 16 reported on delirium after an environmental intervention 7,14,15,18,[48][49][50][51][52][53][54][55][56][57][58][59] ( Figure 1).…”

“…Included studies were conducted between 1997 to 2019, in the USA 19,31,37,39,43,46,58,59 , the Netherlands 14, 32,48,50,51 , Japan 38,41,52,53 , France 33,36,57 , Belgium 13,49 , Denmark 15,34 , Italy 42,47 , Sweden 18,20 , Canada 35 , China 45 , India 40 , Israel 30 , Singapore 55 , South Korea 54 , Thailand 56 , Turkey 44 , and the UK 7 . Of these, 31 studies were conducted among critically ill patients while five reviewed general hospital populations 30,35,41,44,54 , and one a geriatric monitoring unit for acute delirium care 55 .…”

“…Most studies assessed delirium using the Confusion Assessment Method for the ICU (CAM-ICU) 7,15,18,19,34,36,37,39,40,42,[45][46][47][48]51,[56][57][58][59] ; other identification methods included the validated Dutch CAM-ICU 32 , Confusion Assessment Method (CAM) 41,50,55 , Intensive Care Delirium Screening Checklist (ICDSC) 14, 33,43 , Neelon and Champagne Confusion Scale (NEECHAM) 13,49 , non-validated 52 and validated 53 Japanese NEECHAM, Delirium Observation Screening Scale (DOSS) 50 , behavioral observations based on the Diagnostic and Statistical Manual of Mental Disorders, 3 rd edition (DSM-III) 35 , 3 rd edition-revised (DSM-III-R) 38 , and 4 th Edition (DSM-IV) 20,41,44 , and behavioral observations based on International Classification of Diseases, 9 th Revision, Clinical Modification (ICD-9-CM) criteria 30 . One study used both retrospective chart review and site-specific pre-specified criteria based on new and rapid onset of disturbed consciousness and/or perceptual disturbances 31 .…”

“…Of the observational studies, two analyzed for an association between delirium and noise 19,20 , five for light 13,[30][31][32][33] , 12 for sleep [34][35][36][37][38][39][40][41][42][43][44][45] , and two evaluated multiple factors 46,47 . Study populations ranged from 7 to 6660 participants, and the majority were done in an ICU (17 of 21) 13,19,[31][32][33][34][36][37][38][39][40]42,43,[45][46][47] . The remaining studies did not specify a ward 30,35,41,44 .…”

Artificial Intelligence in Neurointensive Care Unit: A Cautious Leap into Future

“…AI-enabled data analysis could improve detection of delirium and enable real-time intervention to improve sleep hygiene. 16…”