Transformers and Human-robot Interaction for Delirium Detection (original) (raw)
Related papers
ArXiv, 2018
Currently, many critical care indices are repetitively assessed and recorded by overburdened nurses, e.g. physical function or facial pain expressions of nonverbal patients. In addition, many essential information on patients and their environment are not captured at all, or are captured in a non-granular manner, e.g. sleep disturbance factors such as bright light, loud background noise, or excessive visitations. In this pilot study, we examined the feasibility of using pervasive sensing technology and artificial intelligence for autonomous and granular monitoring of critically ill patients and their environment in the Intensive Care Unit (ICU). As an exemplar prevalent condition, we also characterized delirious and non-delirious patients and their environment. We used wearable sensors, light and sound sensors, and a high-resolution camera to collected data on patients and their environment. We analyzed collected data using deep learning and statistical analysis. Our system performe...
Intelligent ICU for Autonomous Patient Monitoring Using Pervasive Sensing and Deep Learning
Scientific Reports, 2019
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. Every year, more than 5.7 million adults are admitted to intensive care units (ICU) in the United States, costing the health care system more than 67 billion dollars per year 1. A wealth of information is recorded on each patient in the ICU, including high-resolution physiological signals, various laboratory tests, and detailed medical history in electronic health records (EHR) 2. Nonetheless, important aspects of patient care are not yet captured in an autonomous manner. For example, environmental factors that contribute to sleep disruption and ICU delirium 3 , such as loud background noise, intense room light, and excessive rest-time visits, are not currently measured. Other aspects of patients' well-being, including patient's facial expressions of pain and various emotional states, mobility and functional status 4,5 are not captured in a continuous and granular manner and require self-reporting or repetitive observations by ICU nurses 6,7. It has been shown that self-report and manual observations can suffer from subjectivity, poor recall, limited number of administrations per day, and high staff workload. This lack of granular and continuous monitoring can prevent timely intervention strategies 8-13. With recent advancements in artificial intelligence (AI) and sensing, many researchers are exploring complex autonomous systems in real-world settings 14. In ICU settings, doctors are required to make life-saving decisions while dealing with high level of uncertainty under strict time constraints to synthesize high-volume of complex physiologic and clinical data. The assessment of patients' response to therapy and acute illness, on the other hand, is mainly based on repetitive nursing assessments, thus limited in frequency and granularity. AI technology could assist not only in administering repetitive patient assessments in real-time, but also in integrating and interpreting these data sources with EHR data, thus potentially enabling more timely and targeted interventions 15,16. AI in the critical care setting could reduce nurses' workload to allow them to spend time on more critical tasks, and could also augment human decision-making by offering low-cost and high capacity intelligent data processing. In this study, we examined how pervasive sensing technology and AI can be used for monitoring patients and their environment
SeVA: An AI Solution for Age Friendly Care of Hospitalized Older Adults
Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies
As a dangerous syndrome, delirium affects more than 50% of hospitalized older adults and has an economic burden of 164 billion US dollars per year. It is crucial to prevent, identify and treat this syndrome systematically on all hospitalized patients to prevent its short and long-term complications. Currently, there are no AI-based tools being utilized at a large scale focused on delirium management in hospital settings. The advancement of the Internet of Things in the medical arena can be leveraged to help clinical teams managing the care of patients in the hospital. The renaissance of Artificial Intelligence brings the chance to analyze a large amount of monitoring data. Deep neural networks like Convolutional Neural Network and Recurrent Neural Network revolutionize the fields of Computer Vision and Natural Language Processing. Deep learning tasks like action recognition and language understanding can be incorporated into the routine workflow of healthcare staff to improve care. By leveraging AI and deep learning techniques, we have developed a chatbot based monitoring system (that we refer to as SeVA) to improve the workload of the medical staff by using an Artificial Emotional Intelligence platform. The SeVA platform includes two mobile applications that provide timely patient monitoring, regular nursing checks, and health status recording features. We demonstrate the current progress of deploying the SeVA platform in a healthcare setting.
A machine learning approach to identifying delirium from electronic health records
JAMIA Open
The identification of delirium in electronic health records (EHRs) remains difficult due to inadequate assessment or under-documentation. The purpose of this research is to present a classification model that identifies delirium using retrospective EHR data. Delirium was confirmed with the Confusion Assessment Method for the Intensive Care Unit. Age, sex, Elixhauser comorbidity index, drug exposures, and diagnoses were used as features. The model was developed based on the Columbia University Irving Medical Center EHR data and further validated with the Medical Information Mart for Intensive Care III dataset. Seventy-six patients from Surgical/Cardiothoracic ICU were included in the model. The logistic regression model achieved the best performance in identifying delirium; mean AUC of 0.874 ± 0.033. The mean positive predictive value of the logistic regression model was 0.80. The model promises to identify delirium cases with EHR data, thereby enable a sustainable infrastructure to ...
BMC Health Services Research
Background Hospital cabins are a part and parcel of the healthcare system. Most patients admitted in hospital cabins reside in bedridden and immobile conditions. Though different kinds of systems exist to aid such patients, most of them focus on specific tasks like calling for emergencies, monitoring patient health, etc. while the patients’ limitations are ignored. Though some patient interaction systems have been developed, only singular options like touch, hand gesture or voice based interaction were provided which may not be usable for bedridden and immobile patients. Methods At first, we reviewed the existing literature to explore the prevailing healthcare and interaction systems developed for bedridden and immobile patients. Then, a requirements elicitation study was conducted through semi-structured interviews. Afterwards, design goals were established to address the requirements. Based on these goals and by using computer vision and deep learning technologies, a hospital cabi...
Journal of the American Medical Informatics Association, 2020
Objective: Machine learning models trained on electronic health records have achieved high prognostic accuracy in test datasets, but little is known about their embedding into clinical workflows. We implemented a random forest-based algorithm to identify hospitalized patients at high risk for delirium, and evaluated its performance in a clinical setting. Materials and Methods: Delirium was predicted at admission and recalculated on the evening of admission. The defined prediction outcome was a delirium coded for the recent hospital stay. During 7 months of prospective evaluation, 5530 predictions were analyzed. In addition, 119 predictions for internal medicine patients were compared with ratings of clinical experts in a blinded and nonblinded setting. Results: During clinical application, the algorithm achieved a sensitivity of 74.1% and a specificity of 82.2%. Discrimination on prospective data (area under the receiver-operating characteristic curve ¼ 0.86) was as good as in the test dataset, but calibration was poor. The predictions correlated strongly with delirium risk perceived by experts in the blinded (r ¼ 0.81) and nonblinded (r ¼ 0.62) settings. A major advantage of our setting was the timely prediction without additional data entry. Discussion: The implemented machine learning algorithm achieved a stable performance predicting delirium in high agreement with expert ratings, but improvement of calibration is needed. Future research should evaluate the acceptance of implemented machine learning algorithms by health professionals. Conclusions: Our study provides new insights into the implementation process of a machine learning algorithm into a clinical workflow and demonstrates its predictive power for delirium.
A research algorithm to improve detection of delirium in the intensive care unit
Critical care (London, England), 2006
Delirium is a serious and prevalent problem in intensive care units (ICU). The purpose of this study was to develop a research algorithm to enhance detection of delirium in critically ill ICU patients using chart review to complement a validated clinical delirium instrument. Prospective cohort study of 178 patients 60 years and older admitted to the Medical ICU. The Confusion Assessment Method for the Intensive Care Unit (CAM-ICU) and a validated chart review method for delirium were performed daily. We assessed the diagnostic accuracy of the chart-based delirium method using the CAM-ICU as the gold standard. We then used an algorithm to detect delirium first using the CAM-ICU ratings, then chart review when the CAM-ICU was unavailable. When using both the CAM-ICU and the chart-based review the prevalence of delirium was 143/178 (80%) patients or 929/1457 (64%) of patient-days. Of these, 292 patient-days were classified as delirium by the CAM-ICU, and the remainder (n=637 patient-da...
External Validation of a Machine Learning Based Delirium Prediction Software in Clinical Routine
Studies in health technology and informatics, 2022
Background: Various machine learning (ML) models have been developed for the prediction of clinical outcomes, but there is missing evidence on their performance in clinical routine and external validation. Objectives: Our aim was to deploy and prospectively evaluate an already developed delirium prediction software in clinical routine of an external hospital. Methods: We compared updated ML models of the software and models retrained with the external hospital's data. The best models were deployed in clinical routine for one month, and risk predictions for all admitted patients were compared to the risk ratings of a senior physician. After using the software, clinicians completed a questionnaire assessing technology acceptance. Results: Retrained models achieved a high discriminative performance (AUROC > 0.92). Compared to clinical risk ratings, the software achieved a sensitivity of 100.0% and a specificity of 90.6%. Usefulness, ease of use and output quality were rated positively by the users. Conclusion: A ML based delirium prediction software achieved a high discriminative performance and high technology acceptance at an external hospital using retrained ML models.
Patient Monitoring Using Emotion Recognition
International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022
Due to technology improvements, recognising the patient's emotions using deep learning algorithms has gotten a lot of interest recently. Automatically detecting emotions can aid in the development of smart healthcare centers that can detect pain and tiredness in patients so that medication can be started sooner. One of the most fascinating themes is the use of advanced technology to discern emotions, as it defines the human-machine interaction. Various strategies were used to teach machines how to predict emotions. Recent research in the field of employing neural networks to recognise emotions will be used in our system. Our system focuses on recognising emotions from facial expressions and demonstrating several approaches for implementing these algorithms in the real world. Techniques for recognising emotions can be utilized as a surveillance system in healthcare canters to monitor patients.
Australasian Journal on Ageing, 2018
ObjectivesDelirium is common in the intensive care unit (ICU), often affecting older patients. A bedside electronic tool has the potential to revolutionise delirium screening. Our group describe a novel approach to the design and development of delirium screening questions for the express purpose of use within an electronic device. Preliminary results are presented.MethodsOur group designed a series of tests which targeted the clinical criteria for delirium according to Diagnostic and Statistical Manual of Mental Disorders – Fifth Edition (DSM‐5) criteria against predefined requirements, including applicability to older patients.ResultsCandidate questions, including tests of attention and awareness, were devised and then refined by an expert multidisciplinary group, including geriatricians. A scoring scheme was constructed, with testing to failure an indicator of delirium. The device was tested in healthy controls, aged 20–80 years, who were recorded as being without delirium.Conclu...