Advantage of Vital Sign Monitoring Using a Wireless Wearable Device for Predicting Septic Shock in Febrile Patients in the Emergency Department: A Machine Learning-Based Analysis

User Acceptance of a Home Robotic Assistant for Individuals With Physical Disabilities: Explorative Qualitative Study

BACKGROUND

Health care is shifting toward 5 proactive approaches: personalized, participatory, preventive, predictive, and precision-focused services (P5 medicine). This patient-centered care leverages technologies such as artificial intelligence (AI)-powered robots, which can personalize and enhance services for users with disabilities. These advancements are crucial given the World Health Organization's projection of a global shortage of up to 10 million health care workers by 2030.

OBJECTIVE

This study aimed to investigate the acceptance of a humanoid assistive robot among users with physical disabilities during (1) AI-powered (using a Wizard of Oz methodology) robotic performance of predefined personalized assistance tasks and (2) operator-controlled robotic performance (simulated distant service).

METHODS

An explorative qualitative design was used, involving user testing in a simulated home environment and individual interviews. Directed content analysis was based on the Almere model and the model of domestic social robot acceptance.

RESULTS

Nine participants with physical disabilities aged 27 to 78 years engaged in robot interactions. They shared their perceptions across 7 acceptance concepts: hedonic attitudes, utilitarian attitudes, personal norms, social norms, control beliefs, facilitating conditions, and intention to use. Participants valued the robot's usefulness for practical services but not for personal care. They preferred automation but accepted remote control of the robot for some tasks. Privacy concerns were mixed.

CONCLUSIONS

This study highlights the complex interplay of functional expectations, technological readiness, and personal and societal norms affecting the acceptance of physically assistive robots. Participants were generally positive about robotic assistance as it increases independence and lessens the need for human caregivers, although they acknowledged some current shortcomings. They were open to trying more home testing if future robots could perform most tasks autonomously. AI-powered robots offer new possibilities for creating more adaptable and personalized assistive technologies, potentially enhancing their effectiveness and viability for individuals with disabilities.

A novel deep learning algorithm for real-time prediction of clinical deterioration in the emergency department for a multimodal clinical decision support system

The array of complex and evolving patient data has limited clinical decision making in the emergency department (ED). This study introduces an advanced deep learning algorithm designed to enhance real-time prediction accuracy for integration into a novel Clinical Decision Support System (CDSS). A retrospective study was conducted using data from a level 1 tertiary hospital. The algorithm's predictive performance was evaluated based on in-hospital cardiac arrest, inotropic circulatory support, advanced airway, and intensive care unit admission. We developed an artificial intelligence (AI) algorithm for CDSS that integrates multiple data modalities, including vitals, laboratory, and imaging results from electronic health records. The AI model was trained and tested on a dataset of 237,059 ED visits. The algorithm's predictions, based solely on triage information, significantly outperformed traditional logistic regression models, with notable improvements in the area under the precision-recall curve (AUPRC). Additionally, predictive accuracy improved with the inclusion of continuous data input at shorter intervals. This study suggests the feasibility of using AI algorithms in diverse clinical scenarios, particularly for earlier detection of clinical deterioration. Future work should focus on expanding the dataset and enhancing real-time data integration across multiple centers to further optimize its application within the novel CDSS.

MiVitals- xed Reality Interface for Monitoring: A HoloLens based prototype for healthcare practices

In this paper, we introduce MiVitals-a Mixed Reality (MR) system designed for healthcare professionals to monitor patients in wards or clinics. We detail the design, development, and evaluation of MiVitals, which integrates real-time vital signs from a biosensor-equipped wearable, Vitaliti TM. The system generates holographic visualizations, allowing healthcare professionals to interact with medical charts and information panels holographically. These visualizations display vital signs, trends, other significant physiological signals, and medical early warning scores in a comprehensive manner. We conducted a User Interface/User Experience (UI/UX) study focusing on novel holographic visualizations and interfaces that intuitively present medical information. This approach brings traditional bedside medical information to life in the real environment through non-contact 3D images, supporting rapid decision-making, vital pattern and anomaly detection, and enhancing clinicians' performance in wards. Additionally, we present findings from a usability study involving medical doctors and healthcare practitioners to assess MiVitals' efficacy. The System Usability Scale study yielded a score of 84, indicating that the MiVitals system has high usability.

Designing Chinese hospital emergency departments to leverage artificial intelligence-a systematic literature review on the challenges and opportunities

Artificial intelligence (AI) has witnessed rapid advances in the healthcare domain in recent years, especially in the emergency field, where AI is likely to radically reshape medical service delivery. Although AI has substantial potential to enhance diagnostic accuracy and operational efficiency in hospitals, research on its applications in Emergency Department building design remains relatively scarce. Therefore, this study aims to investigate Emergency Department facility design by identifying the challenges and opportunities of using AI. Two systematic literature reviews are combined, one in AI and the other in sensors, to explore their potential application to support decision-making, resource optimisation and patient monitoring. These reviews have then informed a discussion on integrating AI sensors in contemporary Emergency Department designs for use in China to support the evidence base on resuscitation units, emergency operating rooms and Emergency Department Intensive Care Unit (ED-ICU) design. We hope to inform the strategic implementation of AI sensors and how they might transform Emergency Department design to support medical staff and enhance the patient experience.

Wearable Devices: Implications for Precision Medicine and the Future of Health Care

Wearable devices are integrated analytical units equipped with sensitive physical, chemical, and biological sensors capable of noninvasive and continuous monitoring of vital physiological parameters. Recent advances in disciplines including electronics, computation, and material science have resulted in affordable and highly sensitive wearable devices that are routinely used for tracking and managing health and well-being. Combined with longitudinal monitoring of physiological parameters, wearables are poised to transform the early detection, diagnosis, and treatment/management of a range of clinical conditions. Smartwatches are the most commonly used wearable devices and have already demonstrated valuable biomedical potential in detecting clinical conditions such as arrhythmias, Lyme disease, inflammation, and, more recently, COVID-19 infection. Despite significant clinical promise shown in research settings, there remain major hurdles in translating the medical uses of wearables to the clinic. There is a clear need for more effective collaboration among stakeholders, including users, data scientists, clinicians, payers, and governments, to improve device security, user privacy, data standardization, regulatory approval, and clinical validity. This review examines the potential of wearables to offer affordable and reliable measures of physiological status that are on par with FDA-approved specialized medical devices. We briefly examine studies where wearables proved critical for the early detection of acute and chronic clinical conditions with a particular focus on cardiovascular disease, viral infections, and mental health. Finally, we discuss current obstacles to the clinical implementation of wearables and provide perspectives on their potential to deliver increasingly personalized proactive health care across a wide variety of conditions.

Prediction of intrapartum fever using continuously monitored vital signs and heart rate variability

Objectives

Neonatal early onset sepsis (EOS), bacterial infection during the first seven days of life, is difficult to diagnose because presenting signs are non-specific, but early diagnosis before birth can direct life-saving treatment for mother and baby. Specifically, maternal fever during labor from placental infection is the strongest predictor of EOS. Alterations in maternal heart rate variability (HRV) may precede development of intrapartum fever, enabling incipient EOS detection. The objective of this work was to build a predictive model for intrapartum fever.

Methods

Continuously measured temperature, heart rate, and beat-to-beat RR intervals were obtained from wireless sensors on women (n = 141) in labor; traditional manual vital signs were taken every 3-6 hours. Validated measures of HRV were calculated in moving 5-minute windows of RR intervals: standard deviation of normal-to-normal intervals (SDNN) and root mean square of successive differences (RMSSD) between normal heartbeats.

Results

Fever (>38.0 °C) was detected by manual or continuous measurements in 48 women. Compared to afebrile mothers, average SDNN and RMSSD in febrile mothers decreased significantly (p < 0.001) at 2 and 3 hours before fever onset, respectively. This observed HRV divergence and raw recorded vitals were applied to a logistic regression model at various time horizons, up to 4-5 hours before fever onset. Model performance increased with decreasing time horizons, and a model built using continuous vital signs as input variables consistently outperformed a model built from episodic vital signs.

Conclusions

HRV-based predictive models could identify mothers at risk for fever and infants at risk for EOS, guiding maternal antibiotic prophylaxis and neonatal monitoring.