International journal of medical informatics
-
With the recent advances in computational science, machine-learning methods have been increasingly used in medical research. Because such projects usually require both a clinician and a computational data scientist, there is a need for interdisciplinary research collaboration. However, there has been no published analysis of research collaboration networks in cardiovascular medicine using machine intelligence. ⋯ A co-authorship network analysis revealed a structure of collaboration networks in the application of machine learning in the field of cardiovascular disease, which can be useful for planning future scientific collaboration.
-
Usability associates with patient safety and quality of care. This article reports results from nation-wide usability-focused survey studies for physicians and nurses in Finland. Earlier research has shown dissatisfaction and serious deficiencies, which hamper the efficient use of health information systems (HIS); however, evaluation studies covering the viewpoints of both user groups are practically lacking. Our study aimed at comparing end-users' experiences on the usability of electronic health record (EHR) systems by employment sector and EHR brand. ⋯ Nurses' and physicians' experiences on EHR usability appear to vary more by EHR brand and employment sector rather than either professional group being generally more satisfied. Development of EHR systems should consider the perspectives of these two main user groups and their working contexts.
-
Emergency departments (ED) are a portal of entry into the hospital and are uniquely positioned to influence the health care trajectories of older adults seeking medical attention. Older adults present to the ED with distinct needs and complex medical histories, which can make disposition planning more challenging. Machine learning (ML) approaches have been previously used to inform decision-making surrounding ED disposition in the general population. However, little is known about the performance and utility of ML methods in predicting hospital admission among older ED patients. We applied a series of ML algorithms to predict ED admission in older adults and discuss their clinical and policy implications. ⋯ To the best of our knowledge, this is the first study to predict hospital admission in older ED patients using a series of geriatric syndromes and functional assessments. We were able to predict hospital admission in older ED patients with good accuracy using the items available in the interRAI ED Contact Assessment. This information can be used to inform decision-making about ED disposition and may expedite admission processes and proactive discharge planning.
-
Vital signs monitoring is used to identify deteriorating patients in hospital. The most common tool for vital signs monitoring is an early warning score, although emerging technologies allow for remote, continuous patient monitoring. A number of reviews have examined the impact of continuous monitoring on patient outcomes, but little is known about the patient experience. This study aims to discover what patients think of monitoring in hospital, with a particular emphasis on intermittent early warning scores versus remote continuous monitoring, in order to inform future implementations of continuous monitoring technology. ⋯ Early warning score systems are widely used to facilitate detection of the deteriorating patient. Continuous monitoring technologies may provide added reassurance. However, patients value personal contact with their healthcare professionals and remote monitoring should not replace this. We suggest that remote monitoring is best introduced in a phased manner, and initially as an adjunct to usual care, with careful consideration of the patient experience throughout.
-
To explore attitudes about artificial intelligence (AI) among staff who utilized AI-based clinical decision support (CDS). ⋯ AI-based CDS tools that are perceived negatively by staff may reduce staff excitement about AI technology, and hands-on experience with AI may lead to more realistic expectations about the technology's capabilities. In our setting, although AI-based CDS prompted an interdisciplinary discussion about the needs of patients at high risk for poor glycemic control, the interventions recommended by the CDS were often perceived to be poorly tailored, inappropriate, or not useful. Developers should carefully consider tasks that are best performed by AI and those best performed by the patient's care team.