Search AMIA.org

Although supervised machine learning is popular for information extraction from clinical notes, creating large annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have demonstrated promising transfer learning capability. In this study, we explored whether recent LLMs could reduce the need for large-scale data annotations.

Delirium is a syndrome that leads to severe complications in hospitalized patients, but is considered preventable in many cases. One of the biggest challenges is to identify patients at risk in a hectic clinical routine, as most screening tools cause additional workload. The aim of this study was to validate a machine learning (ML)-based delirium prediction tool on surgical in-patients undergoing a systematic assessment of delirium.

This study uses electronic health record (EHR) data to predict 12 common cancer symptoms, assessing the efficacy of machine learning (ML) models in identifying symptom influencers.

 The use of artificial intelligence-driven code completion tools, particularly the integration of GitHub Copilot with Visual Studio, has potential implications for Health Informatics education, particularly for students learning SQL and Python.

 In this case report, we describe the development of an innovative workshop to bridge the gap in data science education for practicing clinicians (and particularly nurses). In the workshop, we emphasize the core concepts of machine learning and predictive modeling to increase understanding among clinicians.

 Choice architecture refers to the design of decision environments, which can influence decision-making in health care. Nudges are subtle adjustments in these environments that guide decisions toward desired outcomes. For example, computerized provider order entry within electronic health records (EHRs) recommends frequencies for interventions such as nursing assessments and medication administrations, but these can link to around-the-clock schedules without clinical necessity.

 High-value care aims to enhance meaningful patient outcomes while reducing costs and is accelerated by curating data across health care systems through common data models (CDMs), such as Observational Medical Outcomes Partnership (OMOP). Meaningful patient outcomes, such as physical function, must be included in these CDMs. However, the extent to which physical therapy assessments are covered in the OMOP CDM is unclear.

 Interruptive alerts are known to be associated with clinician alert fatigue, and poorly performing alerts should be evaluated for alternative solutions. An interruptive alert to remind clinicians about a required peripherally inserted central catheter (PICC) dressing change within the first 48 hours after placement resulted in 617 firings in a 6-month period with only 11 (1.7%) actions taken from the alert.

Hospital at Home (HaH) programs currently lack decision support tools to help efficiently navigate the complex decision-making process surrounding HaH as a care option. We assessed user needs and perspectives to guide early prototyping and co-creation of 4PACS (Partnering Patients and Providers for Personalized Acute Care Selection), a decision support app to help patients make an informed decision when presented with discrete hospitalization options.

The aims of this systematic review were to (1) synthesize the available qualitative evidence on the barriers and facilitators influencing implementation of the electronic collection and use of patient-reported measures (PRMs) in older adults' care from various stakeholder perspectives and (2) map these factors to the digital technology implementation framework Non-adoption, Abandonment, challenges to the Scale-up, Spread, Sustainability (NASSS) and behavior change framework Capability, Opportunity, Motivation, Behaviour (COM-B).