Studies in health technology and informatics
-
Much has been written on the benefits of big data for healthcare such as improving patient outcomes, public health surveillance, and healthcare policy decisions. Over the past five years, Big Data, and the data sciences field in general, has been hyped as the "Holy Grail" for the healthcare industry promising a more efficient healthcare system with the promise of improved healthcare outcomes. ⋯ Our study results show that although Big Data is built up to be as a the "Holy Grail" for healthcare, small data techniques using traditional statistical methods are, in many cases, more accurate and can lead to more improved healthcare outcomes than Big Data methods. In sum, Big Data for healthcare may cause more problems for the healthcare industry than solutions, and in short, when it comes to the use of data in healthcare, "size isn't everything."
-
Stud Health Technol Inform · Jan 2017
Mapping Equivalence of German Emergency Department Medical Record Concepts with SNOMED CT After Implementation with HL7 CDA.
The German Emergency Department Medical Record (GEDMR) was created by medical domain experts and healthcare providers providing a dataset as well as a form. The trauma module of GEDMR was syntactically standardized using HL7 CDA and semantically standardized using different terminologies including SNOMED CT, LOINC and proprietary coding systems. This study depicts the mapping accuracy with aforementioned syntactical and semantical standards in general and especially the content coverage of SNOMED CT. ⋯ The terminology binding problem is relevant when combining different standards for syntactic and semantic interoperability with best practice documents and reference specifications providing guidance. A national license and extension for SNOMED CT in Germany as well as an ongoing effort in contributing to the International Version of SNOMED CT would be necessary to gain full coverage for concepts in German Emergency Medicine and to leverage the associated standardization process.
-
Stud Health Technol Inform · Jan 2017
Machine Learning Models of Post-Intubation Hypoxia During General Anesthesia.
Fine-meshed perioperative measurements are offering enormous potential for automatically investigating clinical complications during general anesthesia. In this study, we employed multiple machine learning methods to model perioperative hypoxia and compare their respective capabilities. After exporting and visualizing 620 series of perioperative vital signs, we had ten anesthesiologists annotate the subjective presence and severity of temporary post-intubation oxygen desaturation. ⋯ Furthermore, we deployed our classification methods for processing unlabeled inputs to estimate the incidence of hypoxic episodes in another sizeable patient cohort, which attests to the feasibility of using the approach on a larger scale. We interpret that our machine learning models could be instrumental for computerized observational studies of the clinical determinants of post-intubation oxygen deficiency. Future research might also investigate potential benefits of more advanced preprocessing approaches such as automated feature learning.
-
Stud Health Technol Inform · Jan 2017
Disseminating a Standard for Medical Records in Emergency Departments Among Different Software Vendors Using HL7 CDA.
A standardized medical record for the emergency department (GEDMR) was released in Germany, but only sparsely and randomly implemented by emergency department (ED) electronic health record (EHR) vendors. A reason for this may be a lacking common language between the medical and the Health Information Technology (HIT) domain. HL7 clinical document architecture (CDA) may leverage this communication gap. ⋯ Five additional vendors are adapting or developing an ED-EHR. The GEDMR-CDA implementation guide with funding for implementation in project hospitals had a significant impact on the German ED-EHR market. Within two years after release, a broadening and increasingly self-enforcing support by German ED-EHR vendors is notable.
-
Current efforts to improve nursing handover frequently use prescriptive approaches based on research evidence of handover issues within a single nursing ward or nursing specialty. Despite reported handover improvement, few studies adequately consider the transferability of results to other nursing handover environments or acknowledge the unique attributes that supported sustained improvement. ⋯ This paper describes a qualitative research project that examined nursing handover in three different wards - General Medicine, General Surgery and Department of Emergency Medicine in a tertiary teaching hospital. Through conduct of a detailed analysis of nursing handover processes, this paper highlights the similarities and differences in the handover among the three different wards and presents five key socio-technical insights to support safe nursing handover.