Guest editorialClinical decision support systems: Need for evidence, need for evaluation
Introduction
Modern health care is unthinkable without the progress in theory and practice of health information systems [1]. Health informatics (alias Health IT, or HIT) in general has been shown to have the potential for positive impact on quality and efficiency of patient care [2], [3], [4]. On the other side, experience shows that these benefits are not self-evident; they can only be reached when Health IT is carefully designed, implemented, and managed [5]. Failures in this respect can lead to ill-functioning or user-unfriendly technology that does not understand and is not well integrated into the clinical workflow and is therefore not accepted by the users [6], [7]. This, in turn, can negatively affect clinical processes and may even lead to patient harm [8], [9], [10].
In any aspect of healthcare, policies and practice should be firmly based on evidence, and informatics should be no exception [11]. Consequently, any decision regarding design, implementation, and management of Health IT needs to consider carefully all opportunities and risks for quality and efficiency of patient care, based on the available scientific evidence. Evaluation is a robust source of such evidence, provided the evaluation is scientific. Thus, evidence should come from well-designed qualitative and quantitative evaluation studies [12].
Section snippets
CDSS in health care
Clinical decision support systems (CDSSs) in Health Care have a long history going back to the 1970s [13], with recent reviews showing that their number and uptake is increasing [14], [15]. CDSSs can support many different activities such as diagnosis, therapy, monitoring, or prevention and are used in all kinds of medical domains such as chronic illness, acute care, primary care, and patient advice lines. CDSSs may provide many different services such as access to knowledge, statistical
Aim of this special issue
The aim of this special issue is to collect original research papers presenting progress in the methodology or practice of CDSS evaluation. Overall, we received 29 submissions. After international peer-review, six of them were selected for this special issue. Each of the six selected papers presents learning opportunities and evidence for decision-makers regarding design, implementation, and management of CDSSs.
Advances in CDSS evaluation and evidence for decision-makers
The paper by Kilsdonk et al. [23] shows how user-centred design of a CDSS can help to improve usability. Their CDSS was designed to improve retrieval of childhood cancer survivors’ follow-up screening procedures. To develop the CDSS prototype, the authors applied a user-centred design process that was informed by a detailed analysis of usability problems with the earlier paper-based system. When the prototype was available, the authors systematically compared it to the old system. They found
Conclusion
Summarizing, the six included studies present broad evidence on CDSS design and implementation. They show how various study designs (from retrospective data analysis to prospective randomized controlled trials) and various methods (from qualitative to quantitative) can be carefully applied to answer specific study questions. The studies also show that issues such as validity of the knowledge base, management of knowledge, training of users, alert design and usability and safety issues need to
Acknowledgement
We thank all reviewers that contributed to the selection of the papers for this special issue.
References (28)
Health information systems – past, present, future
International Journal of Medical Informatics
(2006)Patient care information systems and healthcare work: a sociotechnical approach
International Journal of Medical Informatics
(1999)- et al.
The unintended consequences of computerized provider order entry: findings from a mixed methods exploration
International Journal of Medical Informatics
(2009) - et al.
The role of standardized data and terminological systems in computerized clinical decision support systems: literature review and survey
International Journal of Medical Informatics
(2011) - et al.
Guideline for good evaluation practice in health informatics (GEP-HI)
International Journal of Medical Informatics
(2011) - et al.
STARE-HI – statement on reporting of evaluation studies in health informatics
International Journal of Medical Informatics
(2009) - et al.
From an expert-driven paper guideline to a user-centered decision support system; a usability comparison study
Artificial Intelligence in Medicine
(2013) - et al.
Evaluation of rule effectiveness and positive predictive value of clinical rules in a Dutch clinical decision support system in daily hospital pharmacy practice
Artificial Intelligence in Medicine
(2013) - et al.
Safety and usability evaluation of a web-based insulin self-titration system for patients with type 2 diabetes mellitus
Artificial Intelligence in Medicine
(2013) - et al.
Physicians’ responses to clinical decision support on an intensive care unit – comparison of four different alerting methods
Artificial Intelligence in Medicine
(2013)
Impact of four training conditions on physician use of a web-based clinical decision support system
Artificial Intelligence in Medicine
A pilot study of distributed knowledge management and clinical decision support in the cloud
Artificial Intelligence in Medicine
Systematic review: impact of health information technology on quality, efficiency, and costs of medical care
Annals of Internal Medicine
The impact of computerized physician order entry on medication error prevention
Journal of the American Medical Informatics Association
Cited by (15)
Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson's disease
2016, Artificial Intelligence in MedicineCitation Excerpt :Therefore in our future work we plan to perform deeper spiral analysis and evaluate spiral specific features. Decision support tools are gaining significant research interest due to their potential to improve health-care provision [5,6]. Among many possible approaches, those that provide noninvasive monitoring and diagnosis of diseases are of increased interest to clinicians and biomedical engineers.
Transfer Learning and Pressure Effect for Handwriting to Early Detection of Parkinson’s Disease
2022, Lecture Notes in Networks and SystemsA systematic review of the applications of Expert Systems (ES) and machine learning (ML) in clinical urology
2021, BMC Medical Informatics and Decision MakingA framework for disease identification from unstructured data using text classification and disease knowledge base
2019, 2019 5th International Conference on Advances in Electrical Engineering, ICAEE 2019