Artikel
Prospective user-friendly design of clinical decision support systems – first results of the Junior Research Group CDS2USE
Suche in Medline nach
Autoren
-
Brita Sedlmayr
- Institut für Medizinische Informatik und Biometrie, Medizinische Fakultät Carl Gustav Carus der Technischen Universität Dresden, Dresden, Germany
-
Najia Ahmadi
- Institut für Medizinische Informatik und Biometrie, Medizinische Fakultät Carl Gustav Carus der Technischen Universität Dresden, Dresden, Germany
-
Ian-Christopher Jung
- Institut für Medizinische Informatik und Biometrie, Medizinische Fakultät Carl Gustav Carus der Technischen Universität Dresden, Dresden, Germany
-
Maria Zerlik
- Institut für Medizinische Informatik und Biometrie, Medizinische Fakultät Carl Gustav Carus der Technischen Universität Dresden, Dresden, Germany
-
Martin Sedlmayr
- Institut für Medizinische Informatik und Biometrie, Medizinische Fakultät Carl Gustav Carus der Technischen Universität Dresden, Dresden, Germany
| Veröffentlicht: | 24. September 2021 |
|---|
Gliederung
Text
Introduction: Clinical decision support systems (CDSS) have great potential for personalized medicine [1], [2], [3], [4], [5]. However, CDSS are often insufficiently accepted and used, mainly because no user-centered development process is followed [6], [7], [8]. The BMBF-junior research group CDS2USE of the Medical Informatics Initiative (MI-I) [9] aims at researching how CDSS can be enabled to be more context-sensitive, to develop visualization concepts for transparent, comprehensible decision support, and to advance existing user-centered evaluation methods. The article presents the group' s first results.
Methods: During the “set-up phase”, requirements for developing algorithms for context-sensitive CDSS will be specified; existing concepts for the transparent presentation of results will be identified and methods for a user-centered design will be compiled. In the “application phase”, the findings will be further developed for selected use cases. The "generalization phase" will transfer the methods and tools to as many types of CDSS as possible in the context of personalized medicine. CDS2USE follows a systems engineering approach, which takes equal account of the end user, the technology used, and the work processes (organization).
The results of CDS2USE currently cover the “set-up phase”: Several literature studies (scoping and narrative reviews) were conducted to identify existing concepts for context-sensitive algorithms, understandable user interfaces, design guidelines, models of human decision-making and potential user-centered design and evaluation methods for CDSS.
Results: Related to algorithmic concepts a search for articles (550 articles identified, 19 included in analysis) showed that the methods used are very diverse, for example, if-then-rules, artificial neuronal networks, ml-methods, ontology-based rule language, and fuzzy logic. Research gaps were found in precise and unambiguous language design, careful selection of modes for counseling, or organization of information by problem and clinical goal, among others.
Existing concepts for user interfaces show a high diversity and have been clustered according to the arrangement of elements, presentation of data and visualization of information resulting in a taxonomy of explanations for CDSS. Usability guidelines relevant to CDSS are very general in nature and do not offer specific guidance. Models and components of human decision-making are helpful to understand the processes in general but not specific to clinical staff.
For creating a method toolbox for CDSS, a model of specific acceptance factors was developed and suitable methods for measuring the factors were compiled. The toolbox contains 120 methods for user-centered development of interactive systems, 113 standardized evaluation questionnaires and 12 methods for measuring physiological parameters. Currently, the methods are being evaluated for their applicability and suitability for CDSS.
Discussion: The results of CDS2USE comprise both scientific methods and practical tools for developers of CDSS, which contribute to designing the technological innovations of the MI-I in a user-friendly and context-adaptive way. This is an elementary prerequisite for the developed innovations to be accepted and used in working practice in the future.
Conclusion: The focus of CDS2USE is on user-centered design of CDSS in the context of personalized medicine. Thereby, CDS2USE completes the developments of the MI-I and contributes to achieving improved patient care and medical research.
The authors declare that they have no competing interests.
The authors declare that an ethics committee vote is not required.
References
- 1.
- Muhiyaddin R, Abd-Alrazaq AA, Househ M, Alam T, Shah Z. The Impact of Clinical Decision Support Systems (CDSS) on Physicians: A Scoping Review. Stud Health Technol Inform. 2020;272:470-473. DOI: 10.3233/SHTI200597
- 2.
- Cha KH, Hadjiiski LM, Cohan RH, Chan HP, Caoili EM, Davenport M, Samala RK, Weizer AZ, Alva A, Kirova-Nedyalkova DG, et al. Diagnostic Accuracy of CT for Prediction of Bladder Cancer Treatment Response with and without Computerized Decision Support. Acad Radiol. 2019; 26(9):1137-1145. DOI: 10.1016/j.acra.2018.10.010
- 3.
- Bruun M, Frederiksen KS, Rhodius-Meester HFM, Baroni M, Gjerum L, Koikkalainen J, Urhemaa T, Tolonen A, van Gils M, Rueckert D, et al. Impact of a clinical decision support tool on prediction of pro-gression in early-stage dementia: a prospective validation study. Alzheimers Res Ther. 2019; 11(1):25. DOI: 10.1186/s13195-019-0482-3
- 4.
- Heard KL, Hughes S, Mughal N, Azadian BS, Moore LSP. Evaluating the impact of the ICNET(R) clini-cal decision support system for antimicrobial stewardship. Antimicrob Resist Infect Control. 2019; 8:51. DOI: 10.1186/s13756-019-0496-4
- 5.
- Shahmoradi L, Safdari R, Ahmadi H, Zahmatkeshan M. Clinical decision support systems-based inter-ventions to improve medication outcomes: A systematic literature review on features and effects. Med J Islam Repub Iran. 2021 Feb 22;35:27. DOI: 10.47176/mjiri.35.27
- 6.
- Liberati EG, Ruggiero F, Galuppo L, Gorli M, Gonzalez-Lorenzo M, Maraldi M, Ruggieri P, Polo Friz H, Scaratti G, Kwag KH et al. What hinders the uptake of computerized decision support systems in hospi-tals? A qualitative study and framework for implementation. Implement Sci. 2017; 12(1):113. DOI: 10.1186/s13012-017-0644-2
- 7.
- Khairat S, Marc D, Crosby W, Al Sanousi A. Reasons For Physicians Not Adopting Clinical Decision Support Systems: Critical Analysis. JMIR Med Inform. 2018; 6(2):e24. DOI: 10.2196/medinform.8912
- 8.
- Kannry J, McCullagh L, Kushniruk A, Mann D, Edonyabo D, McGinn T. A Framework for Usable and Effective Clinical Decision Support: Experience from the iCPR Randomized Clinical Trial. EGEMS (Wash DC). 2015; 3(2):1150. DOI: 10.13063/2327-9214.1150
- 9.
- Medical Informatics Initiative Germany. About the initiative [Internet]. Berlin: Medical Informatics Initiative c/o TMF e.V. Central Office; [cited 2021 August 6]. Available from:https://www.medizininformatik-initiative.de/en/about-initiative
