What Should Oversight of Clinical Decision Support Systems Look Like?

Evans, Emily L.; Whicher, Danielle

doi:10.1001/amajethics.2018.857

Cited by 13 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning health systems with their intentionally blurred boundaries between research and care - particularly in the case of EHR decision support - require a new approach of oversight to be adopted. Measures towards securing enough insight into the certainty and reliability of algorithms and offering additional recommendations, e.g ., from guidelines, together with monitoring data quality and preserving confidentiality need particular oversight to be implemented via establishing an independent body of experts with the capability to enforce the rules 47 . The AMIA working group Ethical, Legal, and Social Issues 48 worked on patient access to EHRs in a learning health system rather from the opportunity than from the risk position.…”

Section: Resultsmentioning

confidence: 99%

Clinical Information Systems – Seen through the Ethics Lens

2020

View full text Add to dashboard Cite

Objective: The more people there are who use clinical information systems (CIS) beyond their traditional intramural confines, the more promising the benefits are, and the more daunting the risks will be. This review thus explores the areas of ethical debates prompted by CIS conceptualized as smart systems reaching out to patients and citizens. Furthermore, it investigates the ethical competencies and education needed to use these systems appropriately. Methods: A literature review covering ethics topics in combination with clinical and health information systems, clinical decision support, health information exchange, and various mobile devices and media was performed searching the MEDLINE database for articles from 2016 to 2019 with a focus on 2018 and 2019. A second search combined these keywords with education. Results: By far, most of the discourses were dominated by privacy, confidentiality, and informed consent issues. Intertwined with confidentiality and clear boundaries, the provider-patient relationship has gained much attention. The opacity of algorithms and the lack of explicability of the results pose a further challenge. The necessity of sociotechnical ethics education was underpinned in many studies including advocating education for providers and patients alike. However, only a few publications expanded on ethical competencies. In the publications found, empirical research designs were employed to capture the stakeholders’ attitudes, but not to evaluate specific implementations. Conclusion: Despite the broad discourses, ethical values have not yet found their firm place in empirically rigorous health technology evaluation studies. Similarly, sociotechnical ethics competencies obviously need detailed specifications. These two gaps set the stage for further research at the junction of clinical information systems and ethics.

show abstract

Section: Resultsmentioning

confidence: 99%

Clinical Information Systems – Seen through the Ethics Lens

2020

View full text Add to dashboard Cite

show abstract

“…Exemplary, there are systems for risk evaluation, pre-processing or pre-sorting of telemetric and visual data, differentiation of patients into subgroups or integration into diagnostic procedures. Overall, the application of artificial intelligence in medicine is beneficial but requires ethical oversight in implementation and usage ( 36 ).…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Classification of Inflammatory Bowel Disease in Children Based on a Large Real-World Pediatric Cohort CEDATA-GPGE® Registry

et al. 2021

View full text Add to dashboard Cite

Introduction: The rising incidence of pediatric inflammatory bowel diseases (PIBD) facilitates the need for new methods of improving diagnosis latency, quality of care and documentation. Machine learning models have shown to be applicable to classifying PIBD when using histological data or extensive serology. This study aims to evaluate the performance of algorithms based on promptly available data more suited to clinical applications.Methods: Data of inflammatory locations of the bowels from initial and follow-up visitations is extracted from the CEDATA-GPGE registry and two follow-up sets are split off containing only input from 2017 and 2018. Pre-processing excludes patients in remission and encodes the categorical data numerically. For classification of PIBD diagnosis, a support vector machine (SVM), a random forest algorithm (RF), extreme gradient boosting (XGBoost), a dense neural network (DNN) and a convolutional neural network (CNN) are employed. As best performer, a convolutional neural network is further improved using grid optimization.Results: The achieved accuracy of the optimized neural network reaches up to 90.57% on data inserted into the registry in 2018. Less performant methods reach 88.78% for the DNN down to 83.94% for the XGBoost. The accuracy of prediction for the 2018 follow-up dataset is higher than those for older datasets. Neural networks yield a higher standard deviation with 3.45 for the CNN compared to 0.83–0.86 of the support vector machine and ensemble methods.Discussion: The displayed accuracy of the convolutional neural network proofs the viability of machine learning classification in PIBD diagnostics using only timely available data.

show abstract

“…Professionals raised concerns about reliability of the output generated by the system and the adaptability of the system to local and contextual needs (CFIR: Characteristics of Individuals). Previous research confirmed that frequently found errors in data processing and output of clinical decision support tools negatively affect users' perception as unsuitable suggestions for decision-making lead to doubts about safety and accuracy [25][26][27]. Resistance was also expressed regarding the potential lack of clinical nuances for psychosocial factors in the well-structured patient overview provided by the first component (CFIR: Characteristics of Individuals).…”

Section: Relation To Other Studiesmentioning

confidence: 99%

Barriers and Facilitators for Implementation of a Computerized Clinical Decision Support System in Lung Cancer Multidisciplinary Team Meetings—A Qualitative Assessment

Klarenbeek¹,

Schuurbiers-Siebers

Heuvel

et al. 2020

Biology

View full text Add to dashboard Cite

Background: Oncological computerized clinical decision support systems (CCDSSs) to facilitate workflows of multidisciplinary team meetings (MDTMs) are currently being developed. To successfully implement these CCDSSs in MDTMs, this study aims to: (a) identify barriers and facilitators for implementation for the use case of lung cancer; and (b) provide actionable findings for an implementation strategy. Methods: The Consolidated Framework for Implementation Science was used to create an interview protocol and to analyze the results. Semi-structured interviews were conducted among various health care professionals involved in MDTMs. The transcripts were analyzed using a thematic analysis following a deductive approach. Results: Twenty-six professionals participated in the interviews. The main facilitators for implementation of the CCDSS were considered to be easy access to well-structured patient data, and the resulting reduction of MDTM preparation time and of duration of MDTMs. Main barriers for adoption were seen in incomplete or non-trustworthy output generated by the system and insufficient adaptability of the system to local and contextual needs. Conclusion: Using a CCDSS in lung cancer MDTMs was expected to increase efficiency of workflows. Successful implementation was seen as dependent on the reliability and adaptability of the CCDSS and involvement of key users in the implementation process.

show abstract

What Should Oversight of Clinical Decision Support Systems Look Like?

Cited by 13 publications

References 7 publications

Clinical Information Systems – Seen through the Ethics Lens

Clinical Information Systems – Seen through the Ethics Lens

Machine Learning Classification of Inflammatory Bowel Disease in Children Based on a Large Real-World Pediatric Cohort CEDATA-GPGE® Registry

Barriers and Facilitators for Implementation of a Computerized Clinical Decision Support System in Lung Cancer Multidisciplinary Team Meetings—A Qualitative Assessment

Contact Info

Product

Resources

About