scholarly journals Opal: an implementation science tool for machine learning clinical decision support in anesthesia

2021 ◽  
Author(s):  
Andrew Bishara ◽  
Andrew Wong ◽  
Linshanshan Wang ◽  
Manu Chopra ◽  
Wudi Fan ◽  
...  
Keyword(s):  
Decision Support ◽  
Implementation Science ◽  
Clinical Decision Support ◽  
Web Application ◽  
Kidney Injury ◽  
Clinical Decision ◽  
Receiver Operating Curve ◽  
Gradient Boosting ◽  
Decision Threshold ◽  
Machine Model

AbstractOpal is the first published example of a full-stack platform infrastructure for an implementation science designed for ML in anesthesia that solves the problem of leveraging ML for clinical decision support. Users interact with a secure online Opal web application to select a desired operating room (OR) case cohort for data extraction, visualize datasets with built-in graphing techniques, and run in-client ML or extract data for external use. Opal was used to obtain data from 29,004 unique OR cases from a single academic institution for pre-operative prediction of post-operative acute kidney injury (AKI) based on creatinine KDIGO criteria using predictors which included pre-operative demographic, past medical history, medications, and flowsheet information. To demonstrate utility with unsupervised learning, Opal was also used to extract intra-operative flowsheet data from 2995 unique OR cases and patients were clustered using PCA analysis and k-means clustering. A gradient boosting machine model was developed using an 80/20 train to test ratio and yielded an area under the receiver operating curve (ROC-AUC) of 0.85 with 95% CI [0.80–0.90]. At the default probability decision threshold of 0.5, the model sensitivity was 0.9 and the specificity was 0.8. K-means clustering was performed to partition the cases into two clusters and for hypothesis generation of potential groups of outcomes related to intraoperative vitals. Opal’s design has created streamlined ML functionality for researchers and clinicians in the perioperative setting and opens the door for many future clinical applications, including data mining, clinical simulation, high-frequency prediction, and quality improvement.

scholarly journals XML Data and Knowledge-Encoding Structure for a Web-Based and Mobile Antenatal Clinical Decision Support System: Development Study

10.2196/17512 ◽  
2020 ◽  
Vol 4 (10) ◽  
pp. e17512
Author(s):  
Ever Augusto Torres Silva ◽  
Sebastian Uribe ◽  
Jack Smith ◽  
Ivan Felipe Luna Gomez ◽  
Jose Fernando Florez-Arango
Keyword(s):  
Decision Support ◽  
Antenatal Care ◽  
Clinical Decision Support ◽  
Web Application ◽  
Clinical Care ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Structure Design ◽  
Mobile App ◽  
Clinical Workflow

Background Displeasure with the functionality of clinical decision support systems (CDSSs) is considered the primary challenge in CDSS development. A major difficulty in CDSS design is matching the functionality to the desired and actual clinical workflow. Computer-interpretable guidelines (CIGs) are used to formalize medical knowledge in clinical practice guidelines (CPGs) in a computable language. However, existing CIG frameworks require a specific interpreter for each CIG language, hindering the ease of implementation and interoperability. Objective This paper aims to describe a different approach to the representation of clinical knowledge and data. We intended to change the clinician’s perception of a CDSS with sufficient expressivity of the representation while maintaining a small communication and software footprint for both a web application and a mobile app. This approach was originally intended to create a readable and minimal syntax for a web CDSS and future mobile app for antenatal care guidelines with improved human-computer interaction and enhanced usability by aligning the system behavior with clinical workflow. Methods We designed and implemented an architecture design for our CDSS, which uses the model-view-controller (MVC) architecture and a knowledge engine in the MVC architecture based on XML. The knowledge engine design also integrated the requirement of matching clinical care workflow that was desired in the CDSS. For this component of the design task, we used a work ontology analysis of the CPGs for antenatal care in our particular target clinical settings. Results In comparison to other common CIGs used for CDSSs, our XML approach can be used to take advantage of the flexible format of XML to facilitate the electronic sharing of structured data. More importantly, we can take advantage of its flexibility to standardize CIG structure design in a low-level specification language that is ubiquitous, universal, computationally efficient, integrable with web technologies, and human readable. Conclusions Our knowledge representation framework incorporates fundamental elements of other CIGs used in CDSSs in medicine and proved adequate to encode a number of antenatal health care CPGs and their associated clinical workflows. The framework appears general enough to be used with other CPGs in medicine. XML proved to be a language expressive enough to describe planning problems in a computable form and restrictive and expressive enough to implement in a clinical system. It can also be effective for mobile apps, where intermittent communication requires a small footprint and an autonomous app. This approach can be used to incorporate overlapping capabilities of more specialized CIGs in medicine.

scholarly journals Implementation of clinical decision support to manage acute kidney injury in secondary care: an ethnographic study

2019 ◽  
Vol 29 (5) ◽  
pp. 382-389
Author(s):  
Simon Bailey ◽  
Carianne Hunt ◽  
Adam Brisley ◽  
Susan Howard ◽  
Lynne Sykes ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Patient Safety ◽  
Quality Improvement ◽  
Decision Support ◽  
Clinical Decision Support ◽  
Kidney Injury ◽  
Clinical Decision ◽  
Ethnographic Study ◽  
Routine Practice ◽  
Trade Offs

BackgroundOver the past decade, acute kidney injury (AKI) has become a global priority for improving patient safety and health outcomes. In the UK, a confidential inquiry into AKI led to the publication of clinical guidance and a range of policy initiatives. National patient safety directives have focused on the mandatory establishment of clinical decision support systems (CDSSs) within all acute National Health Service (NHS) trusts to improve the detection, alerting and response to AKI. We studied the organisational work of implementing AKI CDSSs within routine hospital care.MethodsAn ethnographic study comprising non-participant observation and interviews was conducted in two NHS hospitals, delivering AKI quality improvement programmes, located in one region of England. Three researchers conducted a total of 49 interviews and 150 hours of observation over an 18-month period. Analysis was conducted collaboratively and iteratively around emergent themes, relating to the organisational work of technology adoption.ResultsThe two hospitals developed and implemented AKI CDSSs using very different approaches. Nevertheless, both resulted in adaptive work and trade-offs relating to the technology, the users, the organisation and the wider system of care. A common tension was associated with attempts to maximise benefit while minimise additional burden. In both hospitals, resource pressures exacerbated the tensions of translating AKI recommendations into routine practice.ConclusionsOur analysis highlights a conflicted relationship between external context (policy and resources), and organisational structure and culture (eg, digital capability, attitudes to quality improvement). Greater consideration is required to the long-term effectiveness of the approaches taken, particularly in light of the ongoing need for adaptation to incorporate new practices into routine work.

scholarly journals Machine Learning Approach to Reduce Alert Fatigue Using a Disease Medication–Related Clinical Decision Support System: Model Development and Validation (Preprint)

2020 ◽  
Author(s):  
Tahmina Nasrin Poly ◽  
Md.Mohaimenul Islam ◽  
Muhammad Solihuddin Muhtar ◽  
Hsuan-Chia Yang ◽  
Phung Anh (Alex) Nguyen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Clinical Decision Support ◽  
Prediction Models ◽  
Clinical Decision ◽  
Gradient Boosting ◽  
Support Vector ◽  
Learning Models ◽  
Alert Fatigue ◽  
Machine Learning Models

BACKGROUND Computerized physician order entry (CPOE) systems are incorporated into clinical decision support systems (CDSSs) to reduce medication errors and improve patient safety. Automatic alerts generated from CDSSs can directly assist physicians in making useful clinical decisions and can help shape prescribing behavior. Multiple studies reported that approximately 90%-96% of alerts are overridden by physicians, which raises questions about the effectiveness of CDSSs. There is intense interest in developing sophisticated methods to combat alert fatigue, but there is no consensus on the optimal approaches so far. OBJECTIVE Our objective was to develop machine learning prediction models to predict physicians’ responses in order to reduce alert fatigue from disease medication–related CDSSs. METHODS We collected data from a disease medication–related CDSS from a university teaching hospital in Taiwan. We considered prescriptions that triggered alerts in the CDSS between August 2018 and May 2019. Machine learning models, such as artificial neural network (ANN), random forest (RF), naïve Bayes (NB), gradient boosting (GB), and support vector machine (SVM), were used to develop prediction models. The data were randomly split into training (80%) and testing (20%) datasets. RESULTS A total of 6453 prescriptions were used in our model. The ANN machine learning prediction model demonstrated excellent discrimination (area under the receiver operating characteristic curve [AUROC] 0.94; accuracy 0.85), whereas the RF, NB, GB, and SVM models had AUROCs of 0.93, 0.91, 0.91, and 0.80, respectively. The sensitivity and specificity of the ANN model were 0.87 and 0.83, respectively. CONCLUSIONS In this study, ANN showed substantially better performance in predicting individual physician responses to an alert from a disease medication–related CDSS, as compared to the other models. To our knowledge, this is the first study to use machine learning models to predict physician responses to alerts; furthermore, it can help to develop sophisticated CDSSs in real-world clinical settings.

scholarly journals Integrating the Practical Robust Implementation and Sustainability Model With Best Practices in Clinical Decision Support Design: Implementation Science Approach

10.2196/19676 ◽  
2020 ◽  
Vol 22 (10) ◽  
pp. e19676
Author(s):  
Katy E Trinkley ◽  
Michael G Kahn ◽  
Tellen D Bennett ◽  
Russell E Glasgow ◽  
Heather Haugen ◽  
...  
Keyword(s):  
Decision Support ◽  
Best Practices ◽  
Implementation Science ◽  
Clinical Decision Support ◽  
Integrated Approach ◽  
Clinical Decision ◽  
Lessons Learned ◽  
Support Design ◽  
Robust Implementation ◽  
Sustainability Model

Background Clinical decision support (CDS) design best practices are intended to provide a narrative representation of factors that influence the success of CDS tools. However, they provide incomplete direction on evidence-based implementation principles. Objective This study aims to describe an integrated approach toward applying an existing implementation science (IS) framework with CDS design best practices to improve the effectiveness, sustainability, and reproducibility of CDS implementations. Methods We selected the Practical Robust Implementation and Sustainability Model (PRISM) IS framework. We identified areas where PRISM and CDS design best practices complemented each other and defined methods to address each. Lessons learned from applying these methods were then used to further refine the integrated approach. Results Our integrated approach to applying PRISM with CDS design best practices consists of 5 key phases that iteratively interact and inform each other: multilevel stakeholder engagement, designing the CDS, design and usability testing, thoughtful deployment, and performance evaluation and maintenance. The approach is led by a dedicated implementation team that includes clinical informatics and analyst builder expertise. Conclusions Integrating PRISM with CDS design best practices extends user-centered design and accounts for the multilevel, interacting, and dynamic factors that influence CDS implementation in health care. Integrating PRISM with CDS design best practices synthesizes the many known contextual factors that can influence the success of CDS tools, thereby enhancing the reproducibility and sustainability of CDS implementations. Others can adapt this approach to their situation to maximize and sustain CDS implementation success.

scholarly journals Sustained effects of a clinical decision support system for acute kidney injury

2020 ◽  
Vol 35 (10) ◽  
pp. 1819-1821
Author(s):  
Ayham Bataineh ◽  
Dilhari Dealmeida ◽  
Andrew Bilderback ◽  
Richard Ambrosino ◽  
Mohammed J Al-Jaghbeer ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Decision Support ◽  
Decision Support System ◽  
Clinical Decision Support ◽  
Support System ◽  
Clinical Decision Support System ◽  
Kidney Injury ◽  
Clinical Decision ◽  
Sustained Effects

SMART COVID Navigator: A Clinical Decision Support for COVID-19 (Preprint)

2021 ◽  
Author(s):  
Varun Suraj ◽  
Catherine Del Vecchio Fitz ◽  
Laura B. Kleiman ◽  
Jeremy Warner ◽  
Gil Alterovitz
Keyword(s):  
Decision Support ◽  
Clinical Decision Support ◽  
Web Application ◽  
Decision Support Tool ◽  
Clinical Decision ◽  
Observational Research ◽  
Large Set ◽  
Health Records ◽  
Support Tool ◽  
Research Findings

UNSTRUCTURED The coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has infected 83 million individuals at the time of writing. In this paper, we describe the creation of a clinical decision support tool, the SMART COVID Navigator, a web application to assist clinicians in treating COVID-19 patients. A large volume of research findings from observational studies about disease interactions with COVID-19 are being produced almost daily. Our app allows clinicians to access a patient’s electronic health records and identify disease interactions from a large set of observational research studies that affect severity and fatality due to COVID-19. We also analyze the results of the collected studies to determine which medical conditions result in an increased chance of severity and/or fatality of COVID-19 progression.

scholarly journals Machine Learning Approach to Reduce Alert Fatigue Using a Disease Medication–Related Clinical Decision Support System: Model Development and Validation

10.2196/19489 ◽  
2020 ◽  
Vol 8 (11) ◽  
pp. e19489
Author(s):  
Tahmina Nasrin Poly ◽  
Md.Mohaimenul Islam ◽  
Muhammad Solihuddin Muhtar ◽  
Hsuan-Chia Yang ◽  
Phung Anh (Alex) Nguyen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Clinical Decision Support ◽  
Prediction Models ◽  
Clinical Decision ◽  
Gradient Boosting ◽  
Support Vector ◽  
Learning Models ◽  
Alert Fatigue ◽  
Machine Learning Models

Background Computerized physician order entry (CPOE) systems are incorporated into clinical decision support systems (CDSSs) to reduce medication errors and improve patient safety. Automatic alerts generated from CDSSs can directly assist physicians in making useful clinical decisions and can help shape prescribing behavior. Multiple studies reported that approximately 90%-96% of alerts are overridden by physicians, which raises questions about the effectiveness of CDSSs. There is intense interest in developing sophisticated methods to combat alert fatigue, but there is no consensus on the optimal approaches so far. Objective Our objective was to develop machine learning prediction models to predict physicians’ responses in order to reduce alert fatigue from disease medication–related CDSSs. Methods We collected data from a disease medication–related CDSS from a university teaching hospital in Taiwan. We considered prescriptions that triggered alerts in the CDSS between August 2018 and May 2019. Machine learning models, such as artificial neural network (ANN), random forest (RF), naïve Bayes (NB), gradient boosting (GB), and support vector machine (SVM), were used to develop prediction models. The data were randomly split into training (80%) and testing (20%) datasets. Results A total of 6453 prescriptions were used in our model. The ANN machine learning prediction model demonstrated excellent discrimination (area under the receiver operating characteristic curve [AUROC] 0.94; accuracy 0.85), whereas the RF, NB, GB, and SVM models had AUROCs of 0.93, 0.91, 0.91, and 0.80, respectively. The sensitivity and specificity of the ANN model were 0.87 and 0.83, respectively. Conclusions In this study, ANN showed substantially better performance in predicting individual physician responses to an alert from a disease medication–related CDSS, as compared to the other models. To our knowledge, this is the first study to use machine learning models to predict physician responses to alerts; furthermore, it can help to develop sophisticated CDSSs in real-world clinical settings.

Sign in / Sign up

Export Citation Format

Share Document