Principles for Designing and Developing a Workflow Monitoring Tool to Enable and Enhance Clinical Workflow Automation

Optimization of Electronic Health Record Usability Through a Department-Led Quality Improvement Process

BACKGROUND

Electronic health records (EHR) have become commonplace in medicine. A disconnect between developers and users while creating the interface often fails to create a product that captures clinical workflow, and issues become apparent with implementation. Optimization allows collaboration of clinicians and informaticists after implementation, but documentation of success has only been at the institutional level.

METHODS

A 4-month, department-wide EHR optimization was conducted with information technology (IT). Optimizations were developed from an intensive quality improvement process involving all levels of clinicians and clinical staff. The optimizations were then categorized as accommodations (department adjusted workflow to EHR), creations (IT developed new workflows within EHR), discoveries (department found workflows within EHR), and modifications (IT changed workflows within EHR). Departmental productivity, defined as number of visits, charges, and payments, was standardized to ratios prior to the COVID-19 pandemic and evaluated by Taylor's change point analysis. Significant improvements were defined as shifts (change points), trends (5 or more consecutive values above/below the mean), and values outside 95% CIs.

RESULTS

The 124 optimizations were categorized as 43 accommodations, 13 creations, 54 discoveries, and 14 modifications. Productivity ratios of monthly charges (0.74 to 1.28) and payments (0.83 to 1.58) significantly improved with the optimization efforts. Monthly visit ratios increased (0.65 to 0.98) but did not change significantly.

CONCLUSION

Departmental collaboration with organizational IT for EHR optimization focused on detailed analysis of how workflows can impact productivity. Discovery optimization predominance indicates many solutions to EHR usability problems were already in the system. A large proportion of accommodation optimizations reinforced the need for better developer-user collaboration before implementation.Annals Early Access.

An Explainable Knowledge-Based System Using Subjective Preferences and Objective Data for Ranking Decision Alternatives

BACKGROUND

 Allergy is a hypersensitive reaction that occurs when the allergen reacts with the immune system. The prevalence and severity of the allergies are uprising in South Asian countries. Allergy often occurs in combinations which becomes difficult for physicians to diagnose.

OBJECTIVES

 This work aims to develop a decision-making model which aids physicians in diagnosing allergy comorbidities. The model intends to not only provide rational decisions, but also explainable knowledge about all alternatives.

METHODS

 The allergy data gathered from real-time sources contain a smaller number of samples for comorbidities. Decision-making model applies three sampling strategies, namely, ideal, single, and complete, to balance the data. Bayes theorem-based probabilistic approaches are used to extract knowledge from the balanced data. Preference weights for attributes with respect to alternatives are gathered from a group of domain-experts affiliated to different allergy testing centers. The weights are combined with objective knowledge to assign confidence values to alternatives. The system provides these values along with explanations to aid decision-makers in choosing an optimal decision.

RESULTS

 Metrics of explainability and user satisfaction are used to evaluate the effectiveness of the system in real-time diagnosis. Fleiss' Kappa statistic is 0.48, and hence the diagnosis of experts is said to be in moderate agreement. The decision-making model provides a maximum of 10 suitable and relevant pieces of evidence to explain a decision alternative. Clinicians have improved their diagnostic performance by 3% after using CDSS (77.93%) with a decrease in 20% of time taken.

CONCLUSION

 The performance of less-experienced clinicians has improved with the support of an explainable decision-making model. The code for the framework with all intermediate results is available at https://github.com/kavya6697/Allergy-PT.git.