Assessing the implementation of a clinical decision support tool in primary care for diabetes prevention: a qualitative interview study using the Consolidated Framework for Implementation Science

Background In this paper we describe the use of the Consolidated Framework for Implementation Research (CFIR) to study implementation of a web-based, point-of-care, EHR-linked clinical decision support (CDS) tool designed to identify and provide care recommendations for adults with prediabetes (Pre-D CDS). Methods As part of a large NIH-funded clinic-randomized trial, we identified a convenience sample of interview participants from 22 primary care clinics in Minnesota, North Dakota, and Wisconsin that were randomly allocated to receive or not receive a web-based EHR-integrated prediabetes CDS intervention. Participants included 11 clinicians, 6 rooming staff, and 7 nurse or clinic managers recruited by study staff to participate in telephone interviews conducted by an expert in qualitative methods. Interviews were recorded and transcribed, and data analysis was conducted using a constructivist version of grounded theory. Results Implementing a prediabetes CDS tool into primary care clinics was useful and well received. The intervention was integrated with clinic workflows, supported primary care clinicians in clearly communicating prediabetes risk and management options with patients, and in identifying actionable care opportunities. The main barriers to CDS use were time and competing priorities. Finally, while the implementation process worked well, opportunities remain in engaging the care team more broadly in CDS use. Conclusions The use of CDS tools for engaging patients and providers in care improvement opportunities for prediabetes is a promising and potentially effective strategy in primary care settings. A workflow that incorporates the whole care team in the use of such tools may optimize the implementation of CDS tools like these in primary care settings. Trial registration Name of the registry: Clinicaltrial.gov. Trial registration number: NCT02759055. Date of registration: 05/03/2016. URL of trial registry record: https://clinicaltrials.gov/ct2/show/NCT02759055 Prospectively registered.

eCOVID19 – Development of Ontology-based Clinical Decision Support System for COVID-19

Introduction: Humankind is passing through a period of significant instability and a worldwide health catastrophe that has never been seen before. COVID-19 spread over the world at an unprecedented rate. In this context, we undertook a rapid research project in the Sultanate of Oman. We developed ecovid19 application, an ontology-based clinical decision support system (CDSS) with teleconference capability for easy, fast diagnosis and treatment for primary health centers/Satellite Clinics of the Royal Oman Police (ROP) of Sultanate of Oman.Materials and Methods: The domain knowledge and clinical guidelines are represented using ontology. Ontology is one of the most powerful methods for formally encoding medical knowledge. The primary data was from the ROP hospital's medical team, while the secondary data came from articles published in reputable journals. The application includes a COVID-19 Symptom checker for the public users with a text interface and an AI-based voice interface and is available in English and Arabic. Based on the given information, the symptom checker provides recommendations to the user. The suspected cases will be directed to the nearby clinic if the risk of infection is high. Based on the patient's current medical condition in the clinic, the CDSS will make suitable suggestions to triage staff, doctors, radiologists, and lab technicians on procedures and medicines. We used Teachable Machine to create a TensorFlow model for the analysis of X-rays. Our CDSS also has a WebRTC (Web Real-Time Communication system) based teleconferencing option for communicating with expert clinicians if the patient develops difficulties or if expert opinion is requested.Results: The ROP hospital's specialized doctors tested our CDSS, and the user interfaces were changed based on their suggestions and recommendations. The team put numerous types of test cases to assess the clinical efficacy. Precision, sensitivity (recall), specificity, and accuracy were adequate in predicting the various categories of patient instances.Conclusion: The proposed CDSS has the potential to significantly improve the quality of care provided to Oman's citizens. It can also be tailored to fit other terrifying pandemics.

A Mixed-Methods Feasibility Study of a Novel AI-Enabled, Web-Based, Clinical Decision Support System for the Treatment of Major Depression in Adults

The objective of this paper is to discuss perceived clinical utility and impact on physician-patient relationship of a novel, artificial-intelligence (AI) enabled clinical decision support system (CDSS) for use in the treatment of adults with major depression. Patients had a baseline appointment, followed by a minimum of two appointments with the CDSS. For both physicians and patients, study exit questionnaires and interviews were conducted to assess perceived clinical utility, impact on patient-physician relationship, and understanding and trust in the CDSS. 17 patients consented to participate in the study, of which 14 completed. 86% of physicians (6/7) felt the information provided by the CDSS provided a more comprehensive understanding of patient situations and 71% (5/7) felt the information was helpful. 86% of physicians (6/7) reported the AI/predictive model was useful when making treatment decisions. 62% of patients (8/13) reported improvement in their care as a result of the tool. 46% of patients (6/13) felt the app significantly or somewhat improved their relationship with their physicians; 54% felt it did not change. 71% of physicians (5/7) and 62% of patients (8/13) rated they trusted the tool. Qualitative results are analyzed and presented. Findings suggest physicians perceived the tool as useful in conducting appointments and used it while making treatment decisions. Physicians and patients generally found the tool trustworthy, and it may have positive effects on physician-patient relationships.

Automated Clinical Decision Support for Coronary Plaques Characterization from Optical Coherence Tomography Imaging with Fused Neural Networks

Deep Neural Networks (DNNs) are nurturing clinical decision support systems for the detection and accurate modeling of coronary arterial plaques. However, efficient plaque characterization in time-constrained settings is still an open problem. The purpose of this study is to develop a novel automated classification architecture viable for the real-time clinical detection and classification of coronary artery plaques, and secondly, to use the novel dataset of OCT images for data augmentation. Further, the purpose is to validate the efficacy of transfer learning for arterial plaques classification. In this perspective, a novel time-efficient classification architecture based on DNNs is proposed. A new data set consisting of in-vivo patient Optical Coherence Tomography (OCT) images labeled by three trained experts was created and dynamically programmed. Generative Adversarial Networks (GANs) were used for populating the coronary aerial plaques dataset. We removed the fully connected layers, including softmax and the cross-entropy in the GoogleNet framework, and replaced them with the Support Vector Machines (SVMs). Our proposed architecture limits weight up-gradation cycles to only modified layers and computes the global hyper-plane in a timely, competitive fashion. Transfer learning was used for high-level discriminative feature learning. Cross-entropy loss was minimized by using the Adam optimizer for model training. A train validation scheme was used to determine the classification accuracy. Automated plaques differentiation in addition to their detection was found to agree with the clinical findings. Our customized fused classification scheme outperforms the other leading reported works with an overall accuracy of 96.84%, and multiple folds reduced elapsed time demonstrating it as a viable choice for real-time clinical settings.

A 12-hospital prospective evaluation of a clinical decision support prognostic algorithm based on logistic regression as a form of machine learning to facilitate decision making for patients with suspected COVID-19

Objective To prospectively evaluate a logistic regression-based machine learning (ML) prognostic algorithm implemented in real-time as a clinical decision support (CDS) system for symptomatic persons under investigation (PUI) for Coronavirus disease 2019 (COVID-19) in the emergency department (ED). Methods We developed in a 12-hospital system a model using training and validation followed by a real-time assessment. The LASSO guided feature selection included demographics, comorbidities, home medications, vital signs. We constructed a logistic regression-based ML algorithm to predict “severe” COVID-19, defined as patients requiring intensive care unit (ICU) admission, invasive mechanical ventilation, or died in or out-of-hospital. Training data included 1,469 adult patients who tested positive for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) within 14 days of acute care. We performed: 1) temporal validation in 414 SARS-CoV-2 positive patients, 2) validation in a PUI set of 13,271 patients with symptomatic SARS-CoV-2 test during an acute care visit, and 3) real-time validation in 2,174 ED patients with PUI test or positive SARS-CoV-2 result. Subgroup analysis was conducted across race and gender to ensure equity in performance. Results The algorithm performed well on pre-implementation validations for predicting COVID-19 severity: 1) the temporal validation had an area under the receiver operating characteristic (AUROC) of 0.87 (95%-CI: 0.83, 0.91); 2) validation in the PUI population had an AUROC of 0.82 (95%-CI: 0.81, 0.83). The ED CDS system performed well in real-time with an AUROC of 0.85 (95%-CI, 0.83, 0.87). Zero patients in the lowest quintile developed “severe” COVID-19. Patients in the highest quintile developed “severe” COVID-19 in 33.2% of cases. The models performed without significant differences between genders and among race/ethnicities (all p-values > 0.05). Conclusion A logistic regression model-based ML-enabled CDS can be developed, validated, and implemented with high performance across multiple hospitals while being equitable and maintaining performance in real-time validation.