Clinical Workflow Integration Research Articles

The Role of Artificial Intelligence and Machine Learning in Cardiovascular Imaging and Diagnosis.

Cardiovascular diseases remain the leading cause of global mortality, underscoring the critical need for accurate and timely diagnosis. This narrative review examines the current applications and future potential of artificial intelligence (AI) and machine learning (ML) in cardiovascular imaging. We discuss the integration of these technologies across various imaging modalities, including echocardiography, computed tomography, magnetic resonance imaging, and nuclear imaging techniques. The review explores AI-assisted diagnosis in key areas such as coronary artery disease detection, valve disorders assessment, cardiomyopathy classification, arrhythmia detection, and prediction of cardiovascular events. AI demonstrates promise in improving diagnostic accuracy, efficiency, and personalized care. However, significant challenges persist, including data quality standardization, model interpretability, regulatory considerations, and clinical workflow integration. We also address the limitations of current AI applications and the ethical implications of their implementation in clinical practice. Future directions point towards advanced AI architectures, multimodal imaging integration, and applications in precision medicine and population health management. The review emphasizes the need for ongoing collaboration between clinicians, data scientists, and policymakers to realize the full potential of AI in cardiovascular imaging while ensuring ethical and equitable implementation. As the field continues to evolve, addressing these challenges will be crucial for the successful integration of AI technologies into cardiovascular care, potentially revolutionizing diagnostic capabilities and improving patient outcomes.

A large language model-based clinical decision support system for syncope recognition in the emergency department: A framework for clinical workflow integration

Differentiation of syncope from transient loss of consciousness can be challenging in the emergency department (ED). Natural Language Processing (NLP) enables the analysis of free text in the electronic medical records (EMR).The present paper aimed to develop a large language models (LLM) for syncope recognition in the ED and proposed a framework for model integration within the clinical workflow.Two models, based on both the Italian and Multilingual Bidirectional Encoder Representations from Transformers (BERT) language model, were developed using consecutive EMRs. The “triage” model was only based on notes contained in the “triage” section of the EMR. The “anamnesis” model added data contained in the “medical history” section. Interpretation and calibration plots were generated.The Italian and Multi BERT models were developed and tested on both 15,098 and 15,222 EMRs, respectively. The triage model had an AUC of 0·95 for the Italian BERT and 0·94 for the Multi BERT. The anamnesis model had an AUC of 0·98 for the Italian BERT and 0·97 for Multi BERT. The LLM identified syncope when not explicitly mentioned in the EMR and also recognized common prodromal symptoms preceding syncope.Both models identified syncope patients in the ED with a high discriminative capability from nurses and doctors’ notes, thus potentially acting as a tool helping physicians to differentiate syncope from others transient loss of consciousness.

Feasibility of a family-involved intervention to increase engagement in evidenced-based psychotherapies for posttraumatic stress disorder: A pilot study.

To assess the feasibility of a family-involved intervention, family support in mental health recovery (FAMILIAR), for veterans with posttraumatic stress disorder (PTSD) seeking psychotherapy at a single Veterans Administration Health System. This mixed-methods study reports qualitative and quantitative findings from a single-group pilot of 24 veterans and their support partners (SPs) about experiences with the intervention and interviews with eight VA mental health clinicians and leaders and the study interventionist to explore intervention feasibility. Findings across data sources were merged within domains of Bowen and colleagues' pilot study feasibility framework. Out of 24 dyads, 16 veterans and 15 associated SPs completed the intervention. Participants viewed the intervention to be valuable and feasible. Veterans and SPs reported that they enrolled in the study to develop a shared understanding of PTSD and treatment. While participants identified few logistical barriers, finding a time for conjoint sessions could be a challenge. Veterans, SPs, and providers discussed benefits of the intervention, including that it facilitated conversation between the veteran and SP about PTSD and mental health care and helped to prepare the dyad for treatment. Providers noted potential challenges integrating family-involved interventions into clinical workflow in VA and suggested the need for additional training and standardized procedures for family-centered care. Our study identified potential implementation facilitators (e.g., standard operating procedures about session documentation, confidentiality, and family ethics) and challenges (e.g., clinical workflow integration) that require further study to bring FAMILIAR into routine clinical care. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Applying Implementation Frameworks to Health IT Development in Dementia Care: Lessons from the CareHeroes Project

AbstractBackgroundCaregiving and clinical care for people living with dementia (PLWD) is complex and complicated by communication challenges among caregivers and providers (Gaugler et al., 2022; Ruggiano et al. 2012; 2019). These challenges can constrain decision making about treatment options (Hinton et al., 2007; Miller et al., 2016; Wolff et al., 2020) and may contribute to negative mental health outcomes often reported by family caregivers (Gaugler et al., 2022), which disproportionately impact vulnerable caregivers (e.g., underserved racial/ethnic groups, rural caregivers (Abner et al., 2016; Fabius et al., 2020)). Health information technology (HIT) has been identified as a potential solution to communication challenges in dementia care (Ruggiano et al., 2019; Vedel et al., 2013). However, few studies have reported how to effectively integrate new HIT into practice to support provider‐caregiver communication. In this study, a four‐stage implementation science framework (Meyers et al., 2012) was used to integrate a newly developed web‐based application (app) technology, called CareHeroes (Brown et al., 2016), into clinical practice at two memory clinics to promote caregiver‐physician communication. CareHeroes is multi‐functional and allows secure sharing of patient‐related clinical information between caregivers and providers. It also provides education and support, including an educational chatbot that provides tailored, expert feedback to caregiver questions.MethodEarly stages of implementation involved interviews with caregivers and focus groups with clinic providers to develop a clinical workflow integration plan for the new app. Then, the research team collected user data collected through the app during implementation as well as caregiver psychosocial outcome data (e.g., depression, burden) at baseline and 3‐month follow‐up to evaluate implementation.ResultThirty‐six caregivers and eight clinic providers provided qualitative data that informed the clinical workflow integration plan. The same providers and 21 additional caregivers enrolled in the CareHeroes implementation demonstration study. While user data demonstrated that it was feasible for caregivers to share clinical information and engage in self‐support using CareHeroes, expected outcomes were confounded by complications during the COVID‐19 pandemic.ConclusionThrough using the implementation framework, several lessons were learned regarding potential success and challenges in integrating new HIT into clinical care to support dementia care and caregiving.

#3226 DEVELOPMENT AND USABILITY ASSESSMENT OF AN AI-ENHANCED DASHBOARD SUPPORTING AVF MANAGEMENT IN CLINICAL PRACTICE

Abstract Background and Aims Despite the rise in publications reporting Artificial Intelligence (AI) solutions in healthcare, their usage in clinical practice remains limited. Prominent barriers for their implementation in clinical practice are the lack of integration of AI-based tools in the hospital health information system and clinical workflows. We previously developed an AVF Failure risk score to assess the expected incidence of AVF failures within 3 months based on routinely collected dialysis data. The risk score showed high accuracy (AUC = 0.81) and calibration. Based on this risk score, we developed an AI-enhanced dashboard supporting the management of AVF in hemodialysis patients. The usability and usefulness of the AI-enhanced AVF management dashboard was evaluated in a pilot quality improvement program. Method A quality improvement framework was used to evaluate the usability of an AI-enhanced dashboard for AVF management (Fig. 1A). First, healthcare professionals (HCP) were involved to provide inputs for model design, endpoint definition, and potential predictors through various qualitative interview techniques such as brainstorming sessions and focus groups (Phase I). A machine learning model was then developed to assess the expected incidence of AVF failure within 3 months. The model used routinely collected clinical data to minimize additional burden on clinical workflow. (Phase II). After developing and validating the model, a model error analysis was conducted using case studies methodology to improve model performance (Phase III). Once the model reached a good accuracy, think-aloud interview was used to abstract HCP needs and to design a user interface for model output. A user-friendly dashboard was developed to display the risk of AVF failure within 3-months and patient's vascular access history (Phase IV). This solution was integrated in the health record system and updated monthly with the latest risk score and medical information. A pilot quality improvement program was conducted in 15 clinics across 4 countries (IT, CZ, SK, SG) from May to December 2022. HCP were asked to evaluate their agreement with the risk score using a 5-point Likert scale (completely disagree to agree) and assess the usefulness of the dashboard in clinical decision making. At this stage the dashboard is not used for medical decision making (Phase V). The evaluation results were compiled into a monthly report and shared with all the HCP involved in the project to promote awareness and engagement. After 3 months of usage, a round-table discussion was held with all participants to gather their feedback and discuss clinical cases (Phase VI). Results Access to the AI-enhanced dashboard increased during the evaluation period. In the first two months of the pilot quality improvement program, the AI-enhanced dashboard was evaluated for 20% patients with an AVF, a proportion that doubled by the end of the program (Fig. 1B). HCP reported 90% agreement with risk model rating (Fig. 1C), suggesting that the model capture relevant physiological status of the patient and its output is understandable by the healthcare staff. Qualitative analysis of round-table discussions showed that the dashboard is perceived as useful and clear. HCP suggested few changes in the user interface to enhance actionability and improve clinical workflow integration. Conclusion Our results support the usefulness and intelligibility of the AI-enhanced AVF management dashboard. The advance of AI-models highlighted the importance to develop new strategies for their integration and evaluation in clinical practice. The engagement of HCP in the early phases of AI-model design and development grants a continuous feedback loop bringing clinical and AI world together. A clinical perspective in dashboard design reflects the needs of healthcare professionals and enhance consideration of patient medical needs. The synergy between theoretical and clinical perspective is crucial to improve model performance, usability, and implementation in clinical practice.

Lost in translation? Information exchange during breast cancer care and implications for technology design.

1558 Background: Almost 4 million women in the US have had breast cancer, with 300,000 women diagnosed each year. Treatment decision-making following breast cancer diagnosis can be challenging as there are often several clinically appropriate treatment options, each with differing impacts on patient short- and long-term quality of life. Further, patients must manage this information during a time of high emotional burden, which can hinder decision-making. Not surprisingly, studies have found that less than 50% of patients believe their treatment plan aligns with their preferences. Numerous decision aids have been developed to support patient decision-making. However, sustained use of decision aids is limited due to poor integration in clinical workflow. We need to better understand the complex workflows and needs of decision aid users - patients and breast cancer clinicians. In this study, we investigate the information exchange between patients and clinicians when making breast cancer treatment decisions and identify design requirements for patient-centered decision support tools. Methods: This study is part of a larger research project to design a COMputerized PAtient-centered Collaborative Technology (COMPACT) to support personalized breast cancer decision-making. We observed clinicians at one academic medical center’s breast center from February-August 2022. Participating clinicians were followed throughout their clinical shift. Using a tablet computer and smart pencil, we recorded all aspects of clinician workflow. Written notes were transcribed and uploaded into Dedoose. Two human factors researchers inductively coded each observation in a consensus-based process. Results: We observed 79 hours of clinical care and 119 patient encounters across 20 observations of various clinical roles. Overall, we found that patients with breast cancer must manage an enormous amount of highly complex information that includes technical medical terms, mathematical concepts (e.g., risk), and uncertainty. We identified over 20 distinct decisions that patients face during their cancer journey, which were interdependent and evolved over time. We identified numerous patient-specific factors that influenced treatment decision-making, such as the patient’s work and family circumstances. For instance, one patient was organizing a conference and needed to plan her surgery around this event. Patients were frequently asked to remember and relay information across members of the care team, indicating inadequate system support of information transfer within the large cancer team. Based on these findings, we identified design requirements for interventions to support care coordination and patient-centered decision-making. Conclusions: These findings can inform the design of interventions to support breast cancer decision-making and improve patient-centered cancer care.

Implementation barriers and considerations for recommending and administering the human papillomavirus (HPV) vaccination in oncology settings.

Survivors of childhood and adolescent cancer experience low human papillomavirus (HPV) vaccination rates-a crucial form of cancer prevention. Oncology provider recommendations may increase young survivors HPV vaccine intent, but HPV vaccination is not typicallyprovided in the oncology setting. Thus, we explored the implementation barriers of providing the HPV vaccine in oncology. We interviewed oncology providers in a variety of specialty areas about their perceptions of the HPV vaccine and to explore barriers to recommending and administering the vaccine in their clinics. Interviewswere audio recorded, quality checked, and thematically analyzed. Emergent themes were then mapped onto the Capability, Opportunity, Motivation, and Behavior (COM-B) Model and the Theoretical Domains Framework. A total of N=24 oncology providers were interviewed. Most provided direct clinical care (87.5%) and most commonly specialized in pediatric oncology (20.8%), medical oncology (16.7%), bone marrow transplant (16.7%), and nurse coordination (16.7%). Two themes emerged within each COM-B domain. Capability: 1) educational barriers to HPV vaccination and 2)complicated post treatment HPV vaccination guidelines. 1) perceived importance of HPV vaccine and 2)concern about blurred scope of practice. 1) hospital administration and time concern barriers and 2) clinical workflow integration concerns. Implementing HPV vaccination in the oncology setting has the potential to increase HPV vaccination rates among young survivors. Multi-level barriers to providing the HPV vaccine in the oncology setting were identified by participants. Leveraging existing implementation strategies may be an effective way to mitigate provider identified barriers and increase vaccination rates.

Artificial Intelligence in Diagnostic Dermatology: Challenges and the Way Forward

Artificial Intelligence (AI) has emerged as a transformative force in the field of diagnostic dermatology, offering unprecedented capabilities in image recognition and data analysis. Despite its promise, the integration of AI into clinical practice faces multifaceted challenges that span technical, ethical, and regulatory domains. This article provides a narrative overview of the current state of AI in dermatology, tracing its historical evolution from early diagnostic tools to contemporary hybrid supervised models. We identify and categorize six critical challenges: data quality and quantity, algorithmic development and explainability, ethical considerations, clinical workflow integration, regulatory frameworks, and stakeholder collaboration. Each challenge is dissected from the perspectives of academia, industry, and healthcare providers, offering actionable recommendations for future research and implementation. We also highlight the paradigm shift in AI research, emphasizing the potential of transformer architectures in revolutionizing diagnostic methodologies. By addressing the challenges and harnessing the latest advancements, AI has the potential to significantly impact diagnostic accuracy and patient outcomes in dermatology.

Newborn Eye Screening as an Application of AI.

Artificial intelligence (AI) applications are diverse and serve varied functions in clinical practice. The most successful products today are clinical decision tools used by physicians, but autonomous AI is gaining traction. Widespread use of AI is limited in part because of concerns about bias, fault-tolerance, and specificity. Adoption of AI often depends on removing cost and complexity in clinical workflow integration, providing clear incentives for use, and providing clear demonstration of clinical outcome. Existing wide-angle photographic screening could be integrated into the clinical workflow based on prior implementations for premature babies and linked with AI interpretation with existing technology. Incidence of retinal abnormality, clinical considerations, AI performance, grading variation for AI-augmented human grading, and cost and policy aspects play a significant role. Improved outcomes for newborns and a relatively high estimated incidence of abnormality have been named as benefits to counterweigh costs in the long term. [Ophthalmic Surg Lasers Imaging Retina. 2021;52:S17-S22.].

Mobile health in preventive cardiology: current status and future perspective.

Despite cutting edge acute interventions and growing preventive strategies supported by robust clinical trials, cardiovascular disease (CVD) has stubbornly persisted as a leading cause of death in the United States and globally. The American Heart Association recognizes mobile health technologies (mHealth) as an emerging strategy in the mitigation of CVD risk factors, with significant potential for improving population health. The purpose of this review is to highlight and summarize the latest available literature on mHealth applications and provide perspective on future directions and barriers to implementation. While available randomized controlled trials and systematic reviews tend to support efficacy of mHealth, published literature includes heterogenous approaches to similar problems with inconsistent results. Some of the strongest recent evidence has been focused on the use of wearables in arrhythmia detection. Systematic reviews of mHealth approaches demonstrate benefit when applied to risk factor modification in diabetes, cigarette smoking cessation, and physical activity/weight loss, while also showing promise in multi risk factor modification via cardiac rehabilitation. Evidence supports efficacy of mHealth in a variety of applications for CVD prevention and management, but continued work is needed for further validation and scaling. Future directions will focus on platform optimization, data and sensor consolidation, and clinical workflow integration. Barriers include application heterogeneity, lack of reimbursement structures, and inequitable access to technology. Policies to promote access to technology will be critical to evidence-based mHealth technologies reaching diverse populations and advancing health equity.

Performance of an artificial intelligence tool with real-time clinical workflow integration - Detection of intracranial hemorrhage and pulmonary embolism.

Performance of an artificial intelligence tool with real-time clinical workflow integration - Detection of intracranial hemorrhage and pulmonary embolism.

Rapid Deployment of Inpatient Telemedicine In Response to COVID-19 Across Three Health Systems.

ObjectiveTo reduce pathogen exposure, conserve personal protective equipment, and facilitate health care personnel work participation in the setting of the COVID-19 pandemic, three affiliated institutions rapidly and independently deployed inpatient telemedicine programs during March 2020. We describe key features and early learnings of these programs in the hospital setting.MethodsRelevant clinical and operational leadership from an academic medical center, pediatric teaching hospital, and safety net county health system met to share learnings shortly after deploying inpatient telemedicine. A summative analysis of their learnings was re-circulated for approval.ResultsAll three institutions faced pressure to urgently standup new telemedicine systems while still maintaining secure information exchange. Differences across patient demographics and technological capabilities led to variation in solution design, though key technical considerations were similar. Rapid deployment in each system relied on readily available consumer-grade technology, given the existing familiarity to patients and clinicians and minimal infrastructure investment. Preliminary data from the academic medical center over one month suggested positive adoption with 631 inpatient video calls lasting an average (standard deviation) of 16.5 minutes (19.6) based on inclusion criteria.DiscussionThe threat of an imminent surge of COVID-19 patients drove three institutions to rapidly develop inpatient telemedicine solutions. Concurrently, federal and state regulators temporarily relaxed restrictions that would have previously limited these efforts. Strategic direction from executive leadership, leveraging off-the-shelf hardware, vendor engagement, and clinical workflow integration facilitated rapid deployment.ConclusionThe rapid deployment of inpatient telemedicine is feasible across diverse settings as a response to the COVID-19 pandemic.

Abstract WP423: Advanced Machine Learning in Action: Radiomic Based Outcome Prediction of Acute Intracranial Hemorrhage on Computed Tomography

Background: Intracranial hemorrhage (ICH) requires prompt diagnosis to optimize patient outcomes 1 . We hypothesized that machine learning algorithms could automatically analyze non-contrast computed tomography (NECT) of the head and predict clinical outcome of ICH patients 2 . Methods: 300 NECTs with acute spontaneous ICH between 2014-2019 were retrospectively included from the database at a tertiary university hospital. A binary outcome was defined as Modified Ranking Scale (mRS) 0-3 (good outcome) and mRS 4-6 (bad outcome) at discharge. Radiomic features including shape, histogram and texture markers were extracted from non- , wavelet- and log-sigma-filtered images using regions of interest of ICH. The quantitative predictors were evaluated utilizing random forest algorithms with 5-fold model-external cross-validation. Results: The model achieved an area under the ROC curve of 0.81 (95% CI [0.077; 0.86]; P<0.01), specificities and sensitivities reached 78% at Youden’s Index optimal cut-off point for the prediction of functional clinical outcome at discharge (mRS). Discussion: In conclusion, quantitative features of acute NECT images in a machine learning algorithm provided high discriminatory power in predicting functional outcome. In clinical routine, this proposed approach could allow early triage of high-risk patients for poor outcome. Indication of source:1 Qureshi, A. I. et al. Intracerebral haemorrhage. Lancet. 2009. 2 Mohammad R. Arbabshirani et al. Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration. npj Digital Medicine. 2018.

The Effects of Information and Communication Technology on Health Service Delivery at Tafo Government Hospital

This study sought to find out the effects of Information and Communication Technology (ICT) on health service delivery at Tafo Government Hospital. A descriptive survey design was used. Data were collected through the use of semi-structured questionnaire and administered to 50 respondents where stratified random sampling technique was used by ranking position as strata. Data were analyzed using descriptive statistics. From the findings, 56% of the respondents overwhelmingly agreed to the fact that the applications of ICT provide quicker medical diagnoses, reduced workload among users, improvement in patients’ waiting time and information accessibility. Nonetheless, 72% bemoaned lack of ICT infrastructure, poor ICT network concerns coupled with that insufficient knowledge on the use of ICT could impede the impact of ICT in quality service delivery. This could be deduced from the findings that ICT improves collaboration and clinical decision support in facilitating clinical work flow integration among nurses and other medical professionals. Moreover, the findings above affirm the fact that without electricity, ICT infrastructure, insufficient skills and technical knowledge in dealing with ICT innovations, it is impossible to successfully adopt ICT resources in health care delivery. The above findings show that the majority of healthcare professional generally had a positive attitude towards ICT prospects as they rated their skill as fairly well. The study recommends that the Ministry of Health plays a supporting role by investing in health care ICT.

Rapid sequence induction traceability in an ICU dedicated patient data management system: a multicentric retrospective study

PurposePatient data management systems (PDMS) are widely used in intensive care units (ICUs) to improve care traceability. Verbal orders are still used for prescriptions requiring immediate execution but should be subsequently recorded in the system. We assessed the rapid sequence induction (RSI) traceability for endotracheal intubation in an ICU dedicated PDMS. Materials and methodsA retrospective study was conducted on anonymous databases in 21 ICUs. Endotracheal tube insertions performed during one year were compared to the number of RSI registered in the PDMS. ResultsWe listed 5516 endotracheal tube insertions. A suxamethonium injection was registered in 829 cases and a rocuronium administration in 909 cases. The RSI traceability rate in the overall cohort was 31.5% and was greater in the units where nurses were allowed to record a drug administration before the computerized physician order entry. ConclusionsPDMS are supposed to improve prescription completeness and traceability, but our study suggests an opposite result. A co-responsibility policy between physicians and nurses should be promoted to improve care traceability. PDMS ergonomic improvements and enhanced integration in clinical workflow might also result in better compliance with documentation requirements. In each centre, indicators of PDMS correct use should be defined and periodically monitored.

A Megavoltage CT Image Enhancement Method for Image-Guided and Adaptive Helical TomoTherapy.

Purpose: To propose a novel method to improve the mega-voltage CT (MVCT) image quality for helical TomoTherapy while maintaining the stability on dose calculation.Materials and Methods: The Block-Matching 3D-transform (BM3D) and Discriminative Feature Representation (DFR) methods were combined into a novel BM3D + DFR method for their respective advantages. A phantom (Catphan504) and three serials of clinical (head & neck, chest, and pelvis) MVCT images from 30 patients were acquired using the helical TomoTherapy system. The contrast-to-noise ratio (CNR) and edge detection algorithm (canny) was employed for image quality comparisons between the original and BM3D + DFR enhanced MVCT. A simulated rectangular field of 6 MV X-ray beams were vertically delivered on the original and post-processed MVCT serials of the same CT density phantom, and the dose curves on both serials were compared to test the effects of image enhancement on dose calculation accuracy.Results: In total, 466 transversal MVCT slices were acquired and processed by both BM3D and the proposed BM3D + DFR methods. Compared to the original MVCT image, the BM3D + DFR method presented a remarkable improvement in terms of the soft tissue contrast and noise reduction. For the phantom image, the CNR of the region of interest (ROI) was improved from 1.70 to 4.03. The average CNR of ROIs for 10 patients from each anatomical group, were increased significantly from 1.45 ± 1.51 to 2.09 ± 1.68 for the head & neck (p < 0.001), from 0.92 ± 0.78 to 1.36 ± 0.85 for the chest (p < 0.001), and from 1.12 ± 1.22 to 1.76 ± 1.31 for the pelvis (p < 0.001), respectively. The canny edge detection operator showed that BM3D + DFR provided clearer organ boundaries with less chaos. The root-mean-square of the dosimetry difference on the iso-center passed horizontal dose profile curves and vertical percentage depth dose curves were only 0.09% and 0.06%, respectively.Conclusions: The proposed BM3D + DFR method is feasible to improve the soft tissue contrast for the original MVCT images with coincidence in dose calculation and without compromising resolution. After integration in clinical workflow, the post-processed MVCT may be better applied on image-guided and adaptive helical TomoTherapy.

Eye of the beholder: Risk calculators and barriers to adoption in surgical trainees

Accurate risk assessment before surgery is complex and hampered by behavioral factors. Underutilized risk-based decision-support tools may counteract these barriers. The purpose of this study was to identify perceptions of and barriers to the use of surgical risk-assessment tools and assess the importance of data framing as a barrier to adoption in surgical trainees. We distributed a survey and risk assessment activity to surgical trainees at four training institutions. The primary outcomes of this study were descriptive risk assessment practices currently performed by residents, identifiable influences and obstacles to adoption, and the variability of preference sets when comparing modified System Usability Scores of a current risk calculator to a purpose-built calculator revision. Risk calculator comparison responses were compared with simple and multivariable regression to identify predictors for preferentiality. We collected responses from 124 surgical residents (39% response rate). Participants endorsed familiarity with direct verbal communication (100%), sketch diagrams (87%), and brochures (59%). The most contemporary risk communication frameworks, such as best-worst case scenario framing (38%), case-specific risk calculators (43%), and all-procedure calculators (52%) were the least familiar. Usage favored traditional models of communication with only 26% of residents regularly using a strategy other than direct verbal discussion or anatomic sketch diagrams. Barriers limiting routine use included lack of electronic and clinical workflow integration. The mean modified System Usability Scores domain scores were widely dispersed for all domains, and no domain demonstrated one calculator's superiority over another. Risk assessment tools are underutilized by trainees. Of importance, preference sets of clinicians appear to be unpredictable and may benefit more from a customizable, bespoke approach.

Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration

Intracranial hemorrhage (ICH) requires prompt diagnosis to optimize patient outcomes. We hypothesized that machine learning algorithms could automatically analyze computed tomography (CT) of the head, prioritize radiology worklists and reduce time to diagnosis of ICH. 46,583 head CTs (~2 million images) acquired from 2007–2017 were collected from several facilities across Geisinger. A deep convolutional neural network was trained on 37,074 studies and subsequently evaluated on 9499 unseen studies. The predictive model was implemented prospectively for 3 months to re-prioritize “routine” head CT studies as “stat” on realtime radiology worklists if an ICH was detected. Time to diagnosis was compared between the re-prioritized “stat” and “routine” studies. A neuroradiologist blinded to the study reviewed false positive studies to determine whether the dictating radiologist overlooked ICH. The model achieved an area under the ROC curve of 0.846 (0.837–0.856). During implementation, 94 of 347 “routine” studies were re-prioritized to “stat”, and 60/94 had ICH identified by the radiologist. Five new cases of ICH were identified, and median time to diagnosis was significantly reduced (p < 0.0001) from 512 to 19 min. In particular, one outpatient with vague symptoms on anti-coagulation was found to have an ICH which was treated promptly with reversal of anticoagulation, resulting in a good clinical outcome. Of the 34 false positives, the blinded over-reader identified four probable ICH cases overlooked in original interpretation. In conclusion, an artificial intelligence algorithm can prioritize radiology worklists to reduce time to diagnosis of new outpatient ICH by 96% and may also identify subtle ICH overlooked by radiologists. This demonstrates the positive impact of advanced machine learning in radiology workflow optimization.

TU‐A‐BRF‐01: MR Guided Radiation Therapy

In recent years, there has been an increasing interest in the development of new technologies focused on the deeper integration of MR in radiotherapy. The innovations span from image data acquisition and post‐processing to clinical implementation of MR‐guided RT systems and workflow development. The session is intended to provide a review of the key and most recent advancements. Targeted discussions will cover topics which currently define the concept of MR‐guided radiotherapy including a) system commissioning, quality control and safety, b) MR data manipulation for dose computations and treatment simulation, c) quantification/management of organ motion and treatment delivery guidance.Learning Objectives: Understand the concept and specifics of MR‐guided radiotherapy; Understand the requirements for system integration in clinical workflow; Become familiar with the proposed strategies for system commissioning, RT planning and delivery guidance.

Provider interaction with the electronic health record: The effects on patient-centered communication in medical encounters

ObjectiveThe computer with the electronic health record (EHR) is an additional ‘interactant’ in the medical consultation, as clinicians must simultaneously or in alternation engage patient and computer to provide medical care. Few studies have examined how clinicians’ EHR workflow (e.g., gaze, keyboard activity, and silence) influences the quality of their communication, the patient's involvement in the encounter, and conversational control of the visit. MethodsTwenty-three primary care providers (PCPs) from USA Veterans Administration (VA) primary care clinics participated in the study. Up to 6 patients per PCP were recruited. The proportion of time PCPs spent gazing at the computer was captured in real time via video-recording. Mouse click/scrolling activity was captured through Morae, a usability software that logs mouse clicks and scrolling activity. Conversational silence was coded as the proportion of time in the visit when PCP and patient were not talking. After the visit, patients completed patient satisfaction measures. Trained coders independently viewed videos of the interactions and rated the degree to which PCPs were patient-centered (informative, supportive, partnering) and patients were involved in the consultation. Conversational control was measured as the proportion of time the PCP held the floor compared to the patient. ResultsThe final sample included 125 consultations. PCPs who spent more time in the consultation gazing at the computer and whose visits had more conversational silence were rated lower in patient-centeredness. PCPs controlled more of the talk time in the visits that also had longer periods of mutual silence. ConclusionsPCPs were rated as having less effective communication when they spent more time looking at the computer and when there was more periods of silence in the consultation. Because PCPs increasingly are using the EHR in their consultations, more research is needed to determine effective ways that they can verbally engage patients while simultaneously managing data in the EHR. Practice implicationsEHR activity consumes an increasing proportion of clinicians’ time during consultations. To ensure effective communication with their patients, clinicians may benefit from using communication strategies that maintain the flow of conversation when working with the computer, as well as from learning EHR management skills that prevent extended periods of gaze at computer and long periods of silence. Next-generation EHR design must address better usability and clinical workflow integration, including facilitating patient-clinician communication.