Clinical Decision Support Tool Research Articles

Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography

BackgroundAutomated identification of spectral domain optical coherence tomography (SD-OCT) features can improve retina clinic workflow efficiency as they are able to detect pathologic findings. The purpose of this study was to test a deep learning (DL)-based algorithm for the identification of Idiopathic Full Thickness Macular Hole (IFTMH) features and stages of severity in SD-OCT B-scans.MethodsIn this cross-sectional study, subjects solely diagnosed with either IFTMH or Posterior Vitreous Detachment (PVD) were identified excluding secondary causes of macular holes, any concurrent maculopathies, or incomplete records. SD-OCT scans (512 × 128) from all subjects were acquired with CIRRUS™ HD-OCT (ZEISS, Dublin, CA) and reviewed for quality. In order to establish a ground truth classification, each SD-OCT B-scan was labeled by two trained graders and adjudicated by a retina specialist when applicable. Two test sets were built based on different gold-standard classification methods. The sensitivity, specificity and accuracy of the algorithm to identify IFTMH features in SD-OCT B-scans were determined. Spearman’s correlation was run to examine if the algorithm’s probability score was associated with the severity stages of IFTMH.ResultsSix hundred and one SD-OCT cube scans from 601 subjects (299 with IFTMH and 302 with PVD) were used. A total of 76,928 individual SD-OCT B-scans were labeled gradable by the algorithm and yielded an accuracy of 88.5% (test set 1, 33,024 B-scans) and 91.4% (test set 2, 43,904 B-scans) in identifying SD-OCT features of IFTMHs. A Spearman’s correlation coefficient of 0.15 was achieved between the algorithm’s probability score and the stages of the 299 (47 [15.7%] stage 2, 56 [18.7%] stage 3 and 196 [65.6%] stage 4) IFTMHs cubes studied.ConclusionsThe DL-based algorithm was able to accurately detect IFTMHs features on individual SD-OCT B-scans in both test sets. However, there was a low correlation between the algorithm’s probability score and IFTMH severity stages. The algorithm may serve as a clinical decision support tool that assists with the identification of IFTMHs. Further training is necessary for the algorithm to identify stages of IFTMHs.

Implementation of clopidogrel pharmacogenetic clinical decision support for a preemptive return of results program.

To describe our experiences implementing and iterating CYP2C19 genotype-guided clopidogrel pharmacogenetic clinical decision support (CDS) tools over time in the setting of a large health system-wide, preemptive pharmacogenomics program. Clopidogrel-treated patients who are genetically predicted cytochrome P450 isozyme 2C19 (CYP2C19) intermediate or poor metabolizers have an increased risk of atherothrombotic events, some of which can be life-threatening. The Clinical Pharmacogenetics Implementation Consortium provides guidance for the use of clopidogrel based on CYP2C19 genotype in patients with cardiovascular and cerebrovascular diseases. Our multidisciplinary team implemented an automated, interruptive alert that fires when clopidogrel is ordered or refilled for biobank participants with structured CYP2C19 intermediate or poor metabolizer genomic indicators in the electronic health record. The implementation began with a narrow cardiovascular indication and setting and was then scaled in 4 primary dimensions: (1) clinical indication; (2) availability across health-system locations; (3) care venue (e.g., inpatient vs outpatient); and (4) provider groups (eg, cardiology and neurology). We iterated our approach over time based on evolving clinical evidence and proactive strategies to optimize CDS maintenance and sustainability. A key facilitator of expansion was socialization of the broader pharmacogenomics initiative among our academic medical center community, accompanied by clinician acceptance of pharmacogenetic alerts in practice. A multidisciplinary collaboration is recommended to facilitate the use of CYP2C19 genotype-guided antiplatelet therapy in patients with cardiovascular and cerebrovascular diseases. Evolving clopidogrel pharmacogenetic evidence necessitates thoughtful iteration of implementation efforts and strategies to optimize long-term maintenance and sustainability.

Use of Computerized Physician Order Entry with Clinical Decision Support to Prevent Dose Errors in Pediatric Medication Orders: A Systematic Review.

Prescribing is a high-risk task within the pediatric medication-use process and requires defenses to prevent errors. Such system-centric defenses include electronic health record systems with computerized physician order entry (CPOE) and clinical decision support (CDS) tools that assist safe prescribing. The objective of this study was to examine the effects of CPOE systems with CDS functions in preventing dose errors in pediatric medication orders. This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 criteria and Synthesis Without Meta-Analysis (SWiM) items. The study protocol was registered in PROSPERO (CRD42021277413). The final literature search on MEDLINE (Ovid), Scopus, Web of Science, and EMB Reviews was conducted on 10 September 2023. Only peer-reviewed studies considering both CPOE and CDS systems in pediatric inpatient or outpatient settings were included. Study selection, data extraction, and evidence quality assessment (JBI critical appraisal tool assessment and GRADE approach) were carried out by two individual reviewers. Vote counting method was used to evaluate the effects of CPOE-CDS systems on dose errors rates. A total of 17 studies published in 2007-2021 met the inclusion criteria. The most used CDS tools were dose range check (n = 14), dose calculator (n = 8), and dosing frequency check (n = 8). Alerts were recorded in 15 studies. A statistically significant reduction in dose errors was found in eight studies, whereas an increase of dose errors was not reported. The CPOE-CDS systems have the potential to reduce pediatric dose errors. Most beneficial interventions seem to be system customization, implementing CDS alerts, and the use of dose range check. While human factors are still present within the medication use process, further studies and development activities are needed to optimize the usability of CPOE-CDS systems.

Evaluation of an artificial intelligence-based decision support for the detection of cutaneous melanoma in primary care: a prospective real-life clinical trial.

Use of artificial intelligence (AI), or machine learning, to assess dermoscopic images of skin lesions to detect melanoma has, in several retrospective studies, shown high levels of diagnostic accuracy on par with - or even outperforming - experienced dermatologists. However, the enthusiasm around these algorithms has not yet been matched by prospective clinical trials performed in authentic clinical settings. In several European countries, including Sweden, the initial clinical assessment of suspected skin cancer is principally conducted in the primary healthcare setting by primary care physicians, with or without access to teledermoscopic support from dermatology clinics. To determine the diagnostic performance of an AI-based clinical decision support tool for cutaneous melanoma detection, operated by a smartphone application (app), when used prospectively by primary care physicians to assess skin lesions of concern due to some degree of melanoma suspicion. This prospective multicentre clinical trial was conducted at 36 primary care centres in Sweden. Physicians used the smartphone app on skin lesions of concern by photographing them dermoscopically, which resulted in a dichotomous decision support text regarding evidence for melanoma. Regardless of the app outcome, all lesions underwent standard diagnostic procedures (surgical excision or referral to a dermatologist). After investigations were complete, lesion diagnoses were collected from the patients' medical records and compared with the app's outcome and other lesion data. In total, 253 lesions of concern in 228 patients were included, of which 21 proved to be melanomas, with 11 thin invasive melanomas and 10 melanomas in situ. The app's accuracy in identifying melanomas was reflected in an area under the receiver operating characteristic (AUROC) curve of 0.960 [95% confidence interval (CI) 0.928-0.980], corresponding to a maximum sensitivity and specificity of 95.2% and 84.5%, respectively. For invasive melanomas alone, the AUROC was 0.988 (95% CI 0.965-0.997), corresponding to a maximum sensitivity and specificity of 100% and 92.6%, respectively. The clinical decision support tool evaluated in this investigation showed high diagnostic accuracy when used prospectively in primary care patients, which could add significant clinical value for primary care physicians assessing skin lesions for melanoma.

Trust in Machine Learning Driven Clinical Decision Support Tools Among Otolaryngologists.

Machine learning driven clinical decision support tools (ML-CDST) are on the verge of being integrated into clinical settings, including in Otolaryngology-Head & Neck Surgery. In this study, we investigated whether such CDST may influence otolaryngologists' diagnostic judgement. Otolaryngologists were recruited virtually across the United States for this experiment on human-AI interaction. Participants were shown 12 different video-stroboscopic exams from patients with previously diagnosed laryngopharyngeal reflux or vocal fold paresis and asked to determine the presence of disease. They were then exposed to a random diagnosis purportedly resulting from an ML-CDST and given the opportunity to revise their diagnosis. The ML-CDST output was presented with no explanation, a general explanation, or a specific explanation of its logic. The ML-CDST impact on diagnostic judgement was assessed with McNemar's test. Forty-five participants were recruited. When participants reported less confidence (268 observations), they were significantly (p = 0.001) more likely to change their diagnostic judgement after exposure to ML-CDST output compared to when they reported more confidence (238 observations). Participants were more likely to change their diagnostic judgement when presented with a specific explanation of the CDST logic (p = 0.048). Our study suggests that otolaryngologists are susceptible to accepting ML-CDST diagnostic recommendations, especially when less confident. Otolaryngologists' trust in ML-CDST output is increased when accompanied with a specific explanation of its logic. 2 Laryngoscope, 134:2799-2804, 2024.

Clinical Needs Assessment of a Machine Learning-Based Asthma Management Tool: User-Centered Design Approach.

Personalized asthma management depends on a clinician's ability to efficiently review patient's data and make timely clinical decisions. Unfortunately, efficient and effective review of these data is impeded by the varied format, location, and workflow of data acquisition, storage, and processing in the electronic health record. While machine learning (ML) and clinical decision support tools are well-positioned as potential solutions, the translation of such frameworks requires that barriers to implementation be addressed in the formative research stages. We aimed to use a structured user-centered design approach (double-diamond design framework) to (1) qualitatively explore clinicians' experience with the current asthma management system, (2) identify user requirements to improve algorithm explainability and Asthma Guidance and Prediction System prototype, and (3) identify potential barriers to ML-based clinical decision support system use. At the "discovery" phase, we first shadowed to understand the practice context. Then, semistructured interviews were conducted digitally with 14 clinicians who encountered pediatric asthma patients at 2 outpatient facilities. Participants were asked about their current difficulties in gathering information for patients with pediatric asthma, their expectations of ideal workflows and tools, and suggestions on user-centered interfaces and features. At the "define" phase, a synthesis analysis was conducted to converge key results from interviewees' insights into themes, eventually forming critical "how might we" research questions to guide model development and implementation. We identified user requirements and potential barriers associated with three overarching themes: (1) usability and workflow aspects of the ML system, (2) user expectations and algorithm explainability, and (3) barriers to implementation in context. Even though the responsibilities and workflows vary among different roles, the core asthma-related information and functions they requested were highly cohesive, which allows for a shared information view of the tool. Clinicians hope to perceive the usability of the model with the ability to note patients' high risks and take proactive actions to manage asthma efficiently and effectively. For optimal ML algorithm explainability, requirements included documentation to support the validity of algorithm development and output logic, and a request for increased transparency to build trust and validate how the algorithm arrived at the decision. Acceptability, adoption, and sustainability of the asthma management tool are implementation outcomes that are reliant on the proper design and training as suggested by participants. As part of our comprehensive informatics-based process centered on clinical usability, we approach the problem using a theoretical framework grounded in user experience research leveraging semistructured interviews. Our focus on meeting the needs of the practice with ML technology is emphasized by a user-centered approach to clinician engagement through upstream technology design.

Implementing a Clinical Decision Support Tool to Improve Physical Activity.

Currently, only about half of U.S. adults achieve current physical activity guidelines. Routine physical activity is not regularly assessed, nor are patients routinely counseled by their healthcare provider on achieving recommended levels. The three-question physical activity vital sign (PAVS) was developed to assess physical activity duration and intensity and identify adults not meeting physical activity guidelines. Clinical decision support provided via a best practice advisory in an electronic health record (EHR) system can be triggered as a prompt, reminding healthcare providers to implement the best practice intervention when appropriate. Remote patient monitoring of physical activity can provide objective data in the EHR. This study aimed to evaluate the feasibility and clinical utility of embedding the PAVS and a triggered best practice advisor into the EHR in an ambulatory preventive cardiology practice setting to alert providers to patients reporting low physical activity and prompt healthcare providers to counsel these patients as needed. Three components based in the EHR were integrated for the purpose of this study: Patients completed the PAVS through their electronic patient portal prior to an office visit, a best practice advisory was created to prompt providers to counsel patients who reported low levels of physical activity, and remote patient monitoring via Fitbit synced to the EHR provided objective physical activity data. The intervention was pilot-tested in the Epic EHR for 1 year (July 1, 2021 to June 30, 2022). Qualitative feedback on the intervention from both providers and patients was obtained at the completion of the study. Monthly assessments of the use of the PAVS and best practice advisory and remote patient monitoring were completed. Patients' completion of the PAVS varied from 35% to 48% per month. The best practice advisory was signed by providers between 2% and 65% and was acknowledged by 2%-22% per month. The majority (58%) of patients were able to sync a Fitbit device to their EHR for remote monitoring. Although uptake of each component needs improvement, this pilot demonstrated the feasibility of incorporating a physical activity promotion intervention into the EHR. Qualitative feedback provided guidance for future implementation.

Population-Level Portal-Based Anxiety and Depression Screening Perspectives in HIV Care Clinicians: Qualitative Study Using the Consolidated Framework for Implementation Research.

Depression and anxiety are common among people with HIV and are associated with inadequate viral suppression, disease progression, and increased mortality. However, depression and anxiety are underdiagnosed and undertreated in people with HIV owing to inadequate visit time and personnel availability. Conducting population-level depression and anxiety screening via the patient portal is a promising intervention that has not been studied in HIV care settings. We aimed to explore facilitators of and barriers to implementing population-level portal-based depression and anxiety screening for people with HIV. We conducted semistructured hour-long qualitative interviews based on the Consolidated Framework for Implementation Research with clinicians at an HIV clinic. A total of 10 clinicians participated in interviews. In total, 10 facilitators and 7 barriers were identified across 5 Consolidated Framework for Implementation Research domains. Facilitators included advantages of systematic screening outside clinic visits; the expectation that assessment frequency could be tailored to patient needs; evidence from the literature and previous experience in other settings; respect for patient privacy; empowering patients and facilitating communication about mental health; compatibility with clinic culture, workflows, and systems; staff beliefs about the importance of mental health screening and benefits for HIV care; engaging all clinic staff and leveraging their strengths; and clear planning and communication with staff. Barriers included difficulty in ensuring prompt response to suicidal ideation; patient access, experience, and comfort using the portal; limited availability of mental health services; variations in how providers use the electronic health record and communicate with patients; limited capacity to address mental health concerns during HIV visits; staff knowledge and self-efficacy regarding the management of mental health conditions; and the impersonal approach to a sensitive topic. We proposed 13 strategies for implementing population-level portal-based screening for people with HIV. Before implementation, clinics can conduct local assessments of clinicians and clinic staff; engage clinicians and clinic staff with various roles and expertise to support the implementation; highlight advantages, relevance, and evidence for population-level portal-based mental health screening; make screening frequency adaptable based on patient history and symptoms; use user-centered design methods to refine results that are displayed and communicated in the electronic health record; make screening tools available for patients to use on demand in the portal; and create protocols for positive depression and anxiety screeners, including those indicating imminent risk. During implementation, clinics should communicate with clinicians and clinic staff and provide training on protocols; provide technical support and demonstrations for patients on how to use the portal; use multiple screening methods for broad reach; use patient-centered communication in portal messages; provide clinical decision support tools, training, and mentorship to help clinicians manage mental health concerns; and implement integrated behavioral health and increase mental health referral partnerships.

An Introduction to Clinical Informatics for Early Medical Learners Using Colorectal Cancer Screening.

Clinical informatics is an important component of the AMA-endorsed third pillar of undergraduate medical education, health systems science. Discrete educational opportunities for clinical informatics and health systems science among early learners are lacking in medical school curricula. We developed and evaluated a multistep, 2.5-hour activity during the gastroenterology module to introduce these topics to preclerkship medical students. A didactic session introducing clinical informatics and clinical decision support and reviewing health promotion and screening concepts was followed by small-group activities. Students worked through a series of exercises culminating in the generation of a clinical decision support tool based on the United States Preventive Services Task Force (USPSTF) colorectal cancer screening recommendations. Between 2022 and 2023, 326 first-year medical students participated in this workshop. Feedback was predictably mixed. In 2022, 88% of postclass survey respondents confirmed having a better clinical informatics understanding after the workshop. In 2023, students reported a statistically significant increase in their self-reported understanding of the role of clinical informatics, clinical decision support, and USPSTF colorectal cancer recommendations. Clinical decision support is a viable pathway for introduction of clinical informatics, health systems science, and public health/prevention topics. Our educational approach offers an interactive introduction to this group of topics that can benefit future physicians. While colon cancer provides a robust option for the clinical situation, this activity could be modified to fit into many different clinical scenarios, allowing for interdisciplinary education during either undergraduate or graduate medical education.

Impact of point-of-care clinical decision support on referrer behavior, imaging volume, patient radiation dose exposure, and sustainability

ObjectivesWhen referring patients to radiology, it is important that the most appropriate test is chosen to avoid inappropriate imaging that may lead to delayed diagnosis, unnecessary radiation dose, worse patient outcome, and poor patient experience. The current radiology appropriateness guidance standard at our institution is via access to a standalone web-based clinical decision support tool (CDST). A point-of-care (POC) CDST that incorporates guidance directly into the physician workflow was implemented within a subset of head and neck cancer specialist referrers. The purpose of this audit was to evaluate the imaging pathway, pre- and post-implementation to assess changes in referral behavior.MethodsCT and MRI neck data were collected retrospectively to examine the relationship between imaging referrals pre- and post-POC CDST implementation. Effective radiation dose and estimated carbon emissions were also compared.ResultsThere was an overall reduction in absolute advanced imaging volume by 8.2%, and a reduction in duplicate CT and MRI imaging by 61%, p < 0.0001. There was also a shift in ordering behavior in favor of MRI (OR [95% CI] = 1.50 [1.02–2.22], p = 0.049). These changes resulted in an effective radiation dose reduction of 0.27 mSv per patient, or 13 equivalent chest x-rays saved per patient, p < 0.0001. Additionally, the reduction in unnecessary duplicate imaging led to a 13.5% reduction in carbon emissions, p = 0.0002.ConclusionsImplementation of the POC CDST resulted in a significant impact on advanced imaging volume, saved effective dose, and reduction in carbon emissions.Critical relevance statementThe implementation of a point-of-care clinical decision support tool may reduce multimodality ordering and advanced imaging volume, manifesting in reduced effective dose per patient and reduced estimated carbon emissions. Widespread utilization of the point-of-care clinical decision support tool has the potential to reduce imaging wait times.Key points• Implementation of the point-of-care clinical decision support tool reduced the number of patients who simultaneously had a CT and MRI ordered for the same clinical indication compared to a standalone web-based clinical decision support tool.• The point-of-care clinical decision support tool reduced the absolute number of CT/MRI scans requested compared to the standalone web-based clinical decision support tool.• Utilization of the point-of-care clinical decision support tool led to a significant reduction in the effective dose per patient compared to the standalone web-based clinical decision support tool.Graphical

The role of rapid syndromic diagnostic testing of gastrointestinal pathogens as a clinical decision support tool in a pediatric emergency department

PurposeThis study aimed to investigate the role of rapid syndromic diagnostic testing of gastrointestinal pathogens as a clinical decision support tool in a pediatric emergency department (ED) by comparing clinical decision and patient outcome parameters pre- and post-implementation.MethodsThis was a big data analytical study of children < 18 years old without any underlying diseases, that visited the ED with acute moderate to severe diarrhea during a 34-month period from 2018 to 2022 using Seoul St. Mary’s hospital’s healthcare corporate data warehouse to retrieve demographic, clinical, and laboratory parameters. Outcome measures pre- and post-implementation of a rapid syndromic multiplex gastrointestinal panel (GI panel) were compared.ResultsA total of 4,184 patients’ data were included in the analyses. Broad spectrum antibiotics were prescribed at a significantly lower rate to patients presenting with acute infectious diarrhea at discharge from the ED (9.9% vs 15.8%, P < 0.001) as well as upon admission (52.2% vs 66.0%, P < 0.001) during the post-implementation period compared to the pre-implementation period. Although the duration of ED stay was found to be significantly longer (6.5 vs 5.5 h, P < 0.0001), the rate of ED revisit due to persistent or aggravated symptoms was significantly lower (Δ in intercept, β = -0.027; SE = 0.013; P = 0.041), and the admission rate at follow up after being discharged from the ED shown to be significantly lower during the post-implementation period compared to the pre-implementation period (0.8% vs. 2.1%, P = 0.001, respectively). No significant difference in disease progression was observed (P = 1.000).ConclusionUsing the GI panel in the ED was shown to decrease broad spectrum antibiotic prescribing practices and reduce revisits or admission at follow up by aiding clinical decisions and improving patient outcome.

Collecting electronic health record (EHR) to support holistic spa therapy as a diagnostic procedure for advance care planning (ACP): a literature review

Developing technology and collecting electronic information are fostering the creation of new procedures and clinical decision-support tools for therapy in rehabilitation hospitals and spa resorts. Electronic health records (EHR) does not take into account the complementarity of activities with the need for effective patient care in rehabilitation and sanatorium hospitals and spas. This paper aims to present a proposal for a complementary electronic anamnestic tool (CEAT) in a holistic approach to the patient's prevention and rehabilitation process in a rehabilitation hospital or a spa resort using EHRs that will be effective in ACP. To achieve the objective thus formulated, the literature was reviewed and thoroughly analyzed in terms of stratification and classification of the tools using EHRs. designed CEAT tool consists of a history of physical status (weight, height, waist circumference), neurological incidents, cardiovascular disorders, past treatments/surgeries, psychiatric disorders, and level of daily physical activity, supplemented by survey questionnaires selected in a literature review based on their widespread usefulness supported by scientific evidence. The questionnaires included in CEAT allow for a multifaceted assessment of the patient's health status, taking into account their physical state, functional capacity, and well-being.

Application of a user experience design approach for an EHR-based clinical decision support system.

We applied a user experience (UX) design approach to clinical decision support (CDS) tool development for the specific use case of pediatric asthma. Our objective was to understand physicians' workflows, decision-making processes, barriers (ie, pain points), and facilitators to increase usability of the tool. We used a mixed-methods approach with semi-structured interviews and surveys. The coded interviews were synthesized into physician-user journey maps (ie, visualization of a process to accomplish goals) and personas (ie, user types). Interviews were conducted via video. We developed physician journey maps and user personas informed by their goals, systems interactions, and experiences with pediatric asthma management. The physician end-user personas identified were: efficiency, relationship, and learning. Features of a potential asthma CDS tool sought varied by physician practice type and persona. It was important to the physician end-user that the asthma CDS tool demonstrate value by lowering workflow friction (ie, difficulty or obstacles), improving the environment surrounding physicians and patients, and using it as a teaching tool. Customizability versus standardization were important considerations for uptake. Different values and motivations of physicians influence their use and interaction with the EHR and CDS tools. These different perspectives can be captured by applying a UX design approach to the development process. For example, with the importance of customizability, one approach may be to build a core module with variations depending on end-user preference. A UX approach can drive design to help understand physician-users and meet their needs; ultimately with the goal of increased uptake.

Qualitative Assessment of a Smartphone-Based Mobile Health Tool to Guide Diarrhea Management in Bangladesh.

Diarrheal diseases are a major cause of morbidity and mortality in children worldwide and a significant contributor to antimicrobial resistance. In the absence of laboratory diagnostics to establish diarrhea etiology, electronic clinical decision support tools can help physicians make informed treatment decisions for children with diarrhea. In Bangladesh, we assessed the feasibility and acceptability of an electronic Diarrhea Etiology Prediction algorithm (DEP tool) embedded into a rehydration calculator, which was designed to help physicians manage children with diarrhea, including decisions on antibiotic use. A team of Bangladeshi anthropologists conducted in-depth interviews with physicians (N = 13) in three public hospitals in Bangladesh about their experience using the tool in the context of a pilot trial. Physicians expressed positive opinions of the DEP tool. Participants perceived the tool to be simple and easy to use, with structured guidance on collecting and entering clinical data from patients. Significant strengths of the tool were as follows: standardization of protocol, efficiency of clinical decision-making, and improved clinical practice. Participants also noted barriers that might restrict the widespread impact of the tool, including physicians' reluctance to use an electronic tool for clinical decision-making, increasing work in overburdened healthcare settings, unavailability of a smartphone, and patients' preferences for antibiotics. We conclude that an electronic clinical decision support tool is a promising method for improving diarrheal management and antibiotic stewardship. Future directions include developing and implementing such a tool for informal healthcare physicians in low-resource settings, where families may first seek care for pediatric diarrhea.

Clinical decision support to enhance venous thromboembolism pharmacoprophylaxis prescribing for pediatric inpatients with COVID-19.

To design and evaluate a clinical decision support (CDS) module to improve guideline concordant venous thromboembolism (VTE) pharmacoprophylaxis prescribing for pediatric inpatients with COVID-19. The proportion of patients who met our institutional clinical practice guideline's (CPG) criteria for VTE prophylaxis was compared to those who triggered a CDS alert, indicating the patient needed VTE prophylaxis, and to those who were prescribed prophylaxis pre and post the launch of a new VTE CDS module to support VTE pharmacoprophylaxis prescribing. The sensitivity, specificity, positive predictive value (PPV), negative predictive value, F1-score and accuracy of the tool were calculated for the pre- and post-intervention periods using the CPG recommendation as the gold standard. Accuracy was defined as the sum of the true positives and true negatives over the sum of the true positives, false positives, true negatives, and false negatives. Logistic regression was used to identify variables associated with correct thromboprophylaxis prescribing. A significant increase in the proportion of patients triggering a CDS alert occurred in the post-intervention period (44.3% vs. 6.9%, p<.001); however, no reciprocal increase in VTE prophylaxis prescribing was achieved (36.6% vs. 40.9%, p=.53). The updated CDS module had an improved sensitivity (55.0% vs. 13.3%), NPV (44.9% vs. 36.3%), F1-score (66.7% vs. 23.5%), and accuracy (62.5% vs. 42.0%), but an inferior specificity (78.6% vs. 100%) and PPV (84.6% vs. 100%). The updated CDS model had an improved accuracy and overall performance in correctly identifying patients requiring VTE prophylaxis. Despite an increase in correct patient identification by the CDS module, the proportion of patients receiving appropriate pharmacologic prophylaxis did not change. CDS tools to support correct VTE prophylaxis prescribing need ongoing refinement and validation to maximize clinical utility.

A decade of clinical microbiology: top 10 advances in 10 years: what every infection preventionist and antimicrobial steward should know.

The past 10 years have brought paradigm-shifting changes to clinical microbiology. This paper explores the top 10 transformative innovations across the diagnostic spectrum, including not only state of the art technologies but also preanalytic and post-analytic advances. Clinical decision support tools have reshaped testing practices, curbing unnecessary tests. Innovations like broad-range polymerase chain reaction and metagenomic sequencing, whole genome sequencing, multiplex molecular panels, rapid phenotypic susceptibility testing, and matrix-assisted laser desorption ionization time-of-flight mass spectrometry have all expanded our diagnostic armamentarium. Rapid home-based testing has made diagnostic testing more accessible than ever. Enhancements to clinician-laboratory interfaces allow for automated stewardship interventions and education. Laboratory restructuring and consolidation efforts are reshaping the field of microbiology, presenting both opportunities and challenges for the future of clinical microbiology laboratories. Here, we review key innovations of the last decade.

Standardizing Medication Reconciliation in a Pediatric Emergency Department.

Medication errors are common during transitions of care, such as discharge from the emergency department (ED) or urgent care (UC). The Joint Commission has identified medication reconciliation as a key safety practice. Our aim was to increase the percentage of patients with completed medication reconciliation at discharge from our pediatric ED and 4 UCs from 25% to 75% in 12 months. Key stakeholders included ED and UC physicians and nurses, informatics, and quality management. The baseline process for medication reconciliation was mapped and modified to create a standard process for nurses and physicians. An Ishikawa diagram was created to assess potential failures. Electronic health record interventions included adapting an inpatient workflow and using a clinical decision support tool. Educational interventions included just-in-time training, physician education via division meeting presentations, video tutorials, and physician-specific and group feedback using funnel plots. The secondary process measure was the proportion of patients discharged from the ED and UCs with completed home medication nursing review. We used statistical process control to analyze changes in measures over time. In the UCs, home medication nursing review increased from 91% to 98% and medication reconciliation increased from 35% to 82% within 4 months. In the ED, home medication nursing review increased from 2% to 83% within 8 months and medication reconciliation increased from 26% to 64% within 18 months. We successfully increased the proportion of UC and ED discharged patients with completed medication reconciliation.

Role of machine learning in the management of epilepsy: a systematic review protocol

IntroductionMachine learning is a rapidly expanding field and is already incorporated into many aspects of medicine including diagnostics, prognostication and clinical decision-support tools. Epilepsy is a common and disabling neurological...

Technological Innovations to Improve Patient Engagement in Nephrology.

Technological innovation has accelerated exponentially over the last 2decades. From the rise of smartphones and social media in the early 2000s to the mainstream accessibility of artificial intelligence (AI) in 2023, digital advancements have transformed the way we live and work. These innovations have permeated health care, covering a spectrum of applications from virtual reality training platforms to AI-powered clinical decision support tools. In this review, we explore fascinating recent innovations that have and can facilitate patient engagement in nephrology. These include integrated care mobile applications, wearable health monitoring tools, virtual/augmented reality consultation and education platforms, AI-powered appointment booking systems, and patient information tools. We also discuss potential pitfalls in implementation and paradigms to adopt that may protect patients from unintended consequences of being cared for in a digitalized health care system.

A deep learning approach using an ensemble model to autocreate an image-based hip fracture registry.

With more than 300,000 patients per year in the United States alone, hip fractures are one of the most common injuries occurring in the elderly. The incidence is predicted to rise to 6 million cases per annum worldwide by 2050. Many fracture registries have been established, serving as tools for quality surveillance and evaluating patient outcomes. Most registries are based on billing and procedural codes, prone to under-reporting of cases. Deep learning (DL) is able to interpret radiographic images and assist in fracture detection; we propose to conduct a DL-based approach intended to autocreate a fracture registry, specifically for the hip fracture population. Conventional radiographs (n = 18,834) from 2919 patients from Massachusetts General Brigham hospitals were extracted (images designated as hip radiographs within the medical record). We designed a cascade model consisting of 3 submodules for image view classification (MI), postoperative implant detection (MII), and proximal femoral fracture detection (MIII), including data augmentation and scaling, and convolutional neural networks for model development. An ensemble model of 10 models (based on ResNet, VGG, DenseNet, and EfficientNet architectures) was created to detect the presence of a fracture. The accuracy of the developed submodules reached 92%-100%; visual explanations of model predictions were generated through gradient-based methods. Time for the automated model-based fracture-labeling was 0.03 seconds/image, compared with an average of 12 seconds/image for human annotation as calculated in our preprocessing stages. This semisupervised DL approach labeled hip fractures with high accuracy. This mitigates the burden of annotations in a large data set, which is time-consuming and prone to under-reporting. The DL approach may prove beneficial for future efforts to autocreate construct registries that outperform current diagnosis and procedural codes. Clinicians and researchers can use the developed DL approach for quality improvement, diagnostic and prognostic research purposes, and building clinical decision support tools.