Average Clinician Research Articles

The drug titration paradox: a control engineering perspective.

The drug titration paradox describes that, from a population standpoint, drug doses appear to have a negative correlation with its clinical effect. This paradox is a relatively modern discovery in anesthetic pharmacology derived from large clinical data sets. This review will interpret the paradox using a control engineering perspective. Drug titration is a challenging endeavor, and the medication delivery systems used in everyday clinical practice, including infusion pumps and vaporizers, typically do not allow for rapid or robust titration of medication being delivered. In addition, clinicians may be reluctant to deviate from a predetermined plan or may be content to manage patients within fixed goal boundaries. This drug titration paradox describes the constraints of how the average clinician will dose a patient with an unknown clinical response. While our understanding of the paradox is still in its infancy, it remains unclear how alternative dosing schemes, such as through automation, may exceed the boundaries of the paradox and potentially affect its conclusions.

The extended impact of co-designed personalised aids for people living with chronic conditions: an exploratory study in a healthcare setting

Assistive technology has great potential to help individuals living with chronic health conditions, however devices often fail to align with the unique requirements of users. These results in device abandonment and missed opportunities to benefit people. This exploratory study aims to evaluate the short and longer-term satisfaction, psychological benefit, use and resources involved in co-designed customised assistive devices within a current healthcare service. Individuals with chronic health conditions identified daily living challenges. Eleven individuals completed the trial and were involved throughout the design process. Outcome measures evaluated the impact of the devices provided, healthcare utilisation, help required, and resources used. Nineteen custom assistive devices were produced for twenty-four challenges in daily living identified. At 3-months, eighteen devices were still being used. Daily challenges had become easier for individuals to complete and required less help from informal carers. Individuals were satisfied with the devices and service provided. Improvements in competence, adaptability and self-esteem were sustained long-term. The average clinician’s time required to produce a device was 5 h 55 min, with an average cost of £203.79. People with chronic conditions were able to benefit from the co-design process resulting in satisfaction and long-term utilisation of the device, and positive psycho-social benefits. The costs associated with embedding this approach in a healthcare service were calculated. Scaling up the co-design process reduced the associated costs per device compared to previous work. Further work is required to evaluate co-designing across larger samples and explore opportunities to further improve the cost-efficiency.

A Proof-of-Concept Computer Vision Approach for Measurement of Tympanic Membrane Perforations.

Size, an important characteristic of a tympanic membrane perforation (TMP), is commonly assessed with gross estimation via visual inspection, a practice which is prone to inaccuracy. Herein, we demonstrate feasibility of a proof-of-concept computer vision model for estimating TMP size in a small set of perforations. An open-source deep learning architecture was used to train a model to segment and calculate the area of a perforation and the visualized tympanic membrane (TM) in a set of endoscopic images of mostly anterior and relatively small TMPs. The model then computed relative TMP size by calculating the ratio of perforation area to TM area. Model performance on the test dataset was compared to ground-truth manual annotations. In a validation survey, otolaryngologists were tasked with estimating the size of TMPs from the test dataset. The primary outcome was the average absolute error of model size predictions and clinician estimates compared to sizes determined by ground-truth manual annotations. The model's average absolute error for size predictions was a 0.8% overestimation for all test perforations. Conversely, among the 38 survey respondents, the average clinician error was a 11.0% overestimation (95% CI, 5.2-16.7%, p = 0.003). In a small sample of TMPs, we demonstrated a computer vision approach for estimating TMP size is feasible. Further validation studies must be done with significantly larger and more heterogenous datasets. N/A Laryngoscope, 134:2906-2911, 2024.

Deep Learning Algorithms to Detect Murmurs Associated With Structural Heart Disease.

Background The success of cardiac auscultation varies widely among medical professionals, which can lead to missed treatments for structural heart disease. Applying machine learning to cardiac auscultation could address this problem, but despite recent interest, few algorithms have been brought to clinical practice. We evaluated a novel suite of Food and Drug Administration-cleared algorithms trained via deep learning on >15 000 heart sound recordings. Methods and Results We validated the algorithms on a data set of 2375 recordings from 615 unique subjects. This data set was collected in real clinical environments using commercially available digital stethoscopes, annotated by board-certified cardiologists, and paired with echocardiograms as the gold standard. To model the algorithm in clinical practice, we compared its performance against 10 clinicians on a subset of the validation database. Our algorithm reliably detected structural murmurs with a sensitivity of 85.6% and specificity of 84.4%. When limiting the analysis to clearly audible murmurs in adults, performance improved to a sensitivity of 97.9% and specificity of 90.6%. The algorithm also reported timing within the cardiac cycle, differentiating between systolic and diastolic murmurs. Despite optimizing acoustics for the clinicians, the algorithm substantially outperformed the clinicians (average clinician accuracy, 77.9%; algorithm accuracy, 84.7%.) Conclusions The algorithms accurately identified murmurs associated with structural heart disease. Our results illustrate a marked contrast between the consistency of the algorithm and the substantial interobserver variability of clinicians. Our results suggest that adopting machine learning algorithms into clinical practice could improve the detection of structural heart disease to facilitate patient care.

Osteoporosis prediction in lumbar spine X-ray images using the multi-scale weighted fusion contextual transformer network

Osteoporosis is a bone-related disease characterized by decreased bone density and mass, leading to brittle fractures. Osteoporosis assessment from radiographs using a deep learning algorithm has proven a low-cost alternative to the golden standard DXA. Due to the considerable noise and low contrast, automated diagnosis of osteoporosis in X-ray images still poses a significant challenge for traditional diagnostic methods. In this paper, an end-to-end transformer-style network was proposed, termed FCoTNet, to overcome the shortcoming of insufficient fusion of texture information and local features in the traditional CoTNet. To extract complementary geometric representations at each scale of the transformer module, we integrated parallel multi-scale feature extraction architectures in each unit layer of FCoTNet to utilize convolution to aggregate features from different receptive fields. Moreover, in order to extract small-scale texture features which were more critical to the diagnosis of osteoporosis in radiographs, larger fusion weights were assigned to the feature maps with small-size receptive fields. Afterward, the multi-scale global modeling was conducted by self-attention mechanism. The proposed model was first investigated on a private lumbar spine X-ray dataset with the 5-fold cross-validation strategy, obtaining an average accuracy of 78.29 ± 0.93 %, an average sensitivity of 69.72 ± 2.35 %, and an average specificity of 88.92 ± 0.67 % for the multi-classification of normal, osteopenia, and osteoporosis categories. We then conducted a controlled trial with five orthopedic clinicians to evaluate the clinical value of the model. The average clinician's accuracy improved from 61.50 ± 10.79 % unaided to 80.00 ± 5.92 % aided (18.50 % improvement), sensitivity improved from 64.38 ± 8.07 % unaided to 83.31 ± 5.43 % aided (18.93 % improvement), and specificity improved from 80.11 ± 4.72 % unaided to 89.94 ± 3.82 % aided (9.83 % improvement). Meanwhile, the prediction consistency among clinicians significantly improved with the assistance of FCoTNet. Furthermore, the proposed model showed good robustness on an external test dataset. These investigations indicate that the proposed deep learning model achieves state-of-the-art performance for osteoporosis prediction, which substantially improves osteoporosis screening and reduced osteoporosis fractures.

ATA2023Annual Conference & ExpoMarch 4–6, 2023San Antonio, Texas

ATA2023Annual Conference & ExpoMarch 4–6, 2023San Antonio, Texas

Effect of Integrating Access to a Prescription Drug Monitoring Program Within the Electronic Health Record on the Frequency of Queries by Primary Care Clinicians

Tools that are directly integrated with the electronic health record (EHR) workflow can reduce the hassle cost of certain guideline-concordant practices, such as querying a prescription drug monitoring program (PDMP) before prescribing opioids. To investigate the effect of integrating access to a PDMP within the EHR on the frequency of program queries by primary care clinicians. The PRINCE (Prescribing Interventions for Chronic Pain Using the Electronic Health Record) randomized trial used a factorial cluster design at the clinic level in 43 primary care clinics in Minnesota. In all, 309 clinicians participated; 161 clinicians were given EHR-integrated access to PDMP at the intervention clinics, and 148 clinicians had the usual access at the control clinics. The intervention went live on August 27, 2020, and data were collected through March 3, 2021. Single sign-on access to the Minnesota PDMP was integrated into the EHR, allowing clinicians to query a patient's controlled substance prescription and dispensing history as recorded in the Minnesota PDMP directly from the patient's EHR record without logging into a separate web portal. Additionally, the integration tool alerted clinicians and reminded them to review the PDMP if a patient had 3 or more opioid prescriptions in the past year and 1 or more in the past 6 months. Clinics in the control group did not receive access to the EHR-integrated PDMP tool; instead, these participants logged into the PDMP web portal separately. Monthly PDMP query counts for primary care clinicians, overall and by modality (EHR-based, web-based, via a clinical delegate), adjusted for clinician characteristics, including type (physician, nurse practitioner, physician assistant), sex, and years in practice. Data were analyzed from August 2021 to May 2022. Of the 43 participating clinics with 309 clinicians, 21 clinics with 161 clinicians (102 [63.4%] women; 114 [70.8%] physicians; tenure, 10.6 [4.4] years) received the PDMP integration intervention. Baseline unadjusted monthly PDMP query rates for the average clinician were 6.6 (95% CI, 4.4-9.9) vs 8.8 (95% CI, 6.0-13.1) queries in the control vs the PDMP integration group, respectively. During the intervention, PDMP query rates for the average clinician were 6.9 (95% CI, 4.7-10.3) vs 14.8 (95% CI, 10.0-22.0) queries among the control vs the PDMP integration group, respectively. Compared with the control group, the EHR-integrated PDMP tool produced a 60% greater increase in the relative change in monthly PDMP queries (95% CI, 51%-70%). An increase in PDMP queries via the EHR-integrated PDMP tool drove this increase, while web-based and delegate queries declined by 39% more among the intervention compared with the control group (95% CI, 34%-43%). This cluster randomized clinical trial found that integrating access to the PDMP in the EHR increased PDMP-querying rates, suggesting that direct access reduced hassle costs and can dramatically improve adherence to guideline-concordant care practices among primary care clinicians. ClinicalTrials.gov Identifier: NCT04601506.

The effect of Medicaid expansion on Medicaid participation, payer mix, and labor supply in primary care

Evidence of increased health care utilization associated with the Medicaid expansion suggests that clinicians increased capacity to meet demand. However, little is known about the mechanism underlying this response. Using a novel source of all-payer data, we quantified clinicians’ response to the Medicaid expansion – examining whether and how they changed their Medicaid participation decisions, payer mix, and overall labor supply. Primary care clinicians in expansion states provided an average of 49 additional appointments per year (a 21% relative increase) for patients insured by Medicaid, compared to clinicians in non-expansion states - with new-patient visits representing half (25 appointments) of this overall increase. Clinicians did not increase their labor supply to accommodate these additional appointments. They instead offset the 1.7 percentage point average increase in Medicaid payer mix with an equivalent reduction in commercial payer mix. However, this reduction in commercial patient share represented only a 2.8% relative decrease, with commercially insured patients still comprising the majority of the average clinician's patient panel. Subsample analyses revealed a larger increase in care for Medicaid patients among clinicians with high Medicaid participation preceding the eligibility expansion.

How trustworthy guidelines can impact outcomes.

If developed using rigorous methods and produced in a timely manner, clinical practice guidelines have the potential to improve patient outcomes. Although the COVID-19 pandemic has highlighted the challenges involved in generating reliable clinical guidance, it has also provided an opportunity to address these challenges. New research addressing drugs for COVID-19 is being produced at unprecedented rates. Incorporating this new knowledge into patient care can be daunting for the average clinician. In collaboration with the BMJ and MAGIC, the WHO has developed a living guideline initiative with the goal of providing rapid and trustworthy clinical guidance in response to practice-changing evidence. As new evidence becomes available, it is incorporated into a living network meta-analysis that informs these guidelines, which are iteratively updated. Until this point, the group has generated guidelines addressing the use of corticosteroids, remdesivir, hydroxychloroquine, lopinavir/ritonavir, and ivermectin for COVID-19. We provide an example of how rapid and rigorous guidelines can be accomplished, even in the setting of a pandemic, capitalizing on expertise, large and dedicated teams, and focused scope. We highlight the benefits of multifaceted knowledge dissemination through multiple formats to ensure global dissemination and in order to maximize impact.

Invasive Hemodynamic and Metabolic Evaluation of HFpEF.

Heart failure with preserved ejection fraction (HFpEF) is a complex and heterogeneous condition of multiple causes, characterized by a clinical syndrome resulting from elevated left ventricular filling pressures, with an apparently unimpaired left ventricular systolic function. Although HFpEF has been long recognized as a distinct entity with significant morbidity for patients, its diagnosis remains challenging to this day. In recent years, few diagnostic algorithms have been postulated to aid in the identification of this condition. Invasive hemodynamic and metabolic evaluation is often warranted for the conclusive diagnosis and risk stratification of HFpEF, in patients presenting with undifferentiated DOE. Rest and provoked hemodynamics remain the golden-standard diagnostic tool to unequivocally confirm the diagnosis of both established and incipient HFpEF, respectively. Cycle exercise hemodynamics is the paramount provocative maneuver to unveil this condition. Rapid saline loading does not offer a significant benefit over that of cycle exercise. Vasoactive agents can also uncover and confirm incipient HFpEF disease. The role of metabolic evaluation in patients presenting with idiopathic dyspnea on exertion (DOE) is of unparalleled value for those who have expertise in cardiopulmonary exercise test (CPET) interpretation; however, the average clinician who focuses solely on oxygen consumption will find it underwhelming. Invasive CPET stands alone as the ultimate diagnostic tool to discriminate between pulmonary, cardiovascular, and skeletal muscle disorders, and their respective contribution to DOE and exercise intolerance. Several hemodynamic and metabolic parameters have demonstrated not only strong diagnostic value, but also predictive power in HFpEF. Additionally, these diagnostic methods have given rise to several therapeutic interventions that are now part of our clinical armamentarium. Regrettably, due to the heterogeneity and multicausality of HFpEF, none of the targeted interventions have been so far successful in decreasing the mortality burden of this prevalent condition.

The management of concussion in sport is not standardized. A systematic review

Introduction: Concussion is traumatic brain injury with associated tissue damage commonly produced by an indirect or direct head or facial trauma that can negatively impact an athletes’ career and personal life. In this context, the importance on how to deal with a concussion has received attention from worldwide literature and has become a topic of enormous interest in the sports medicine arena. Objective: This systematic review aimed to investigate how sports-related concussion is being managed regarding athletic injuries, athletes’ age, clinical signs of concussion, adopted questionnaires, as well as decision making in sports medicine. Methods: A systematic review of the literature was performed searching 10 electronic databases with no limitations for year of publication up to December 2019. The search terms used were: Brain Concussion, Athletes, Sports Medicine, Athletic Injuries, Clinical Decision-Making, and Decision Making. The articles were considered eligible when the studies related to populations of regular sports practitioners, professional or recreational, of any age; sports injury; articles reporting concussion evaluation in at least 30 athletes; and articles published in English, French, Portuguese, Italian. We excluded systematic review articles, reviews, editorials, sport-unrelated concussion, no questionnaire application, approaching retired athletes, consensus statement letters, author’s reply to editorials, synopsis, and abstracts. Results: The parameters adopted for decision-making and management were broadly variable and were based on a variety of clinical signs or scoring outcomes from a myriad of questionnaires with little consistency in protocol or management guidelines, which could guide the average clinician. Conclusion: This systematic review provides current evidence that post-concussion management in sports medicine has yet to accomplish a standardized protocol that clinicians could use to optimally care for athletes. The extensive number of manuscripts and studies addressing the topic confirms that sports-related concussion in the pediatric and adolescent population has come to the forefront in the sports medicine field.

Critical Appraisal of a Machine Learning Paper: A Guide for the Neurologist.

Machine learning (ML), a form of artificial intelligence (AI), is being increasingly employed in neurology. Reported performance metrics often match or exceed the efficiency of average clinicians. The neurologist is easily baffled by the underlying concepts and terminologies associated with ML studies. The superlative performance metrics of ML algorithms often hide the opaque nature of its inner workings. Questions regarding ML model's interpretability and reproducibility of its results in real-world scenarios, need emphasis. Given an abundance of time and information, the expert clinician should be able to deliver comparable predictions to ML models, a useful benchmark while evaluating its performance. Predictive performance metrics of ML models should not be confused with causal inference between its input and output. ML and clinical gestalt should compete in a randomized controlled trial before they can complement each other for screening, triaging, providing second opinions and modifying treatment.

A Protocol is not Enough: Enhanced Recovery Program-Based Care and Clinician Adherence Associated with Shorter Stay After Colorectal Surgery

BackgroundRandomised trials have shown an Enhanced Recovery Program (ERP) can shorten stay after colorectal surgery. Previous research has focused on patient compliance neglecting the role of care providers. National data on implementation and adherence to standardised care are lacking. We examined care organisation and delivery including the ERP, and correlated this with clinical outcomes.MethodsA cross-sectional questionnaire was administered to surgeons and nurses in August–October 2015. All English National Health Service Trusts providing elective colorectal surgery were invited. Responses frequencies and variation were examined. Exploratory factor analysis was performed to identify underlying features of care. Standardised factor scores were correlated with elective clinical outcomes of length of stay, mortality and readmission rates from 2013–15.Results218/600 (36.3%) postal responses were received from 84/90 (93.3%) Trusts that agreed to participate. Combined with email responses, 301 surveys were analysed. 281/301 (93.4%) agreed or strongly agreed that they had a standardised, ERP-based care protocol. However, 182/301 (60.5%) indicated all consultants managed post-operative oral intake similarly. After factor analysis, higher hospital average ERP-based care standardisation and clinician adherence score were significantly correlated with reduced length of stay, as well as higher ratings of teamwork and support for complication management.ConclusionsStandardised, ERP-based care was near universal, but clinician adherence varied markedly. Units reporting higher levels of clinician adherence achieved the lowest length of stay. Having a protocol is not enough. Careful implementation and adherence by all of the team is vital to achieve the best results.

Feasibility and Acceptability of Inpatient Palliative Care E-Family Meetings During COVID-19 Pandemic

Family meetings are fundamental to the practice of palliative medicine and serve as a cornerstone of intervention on the inpatient palliative care consultation service. The COVID-19 pandemic disrupted the structure and process of in-patient family meetings, owing to necessary but restrictive visitor policies that did not allow families to be present in the hospital. We describe implementation of telemedicine to facilitate electronic family (e-family) meetings to facilitate in-patient palliative care. Of 67 scheduled meetings performed by the palliative care service, only two meetings were aborted for a 97% success rate of scheduled meetings occurring. On a five-point Likert-type scale, the average clinician rating of the e-family meeting overall quality was 3.18 (SD, .96). Of the 10 unique family participants who agreed to be interviewed, their overall ratings of the e-family meetings were high. Over 80% of respondent families participants reported that they agreed or strongly agreed that they were able to ask all of their questions, felt comfortable expressing their thoughts and feelings with the clinical team, felt like they understood the care their loved one received, and that the virtual family meeting helped them trust the clinical team. Of patients who were able to communicate, 50% of family respondents reported that the e-family meeting helped them understand their loved one's thoughts and wishes.

The evaluation and comparison on different types of resident doctors in training through DxR Clinician system

Compared with the traditional problem-based learning (PBL) mode, computer-based case simulations (CCS) are more advanced in aspects of clinical reasoning, critical thinking and clinical thinking. CCS program, Diagnosis & Reasoning (DxR) Clinician, has been used for assessment of clinical diagnosis and treatment skills in more than 300 medical colleges and universities around the world. However, the evaluating effectiveness and practicability of this software continue to be uncertain and ambiguity in China. Moreover, the influence factors of the DxR evaluation score are still remain indefinite. The purpose of this study was to investigate the impact of training years, professional background and educational background on DxR scores in order to better improve the clinical skills of residents. Eighty one resident doctors were selected as the experimental subjects to conduct the clinical skills assessment with DxR Clinician. The relationships between residents’ scores in DxR Clinician components (overall score, diagnostic score, and management score) and their training years, professional background and educational background were analysed using simultaneous regression. The results showed that years of training, professional background and educational background are potential influence factors of DxR evaluation score. The average DxR Clinician scores in this study are generally lower than foreign research, so we should strengthen resident standardized training to improve our clinical skills.

The Impact of Medical Scribes on Relative Value Units in a Pediatric Primary Care Practice

Our study assessed the impact of adding medical scribes to an academic pediatric primary practice by measuring the relationship between work relative value units (wRVUs) and use of the medical scribe. This is a retrospective comparative study on the effect of medical scribes on average wRVUs per patient encounter. wRVUs were abstracted from procedure codes in the billing system. Six clinicians performed 2277 patient visits included in the study over 2 different time periods during 2017 and 2018. The first period was without the use of medical scribes and the second period included scribes. Average clinician wRVU production per visit increased by 7.68% (P < .001) with medical scribes over the previous period without them. This study shows that scribes contribute to improving the wRVU per visit in a primary pediatric practice. This finding is consistent with other research showing that scribes help increase volume and improve wRVUs for specialists who perform complex procedures.

ESC/EASD guideline sheds light on diabetes and cardiovascular disease management

ESC/EASD guideline sheds light on diabetes and cardiovascular disease management

Predicting Overt Hepatic Encephalopathy for the Population With Cirrhosis

Hepatic encephalopathy (HE) is associated with poor quality of life, sharply increased mortality, repeated hospitalizations, falls, and motor vehicle accidents. HE manifests with a dynamic spectrum of severity. Overt HE is clinically obvious disorientation, even coma. Although multiple strategies are available to characterize early-stage HE, data are limited that validate these methods in predicting overt HE, many are impractical in clinical practice, and test cutoffs relevant to the average patient clinicians manage are lacking. To accurately and efficiently classify the risk of overt HE in the population with cirrhosis, novel strategies may be needed. Herein, we review the potential competing strategies for the prediction of overt HE. Conclusion: We propose refining diagnostic cutoffs for tests that are designed to define early HE, using overt HE as a gold standard and expanding prediction tools by using measures of components from the risk pathway for HE.

Deep neural network improves fracture detection by clinicians

Suspected fractures are among the most common reasons for patients to visit emergency departments (EDs), and X-ray imaging is the primary diagnostic tool used by clinicians to assess patients for fractures. Missing a fracture in a radiograph often has severe consequences for patients, resulting in delayed treatment and poor recovery of function. Nevertheless, radiographs in emergency settings are often read out of necessity by emergency medicine clinicians who lack subspecialized expertise in orthopedics, and misdiagnosed fractures account for upward of four of every five reported diagnostic errors in certain EDs. In this work, we developed a deep neural network to detect and localize fractures in radiographs. We trained it to accurately emulate the expertise of 18 senior subspecialized orthopedic surgeons by having them annotate 135,409 radiographs. We then ran a controlled experiment with emergency medicine clinicians to evaluate their ability to detect fractures in wrist radiographs with and without the assistance of the deep learning model. The average clinician's sensitivity was 80.8% (95% CI, 76.7-84.1%) unaided and 91.5% (95% CI, 89.3-92.9%) aided, and specificity was 87.5% (95 CI, 85.3-89.5%) unaided and 93.9% (95% CI, 92.9-94.9%) aided. The average clinician experienced a relative reduction in misinterpretation rate of 47.0% (95% CI, 37.4-53.9%). The significant improvements in diagnostic accuracy that we observed in this study show that deep learning methods are a mechanism by which senior medical specialists can deliver their expertise to generalists on the front lines of medicine, thereby providing substantial improvements to patient care.

Skeletal Muscle Dysfunction in Chronic Obstructive Pulmonary Disease. What We Know and Can Do for Our Patients.

Skeletal muscle dysfunction occurs in patients with chronic obstructive pulmonary disease (COPD) and affects both ventilatory and nonventilatory muscle groups. It represents a very important comorbidity that is associated with poor quality of life and reduced survival. It results from a complex combination of functional, metabolic, and anatomical alterations leading to suboptimal muscle work. Muscle atrophy, altered fiber type and metabolism, and chest wall remodeling, in the case of the respiratory muscles, are relevant etiological contributors to this process. Muscle dysfunction worsens during COPD exacerbations, rendering patients progressively less able to perform activities of daily living, and it is also associated with poor outcomes. Muscle recovery measures consisting of a combination of pulmonary rehabilitation, optimized nutrition, and other strategies are associated with better prognosis when administered in stable patients as well as after exacerbations. A deeper understanding of this process' pathophysiology and clinical relevance will facilitate the use of measures to alleviate its effects and potentially improve patients' outcomes. In this review, a general overview of skeletal muscle dysfunction in COPD is offered to highlight its relevance and magnitude to expert practitioners and scientists as well as to the average clinician dealing with patients with chronic respiratory diseases.