Longitudinal Progression of Patients with Long COVID Treated in a Post-COVID Clinic: A Cross-Sectional Survey.

BACKGROUND: In addition to the morbidity and mortality associated with acute infection, COVID-19 has been associated with persistent symptoms (>30 days), often referred to as Long COVID (LC). LC symptoms often cluster into phenotypes, resembling conditions such as fibromyalgia, postural orthostatic tachycardiac syndrome (POTS), and myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS). LC clinics have been established to best address the needs of LC patients and continuity of care. We developed a cross-sectional survey to assess treatment response through our LC Clinic (LCC). METHODS: A 25-question survey (1-10 Likert scale) was expert- and content-validated by LCC clinicians, patients, and patient advocates. The survey assessed LC symptoms and the helpfulness of different interventions, including medications and supplements. A total of 852 LCC patients were asked to complete the survey, with 536 (62.9%) responding. RESULTS: The mean time from associated COVID-19 infection to survey completion was 23.2 ± 6.4 months. The mean age of responders was 52.3 ± 14.1 (63% females). Self-reported symptoms were all significantly improved (P < .001) from the initial visit to the LCC (baseline) to the time of the follow-up survey. However, only 4.5% (24/536) of patients rated all symptoms low (1-2) at the time of the survey, indicating low levels of full recovery in our cohort. The patients rated numerous interventions as being helpful, including low-dose naltrexone (45/77; 58%), vagal nerve stimulation (18/34; 53%), and fisetin (28/44; 64%). CONCLUSIONS: Patients report general improvements in symptoms following the initial LCC visit, but complete recovery rates remain low at 23.2 ± 6.4 months.

Pro Inflammatory Cytokines Profiles of Patients With Long COVID Differ Between Variant Epochs.

BACKGROUND: Over 30% of patients with COVID-19 have persistent symptoms that last beyond 30 days and referred to as Long COVID. Long COVID has been associated with a persistent elevation in peripheral cytokines including interleukin-6, interleukin-1ß, and tumor necrosis factor-α. This study reports cytokine profiles of patients in our clinic across SARS-COV-2 variant epochs. METHODS: The clinical cytokine panel was analyzed in patients with Long COVID during periods that were stratified according to variant epoch. The 4 variant epochs were defined as: (1) wild-type through alpha, (2) alpha/beta/gamma, (3) delta, and (4) omicron variants. RESULTS: A total of 390 patients had the clinical cytokine panel performed; the median age was 48 years (IQR 38-59) and 62% were female. Distribution by variant was wild-type and alpha, 50% (n = 196); alpha/beta/gamma, 7.9% (n = 31); delta, 18% (n = 72); and omicron, 23% (n = 91). Time to cytokine panel testing was significantly longer for the earlier epochs. Tumor necrosis factor-α (P < .001) and interleukin 1ß (P < .001) were significantly more elevated in the earlier epochs (median of 558 days in wild-type through Alpha epoch vs 263 days in omicron epoch, P < .001)). Nucleocapsid antibodies were consistently detected across epochs. DISCUSSION: When stratified by variant epoch, patients with early epoch Long COVID had persistently elevated peripheral pro-inflammatory cytokine levels when compared to later epoch Long COVID. Patients with Long COVID have similar clusters of symptoms across epochs, suggesting that the underlying pathology is independent of the peripheral cytokine signature.

Symptom presentation by phenotype of postural orthostatic tachycardia syndrome.

Postural orthostatic tachycardia syndrome (POTS) presents heterogeneously and is diagnosed when appropriate symptoms are present in conjunction with a heart rate increase of at least 30 beats-per-minute upon standing without orthostatic hypotension. Much of the current understanding of POTS is based on clinical expertise, particularly regarding POTS phenotypes and their potential role in targeting pharmacologic treatment. This study describes the symptom presentation of POTS by phenotypes at a subspecialty POTS clinic. Data was collected prospectively during clinical visits between April 17, 2014 and February 8, 2021. This data was abstracted retrospectively by chart review. Most of the 378 study participants were female (89.9%) with a mean age 23.0 ± 4.9 years. Lightheadedness was the most common (97.6%) symptom and the most disruptive of quality of life (29.9%). Patients reported substantial functional impairment across multiple life domains, with 3.0 ± 2.8 days lost and 4.7 ± 2.3 unproductive days per week. There were no differences in symptom presentation among POTS phenotypes. POTS phenotypes are not distinguishable based on symptoms alone; if phenotyping is sought, testing is necessary. Further research is needed in better classifying POTS phenotypes with the potential goal of tailoring treatment.

Digital Pulmonology Practice with Phonopulmography Leveraging Artificial Intelligence: Future Perspectives Using Dual Microwave Acoustic Sensing and Imaging.

Respiratory disorders, being one of the leading causes of disability worldwide, account for constant evolution in management technologies, resulting in the incorporation of artificial intelligence (AI) in the recording and analysis of lung sounds to aid diagnosis in clinical pulmonology practice. Although lung sound auscultation is a common clinical practice, its use in diagnosis is limited due to its high variability and subjectivity. We review the origin of lung sounds, various auscultation and processing methods over the years and their clinical applications to understand the potential for a lung sound auscultation and analysis device. Respiratory sounds result from the intra-pulmonary collision of molecules contained in the air, leading to turbulent flow and subsequent sound production. These sounds have been recorded via an electronic stethoscope and analyzed using back-propagation neural networks, wavelet transform models, Gaussian mixture models and recently with machine learning and deep learning models with possible use in asthma, COVID-19, asbestosis and interstitial lung disease. The purpose of this review was to summarize lung sound physiology, recording technologies and diagnostics methods using AI for digital pulmonology practice. Future research and development in recording and analyzing respiratory sounds in real time could revolutionize clinical practice for both the patients and the healthcare personnel.

Development of a Visit Facilitator Role to Assist Physicians in an Ambulatory Consultative Medical Practice.

Objective: To decrease the electronic health record (EHR) clerical burden and improve patient/clinician satisfaction, allied health staff were trained as visit facilitators (VFs) to assist the physician in clinical and administrative tasks. Patients and Methods: From December 7, 2020, to October 11, 2021, patients with complex medical conditions were evaluated by an internal medicine physician in an outpatient general internal medicine (GIM) consultative practice at a tertiary care institution. A VF assisted with specific tasks before, during, and after the clinical visit. Presurvey and postsurvey assessments were performed to understand the effect of the VF on clinical tasks as perceived by the physician. Results: A total of 57 GIM physicians used a VF, and 41 (82%) physicians and 39 (79%) physicians completed the pre-VF and post-VF surveys, respectively. Physicians reported a significant reduction in time reviewing outside materials, updating pertinent information, and creating/modifying EHR orders (P<.05). Clinicians reported improved interactions with patients and on-time completion of clinical documentation. In the pre-VF survey, "too much time spent" was the most common response for reviewing outside material, placing/modifying orders, completing documentation/clinical notes, resolving in-baskets, completing dismissal letters, and completing tasks outside of work hours. In the post-VF survey, "too much time spent" was not the most common answer to any question. Satisfaction improved in all areas (P<.05). Conclusion: VFs significantly reduced the EHR clinical burden and improved GIM physician practice satisfaction. This model can potentially be used in a wide range of medical practices.

Practicing Digital Gastroenterology through Phonoenterography Leveraging Artificial Intelligence: Future Perspectives Using Microwave Systems.

Production of bowel sounds, established in the 1900s, has limited application in existing patient-care regimes and diagnostic modalities. We review the physiology of bowel sound production, the developments in recording technologies and the clinical application in various scenarios, to understand the potential of a bowel sound recording and analysis device-the phonoenterogram in future gastroenterological practice. Bowel sound production depends on but is not entirely limited to the type of food consumed, amount of air ingested and the type of intestinal contractions. Recording technologies for extraction and analysis of these include the wavelet-based filtering, autoregressive moving average model, multivariate empirical mode decompression, radial basis function network, two-dimensional positional mapping, neural network model and acoustic biosensor technique. Prior studies evaluate the application of bowel sounds in conditions such as intestinal obstruction, acute appendicitis, large bowel disorders such as inflammatory bowel disease and bowel polyps, ascites, post-operative ileus, sepsis, irritable bowel syndrome, diabetes mellitus, neurodegenerative disorders such as Parkinson's disease and neonatal conditions such as hypertrophic pyloric stenosis. Recording and analysis of bowel sounds using artificial intelligence is crucial for creating an accessible, inexpensive and safe device with a broad range of clinical applications. Microwave-based digital phonoenterography has huge potential for impacting GI practice and patient care.

Applying Natural Language Processing Neural Network Architectures to Augment Appointment Request Review of Self-Referred Patients to an Academic Medical Center.

Selecting appropriate consultations for self-referred patients to tertiary medical centers is a time and resource intensive task. Deep learning with natural language processing can potentially augment this task and reduce clinician workload. Appointment request forms for 8168 patients self-referred to General Internal Medicine were reviewed and recommended downstream appointments from manual triage were tabulated. This paper describes the development and performance of thirty-nine deep learning algorithms for multi-label text classification: including convolutional neural networks, recurrent neural networks, and pretrained language models with transformer and reformer architectures implemented using Pytorch and trained on a single graphic processing unit. A model with multiple convolutional neural networks with various kernel sizes (1-7 words) and 300 dimensional FastText word embeddings performed best (AUC 0.949, MCC 0.734, F1 0.775). Generally, models with convolutional networks were highest performers. Highly performing models may be candidates for implementation to augment clinician workflow.

Virtual Reality for Health Care Professionals During a Pandemic: A Pilot Program.

OBJECTIVE: The purpose of this pilot study was to evaluate the safety and use of a nature-based virtual reality (VR) experience among health care providers (HCP) during a pandemic. METHODS: Twenty-four frontline HCP participated in this crossover pilot where the viewing order of the experiences were randomized. All participants attended in-person consent, baseline, and end-of-study visits. The intervention consisted of viewing 2 nature-based scenes ("walk in the woods" and "forest of focus") through 3-D VR and with computer 4K graphic imagery. Randomization took place with regards to the viewing order (VR vs 4K computer video, scene 1 and 2). Outcomes measured were safety, acceptability and changes in intensity of anxiety feelings, resilience, emotional distress, cognitive function, and self-efficacy. RESULTS: Among the 26 HCP expressing interest in the study, 24 enrolled in this study. The majority were male (58.3%), white (66.7%) and of an average age of 46.3 ± 10.5 years (standard deviation (SD)). End of the study survey showed that almost all participants (96%) would participate in the study again and recommend it to others. Twenty-three of the 24 participants also felt relaxed after seeing the imagery. With respect to anxiety (as measured by the STAI Y1), the VR "walk in the woods" had the greatest reduction from pre to post (6.4 points, SD = 5.98) followed by VR "forest of focus" (5.8 points, SD = 9.29), computer screen "forest of focus" (5.0 points, SD = 8.89), and computer screen "walk in the woods" (4.1 points, SD = 6.22). All 4 sessions had a significant decrease in score from pre to post (P-values ≤.005), but there was no significant difference in the change from pre- to post-session between the 4 groups (P-value = .5835). CONCLUSION: The use of the VR among HCP has promise for reducing stress among health care providers during a high stress period, such as a pandemic but much larger studies are needed.

Creation of a Multispecialty Clinic for Patients with Central Sensitization-Based Chronic Pain Conditions.

OBJECTIVE: To design and evaluate, through a human-centered design approach, a multispeciality clinic for patients with central sensitization syndromes that combined virtual previsit consultations, traditional face-to-face appointments, and technology-enabled educational programming. PATIENTS AND METHODS: Patients with suspected fibromyalgia and chronic abdominal pain were seen in a multispecialty practice, and the performance of the clinic was evaluated against a contemporary cohort. Quantitative and qualitative evaluation measures included team estimates of time spent on care-related tasks, physician rank of alignment of patient need with clinic design, major appointment changes, and nonvisit care tasks. Members of the care team also evaluated strengths, weaknesses, opportunities, and threats to the success of the clinic. RESULTS: The pilot clinic was operated from April 1, 2020, to April 30, 2021, and included 34 patients with suspected fibromyalgia/chronic abdominal pain. During the pilot period, physicians ranked the value of the virtual previsit consultations in providing care as 7.5 on a scale of 0 to 10 and reported an average of 50 minutes in preparation for the appointment, execution of the appointment, and postvisit documentation. We did not observe substantial differences in the number of added appointments or messages received within the patient portal when compared with a comparison cohort. Patients who participated in the combination nurse educator-led and digital education program provided positive feedback about their experience. CONCLUSION: Our clinic model provides a framework for the treatment of patients with debilitating centrally sensitized conditions and future expansion of virtual care delivery models to better meet patient care and educational needs.

Central Sensitization Phenotypes in Post Acute Sequelae of SARS-CoV-2 Infection (PASC): Defining the Post COVID Syndrome.

OBJECTIVE: To develop and implement criteria for description of post COVID syndrome based on analysis of patients presenting for evaluation at Mayo Clinic Rochester between November 2019 and August 2020. METHODS: A total of 465 patients with a history of testing positive for COVID-19 were identified and their medical records reviewed. After a thorough review, utilizing the DELPHI methods by an expert panel, 42 (9%) cases were identified with persistent central sensitization (CS) symptoms persisting after the resolution of acute COVID-19, herein referred to as Post COVID syndrome (PoCoS). In this report we describe the baseline characteristics of these PoCoS patients. RESULTS: Among these 42 PoCoS patients, the mean age was 46.2 years (median age was 46.5 years). Pain (90%), fatigue (74%), dyspnea (43%), and orthostatic intolerance (38%) were the most common symptoms. The characteristics of an initial 14 patients were utilized for the development of clinical criteria via a modified Delphi Method by a panel of experts in central sensitization disorders. These criteria were subsequently applied in the identification of 28 additional cases of suspected PoCoS. A 2-reviewer system was used to analyze agreement with using the criteria, with all 28 cases determined to be either probable or possible cases by the reviewers. Inter-reviewer agreement using these proposed defining criteria was high with a Cohen's alpha of .88. CONCLUSIONS: Here we present what we believe to be the first definitional criteria for Post COVID syndrome. These may be useful in clinical phenotyping of these patients for targeted treatment and future research.

Fibromyalgia screening in patients with unexplained chronic fatigue.

ABSTRACT: Women often complain of symptoms of fatigue and generalized aches and pains around menopause. Even though fibromyalgia is more prevalent in midlife women, not all women presenting with aches and pain and disrupted sleep meet diagnostic criteria for fibromyalgia. This Practice Pearl addresses the distinction between chronic fatigue syndrome and fibromyalgia and the management of fibromyalgia in perimenopausal and postmenopausal women.

Impact of Clinicians' Use of Electronic Knowledge Resources on Clinical and Learning Outcomes: Systematic Review and Meta-Analysis.

BACKGROUND: Clinicians use electronic knowledge resources, such as Micromedex, UpToDate, and Wikipedia, to deliver evidence-based care and engage in point-of-care learning. Despite this use in clinical practice, their impact on patient care and learning outcomes is incompletely understood. A comprehensive synthesis of available evidence regarding the effectiveness of electronic knowledge resources would guide clinicians, health care system administrators, medical educators, and informaticians in making evidence-based decisions about their purchase, implementation, and use. OBJECTIVE: The aim of this review is to quantify the impact of electronic knowledge resources on clinical and learning outcomes. METHODS: We searched MEDLINE, Embase, PsycINFO, and the Cochrane Library for articles published from 1991 to 2017. Two authors independently screened studies for inclusion and extracted outcomes related to knowledge, skills, attitudes, behaviors, patient effects, and cost. We used random-effects meta-analysis to pool standardized mean differences (SMDs) across studies. RESULTS: Of 10,811 studies screened, we identified 25 eligible studies published between 2003 and 2016. A total of 5 studies were randomized trials, 22 involved physicians in practice or training, and 10 reported potential conflicts of interest. A total of 15 studies compared electronic knowledge resources with no intervention. Of these, 7 reported clinician behaviors, with a pooled SMD of 0.47 (95% CI 0.27 to 0.67; P<.001), and 8 reported objective patient effects with a pooled SMD of 0.19 (95% CI 0.07 to 0.32; P=.003). Heterogeneity was large (I2>50%) across studies. When compared with other resources-7 studies, not amenable to meta-analytic pooling-the use of electronic knowledge resources was associated with increased frequency of answering questions and perceived benefits on patient care, with variable impact on time to find an answer. A total of 2 studies compared different implementations of the same electronic knowledge resource. CONCLUSIONS: Use of electronic knowledge resources is associated with a positive impact on clinician behaviors and patient effects. We found statistically significant associations between the use of electronic knowledge resources and improved clinician behaviors and patient effects. When compared with other resources, the use of electronic knowledge resources was associated with increased success in answering clinical questions, with variable impact on speed. Comparisons of different implementation strategies of the same electronic knowledge resource suggest that there are benefits from allowing clinicians to choose to access the resource, versus automated display of resource information, and from integrating patient-specific information. A total of 4 studies compared different commercial electronic knowledge resources, with variable results. Resource implementation strategies can significantly influence outcomes but few studies have examined such factors.

Barriers and facilitators to clinical information seeking: a systematic review.

OBJECTIVE: The study sought to identify barriers to and facilitators of point-of-care information seeking and use of knowledge resources. MATERIALS AND METHODS: We searched MEDLINE, Embase, PsycINFO, and Cochrane Library from 1991 to February 2017. We included qualitative studies in any language exploring barriers to and facilitators of point-of-care information seeking or use of electronic knowledge resources. Two authors independently extracted data on users, study design, and study quality. We inductively identified specific barriers or facilitators and from these synthesized a model of key determinants of information-seeking behaviors. RESULTS: Forty-five qualitative studies were included, reporting data derived from interviews (n = 26), focus groups (n = 21), ethnographies (n = 6), logs (n = 4), and usability studies (n = 2). Most studies were performed within the context of general medicine (n = 28) or medical specialties (n = 13). We inductively identified 58 specific barriers and facilitators and then created a model reflecting 5 key determinants of information-seeking behaviors: time includes subthemes of time availability, efficiency of information seeking, and urgency of information need; accessibility includes subthemes of hardware access, hardware speed, hardware portability, information restriction, and cost of resources; personal skills and attitudes includes subthemes of computer literacy, information-seeking skills, and contextual attitudes about information seeking; institutional attitudes, cultures, and policies includes subthemes describing external individual and institutional information-seeking influences; and knowledge resource features includes subthemes describing information-seeking efficiency, information content, information organization, resource familiarity, information credibility, information currency, workflow integration, compatibility of recommendations with local processes, and patient educational support. CONCLUSIONS: Addressing these determinants of information-seeking behaviors may facilitate clinicians' question answering to improve patient care.

Electronic Knowledge Resources and Point-of-Care Learning: A Scoping Review.

PURPOSE: The authors sought to summarize quantitative and qualitative research addressing electronic knowledge resources and point-of-care learning in a scoping review. METHOD: The authors searched MEDLINE, Embase, PsycINFO, and the Cochrane Database for studies addressing electronic knowledge resources and point-of-care learning. They iteratively revised inclusion criteria and operational definitions of study features and research themes of interest. Two reviewers independently performed each phase of study selection and data extraction. RESULTS: Of 10,811 studies identified, 305 were included and reviewed. Most studies (225; 74%) included physicians or medical students. The most frequently mentioned electronic resources were UpToDate (88; 29%), Micromedex (59; 19%), Epocrates (50; 16%), WebMD (46; 15%), MD Consult (32; 10%), and LexiComp (31; 10%). Eight studies (3%) evaluated electronic resources or point-of-care learning using outcomes of patient effects, and 36 studies (12%) reported objectively measured clinician behaviors. Twenty-five studies (8%) examined the clinical or educational impact of electronic knowledge resource use on patient care or clinician knowledge, 124 (41%) compared use rates of various knowledge resources, 69 (23%) examined the quality of knowledge resource content, and 115 (38%) explored the process of point-of-care learning. Two conceptual clarifications were identified, distinguishing the impact on clinical or educational outcomes versus the impact on test setting decision support, and the quality of information content versus the correctness of information obtained by a clinician-user. CONCLUSIONS: Research on electronic knowledge resources is dominated by studies involving physicians and evaluating use rates. Studies involving nonphysician users, and evaluating resource impact and implementation, are needed.

Prospective validation of a near real-time EHR-integrated automated SOFA score calculator.

OBJECTIVES: We created an algorithm for automated Sequential Organ Failure Assessment (SOFA) score calculation within the Electronic Health Record (EHR) to facilitate detection of sepsis based on the Third International Consensus Definitions for Sepsis and Septic Shock (SEPSIS-3) clinical definition. We evaluated the accuracy of near real-time and daily automated SOFA score calculation compared with manual score calculation. METHODS: Automated SOFA scoring computer programs were developed using available EHR data sources and integrated into a critical care focused patient care dashboard at Mayo Clinic in Rochester, Minnesota. We prospectively compared the accuracy of automated versus manual calculation for a sample of patients admitted to the medical intensive care unit at Mayo Clinic Hospitals in Rochester, Minnesota and Jacksonville, Florida. Agreement was calculated with Cohen's kappa statistic. Reason for discrepancy was tabulated during manual review. RESULTS: Random spot check comparisons were performed 134 times on 27 unique patients, and daily SOFA score comparisons were performed for 215 patients over a total of 1206 patient days. Agreement between automatically scored and manually scored SOFA components for both random spot checks (696 pairs, κ=0.89) and daily calculation (5972 pairs, κ=0.89) was high. The most common discrepancies were in the respiratory component (inaccurate fraction of inspired oxygen retrieval; 200/1206) and creatinine (normal creatinine in patients with no urine output on dialysis; 128/1094). 147 patients were at risk of developing sepsis after intensive care unit admission, 10 later developed sepsis confirmed by chart review. All were identified before onset of sepsis with the ΔSOFA≥2 point criterion and 46 patients were false-positives. CONCLUSIONS: Near real-time automated SOFA scoring was found to have strong agreement with manual score calculation and may be useful for the detection of sepsis utilizing the new SEPSIS-3 definition.

Iterative User Interface Design for Automated Sequential Organ Failure Assessment Score Calculator in Sepsis Detection.

BACKGROUND: The new sepsis definition has increased the need for frequent sequential organ failure assessment (SOFA) score recalculation and the clerical burden of information retrieval makes this score ideal for automated calculation. OBJECTIVE: The aim of this study was to (1) estimate the clerical workload of manual SOFA score calculation through a time-motion analysis and (2) describe a user-centered design process for an electronic medical record (EMR) integrated, automated SOFA score calculator with subsequent usability evaluation study. METHODS: First, we performed a time-motion analysis by recording time-to-task-completion for the manual calculation of 35 baseline and 35 current SOFA scores by 14 internal medicine residents over a 2-month period. Next, we used an agile development process to create a user interface for a previously developed automated SOFA score calculator. The final user interface usability was evaluated by clinician end users with the Computer Systems Usability Questionnaire. RESULTS: The overall mean (standard deviation, SD) time-to-complete manual SOFA score calculation time was 61.6 s (33). Among the 24% (12/50) usability survey respondents, our user-centered user interface design process resulted in >75% favorability of survey items in the domains of system usability, information quality, and interface quality. CONCLUSIONS: Early stakeholder engagement in our agile design process resulted in a user interface for an automated SOFA score calculator that reduced clinician workload and met clinicians' needs at the point of care. Emerging interoperable platforms may facilitate dissemination of similarly useful clinical score calculators and decision support algorithms as "apps." A user-centered design process and usability evaluation should be considered during creation of these tools.

Towards automated calculation of evidence-based clinical scores.

AIM: To determine clinical scores important for automated calculation in the inpatient setting. METHODS: A modified Delphi methodology was used to create consensus of important clinical scores for inpatient practice. A list of 176 externally validated clinical scores were identified from freely available internet-based services frequently used by clinicians. Scores were categorized based on pertinent specialty and a customized survey was created for each clinician specialty group. Clinicians were asked to rank each score based on importance of automated calculation to their clinical practice in three categories - "not important", "nice to have", or "very important". Surveys were solicited via specialty-group listserv over a 3-mo interval. Respondents must have been practicing physicians with more than 20% clinical time spent in the inpatient setting. Within each specialty, consensus was established for any clinical score with greater than 70% of responses in a single category and a minimum of 10 responses. Logistic regression was performed to determine predictors of automation importance. RESULTS: Seventy-nine divided by one hundred and forty-four (54.9%) surveys were completed and 72/144 (50%) surveys were completed by eligible respondents. Only the critical care and internal medicine specialties surpassed the 10-respondent threshold (14 respondents each). For internists, 2/110 (1.8%) of scores were "very important" and 73/110 (66.4%) were "nice to have". For intensivists, no scores were "very important" and 26/76 (34.2%) were "nice to have". Only the number of medical history (OR = 2.34; 95%CI: 1.26-4.67; P < 0.05) and vital sign (OR = 1.88; 95%CI: 1.03-3.68; P < 0.05) variables for clinical scores used by internists was predictive of desire for automation. CONCLUSION: Few clinical scores were deemed "very important" for automated calculation. Future efforts towards score calculator automation should focus on technically feasible "nice to have" scores.

Automating Clinical Score Calculation within the Electronic Health Record. A Feasibility Assessment.

OBJECTIVES: Evidence-based clinical scores are used frequently in clinical practice, but data collection and data entry can be time consuming and hinder their use. We investigated the programmability of 168 common clinical calculators for automation within electronic health records. METHODS: We manually reviewed and categorized variables from 168 clinical calculators as being extractable from structured data, unstructured data, or both. Advanced data retrieval methods from unstructured data sources were tabulated for diagnoses, non-laboratory test results, clinical history, and examination findings. RESULTS: We identified 534 unique variables, of which 203/534 (37.8%) were extractable from structured data and 269/534 (50.4.7%) were potentially extractable using advanced techniques. Nearly half (265/534, 49.6%) of all variables were not retrievable. Only 26/168 (15.5%) of scores were completely programmable using only structured data and 43/168 (25.6%) could potentially be programmable using widely available advanced information retrieval techniques. Scores relying on clinical examination findings or clinical judgments were most often not completely programmable. CONCLUSION: Complete automation is not possible for most clinical scores because of the high prevalence of clinical examination findings or clinical judgments - partial automation is the most that can be achieved. The effect of fully or partially automated score calculation on clinical efficiency and clinical guideline adherence requires further study.