Frequency of alterations in qSOFA, SIRS, MEWS and NEWS scores during the emergency department stay in infectious patients: a prospective study

Background For emergency department (ED) patients with suspected infection, a vital sign-based clinical rule is often calculated shortly after the patient arrives. The clinical rule score (normal or abnormal) provides information about diagnosis and/or prognosis. Since vital signs vary over time, the clinical rule scores can change as well. In this prospective multicentre study, we investigate how often the scores of four frequently used clinical rules change during the ED stay of patients with suspected infection. Methods Adult (≥ 18 years) patients with suspected infection were prospectively included in three Dutch EDs between March 2016 and December 2019. Vital signs were measured in 30-min intervals and the quick Sequential Organ Failure Assessment (qSOFA) score, the Systemic Inflammatory Response Syndrome (SIRS) criteria, the Modified Early Warning Score and the National Early Warning Score (NEWS) score were calculated. Using the established cut-off points, we analysed how often alterations in clinical rule scores occurred (i.e. switched from normal to abnormal or vice versa). In addition, we investigated which vital signs caused most alterations. Results We included 1433 patients, of whom a clinical rule score changed once or more in 637 (44.5%) patients. In 6.7–17.5% (depending on the clinical rule) of patients with an initial negative clinical rule score, a positive score occurred later during ED stay. In over half (54.3–65.0%) of patients with an initial positive clinical rule score, the score became negative later on. The respiratory rate caused most (51.2%) alterations. Conclusion After ED arrival, alterations in qSOFA, SIRS, MEWS and/or NEWS score are present in almost half of patients with suspected infection. The most contributing vital sign to these alterations was the respiratory rate. One in 6–15 patients displayed an abnormal clinical rule score after a normal initial score. Clinicians should be aware of the frequency of these alterations in clinical rule scores, as clinical rules are widely used for diagnosis and/or prognosis and the optimal moment of assessing them is unknown.

Real-time monitoring of drug laboratory test interactions: a proof of concept

Objectives For the correct interpretation of test results, it is important to be aware of drug-laboratory test interactions (DLTIs). If DLTIs are not taken into account by clinicians, erroneous interpretation of test results may lead to a delayed or incorrect diagnosis, unnecessary diagnostic testing or therapy with possible harm for patients. A DLTI alert accompanying a laboratory test result could be a solution. The aim of this study was to test a multicentre proof of concept of an electronic clinical decision support system (CDSS) for real-time monitoring of DLTIs. Methods CDSS was implemented in three Dutch hospitals. So-called ‘clinical rules’ were programmed to alert medical specialists for possible DLTIs based on laboratory test results outside the reference range in combination with prescribed drugs. A selection of interactions from the DLTI database of the Dutch society of clinical chemistry and laboratory medicine were integrated in 43 clinical rules, including 24 tests and 25 drugs. During the period of one month all generated DTLI alerts were registered in the laboratory information system. Results Approximately 65 DLTI alerts per day were detected in each hospital. Most DLTI alerts were generated in patients from the internal medicine and intensive care departments. The most frequently reported DLTI alerts were potassium-proton pump inhibitors (16%), potassium-beta blockers (11%) and creatine kinase-statins (11%). Conclusions This study shows that it is possible to alert for potential DLTIs in real-time with a CDSS. The CDSS was successfully implemented in three hospitals. Further research must reveal its usefulness in clinical practice.

AnFiSA: An open-source computational platform for the analysis of sequencing data for rare genetic disease

Despite genomic sequencing rapidly transforming from being a bench-side tool to a routine procedure in a hospital, there is a noticeable lack of genomic analysis software that supports both clinical and research workflows as well as crowdsourcing. Furthermore, most existing software packages are not forward-compatible in regards to supporting ever-changing diagnostic rules adopted by the genetics community. Regular updates of genomics databases make reproducible and traceable automated genetic diagnostics to be a challenge. Lastly, most of the software tools score low on explainability amongst clinicians. We have created a fully open-source variant curation tool, AnFiSA, with the intention to invite and accept contributions from clinicians, researchers and professional software developers. The design of AnFiSA addresses the aforementioned issues with current genomics software via the following architectural principles: using a multidimensional database management system (DBMS) for genomic data to address reproducibility, curated decision trees adaptable to changing clinical rules, and a crowdsourcing-friendly interface to address difficult-to-diagnose cases. We discuss how we have chosen our technology stack and describe the design and implementation of the software. Finally, we show in detail how selected workflows can be implemented using the current version of AnFiSA by a medical geneticist.

Vital signs, clinical rules and gut feeling: observational study among fever patients

BackgroundGeneral practitioners (GPs) decide which patients with fever need referral to the emergency department (ED). Vital signs, clinical rules and gut feeling can influence this critical management decision.Aimto investigate which vital signs are measured by GPs, and whether referral is associated with vital signs, clinical rules, or gut feeling.Design & settingprospective observational study at two out-of-hours GP cooperativesMethodduring two nine-day periods, GPs performed their regular work-up in patients ≥18 y with fever (≥38.0°C). Subsequently, researchers measured missing vital signs for completion of the Systemic Inflammatory Response Syndrome (SIRS) criteria and the quick Sequential Organ Failure Assessment (qSOFA) score. We investigated associations between the number of referrals, positive SIRS/qSOFA scores and GPs’ gut feeling.ResultsGPs measured and recorded all vital signs required for SIRS/qSOFA calculation in 24 of 108 (22.2%) assessed patients and referred 45 (41.7%) to the ED. Higher respiratory rates, temperatures, clinical rules and gut feeling were associated with referral. During 7-day follow-up, 9 (14.3%) of 63 initially not referred patients were admitted to hospital.ConclusionGPs measured and recorded all vital signs for SIRS and qSOFA in 1 in 5 patients with fever and referred half of 63 SIRS positive and almost all of 22 qSOFA positive patients. Some vital signs and gut feeling were associated with referral, but none were consistently present in all referred patients. The vast majority of patients who were not initially referred remained at home during follow-up.

There Is a Third Condition Aside from Survival and Death that Affects Outcome Statistics: Terminal Discharge

Background: Some patients discharged automatically are classified as terminal discharge, while their clinical outcome is survival, disrupting the results of clinical research. Methods: The data of this study were taken from inpatients admitted to the ICU of the First Medical Center of the People's Liberation Army General Hospital, Beijing, China from 2008-2017. We collected the data regarding medications used over the three days before discharge from the group of patients who survived and the group of patients who died, and the outcomes of all patients were recalculated by three classification algorithms (AdaBoosting, Pearson correlation coefficient, observed to expected ratio-weighted cosine similarity). Our basic assumption is that if the classification result is death but the actual in-hospital outcome is survival, the associated patient was likely terminally discharged. Results: The coincidence rate of the outcomes calculated by the AdaBoosting algorithm was 98.1%, the coincidence rate calculated by the Pearson correlation coefficient was 61.1%, and the coincidence rate calculated by the observed to expected ratio-weighted cosine similarity was 93.4%. When the three classification methods were combined, the accuracy reached 98.56%. Conclusion: The combination of clinical rules and classification methods has a synergistic effect on judgments of patients’ discharge outcomes, greatly saving time on manual retrieval and reducing the negative influence of statistics or rules.

Epidemiology of Cervical Spine Injuries in The Emergency Department at The University Hospital of The West Indies, Jamaica and The Use of Clinical Decision Rules, A Retrospective Review.

Background: Cervical spine injuries are myriad and ubiquitous, however the related demographic information has not been documented for the Jamaican or Caribbean population. These injuries can be life threatening and so it is important for the Emergency Physician to adhere to guidelines which direct management decisions including the need for imaging. This study therefore is an effort to report on the epidemiology of patients with cervical spine injuries presenting to the Emergency Department (ED) at the University Hospital of the West Indies (UHWI) and the use of clinical rules in the diagnosis of these injuries.This was a retrospective study. The log books from the ED at the UHWI were used to identify patients presenting with possible cervical spine injuries from January 1, 2013 to December 31, 2016. Inclusion/exclusion criteria were applied to select study patients. Demographical and clinical information was collected and evaluated.Results: 1,380 charts were identified as possible subjects. Of these, 887 charts were located and 806 (90.9%) were eligible. Ages ranged from 16 to 101 years with an average of 37.5 years. The majority of subjects were male, with a male to female ratio of 3:1. The main causes of these injuries were motor-vehicle collision (46.4%), motor-bike collision (23.8%) and fall from elevation (13.1%). Cervical spine injuries were identified in 20 (2.48%) subjects where motor-vehicle collision (45%) and motor-bike collisions (25%) were the main cause for injuries. Documentation of clinical rules applied to determine the need for radiological testing were present for 37.7% of the study population (NEXUS 36.2%, CCR 0.4% and combination 1.1%)Conclusion: The main source of injuries was due to road traffic accidents. This suggests more needs to be done regarding road safety. There is also room for improvement as it relates to the use of decision rules which may reduce the occurrence of unnecessary imaging.

Improving stroke risk prediction in the general population: Common clinical rules, a new multimorbid index and machine learning based algorithms

We investigated stroke risks in a very large prospective cohort of patients with multimorbidity, using two common clinical rules, a clinical multimorbid index and a machine-learning (ML) approach accounting for the complex relationships among variables, including the dynamic nature of changing risk factors. Methods We studied a prospective US cohort of 3435224 patients from medical databases in a 2-year investigation. Stroke outcomes were examined in relationship to diverse multi-morbid conditions, demographic variables and other inputs, with ML accounting for the dynamic nature of changing multimorbidity risk factors, 2 clinical risk scores and a clinical multimorbid index. Results Common clinical risk scores had moderate and comparable c indices with stroke outcomes in the training and external validation samples (validation – CHADS2: c index 0.812; CHA2DS2-VASc: c index 0.809). A clinical multimorbid index had higher discriminant validity values for both the training/external validation samples (validation: c-index 0.850). The machine learning (ML) based algorithms yielded the highest discriminant validity values for the gradient boosting/neural network logistic regression formulations with no significant differences among the ML approaches (validation for logistic regression: c index 0.866). Calibration of the ML based formulation was satisfactory across a wide range of predicted probabilities. Decision curve analysis demonstrated that clinical utility for the ML based formulation was best. Also, ML models and clinical stroke risk scores were more clinically useful than the ‘treat all’ strategy. Conclusion Complex relationships of various comorbidities uncovered using a ML approach for diverse(and dynamic) multimorbidity changes have major consequences for stroke risk prediction.

A Computer-Interpretable Guideline for COVID-19: Rapid Development and Dissemination

Background COVID-19 is a global pandemic that is affecting more than 200 countries worldwide. Efficient diagnosis and treatment are crucial to combat the disease. Computer-interpretable guidelines (CIGs) can aid the broad global adoption of evidence-based diagnosis and treatment knowledge. However, currently, no internationally shareable CIG exists. Objective The aim of this study was to establish a rapid CIG development and dissemination approach and apply it to develop a shareable CIG for COVID-19. Methods A 6-step rapid CIG development and dissemination approach was designed and applied. Processes, roles, and deliverable artifacts were specified in this approach to eliminate ambiguities during development of the CIG. The Guideline Definition Language (GDL) was used to capture the clinical rules. A CIG for COVID-19 was developed by translating, interpreting, annotating, extracting, and formalizing the Chinese COVID-19 diagnosis and treatment guideline. A prototype application was implemented to validate the CIG. Results We used 27 archetypes for the COVID-19 guideline. We developed 18 GDL rules to cover the diagnosis and treatment suggestion algorithms in the narrative guideline. The CIG was further translated to object data model and Drools rules to facilitate its use by people who do not employ the non-openEHR archetype. The prototype application validated the correctness of the CIG with a public data set. Both the GDL rules and Drools rules have been disseminated on GitHub. Conclusions Our rapid CIG development and dissemination approach accelerated the pace of COVID-19 CIG development. A validated COVID-19 CIG is now available to the public.

There is a Third Condition Aside from Survival and Death That Affects Outcome Statistics: Terminal Discharge

Background: Some patients discharged automatically are classified as terminal discharge, while their clinical outcome is survival, disrupting the results of clinical research.Methods: The data of this study were taken from inpatients who were admitted to the ICU of the First Medical Center of the People's Liberation Army General Hospital. We collected the data regarding medications used over the three days before discharge from the group of patients who survived and the group of patients who died, and the outcomes of all patients were recalculated by three classification algorithms (AdaBoosting, Pearson correlation coefficient, observed to expected ratio-weighted cosine similarity). Our basic assumption is that if the classification result is death but the actual in-hospital outcome is survival, the associated patient was likely terminally discharged.Results: The coincidence rate of the outcomes calculated by the AdaBoosting algorithm was 98.1%, the coincidence rate calculated by the Pearson correlation coefficient was 61.1%, and the coincidence rate calculated by the observed to expected ratio-weighted cosine similarity was 93.4%. When the three classification methods were combined, the accuracy reached 98.56%.Conclusion: The combination of clinical rules and classification methods has a synergistic effect on judgments of patients’ discharge outcomes, greatly saving time on manual retrieval and reducing the negative influence of statistics or rules.