The prevalence of clinically relevant delayed intracranial hemorrhage in head trauma patients treated with oral anticoagulants is very low: a retrospective cohort register study.

BACKGROUND: Current guidelines from Scandinavian Neuro Committee mandate a 24-hour observation for head trauma patients on anticoagulants, even with normal initial head CT scans, as a means not to miss delayed intracranial hemorrhages. This study aimed to assess the prevalence, and time to diagnosis, of clinically relevant delayed intracranial hemorrhage in head trauma patients treated with oral anticoagulants. METHOD: Utilizing comprehensive two-year data from Region Skåne's emergency departments, which serve a population of 1.3 million inhabitants, this study focused on adult head trauma patients prescribed oral anticoagulants. We identified those with intracranial hemorrhage within 30 days, defining delayed intracranial hemorrhage as a bleeding not apparent on their initial CT head scan. These cases were further defined as clinically relevant if associated with mortality, any intensive care unit admission, or neurosurgery. RESULTS: Out of the included 2,362 head injury cases (median age 84, 56% on a direct acting oral anticoagulant), five developed delayed intracranial hemorrhages. None of these five cases underwent neurosurgery nor were admitted to an intensive care unit. Only two cases (0.08%, 95% confidence interval [0.01-0.3%]) were classified as clinically relevant, involving subdural hematomas in patients aged 82 and 87 years, who both subsequently died. The diagnosis of these delayed intracranial hemorrhages was made at 4 and 7 days following initial presentation to the emergency department. CONCLUSION: In patients with head trauma, on oral anticoagulation, the incidence of clinically relevant delayed intracranial hemorrhage was found to be less than one in a thousand, with detection occurring four days or later after initial presentation. This challenges the effectiveness of the 24-hour observation period recommended by the Scandinavian Neurotrauma Committee guidelines, suggesting a need to reassess these guidelines to optimise care and resource allocation. TRIAL REGISTRATION: This is a retrospective cohort study, does not include any intervention, and has therefore not been registered.

The skåne emergency medicine (SEM) cohort.

BACKGROUND: In the European Union alone, more than 100 million people present to the emergency department (ED) each year, and this has increased steadily year-on-year by 2-3%. Better patient management decisions have the potential to reduce ED crowding, the number of diagnostic tests, the use of inpatient beds, and healthcare costs. METHODS: We have established the Skåne Emergency Medicine (SEM) cohort for developing clinical decision support systems (CDSS) based on artificial intelligence or machine learning as well as traditional statistical methods. The SEM cohort consists of 325 539 unselected unique patients with 630 275 visits from January 1st, 2017 to December 31st, 2018 at eight EDs in the region Skåne in southern Sweden. Data on sociodemographics, previous diseases and current medication are available for each ED patient visit, as well as their chief complaint, test results, disposition and the outcome in the form of subsequent diagnoses, treatments, healthcare costs and mortality within a follow-up period of at least 30 days, and up to 3 years. DISCUSSION: The SEM cohort provides a platform for CDSS research, and we welcome collaboration. In addition, SEM's large amount of real-world patient data with almost complete short-term follow-up will allow research in epidemiology, patient management, diagnostics, prognostics, ED crowding, resource allocation, and social medicine.

Factors most strongly associated with breathlessness in a population aged 50-64 years.

Background: Breathlessness is a troublesome and prevalent symptom in the population, but knowledge of related factors is scarce. The aim of this study was to identify the factors most strongly associated with breathlessness in the general population and to describe the shapes of the associations between the main factors and breathlessness. Methods: A cross-sectional analysis was carried out of the multicentre population-based Swedish CArdioPulmonary bioImage Study (SCAPIS) of adults aged 50 to 64 years. Breathlessness was defined as a modified Medical Research Council breathlessness rating ≥2. The machine learning algorithm extreme gradient boosting (XGBoost) was used to classify participants as either breathless or nonbreathless using 449 factors, including physiological measurements, blood samples, computed tomography cardiac and lung measurements, lifestyle, health conditions and socioeconomics. The strength of the associations between the factors and breathlessness were measured by SHapley Additive exPlanations (SHAP), with higher scores reflecting stronger associations. Results: A total of 28 730 participants (52% women) were included in the study. The strongest associated factors for breathlessness were (in order of magnitude): body mass index ( SHAP score 0.39), forced expiratory volume in 1 s (0.32), physical activity measured by accelerometery (0.27), sleep apnoea (0.22), diffusing lung capacity for carbon monoxide (0.21), self-reported physical activity (0.17), chest pain when hurrying (0.17), high-sensitivity C-reactive protein (0.17), recent weight change (0.14) and cough (0.13). Conclusion: This large population-based study of men and women aged 50-64 years identified the main factors related to breathlessness that may be prevented or amenable to public health interventions.

Prior electrocardiograms not useful for machine learning predictions of major adverse cardiac events in emergency department chest pain patients.

At the emergency department (ED), it is important to quickly and accurately determine which patients are likely to have a major adverse cardiac event (MACE). Machine learning (ML) models can be used to aid physicians in detecting MACE, and improving the performance of such models is an active area of research. In this study, we sought to determine if ML models can be improved by including a prior electrocardiogram (ECG) from each patient. To that end, we trained several models to predict MACE within 30 days, both with and without prior ECGs, using data collected from 19,499 consecutive patients with chest pain, from five EDs in southern Sweden, between the years 2017 and 2018. Our results indicate no improvement in AUC from prior ECGs. This was consistent across models, both with and without additional clinical input variables, for different patient subgroups, and for different subsets of the outcome. While contradicting current best practices for manual ECG analysis, the results are positive in the sense that ML models with fewer inputs are more easily and widely applicable in practice.

Factors important for health-related quality of life in men and women: The population based SCAPIS study.

INTRODUCTION: Health-related quality of life (HRQoL) is essential for human wellbeing, influenced by a complex interplay of factors, and is reported lower in women than men. We aimed to evaluate which factors were the most important for HRQoL in a middle-aged general population. METHODS: This was a cross-sectional, multi-centre study of 29,212 men (48%) and women (52%) aged 50-64 in the general population in Sweden. Physical and mental HRQoL (0-100) was assessed using the Short Form 12 questionnaire, and association was evaluated for 356 variables including demographics, lifestyle, symptoms, physiological measurements, and health conditions. Using machine learning, each variable´s importance for HRQoL was measured by an importance score, comparable to effect size, and summarised in 54 factors, in men and women separately. RESULTS: Men and women had similar mean and standard deviation (SD) scores for physical HRQoL (53.4 [SD 8.1] vs 51.4 [9.7]) and mental HRQoL (37.1 [5.0] vs 37.3 [5.4]). The most important factors for physical HRQoL were (importance score) physical activity (40), employment (36), pain (33), sleep (33), and sense of control (26). The most important factors for mental HRQoL were sense of control (18), physical activity (12), depression (12), pain (6), and employment (5). CONCLUSIONS: The factors important for HRQoL identified by this study are likely to be amenable to interventions, and our findings can support prioritising interventions. The identified factors need to be a target even before middle-age to lay the foundation for long and happy lives.

Machine learning for early prediction of acute myocardial infarction or death in acute chest pain patients using electrocardiogram and blood tests at presentation.

AIMS: In the present study, we aimed to evaluate the performance of machine learning (ML) models for identification of acute myocardial infarction (AMI) or death within 30 days among emergency department (ED) chest pain patients. METHODS AND RESULTS: Using data from 9519 consecutive ED chest pain patients, we created ML models based on logistic regression or artificial neural networks. Model inputs included sex, age, ECG and the first blood tests at patient presentation: High sensitivity TnT (hs-cTnT), glucose, creatinine, and hemoglobin. For a safe rule-out, the models were adapted to achieve a sensitivity > 99% and a negative predictive value (NPV) > 99.5% for 30-day AMI/death. For rule-in, we set the models to achieve a specificity > 90% and a positive predictive value (PPV) of > 70%. The models were also compared with the 0 h arm of the European Society of Cardiology algorithm (ESC 0 h); An initial hs-cTnT < 5 ng/L for rule-out and ≥ 52 ng/L for rule-in. A convolutional neural network was the best model and identified 55% of the patients for rule-out and 5.3% for rule-in, while maintaining the required sensitivity, specificity, NPV and PPV levels. ESC 0 h failed to reach these performance levels. DISCUSSION: An ML model based on age, sex, ECG and blood tests at ED arrival can identify six out of ten chest pain patients for safe early rule-out or rule-in with no need for serial blood tests. Future studies should attempt to improve these ML models further, e.g. by including additional input data.

Machine learning compared with rule-in/rule-out algorithms and logistic regression to predict acute myocardial infarction based on troponin T concentrations.

OBJECTIVE: Computerized decision-support tools may improve diagnosis of acute myocardial infarction (AMI) among patients presenting with chest pain at the emergency department (ED). The primary aim was to assess the predictive accuracy of machine learning algorithms based on paired high-sensitivity cardiac troponin T (hs-cTnT) concentrations with varying sampling times, age, and sex in order to rule in or out AMI. METHODS: In this register-based, cross-sectional diagnostic study conducted retrospectively based on 5695 chest pain patients at 2 hospitals in Sweden 2013-2014 we used 5-fold cross-validation 200 times in order to compare the performance of an artificial neural network (ANN) with European guideline-recommended 0/1- and 0/3-hour algorithms for hs-cTnT and with logistic regression without interaction terms. Primary outcome was the size of the intermediate risk group where AMI could not be ruled in or out, while holding the sensitivity (rule-out) and specificity (rule-in) constant across models. RESULTS: ANN and logistic regression had similar (95%) areas under the receiver operating characteristics curve. In patients (n = 4171) where the timing requirements (0/1 or 0/3 hour) for the sampling were met, using ANN led to a relative decrease of 9.2% (95% confidence interval 4.4% to 13.8%; from 24.5% to 22.2% of all tested patients) in the size of the intermediate group compared to the recommended algorithms. By contrast, using logistic regression did not substantially decrease the size of the intermediate group. CONCLUSION: Machine learning algorithms allow for flexibility in sampling and have the potential to improve risk assessment among chest pain patients at the ED.