The Price of Explainability in Machine Learning Models for 100-Day Readmission Prediction in Heart Failure: Retrospective, Comparative, Machine Learning Study.

BACKGROUND: Sensitive and interpretable machine learning (ML) models can provide valuable assistance to clinicians in managing patients with heart failure (HF) at discharge by identifying individual factors associated with a high risk of readmission. In this cohort study, we delve into the factors driving the potential utility of classification models as decision support tools for predicting readmissions in patients with HF. OBJECTIVE: The primary objective of this study is to assess the trade-off between using deep learning (DL) and traditional ML models to identify the risk of 100-day readmissions in patients with HF. Additionally, the study aims to provide explanations for the model predictions by highlighting important features both on a global scale across the patient cohort and on a local level for individual patients. METHODS: The retrospective data for this study were obtained from the Regional Health Care Information Platform in Region Halland, Sweden. The study cohort consisted of patients diagnosed with HF who were over 40 years old and had been hospitalized at least once between 2017 and 2019. Data analysis encompassed the period from January 1, 2017, to December 31, 2019. Two ML models were developed and validated to predict 100-day readmissions, with a focus on the explainability of the model's decisions. These models were built based on decision trees and recurrent neural architecture. Model explainability was obtained using an ML explainer. The predictive performance of these models was compared against 2 risk assessment tools using multiple performance metrics. RESULTS: The retrospective data set included a total of 15,612 admissions, and within these admissions, readmission occurred in 5597 cases, representing a readmission rate of 35.85%. It is noteworthy that a traditional and explainable model, informed by clinical knowledge, exhibited performance comparable to the DL model and surpassed conventional scoring methods in predicting readmission among patients with HF. The evaluation of predictive model performance was based on commonly used metrics, with an area under the precision-recall curve of 66% for the deep model and 68% for the traditional model on the holdout data set. Importantly, the explanations provided by the traditional model offer actionable insights that have the potential to enhance care planning. CONCLUSIONS: This study found that a widely used deep prediction model did not outperform an explainable ML model when predicting readmissions among patients with HF. The results suggest that model transparency does not necessarily compromise performance, which could facilitate the clinical adoption of such models.

Development of a prehospital prediction model for risk stratification of patients with chest pain.

INTRODUCTION: Chest pain is one of the most common reasons for contacting the emergency medical services (EMS). About 15% of these chest pain patients have a high-risk condition, while many of them have a low-risk condition with no need for acute hospital care. It is challenging to at an early stage distinguish whether patients have a low- or high-risk condition. The objective of this study has been to develop prediction models for optimising the identification of patients with low- respectively high-risk conditions in acute chest pain early in the EMS work flow. METHODS: This prospective observational cohort study included 2578 EMS missions concerning patients who contacted the EMS in a Swedish region due to chest pain in 2018. All the patients were assessed as having a low-, intermediate- or high-risk condition, i.e. occurrence of a time-sensitive diagnosis at discharge from hospital. Multivariate regression analyses using data on symptoms and symptom onset, clinical findings including ECG, previous medical history and Troponin T were carried out to develop models for identification of patients with low- respectively high-risk conditions. Developed models where then tested hold-out data set for internal validation and assessing their accuracy. RESULTS: Prediction models for risk-stratification based on variables mutual for both low- and high-risk prediction were developed. The variables included were: age, sex, previous medical history of kidney disease, atrial fibrillation or heart failure, Troponin T, ST-depression on ECG, paleness, pain debut during activity, constant pain, pain in right arm and pressuring pain quality. The high-risk model had an area under the receiving operating characteristic curve of 0.85 and the corresponding figure for the low-risk model was 0.78. CONCLUSIONS: Models based on readily available information in the EMS setting can identify high- and low-risk conditions with acceptable accuracy. A clinical decision support tool based on developed models may provide valuable clinical guidance and facilitate referral to less resource-intensive venues.

Improving Machine Learning 30-Day Mortality Prediction by Discounting Surprising Deaths.

BACKGROUND: Machine learning (ML) is an emerging tool for predicting need of end-of-life discussion and palliative care, by using mortality as a proxy. But deaths, unforeseen by emergency physicians at time of the emergency department (ED) visit, might have a weaker association with the ED visit. OBJECTIVES: To develop an ML algorithm that predicts unsurprising deaths within 30 days after ED discharge. METHODS: In this retrospective registry study, we included all ED attendances within the Swedish region of Halland in 2015 and 2016. All registered deaths within 30 days after ED discharge were classified as either "surprising" or "unsurprising" by an adjudicating committee with three senior specialists in emergency medicine. ML algorithms were developed for the death subclasses by using Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM). RESULTS: Of all 30-day deaths (n = 148), 76% (n = 113) were not surprising to the adjudicating committee. The most common diseases were advanced stage cancer, multidisease/frailty, and dementia. By using LR, RF, and SVM, mean area under the receiver operating characteristic curve (ROC-AUC) of unsurprising deaths in the test set were 0.950 (SD 0.008), 0.944 (SD 0.007), and 0.949 (SD 0.007), respectively. For all mortality, the ROC-AUCs for LR, RF, and SVM were 0.924 (SD 0.012), 0.922 (SD 0.009), and 0.931 (SD 0.008). The difference in prediction performance between all and unsurprising death was statistically significant (P < .001) for all three models. CONCLUSION: In patients discharged to home from the ED, three-quarters of all 30-day deaths did not surprise an adjudicating committee with emergency medicine specialists. When only unsurprising deaths were included, ML mortality prediction improved significantly.

Likelihood of admission to hospital from the emergency department is not universally associated with hospital bed occupancy at the time of admission.

BACKGROUND: The decision to admit into the hospital from the emergency department (ED) is considered to be important and challenging. The aim was to assess whether previously published results suggesting an association between hospital bed occupancy and likelihood of hospital admission from the ED can be reproduced in a different study population. METHODS: A retrospective cohort study of attendances at two Swedish EDs in 2015 was performed. Admission to hospital was assessed in relation to hospital bed occupancy together with other clinically relevant variables. Hospital bed occupancy was categorized and univariate and multivariate logistic regression were performed. RESULTS: In total 89,503 patient attendances were included in the final analysis. Of those, 29.1% resulted in admission within 24 h. The mean hospital bed occupancy by the hour of the two hospitals was 87.1% (SD 7.6). In both the univariate and multivariate analysis, odds ratio for admission within 24 h from the ED did not decrease significantly with an increasing hospital bed occupancy. CONCLUSIONS: A negative association between admission to hospital and occupancy level, as reported elsewhere, was not replicated. This suggests that the previously shown association might not be universal but may vary across sites due to setting specific circumstances.

Spatial peak and mean QRS-T angles: A comparison of similar but different emerging risk factors for cardiac death.

BACKGROUND: The spatial peak and mean QRS-T angles are scientifically but not clinically established risk factors for cardiovascular events including cardiac death. The study aims were to compare these angles, assess their association with hypertension (HT) and diabetes mellitus (DM), and explore the relation between the mean QRS-T angle and the ventricular gradient (VG; reflecting electrical heterogeneity), which both are derived from the QRSarea and Tarea vectors. METHODS: Altogether 1094 participants (aged 50-65 years, 550 women) from the pilot of the population-based Swedish CArdioPulmonary bioImage Study with Frank vectorcardiographic recordings were included and divided into 5 subgroups: apparently healthy n = 320; HT n = 311; DM n = 33; DM + HT n = 53; miscellaneous conditions n = 377. Abnormal peak and mean QRS-T angles were defined as >95th percentile. RESULTS: Peak QRS-T angles were generally narrower than the mean QRS-T angles; both were narrower in women than in men. Abnormal peak (>124°) and/or mean (>119°) QRS-T angles were found in 73 participants (6.7%). The concordance regarding abnormal versus normal-borderline QRS-T angles was good (Cohen's kappa 0.61). The prevalence of abnormal angles varied from 2.5% in healthy to 21.2% in DM. There was an inverse logarithmical relation between the mean QRS-T angle and the VG. CONCLUSIONS: The peak and mean QRS-T angles are not interchangeable but complementary. DM, HT, sex and absence of disease are important determinants of both QRS-T angles. The mean QRS-T angle and the VG relationship is complex. All three VCG derived measures reflect related but differing electrophysiological properties and have potential prognostic value vis-à-vis cardiovascular events.

Long-Term Effects of Oxygen Therapy on Death or Hospitalization for Heart Failure in Patients With Suspected Acute Myocardial Infarction

Background: In the DETO2X-AMI trial (Determination of the Role of Oxygen in Suspected Acute Myocardial Infarction), we compared supplemental oxygen with ambient air in normoxemic patients presenting with suspected myocardial infarction and found no significant survival benefit at 1 year. However, important secondary end points were not yet available. We now report the prespecified secondary end points cardiovascular death and the composite of all-cause death and hospitalization for heart failure. Methods: In this pragmatic, registry-based randomized clinical trial, we used a nationwide quality registry for coronary care for trial procedures and evaluated end points through the Swedish population registry (mortality), the Swedish inpatient registry (heart failure), and cause of death registry (cardiovascular death). Patients with suspected acute myocardial infarction and oxygen saturation of ≥90% were randomly assigned to receive either supplemental oxygen at 6 L/min for 6 to 12 hours delivered by open face mask or ambient air. Results: A total of 6629 patients were enrolled. Acute heart failure treatment, left ventricular systolic function assessed by echocardiography, and infarct size measured by high-sensitive cardiac troponin T were similar in the 2 groups during the hospitalization period. All-cause death or hospitalization for heart failure within 1 year after randomization occurred in 8.0% of patients assigned to oxygen and in 7.9% of patients assigned to ambient air (hazard ratio, 0.99; 95% CI, 0.84­1.18; P=0.92). During long-term follow-up (median [range], 2.1 [1.0­3.7] years), the composite end point occurred in 11.2% of patients assigned to oxygen and in 10.8% of patients assigned to ambient air (hazard ratio, 1.02; 95% CI, 0.88­1.17; P=0.84), and cardiovascular death occurred in 5.2% of patients assigned to oxygen and in 4.8% assigned to ambient air (hazard ratio, 1.07; 95% CI, 0.87­1.33; P=0.52). The results were consistent across all predefined subgroups. Conclusions: Routine use of supplemental oxygen in normoxemic patients with suspected myocardial infarction was not found to reduce the composite of all-cause mortality and hospitalization for heart failure, or cardiovascular death within 1 year or during long-term follow-up. Clinical Trial Registration: URL: https://www.clinicaltrials.gov. Unique identifier: NCT01787110.

Readmission prediction using deep learning on electronic health records.

Unscheduled 30-day readmissions are a hallmark of Congestive Heart Failure (CHF) patients that pose significant health risks and escalate care cost. In order to reduce readmissions and curb the cost of care, it is important to initiate targeted intervention programs for patients at risk of readmission. This requires identifying high-risk patients at the time of discharge from hospital. Here, using real data from over 7500 CHF patients hospitalized between 2012 and 2016 in Sweden, we built and tested a deep learning framework to predict 30-day unscheduled readmission. We present a cost-sensitive formulation of Long Short-Term Memory (LSTM) neural network using expert features and contextual embedding of clinical concepts. This study targets key elements of an Electronic Health Record (EHR) driven prediction model in a single framework: using both expert and machine derived features, incorporating sequential patterns and addressing the class imbalance problem. We evaluate the contribution of each element towards prediction performance (ROC-AUC, F1-measure) and cost-savings. We show that the model with all key elements achieves higher discrimination ability (AUC: 0.77; F1: 0.51; Cost: 22% of maximum possible savings) outperforming the reduced models in at least two evaluation metrics. Additionally, we present a simple financial analysis to estimate annual savings if targeted interventions are offered to high risk patients.

Symptom description in patients with chest pain-A qualitative analysis of emergency medical calls involving high-risk conditions.

AIMS AND OBJECTIVES: To explore the symptoms descriptions and situational information provided by patients during ongoing chest pain events caused by a high-risk condition. BACKGROUND: Chest pain is a common symptom in patients contacting emergency dispatch centres. Only 15% of these patients are later classified as suffering from a high-risk condition. Prehospital personnel are largely dependent on symptom characteristics when trying to identify these patients. DESIGN: Qualitative descriptive. METHODS: Manifest content analysis of 56 emergency medical calls involving patients with chest pain was carried out. A stratified purposive sampling was used to obtain calls concerning patients with high-risk conditions. These calls were then listened to and transcribed. Thereafter, meaning units were identified and coded and finally categorised. Consolidated criteria for reporting qualitative studies guidelines have been applied. RESULTS: A wide range of situational information and symptoms descriptions was found. Pain and affected breathing were dominating aspects, but other situational information and several other symptoms were also reported. The situational information and these symptoms were classified into seven categories: Pain narrative, Affected breathing, Bodily reactions, Time, Bodily whereabouts, Fear and concern and Situation management. The seven categories consisted of 17 subcategories. CONCLUSIONS: Patients with chest pain caused by a high-risk condition present a wide range of symptoms which are described in a variety of ways. They describe different kinds of chest pain accompanied by pain from other parts of the body. Breathing difficulties and bodily reactions such as muscle weakness are also reported. The variety of symptoms and the absence of a typical symptomatology make risk stratification on the basis of symptoms alone difficult. RELEVANCE TO CLINICAL PRACTICE: This study highlights the importance of an open mind when assessing patients with chest pain and the requirement of a decision support tool in order to improve risk stratification in these patients.

Transient repolarization alterations dominate the initial phase of an acute anterior infarction--a vectorcardiography study.

OBJECTIVE: To study effects of ischemia-reperfusion on ventricular electrophysiology in humans by three-dimensional electrocardiography. METHODS: Fifty-seven patients with first-time acute anterior ST elevation myocardial infarction were monitored from admission and >24h after symptom onset with continuous vectorcardiography (VCG; modified Frank orthogonal leads). Global ventricular depolarization and repolarization (VR) measures were compared at maximum vs. minimum ST vector magnitude (STVM) (median 208; 111-303 vs. 362; 165-1359min after symptom onset). RESULTS: At maximum vs. minimum STVM the Tarea (overall VR dispersion) almost tripled (118 vs. 41µVs; p<0.0001), the T-loop bulginess was 90% greater (Tavplan 0.91 vs 0.48µV; p<0.0001), and Tpeak-end/QT was 39% larger (0.32 vs 0.23; p<0.0001). QRSarea (overall dispersion of depolarization) was 12% larger at maximum STVM, while QRS duration was 10% longer at minimum STVM. CONCLUSIONS: Ischemia-reperfusion was accompanied by profound and transient alterations of VR dispersion, while changes in depolarization were modest and delayed.

Synthetic electronic health records generated with variational graph autoencoders.

Data-driven medical care delivery must always respect patient privacy-a requirement that is not easily met. This issue has impeded improvements to healthcare software and has delayed the long-predicted prevalence of artificial intelligence in healthcare. Until now, it has been very difficult to share data between healthcare organizations, resulting in poor statistical models due to unrepresentative patient cohorts. Synthetic data, i.e., artificial but realistic electronic health records, could overcome the drought that is troubling the healthcare sector. Deep neural network architectures, in particular, have shown an incredible ability to learn from complex data sets and generate large amounts of unseen data points with the same statistical properties as the training data. Here, we present a generative neural network model that can create synthetic health records with realistic timelines. These clinical trajectories are generated on a per-patient basis and are represented as linear-sequence graphs of clinical events over time. We use a variational graph autoencoder (VGAE) to generate synthetic samples from real-world electronic health records. Our approach generates health records not seen in the training data. We show that these artificial patient trajectories are realistic and preserve patient privacy and can therefore support the safe sharing of data across organizations.

Health-related quality of life and long-term symptoms among patients with non-severe covid-19 - a prospective cohort study.

BACKGROUND: The vast majority of covid-19 patients experience non-severe disease. Nonetheless, long-term symptoms may be common and the impact on quality of life is uncertain. This study aims to examine these aspects in a prospective, longitudinal cohort. METHODS: Non-hospitalised patients with PCR-confirmed covid-19 were prospectively invited to self-report assessments of background data, symptoms and recovery, illness perception (BIPQ) and health-related quality of life (HR-Qol) measured by EQ5D-VAS. RESULTS: 154 patients were included (mean age 46 years, 69% female). The majority of participants (65%) had symptoms for 1-4 weeks and 12% more than 6 months. The most common symptoms were initially malaise, fatigue, headache, fever and cough and the most common long-term symptoms were impaired physical condition, fatigue, anosmia and headache. The BIPQ index had a negative correlation with the EQ5D-VAS score after the infection, but not with long-term symptoms. Mean differences in the EQ5D-VAS score were significantly lower after the infection and patients with long-term symptoms had a more pronounced negative effect in EQ5D-VAS scores. CONCLUSION: We found that most patients with non-severe covid-19 reported symptoms for 1-4 weeks and approximately 10% developed long-term symptoms. Non-severe covid-19 seems to have a negative influence on HR-Qol, especially in patients with long-term symptoms and with a greater burden from the disease. None of the initial symptoms could predict the presence of long-term symptoms.

Characteristics, management and outcomes in patients with CKD in a healthcare region in Sweden: a population-based, observational study.

OBJECTIVES: To describe chronic kidney disease (CKD) regarding treatment rates, comorbidities, usage of CKD International Classification of Diseases (ICD) diagnosis, mortality, hospitalisation, evaluate healthcare utilisation and screening for CKD in relation to new nationwide CKD guidelines. DESIGN: Population-based observational study. SETTING: Healthcare registry data of patients in Southwest Sweden. PARTICIPANTS: A total cohort of 65 959 individuals aged >18 years of which 20 488 met the criteria for CKD (cohort 1) and 45 470 at risk of CKD (cohort 2). PRIMARY AND SECONDARY OUTCOME MEASURES: Data were analysed with regards to prevalence, screening rates of blood pressure, glucose, estimated glomerular filtration rate (eGFR), Urinary-albumin-creatinine ratio (UACR) and usage of ICD-codes for CKD. Mortality and hospitalisation were analysed with logistic regression models. RESULTS: Of the CKD cohort, 18% had CKD ICD-diagnosis and were followed annually for blood pressure (79%), glucose testing (76%), eGFR (65%), UACR (24%). UACR follow-up was two times as common in hypertensive and cardiovascular versus diabetes patients with CKD with a similar pattern in those at risk of CKD. Statin and renin-angiotensin-aldosterone inhibitor appeared in 34% and 43%, respectively. Mortality OR at CKD stage 5 was 1.23 (CI 0.68 to 0.87), diabetes 1.20 (CI 1.04 to 1.38), hypertension 1.63 (CI 1.42 to 1.88), atherosclerotic cardiovascular disease (ASCVD) 1.84 (CI 1.62 to 2.09) associated with highest mortality risk. Hospitalisation OR in CKD stage 5 was 1.96 (CI 1.40 to 2.76), diabetes 1.15 (CI 1.06 to 1.25), hypertension 1.23 (CI 1.13 to 1.33) and ASCVD 1.52 (CI 1.41 to 1.64). CONCLUSIONS: The gap between patients with CKD by definition versus those diagnosed as such was large. Compared with recommendations patients with CKD have suboptimal follow-up and treatment with renin-angiotensin-aldosterone system inhibitor and statins. Hypertension, diabetes and ASCVD were associated with increased mortality and hospitalisation. Improved screening and diagnosis of CKD, identification and management of risk factors and kidney protective treatment could affect clinical and economic outcomes.

The potential of new prediction models for emergency medical dispatch prioritisation of patients with chest pain: a cohort study.

OBJECTIVES: To develop emergency medical dispatch (EMD) centre prediction models with high sensitivity and satisfying specificity to identify high-priority patients and patients suitable for non-emergency care respectively, when assessing patients with chest pain. METHODS: Observational cohort study of 2917 unselected patients with chest pain who contacted an EMD centre in Sweden due to chest pain during 2018. Multivariate logistic regression was applied to develop models predicting low-risk or high-risk condition, that is, occurrence of time-sensitive diagnosis on hospital discharge. RESULTS: Prediction models were developed for the identification of patients suitable for high- and low-priority dispatch, using 11 and 10 variables respectively. The area under the receiver-operating characteristic curve (AUROC) for the high-risk prediction model was 0.79 and for the low-risk model it was 0.74. When applying the high-risk prediction model, 56% of the EMS missions were given highest priority, compared with 65% with the current standard. When applying the low-risk model, 7% were given the lowest priority compared to 1% for the current standard. The new prediction models outperformed today's dispatch priority accuracy in terms of sensitivity as well as positive and negative predictive value in both high- and low-risk prediction. The low-risk model predicted almost six times as many patients as having low-risk conditions compared with today's standard. This was done without increasing the number of high-risk patients wrongly assessed as low-risk. CONCLUSIONS: By introducing prediction models, based on logistic regression analyses, using variables obtained by standard EMD-questions on age, sex, medical history and symptomology, EMD prioritisation can be improved compared with using current criteria index-based ones. This will allow a more efficient emergency medical services resource allocation.

Clinical presentation in EMS patients with acute chest pain in relation to sex, age and medical history: prospective cohort study.

OBJECTIVE: To assess symptom presentation related to age, sex and previous medical history in patients with chest pain. DESIGN: Prospective observational cohort study. SETTING: Two-centre study in a Swedish county emergency medical service (EMS) organisation. PARTICIPANTS: Unselected inclusion of 2917 patients with chest pain cared for by the EMS during 2018. DATA ANALYSIS: Multivariate analysis on the association between symptom characteristics, patients' sex, age, previous acute coronary syndrome (ACS) or diabetes and the final outcome of acute myocardial infarction (AMI). RESULTS: Symptomology in patients assessed by the EMS due to acute chest pain varied with sex and age and also with previous ACS or diabetes. Women suffered more often from nausea (OR 1.6) and pain in throat (OR 2.1) or back (OR 2.1). Their pain was more often affected by palpation (1.7) or movement (OR 1.4). Older patients more often described pain onset while sleeping (OR 1.5) and that the onset of symptoms was slow, over hours rather than minutes (OR 1.4). They were less likely to report pain in other parts of their body than their chest (OR 1.4). They were to a lesser extent clammy (OR 0.6) or nauseous (OR 0.6). These differences were present regardless of whether the symptoms were caused by AMI or not. CONCLUSIONS: A number of aspects of the symptom of chest pain appear to differ in unselected prehospital patients with chest pain in relation to age, sex and medical history, regardless of whether the chest pain was caused by a myocardial infarction or not. This complicates the possibility in prehospital care of using symptoms to predict the underlying aetiology of acute chest pain.

Prehospital stratification in acute chest pain patient into high risk and low risk by emergency medical service: a prospective cohort study.

OBJECTIVES: To describe contemporary characteristics and diagnoses in prehospital patients with chest pain and to identify factors suitable for the early recognition of high-risk and low-risk conditions. DESIGN: Prospective observational cohort study. SETTING: Two centre study in a Swedish county emergency medical services (EMS) organisation. PARTICIPANTS: Unselected inclusion of 2917 patients with chest pain contacting the EMS due to chest pain during 2018. PRIMARY OUTCOME MEASURES: Low-risk or high-risk condition, that is, occurrence of time-sensitive diagnosis on hospital discharge. RESULTS: Of included EMS missions, 68% concerned patients with a low-risk condition without medical need of acute hospital treatment in hindsight. Sixteen per cent concerned patients with a high-risk condition in need of rapid transport to hospital care. Numerous variables with significant association with low-risk or high-risk conditions were found. In total high-risk and low-risk prediction models shared six predictive variables of which ST-depression on ECG and age were most important. Previously known risk factors such as history of acute coronary syndrome, diabetes and hypertension had no predictive value in the multivariate analyses. Some aspects of the symptoms such as pain intensity, pain in the right arm and paleness did on the other hand appear to be helpful. The area under the curve (AUC) for prediction of low-risk candidates was 0.786 and for high-risk candidates 0.796. The addition of troponin in a subset increased the AUC to >0.8 for both. CONCLUSIONS: A majority of patients with chest pain cared for by the EMS suffer from a low-risk condition and have no prognostic reason for acute hospital care given their diagnosis on hospital discharge. A smaller proportion has a high-risk condition and is in need of prompt specialist care. Building models with good accuracy for prehospital identification of these groups is possible. The use of risk stratification models could make a more personalised care possible with increased patient safety.

Guideline adherence among prehospital emergency nurses when caring for patients with chest pain: a prospective cohort study.

BACKGROUND: The emergency medical services (EMS) use guidelines to describe optimal patient care for a wide range of clinical conditions and symptoms. The intent is to guide personnel to provide patient care in line with best practice. The aim of this study is to describe adherence to such guidelines among prehospital emergency nurses (PENs) when caring for patients with chest pain. OBJECTIVE: To describe guideline adherence among PENs when caring for patients with chest pain. To investigate whether guideline adherence is associated with patient age, sex or final diagnosis of acute myocardial infarction on hospital discharge. METHODS: Guideline adherence in terms of patient examination and pharmaceutical treatment was analysed in a cohort of 2092 EMS missions carried out in 2018 in Region Halland, Sweden. Multivariate regression was used to describe how guideline adherence is associated with patient age, sex and diagnosis on hospital discharge. RESULTS: Guideline adherence was high regarding examination of vital signs (93%) and electrocardiogram (ECG) registration (96%) but lower in terms of pharmaceutical treatment (ranging from 28 to 90%). Adherence was increased in cases in which the patient ended up with acute myocardial infarction (AMI) as diagnosis on discharge. Patients with AMI were given acetylsalicylic acid by PENs in 50% of cases. Women were less likely than men to receive treatment with acetylsalicylic acid and oxycodone. CONCLUSIONS: Guideline adherence among PENs when caring for patients with chest pain is satisfactory in terms vital signs and ECG registration. Regarding pharmaceutical treatment guideline adherence is defective. Improved adherence is mainly associated with male sex in patients and a diagnosis of AMI on hospital discharge. Defective adherence excludes measures known to improve patients' prognoses such as treatment with acetylsalicylic acid.

Dynamics of IgG-avidity and antibody levels after Covid-19.

BACKGROUND: A potentially important aspect of the humoral immune response to Covid-19 is avidity, the overall binding strength between antibody and antigen. As low avidity is associated with a risk of re- infection in several viral infections, avidity might be of value to predict risk for reinfection with covid-19. OBJECTIVES: The purpose of this study was to describe the maturation of IgG avidity and the antibody-levels over time in patients with PCR-confirmed non-severe covid-19. STUDY DESIGN: Prospective longitudinal cohort study including patients with RT-PCR confirmed covid-19. Blood samples were drawn 1, 3 and 6 months after infection. Antibody levels and IgG-avidity were analysed. RESULTS: The majority had detectable s- and n-antibodies (88,1%, 89,1%, N = 75). The level of total n-antibodies significantly increased from 1 to 3 months (median value 28,3 vs 39,3 s/co, p<0.001) and significantly decreased from 3 to 6 months (median value 39,3 vs 17,1 s/co, p<0.001). A significant decrease in the IgG anti-spike levels (median value 37,6, 24,1 and 18,2 RU/ml, p<0.001) as well as a significant increase in the IgG-avidity index (median values 51,6, 66,0 and 71,0%, p<0.001) were seen from 1 to 3 to 6 months. CONCLUSION: We found a significant ongoing increase in avidity maturation after Covid-19 whilst the levels of antibodies were declining, suggesting a possible aspect of long-term immunity.

Receiving care according to national heart failure guidelines is associated with lower total costs: an observational study in Region Halland, Sweden.

AIMS: Patients with heart failure (HF) have high costs, morbidity, and mortality, but it is not known if appropriate pharmacotherapy (AP), defined as compliance with international evidence-based guidelines, is associated with improved costs and outcomes. The purpose of this study was to evaluate HF patients' health care utilization, cost and outcomes in Region Halland (RH), Sweden, and if AP was associated with lower costs. METHODS AND RESULTS: A total of 5987 residents of RH in 2016 carried HF diagnoses. Costs were assigned to all health care utilization (inpatient, outpatient, emergency department, primary health care, and medications) using a Patient Encounter Costing methodology. Care of HF patients cost €58.6 M, (€9790/patient) representing 8.7% of RH's total visit expenses and 14.9% of inpatient care (IPC) expenses. Inpatient care represented 57.2% of this expenditure, totalling €33.5 M (€5601/patient). Receiving AP was associated with significantly lower costs, by €1130 per patient (P < 0.001, 95% confidence interval 574-1687). Comorbidities such as renal failure, diabetes, chronic obstructive pulmonary disease, and cancer were significantly associated with higher costs. CONCLUSION: Heart failure patients are heavy users of health care, particularly IPC. Receiving AP is associated with lower costs even adjusting for comorbidities, although causality cannot be proven from an observational study. There may be an opportunity to decrease overall costs and improve outcomes by improving prescribing patterns and associated high-quality care.

Pitfalls of medication adherence approximation through EHR and pharmacy records: Definitions, data and computation.

BACKGROUND AND PURPOSE: Patients' adherence to medication is a complex, multidimensional phenomenon. Dispensation data and electronic health records are used to approximate medication-taking through refill adherence. In-depth discussions on the adverse effects of data quality and computational differences are rare. The purpose of this article is to evaluate the impact of common pitfalls when computing medication adherence using electronic health records. PROCEDURES: We point out common pitfalls associated with the data and operationalization of adherence measures. We provide operational definitions of refill adherence and conduct experiments to determine the effect of the pitfalls on adherence estimations. We performed statistical significance testing on the impact of common pitfalls using a baseline scenario as reference. FINDINGS: Slight changes in definition can significantly skew refill adherence estimates. Pickup patterns cause significant disagreement between measures and the commonly used proportion of days covered. Common data related issues had a small but statistically significant (p < 0.05) impact on population-level and significant effect on individual cases. CONCLUSION: Data-related issues encountered in real-world administrative databases, which affect various operational definitions of refill adherence differently, can significantly skew refill adherence values, leading to false conclusions about adherence, particularly when estimating adherence for individuals.

Training machine learning models to predict 30-day mortality in patients discharged from the emergency department: a retrospective, population-based registry study.

OBJECTIVES: The aim of this work was to train machine learning models to identify patients at end of life with clinically meaningful diagnostic accuracy, using 30-day mortality in patients discharged from the emergency department (ED) as a proxy. DESIGN: Retrospective, population-based registry study. SETTING: Swedish health services. PRIMARY AND SECONDARY OUTCOME MEASURES: All cause 30-day mortality. METHODS: Electronic health records (EHRs) and administrative data were used to train six supervised machine learning models to predict all-cause mortality within 30 days in patients discharged from EDs in southern Sweden, Europe. PARTICIPANTS: The models were trained using 65 776 ED visits and validated on 55 164 visits from a separate ED to which the models were not exposed during training. RESULTS: The outcome occurred in 136 visits (0.21%) in the development set and in 83 visits (0.15%) in the validation set. The model with highest discrimination attained ROC-AUC 0.95 (95% CI 0.93 to 0.96), with sensitivity 0.87 (95% CI 0.80 to 0.93) and specificity 0.86 (0.86 to 0.86) on the validation set. CONCLUSIONS: Multiple models displayed excellent discrimination on the validation set and outperformed available indexes for short-term mortality prediction interms of ROC-AUC (by indirect comparison). The practical utility of the models increases as the data they were trained on did not require costly de novo collection but were real-world data generated as a by-product of routine care delivery.