Explore the vast range of titles available.

The COVID-19 pandemic has devastated the world with health and economic wreckage. Precise estimates of adverse outcomes from COVID-19 could have led to better allocation of healthcare resources and more efficient targeted preventive measures, including insight into prioritizing how to best distribute a vaccination. We developed MLHO (pronounced as melo), an end-to-end Machine Learning framework that leverages iterative feature and algorithm selection to predict Health Outcomes. MLHO implements iterative sequential representation mining, and feature and model selection, for predicting patient-level risk of hospitalization, ICU admission, need for mechanical ventilation, and death. It bases this prediction on data from patients’ past medical records (before their COVID-19 infection). MLHO’s architecture enables a parallel and outcome-oriented model calibration, in which different statistical learning algorithms and vectors of features are simultaneously tested to improve prediction of health outcomes. Using clinical and demographic data from a large cohort of over 13,000 COVID-19-positive patients, we modeled the four adverse outcomes utilizing about 600 features representing patients’ pre-COVID health records and demographics. The mean AUC ROC for mortality prediction was 0.91, while the prediction performance ranged between 0.80 and 0.81 for the ICU, hospitalization, and ventilation. We broadly describe the clusters of features that were utilized in modeling and their relative influence for predicting each outcome. Our results demonstrated that while demographic variables (namely age) are important predictors of adverse outcomes after a COVID-19 infection, the incorporation of the past clinical records are vital for a reliable prediction model. As the COVID-19 pandemic unfolds around the world, adaptable and interpretable machine learning frameworks (like MLHO) are crucial to improve our readiness for confronting the potential future waves of COVID-19, as well as other novel infectious diseases that may emerge.

The SARS-CoV-2 Omicron subvariant, BA.2, may be less severe than previous variants; however, confounding factors make interpreting the intrinsic severity challenging. To compare the adjusted risks of mortality, hospitalization, intensive care unit admission, and invasive ventilation between the BA.2 subvariant and the Omicron and Delta variants, after accounting for multiple confounders. This was a retrospective cohort study that applied an entropy balancing approach. Patients in a multicenter inpatient and outpatient system in New England with COVID-19 between March 3, 2020, and June 20, 2022, were identified. Cases were assigned as being exposed to the Delta (B.1.617.2) variant, the Omicron (B.1.1.529) variant, or the Omicron BA.2 lineage subvariants. The primary study outcome planned before analysis was risk of 30-day mortality. Secondary outcomes included the risks of hospitalization, invasive ventilation, and intensive care unit admissions. Of 102 315 confirmed COVID-19 cases (mean [SD] age, 44.2 [21.6] years; 63 482 women [62.0%]), 20 770 were labeled as Delta variants, 52 605 were labeled as the Omicron B.1.1.529 variant, and 28 940 were labeled as Omicron BA.2 subvariants. Patient cases were excluded if they occurred outside the prespecified temporal windows associated with the variants or had minimal longitudinal data in the Mass General Brigham system before COVID-19. Mortality rates were 0.7% for Delta (B.1.617.2), 0.4% for Omicron (B.1.1.529), and 0.3% for Omicron (BA.2). The adjusted odds ratio of mortality from the Delta variant compared with the Omicron BA.2 subvariants was 2.07 (95% CI, 1.04-4.10) and that of the original Omicron variant compared with the Omicron BA.2 subvariant was 2.20 (95% CI, 1.56-3.11). For all outcomes, the Omicron BA.2 subvariants were significantly less severe than that of the Omicron and Delta variants. In this cohort study, after having accounted for a variety of confounding factors associated with SARS-CoV-2 outcomes, the Omicron BA.2 subvariant was found to be intrinsically less severe than both the Delta and Omicron variants. With respect to these variants, the severity profile of SARS-CoV-2 appears to be diminishing after taking into account various factors including therapeutics, vaccinations, and prior infections.

This study aims to predict death after COVID-19 using only the past medical information routinely collected in electronic health records (EHRs) and to understand the differences in risk factors across age groups. Combining computational methods and clinical expertise, we curated clusters that represent 46 clinical conditions as potential risk factors for death after a COVID-19 infection. We trained age-stratified generalized linear models (GLMs) with component-wise gradient boosting to predict the probability of death based on what we know from the patients before they contracted the virus. Despite only relying on previously documented demographics and comorbidities, our models demonstrated similar performance to other prognostic models that require an assortment of symptoms, laboratory values, and images at the time of diagnosis or during the course of the illness. In general, we found age as the most important predictor of mortality in COVID-19 patients. A history of pneumonia, which is rarely asked in typical epidemiology studies, was one of the most important risk factors for predicting COVID-19 mortality. A history of diabetes with complications and cancer (breast and prostate) were notable risk factors for patients between the ages of 45 and 65 years. In patients aged 65–85 years, diseases that affect the pulmonary system, including interstitial lung disease, chronic obstructive pulmonary disease, lung cancer, and a smoking history, were important for predicting mortality. The ability to compute precise individual-level risk scores exclusively based on the EHR is crucial for effectively allocating and distributing resources, such as prioritizing vaccination among the general population.

Admissions are generally classified as COVID-19 hospitalizations if the patient has a positive SARS-CoV-2 polymerase chain reaction (PCR) test. However, because 35% of SARS-CoV-2 infections are asymptomatic, patients admitted for unrelated indications with an incidentally positive test could be misclassified as a COVID-19 hospitalization. Electronic health record (EHR)-based studies have been unable to distinguish between a hospitalization specifically for COVID-19 versus an incidental SARS-CoV-2 hospitalization. Although the need to improve classification of COVID-19 versus incidental SARS-CoV-2 is well understood, the magnitude of the problems has only been characterized in small, single-center studies. Furthermore, there have been no peer-reviewed studies evaluating methods for improving classification. The aims of this study are to, first, quantify the frequency of incidental hospitalizations over the first 15 months of the pandemic in multiple hospital systems in the United States and, second, to apply electronic phenotyping techniques to automatically improve COVID-19 hospitalization classification. From a retrospective EHR-based cohort in 4 US health care systems in Massachusetts, Pennsylvania, and Illinois, a random sample of 1123 SARS-CoV-2 PCR-positive patients hospitalized from March 2020 to August 2021 was manually chart-reviewed and classified as \"admitted with COVID-19\" (incidental) versus specifically admitted for COVID-19 (\"for COVID-19\"). EHR-based phenotyping was used to find feature sets to filter out incidental admissions. EHR-based phenotyped feature sets filtered out incidental admissions, which occurred in an average of 26% of hospitalizations (although this varied widely over time, from 0% to 75%). The top site-specific feature sets had 79%-99% specificity with 62%-75% sensitivity, while the best-performing across-site feature sets had 71%-94% specificity with 69%-81% sensitivity. A large proportion of SARS-CoV-2 PCR-positive admissions were incidental. Straightforward EHR-based phenotypes differentiated admissions, which is important to assure accurate public health reporting and research.

Objectives We set out to investigate the benefit of distal main or side branch treatment with a DCB compared to POBA in coronary bifurcation lesions. Background The standard treatment of bifurcation lesions is application of a DES to the main branch with provisional side branch stenting. While this resulted in considerable improvement in overall MACE rate suboptimal side branch results remained a problem. Methods The study was performed from 2011 to 2013 in six German centers. Native bifurcation lesions were included if side branch vessel diameter was ≥2 and ≤3.5 mm and no proximal main branch lesions was found. After successful predilatation randomization was performed to either DCB application or no further treatment. Follow-up angiograms for QCA analysis were done after 9 months. Primary endpoint was late lumen loss (LLL). Results 64 patients were successfully randomized. Minimal lumen diameter and grade of stenosis were equal in both groups. Only five stents were used as bail out. Angiographic follow-up was achieved in 75 % of patients. No patient died. There was one NSTEMI in the POBA group. Restenosis rate was 6 % in the DCB group vs 26 % in the POBA group ( p  = 0.045). TLR was necessary in one patient of the DCB group vs three patients of the POBA. The primary endpoint LLL was 0.13 mm in the DCB vs 0.51 mm in the POBA group ( p  = 0.013). Conclusion In bifurcation lesions that show only class A or B dissection and recoil not beyond 30 % the use of DCBs is a sound strategy.

Habitat specialists are declining worldwide, often paralleling rapid loss of habitat. Grassland habitats across North America are declining precipitously, due in part to intense conversion of grasslands to agriculture and rangelands, and specialist communities reliant upon this landscape are at particular risk of decline and collapse. We explored the relationship between grassland habitat specialism in birds and species population trends using several different grassland specialism indices (GSIs). Our data sources for these indices included (1) a regional bird dataset employing a spatially stratified sampling design (Integrated Monitoring of Bird Conservation Regions) of bird surveys in the Northern Great Plains of North America, and (2) geospatial data of species ranges (BirdLife Int'l) and grassland habitat (CEC North American Land Cover). We found a negative relationship between degree of habitat specialism and species population trends for all specialism metrics. We also found some evidence to support that specialism to grasslands on the wintering grounds partially explains population trends during the breeding season, giving added weight to the consideration of habitat conservation across the full annual cycle of a species to reverse or lessen population decline. Our work is the first to use quantitative methods to confirm the precarious state of grassland specialist songbirds in North America as well as demonstrate multiple methods for quantifying habitat specialism across different types of datasets.

1. The rapid increase of human activity in wild and developed areas presents novel challenges for wildlife. Some species may use human-dominated landscapes because of favourable resources (e.g. high prey availability along roadsides); however, use of these areas may increase exposure to anthropogenic stressors, such as human disturbance or noise, which can negatively affect reproduction or survival. In this case, human-dominated landscapes may act as an ecological trap. 2. We evaluated whether American kestrel Falco sparverius reproductive failure was associated with human disturbance (traffic conditions and land development) or other common predictors of reproductive outcome, such as habitat and clutch initiation date. Also, we examined relationships among human disturbance, corticosterone (CORT) concentrations and nest abandonment to explore potential mechanisms for stress-induced reproductive failure. 3. Twenty-six (36%) of 73 kestrel nesting attempts failed and 88% of failures occurred during incubation. Kestrels nesting in higher disturbance areas were 9·9 times more likely to fail than kestrels nesting in lower disturbance areas. Habitat and clutch initiation date did not explain reproductive outcome. 4. Females in higher disturbance areas had higher CORT and were more likely to abandon nests than females in lower disturbance areas. There was no relationship between male CORT and disturbance or abandonment. Females spent more time incubating than males and may have had more exposure to anthropogenic stressors. Specifically, traffic noise may affect a cavity-nesting bird's perception of the outside environment by masking auditory cues. In response, incubating birds may perceive a greater predation risk, increase vigilance behaviour, decrease parental care, or both. 5. Synthesis and applications. Proximity to large, busy roads and developed areas negatively affected kestrel reproduction by causing increased stress hormones that promoted nest abandonment. These results demonstrate that species presence in a human-dominated landscape does not necessarily indicate a tolerance for anthropogenic stressors. Managers should carefully consider or discourage projects that juxtapose favourable habitat conditions with areas of high human activity to decrease risk of ecological traps. Noise mitigation, while locally effective, may not protect widespread populations from the pervasive threat of traffic noise. Innovative engineering that decreases anthropogenic noise at its source is necessary.

Background Limited data exist regarding baseline characteristics and management of heart failure with reduced ejection fraction (EF) in tertiary care facilities. Methods EVITA-HF comprises web-based case report data on demography, comorbidities, diagnostic and therapy measures, quality of life, adverse events and 1-year follow-up of patients hospitalized for chronic heart failure and an ejection fraction of less than 40 %. Results Between February 2009 and June 2011, a total of 1,853 consecutive, hospitalized patients (pts) were included in 16 centers in Germany. Mean age was 70 years, 76 % were male. Median EF was 30 %, and 63 % were in NYHA III/IV. Ischemic cardiomyopathy was present in 56 %, history of hypertension in 76 %, diabetes in 39 %, impaired renal function in 33 %, thyroid dysfunction in 12 %, and malignoma in 7 %. Sixty-eight percent of pts had a non-elective admission. Rhythm was sinus/atrial fibrillation or flutter/pacemaker in 64, 28 and 11 %, respectively. Median heart rate amounted to 80 bpm, median blood pressure to 122/74 mmHg. LBBB was present in 26 % of non-pacemaker pts. Eighteen percent had an ICD or CRT-D. Medication (admission vs. discharge) consisted of ACEI or ARB in 73 vs. 88 %, β-blocker in 71 vs. 89 %, mineral corticosteroid receptor antagonist (MRA) in 32 vs. 57 %, diuretics in 68 vs. 83 % ( p  < 0.001 for each). Forty-two percent of pts received a specific treatment procedure beyond pharmacotherapy, of these 48 % revascularization, 39 % device therapy, 14 % electrical cardioversion, 5 % ablation procedures, 9 % valvular procedures, 6 % iv inotropes, 1.8 % IABP or LVAD implantation. At discharge, 33 % of survivors had ICD- or CRT-D implants. One-year mortality amounted to 16.8 %, and death or rehospitalization to 56 %. NYHA class III/IV was found in 30 % ( p  < 0.001 vs. index admission), general health status was improved in 45 % and unchanged in 36 % of patients. Eighty-five percent of pts took ACEI or ARB, 86 % β-blockers, 47 % MRA, and 78 % diuretics ( p  < 0.001 vs. index discharge for all). Conclusion Patients with chronic heart failure and low ejection fraction represent an elderly and multimorbid population. While hospitalized, they experience a significant optimization of prognosis-relevant medication, revascularization and device therapy. After 1 year, mortality is moderate; drug adherence is high and NYHA status favourable. The EVITA-HF registry is able to reflect coherently the real-world management, efforts and follow-up in heart failure pts managed in tertiary care facilities.

Background: The area of the left ventricular outflow tract (ALVOT) represents a major component of the continuity equation (CE), which is, i.a., crucial to calculate the aortic valve (AV) area (AAV). The ALVOT is typically calculated using 2D echo assessments as the measured anterior–posterior (a/p) extension, assuming a round LVOT base. Anatomically, however, usually an elliptical shape of the LVOT base is present, with the long diameter extending from the medial–lateral axis (m/l), which is not recognized by two-dimensional (2D) echocardiography. Objective: We aimed to compare standard and three-dimensional (3D)-echocardiography-derived ALVOT calculation and its use in a standard CE (CEstd) and a modified CE (CEmod) to calculate the AAV vs. computed tomography (CT) multi-planar reconstruction (MPR) measurements of the anatomical ALVOT, and AAV, respectively. Methods: Patients were selected if 3D transthoracic echocardiography (TTE), 3D transesophageal echocardiography (TEE), and cardiac CT were all performed, and imaging quality was adequate. The ALVOT was assessed using 2D calculation, (a/p only), 3D-volume MPR, and 3D-biplane calculation (a/p and m/l). AAV was measured using both CEstd and CEmod, and 3D-volume MPR. Data were compared to corresponding CT analyses. Results: From 2017 to 2018, 107 consecutive patients with complete and adequate imaging data were included. The calculated ALVOT was smaller when assessed by 2D- compared to both 3D-volume MPR and 3D-biplane calculation. Calculated AAV was correspondingly smaller in CEstd compared to CEmod or 3D-volume MPR. The ALVOT and AAV, using data from 3D echocardiography, highly correlated and were congruent with corresponding measurements in CT. Conclusion: Due to the elliptic shape of the LVOT, use of measurements and calculations based on 2D echocardiography systematically underestimates the ALVOT and dependent areas, such as the AAV. Anatomically correct assessment can be achieved using 3D echocardiography and adapted calculations, such as CEmod.

In current guidelines, intraaortic balloon pumping (IABP) is considered a class 1 indication in cardiogenic shock complicating acute myocardial infarction. However, evidence is mainly based on retrospective or prospective registries with a lack of randomized clinical trials. Therefore, IABP is currently only used in 20% to 40% of cardiogenic shock cases. The hypothesis of this trial is that IABP in addition to early revascularization by either percutaneous coronary intervention or coronary artery bypass grafting will improve clinical outcome of patients in cardiogenic shock. The IABP-SHOCK II study is a 600-patient, prospective, multicenter, randomized, open-label, controlled trial. The study is designed to compare the efficacy and safety of IABP versus optimal medical therapy on the background of early revascularization by either percutaneous coronary intervention or coronary artery bypass grafting. Patients will be randomized in a 1:1 fashion to 1 of the 2 treatments. The primary efficacy end point of IABP-SHOCK II is 30-day all-cause mortality. Secondary outcome measures, such as hemodynamic, laboratory, and clinical parameters, will serve as surrogate end points for prognosis. Furthermore, an intermediate and long-term follow-up at 6 and 12 months will be performed. Safety will be assessed, by the GUSTO bleeding definition, peripheral ischemic complications, sepsis, and stroke. The IABP-SHOCK II trial addresses important questions regarding the efficacy and safety of IABP in addition to early revascularization in patients with cardiogenic shock complicating myocardial infarction.