Machine Learning Model Identifies Preoperative Opioid Use, Male Sex, and Elevated Body Mass Index as Predictive Factors for Prolonged Opioid Consumption Following Arthroscopic Meniscal Surgery.

PURPOSE: To develop a predictive machine learning model to identify prognostic factors for continued opioid prescriptions after arthroscopic meniscus surgery. METHODS: Patients undergoing arthroscopic meniscal surgery, such as meniscus debridement, repair, or revision at a single institution from 2013 to 2017 were retrospectively followed up to 1 year postoperatively. Procedural details were recorded, including concomitant procedures, primary versus revision, and whether a partial debridement or a repair was performed. Intraoperative arthritis severity was measured using the Outerbridge Classification. The number of opioid prescriptions in each month was recorded. Primary analysis used was the multivariate Cox-Regression model. We then created a naïve Bayesian model, a machine learning classifier that uses Bayes' theorem with an assumption of independence between variables. RESULTS: A total of 581 patients were reviewed. Postoperative opioid refills occurred in 98 patients (16.9%). Multivariate logistic modeling was used; independent risk factors for opioid refills included male sex, larger body mass index, and chronic preoperative opioid use, while meniscus resection demonstrated decreased likelihood of refills. Concomitant procedures, revision procedures, and presence of arthritis graded by the Outerbridge classification were not significant predictors of postoperative opioid refills. The naïve Bayesian model for extended postoperative opioid use demonstrated good fit with our cohort with an area under the curve of 0.79, sensitivity of 94.5%, positive predictive value (PPV) of 83%, and a detection rate of 78.2%. The two most important features in the model were preoperative opioid use and male sex. CONCLUSION: After arthroscopic meniscus surgery, preoperative opioid consumption and male sex were the most significant predictors for sustained opioid use beyond 1 month postoperatively. Intraoperative arthritis was not an independent risk factor for continued refills. A machine learning algorithm performed with high accuracy, although with a high false positive rate, to function as a screening tool to identify patients filling additional narcotic prescriptions after surgery. LEVEL OF EVIDENCE: III, retrospective comparative study.

Cardiac Stroke Volume Index Is Associated With Early Neurological Improvement in Acute Ischemic Stroke Patients.

Early neurological improvement as assessed with the NIH stroke scale (NIHSS) at 24 h has been associated with improved long-term functional outcomes following acute ischemic stroke (AIS). Cardiac dysfunction is often present in AIS, but its association with outcomes is incompletely defined. We performed a pilot study to evaluate the association between non-invasively measured cardiac parameters and 24-h neurological improvement in prospectively enrolled patients with suspected AIS who presented within 12 h of symptom-onset and had an initial systolic blood pressure>140 mm Hg. Patients receiving thrombolytic therapy or mechanical thrombectomy were excluded. Non-invasive pulse contour analysis was used to measure mean arterial blood pressure (MAP), cardiac stroke volume index (cSVI), cardiac output (CO) and cardiac index (CI). Transcranial Doppler recorded mean middle cerebral artery flow velocity (MFV). We defined a decrease of 4 NIHSS points or NIHSS ≤ 1 at 24-h as neurological improvement. Of 75 suspected, 38 had confirmed AIS and did not receive reperfusion therapy. Of these, 7/38 (18.4%) had neurological improvement over 24 h. MAP was greater in those without improvement (108, IQR 96-123 mm Hg) vs. those with (89, IQR 73-104 mm Hg). cSVI, CO, and MFV were similar between those without and with improvement: 37.4 (IQR 30.9-47.7) vs. 44.7 (IQR 42.3-55.3) ml/m2; 5.2 (IQR 4.2-6.6) vs. 5.3 (IQR 4.7-6.7) mL/min; and 39.9 (IQR 32.1-45.7) vs. 34.4 (IQR 27.1-49.2) cm/s, respectively. Multivariate analysis found MAP and cSVI as predictors for improvement (OR 0.93, 95%CI 0.85-0.98 and 1.14, 95%CI 1.03-1.31). In this pilot study, cSVI and MAP were associated with 24-h neurological improvement in AIS.

Review of the COVID-19 Risk in Multiple Sclerosis.

The ongoing pandemic of the novel coronavirus of 2019 (COVID-19) has resulted in over 1 million deaths, primarily affecting older patients with chronic ailments. Multiple sclerosis (MS) patients have been deemed particularly vulnerable given their high rates of disability and increased susceptibility to infections. There have also been concerns regarding disease-modifying therapy (DMT) during the pandemic as many DMTs may increase the risk of infection due to some of their immunosuppressive properties. Furthermore, due to MS-related chronic inflammatory damage within the central nervous system, there have been concerns for worsening neurological injury by COVID-19. This has resulted in an alarmingly high level of anxiety and stress among the MS community leading to a lack of compliance with medications and routine check-ups, and even failure to obtain treatment for relapse. However, there is currently substantial evidence that MS and most DMT usage is not associated with increased COVID-19 severity. MS patients who suffer worse outcomes were more likely to be older and suffer from significant disabilities and comorbid conditions, which would also be expected from those in the general population. Likewise, there is little if any evidence demonstrating an increased susceptibility of MS patients to COVID-19-related neurological complications. Therefore, we aim to summarize the most recent findings related to COVID-19 and MS demonstrating that MS and most DMTs do not appear as risk factors for severe COVID-19.

Machine Learning Applications in the Neuro ICU: A Solution to Big Data Mayhem?

The neurological ICU (neuro ICU) often suffers from significant limitations due to scarce resource availability for their neurocritical care patients. Neuro ICU patients require frequent neurological evaluations, continuous monitoring of various physiological parameters, frequent imaging, and routine lab testing. This amasses large amounts of data specific to each patient. Neuro ICU teams are often overburdened by the resulting complexity of data for each patient. Machine Learning algorithms (ML), are uniquely capable of interpreting high-dimensional datasets that are too difficult for humans to comprehend. Therefore, the application of ML in the neuro ICU could alleviate the burden of analyzing big datasets for each patient. This review serves to (1) briefly summarize ML and compare the different types of MLs, (2) review recent ML applications to improve neuro ICU management and (3) describe the future implications of ML to neuro ICU management.

Molecular Imaging of Apoptosis in Atherosclerosis by Targeting Cell Membrane Phospholipid Asymmetry.

BACKGROUND: Apoptosis in atherosclerotic lesions contributes to plaque vulnerability by lipid core enlargement and fibrous cap attenuation. Apoptosis is associated with exteriorization of phosphatidylserine (PS) and phosphatidylethanolamine (PE) on the cell membrane. Although PS-avid radiolabeled annexin-V has been employed for molecular imaging of high-risk plaques, PE-targeted imaging in atherosclerosis has not been studied. OBJECTIVES: This study sought to evaluate the feasibility of molecular imaging with PE-avid radiolabeled duramycin in experimental atherosclerotic lesions in a rabbit model and compare duramycin targeting with radiolabeled annexin-V. METHODS: Of the 27 rabbits, 21 were fed high-cholesterol, high-fat diet for 16 weeks. Nine of the 21 rabbits received 99mTc-duramycin (test group), 6 received 99mTc-linear duramycin (duramycin without PE-binding capability, negative radiotracer control group), and 6 received 99mTc-annexin-V for radionuclide imaging. The remaining normal chow-fed 6 animals (disease control group) received 99mTc-duramycin. In vivo microSPECT/microCT imaging was performed, and the aortas were explanted for ex vivo imaging and for histological characterization of atherosclerosis. RESULTS: A significantly higher duramycin uptake was observed in the test group compared with that of disease control and negative radiotracer control animals; duramycin uptake was also significantly higher than the annexin-V uptake. Quantitative duramycin uptake, represented as the square root of percent injected dose per cm (√ID/cm) of abdominal aorta was >2-fold higher in atherosclerotic lesions in test group (0.08 ± 0.01%) than in comparable regions of disease control animals (0.039 ± 0.0061%, p = 3.70·10-8). Mean annexin uptake (0.060 ± 0.010%) was significantly lower than duramycin (p = 0.001). Duramycin uptake corresponded to the lesion severity and macrophage burden. The radiation burden to the kidneys was substantially lower with duramycin (0.49% ID/g) than annexin (5.48% ID/g; p = 4.00·10-4). CONCLUSIONS: Radiolabeled duramycin localizes in lipid-rich areas with high concentration of apoptotic macrophages in the experimental atherosclerosis model. Duramycin uptake in atherosclerotic lesions was significantly greater than annexin-V uptake and produced significantly lower radiation burden to nontarget organs.

COVID-19 in multiple sclerosis patients and risk factors for severe infection.

Multiple sclerosis (MS) patients have been considered a higher-risk population for COVID-19 due to the high prevalence of disability and disease-modifying therapy use; however, there is little data identifying clinical characteristics of MS associated with worse COVID-19 outcomes. Therefore, we conducted a multicenter prospective cohort study looking at the outcomes of 40 MS patients with confirmed COVID-19. Severity of COVID-19 infection was based on hospital course, where a mild course was defined as the patient not requiring hospital admission, moderate severity was defined as the patient requiring hospital admission to the general floor, and most severe was defined as requiring intensive care unit admission and/or death. 19/40(47.5%) had mild courses, 15/40(37.5%) had moderate courses, and 6/40(15%) had severe courses. Patients with moderate and severe courses were significantly older than those with a mild course (57[50-63] years old and 66[58.8-69.5] years old vs 48[40-51.5] years old, P = 0.0121, P = 0.0373). There was differing prevalence of progressive MS phenotype in those with more severe courses (severe:2/6[33.3%]primary-progressing and 0/6[0%]secondary-progressing, moderate:1/14[7.14%] and 5/14[35.7%] vs mild:0/19[0%] and 1/19[5.26%], P = 0.0075, 1 unknown). Significant disability was found in 1/19(5.26%) mild course-patients, but was in 9/15(60%, P = 0.00435) of moderate course-patients and 2/6(33.3%, P = 0.200) of severe course-patients. Disease-modifying therapy prevalence did not differ among courses (mild:17/19[89.5%], moderate:12/15[80%] and severe:3/6[50%], P = 0.123). MS patients with more severe COVID-19 courses tended to be older, were more likely to suffer from progressive phenotype, and had a higher degree of disability. However, disease-modifying therapy use was not different among courses.

Machine Learning in Cardiology-Ensuring Clinical Impact Lives Up to the Hype.

Despite substantial advances in the study, treatment, and prevention of cardiovascular disease, numerous challenges relating to optimally screening, diagnosing, and managing patients remain. Simultaneous improvements in computing power, data storage, and data analytics have led to the development of new techniques to address these challenges. One powerful tool to this end is machine learning (ML), which aims to algorithmically identify and represent structure within data. Machine learning's ability to efficiently analyze large and highly complex data sets make it a desirable investigative approach in modern biomedical research. Despite this potential and enormous public and private sector investment, few prospective studies have demonstrated improved clinical outcomes from this technology. This is particularly true in cardiology, despite its emphasis on objective, data-driven results. This threatens to stifle ML's growth and use in mainstream medicine. We outline the current state of ML in cardiology and outline methods through which impactful and sustainable ML research can occur. Following these steps can ensure ML reaches its potential as a transformative technology in medicine.

Manipulation of ACE2 expression in COVID-19.

SARS-CoV-2 is the virus responsible for the ongoing COVID-19 outbreak. The virus uses ACE2 receptor for viral entry. ACE2 is part of the counter-regulatory renin-angiotensin-aldosterone system and is also expressed in the lower respiratory tract along the alveolar epithelium. There is, however, significant controversy regarding the role of ACE2 expression in COVID-19 pathogenesis. Some have argued that decreasing ACE2 expression would result in decreased susceptibility to the virus by decreasing available binding sites for SARS-CoV-2 and restricting viral entry into the cells. Others have argued that, like the pathogenesis of other viral pneumonias, including those stemming from previous severe acute respiratory syndrome (SARS) viruses, once SARS-CoV-2 binds to ACE2, it downregulates ACE2 expression. Lack of the favourable effects of ACE2 might exaggerate lung injury by a variety of mechanisms. In order to help address this controversy, we conducted a literature search and review of relevant preclinical and clinical publications pertaining to SARS-CoV-2, COVID-19, ACE2, viral pneumonia, SARS, acute respiratory distress syndrome and lung injury. Our review suggests, although controversial, that patients at increased susceptibility to COVID-19 complications may have reduced baseline ACE2, and by modulating ACE2 expression one can possibly improve COVID-19 outcomes. Herein, we elucidate why and how this potential mechanism might work.

Single-Cell RNA Sequencing of the Cardiovascular System: New Looks for Old Diseases.

Cardiovascular disease encompasses a wide range of conditions, resulting in the highest number of deaths worldwide. The underlying pathologies surrounding cardiovascular disease include a vast and complicated network of both cellular and molecular mechanisms. Unique phenotypic alterations in specific cell types, visualized as varying RNA expression-levels (both coding and non-coding), have been identified as crucial factors in the pathology underlying conditions such as heart failure and atherosclerosis. Recent advances in single-cell RNA sequencing (scRNA-seq) have elucidated a new realm of cell subpopulations and transcriptional variations that are associated with normal and pathological physiology in a wide variety of diseases. This breakthrough in the phenotypical understanding of our cells has brought novel insight into cardiovascular basic science. scRNA-seq allows for separation of widely distinct cell subpopulations which were, until recently, simply averaged together with bulk-tissue RNA-seq. scRNA-seq has been used to identify novel cell types in the heart and vasculature that could be implicated in a variety of disease pathologies. Furthermore, scRNA-seq has been able to identify significant heterogeneity of phenotypes within individual cell subtype populations. The ability to characterize single cells based on transcriptional phenotypes allows researchers the ability to map development of cells and identify changes in specific subpopulations due to diseases at a very high throughput. This review looks at recent scRNA-seq studies of various aspects of the cardiovascular system and discusses their potential value to our understanding of the cardiovascular system and pathology.

Molecular Imaging of Apoptosis in Ischemia Reperfusion Injury With Radiolabeled Duramycin Targeting Phosphatidylethanolamine: Effective Target Uptake and Reduced Nontarget Organ Radiation Burden.

OBJECTIVES: The purpose of this study was to evaluate the feasibility of imaging apoptosis in experimental ischemia-reperfusion model by technetium-99m (99mTc)-labeled Duramycin, and compare it to an established tracer, 99mTc-labeled Annexin-V, which has a relative disadvantage of high radiation burden to nontarget organs. BACKGROUND: During apoptosis, the cell membrane phospholipids-phosphatidylserine (PS) and phosphatidylethanolamine (PE) are exposed and can be targeted by Annexin-V and Duramycin, respectively, for in vivo imaging. Identification of a reversible cell death process should permit therapeutic intervention to help reduce myocyte loss and left ventricle dysfunction. METHODS: In a 40-min left coronary artery ischemia-reperfusion model in 17 rabbits, 7 mCi of 99mTc-labeled Duramycin (n = 10), 99mTc-linear Duramycin (a negative tracer control; n = 3), or 99mTc-Annexin-V (a positive tracer-control; n = 4) were intravenously administered 30 min after reperfusion. Of the 10 Duramycin group animals, 4 animals were treated with an antiapoptotic agent, minocycline at the time of reperfusion. In vivo and ex vivo micro-single-photon emission computed tomography (µSPECT) and micro-computed tomography (µCT) imaging was performed 3 h after reperfusion, followed by quantitative assessment of tracer uptake and pathological characterization. Fluorescent Duramycin and Annexin-V were injected in 4 rats to visualize colocalization in infarct areas in a 40-min left coronary artery occlusion and 30-min reperfusion model. RESULTS: Intense uptake of Duramycin and Annexin-V was observed in the apical (infarcted) areas. The percent injected dose per gram uptake of Duramycin in apical region (0.751 ± 0.262%) was significantly higher than remote area in same animals (0.045 ± 0.029%; p < 0.01). Duramycin uptake was insignificantly lower than Annexin-V uptake (1.23 ± 0.304%; p > 0.01) but demonstrated substantially lower radiation burden to kidneys (0.358 ± 0.210% vs. 1.58 ± 0.316%, respectively; p < 0.001). Fluorescence studies with Duramycin and Annexin V showed colocalization in infarct areas. Minocycline treatment substantially resolved Duramycin uptake (0.354% ± 0.0624%; p < 0.01). CONCLUSIONS: Duramycin is similarly effective in imaging apoptotic cell death as Annexin-V with lower nontarget organ radiation. Clinical feasibility of apoptosis imaging with a PE-seeking tracer should be tested.

Cardioprotective Effects of HSP72 Administration on Ischemia-Reperfusion Injury.

BACKGROUND: Although early reperfusion is the most desirable intervention after ischemic myocardial insult, it may add to damage through oxidative stress. OBJECTIVES: This study investigated the cardioprotective effects of a single intravenous dose of heat shock protein-72 (HSP72) coupled to a single-chain variable fragment (Fv) of monoclonal antibody 3E10 (3E10Fv) in a rabbit ischemia-reperfusion model. The Fv facilitates rapid transport of HSP72 into cells, even with intact membranes. METHODS: A left coronary artery occlusion (40 min) reperfusion (3 h) model was used in 31 rabbits. Of these, 12 rabbits received the fusion protein (Fv-HSP72) intravenously. The remaining 19 control rabbits received a molar equivalent of 3E10Fv alone (n = 6), HSP72 alone (n = 6), or phosphate-buffered saline (n = 7). Serial echocardiographic examinations were performed to assess left ventricular function before and after reperfusion. Micro-single-photon emission computed tomography imaging of 99mTc-labeled annexin-V was performed with micro-computed tomography scanning to characterize apoptotic damage in vivo, followed by gamma counting of the excised myocardial specimens to quantify cell death. Histopathological characterization of the myocardial tissue and sequential cardiac troponin I measurements were also undertaken. RESULTS: Myocardial annexin-V uptake was 43% lower in the area at risk (p = 0.0003) in Fv-HSP72-treated rabbits compared with control animals receiving HSP72 or 3E10Fv alone. During reperfusion, troponin I release was 42% lower and the echocardiographic left ventricular ejection fraction 27% higher in the Fv-HSP72-treated group compared with control animals. Histopathological analyses confirmed penetration of 3E10Fv-containing molecules into cardiomyocytes in vivo, and treatment with Fv-HSP72 showed fewer apoptotic nuclei compared with control rabbits. CONCLUSIONS: Single-dose administration of Fv-HSP72 fusion protein at the time of reperfusion reduced myocardial apoptosis by almost one-half and improved left ventricular functional recovery after myocardial ischemia-reperfusion injury in rabbits. It might have potential to serve as an adjunct to early reperfusion in the management of myocardial infarction.

Prevalence and long-term prognosis of patients with complete bundle branch block (right or left bundle branch) with normal left ventricular ejection fraction referred for stress echocardiography.

BACKGROUND: The prognostic value of stress echocardiography (SE) in patients with complete bundle branch blocks (BBB) with normal left ventricular ejection fraction (LVEF) has not been well described. We sought to determine the prognostic value of SE in patients with BBB and normal LVEF. METHODS: We analyzed 7214 patients (58 ± 14 years; 57% female) with a mean follow-up time of 9 ± 4 years. Dobutamine SE was performed in 51% of patients and exercise SE was performed in 49%. All-cause mortality data were obtained from the Social Security Death Index. RESULTS: There were 222 (3%) patients with right bundle branch block (RBBB) and 50 (0.7%) patients with left bundle branch block (LBBB). Patients with LBBB were 3 times more likely to have an abnormal stress test after adjusting for age, gender, mode of stress test, and coronary artery disease risk factors (OR = 3.3; 95% CI: 1.86-5.92; P < 0.001). The mortality rates were 4.5%/year for patients with LBBB, 2.5%/year for patients with RBBB, and 1.9%/year for patients without BBB (P < 0.001). Among patients with a normal SE, those with LBBB had similar mortality to those without LBBB (HR = 0.9; 95% CI: 0.4-2.2; P = 0.8). Patients with LBBB and abnormal SE had more than 2 times greater risk of all-cause mortality (HR = 2.4; 95% CI: 1.4-4.2; P = 0.002). CONCLUSION: A normal stress echocardiogram in LBBB is associated with benign prognosis while those with LBBB and abnormal SE have the worst outcomes.

Safety of echocardiographic contrast in hospitalized patients with pulmonary hypertension: a multi-center study.

AIMS: Echocardiographic contrast (EC) improves the diagnostic accuracy of suboptimal echocardiograms. In October 2007, the Food and Drug Administration (FDA) placed a black box warning on the label of the perflutren-based agents Definity and Optison, contraindicating their use in patients with pulmonary hypertension (PHT) and unstable cardiopulmonary status, after serious cardiopulmonary reactions occurred in temporal relation to EC administration. In 2008 and 2011, the FDA revised the black box warning allowing their use in this same population. However, limited data exist regarding the safety profile of these agents in patients with PHT. METHODS AND RESULTS: Consecutive hospitalized patients with PHT who were referred for echocardiographic evaluation, but required the use of EC, were included. All our patients received the EC agent Definity. We evaluated these patients for serious adverse events (respiratory decompensation, hypotension, syncope, convulsions, arrhythmias, anaphylactic reactions, or death) occurring within 24 h of EC administration. The study group included 1513 patients (age 69 ± 14 years, 55% males, BMI 33 ± 9 kg/m(2)), of which 911 (60%) had mild PHT, 515 (34%) had moderate PHT, and 87 (6%) had severe PHT. The mean pulmonary artery systolic pressures (PASP) in the groups with mild, moderate, and severe PHT were 41 ± 4 (range 35-49) mmHg, 55 ± 5 (range 50-69) mmHg, and 78 ± 9 (range 70-122) mmHg, respectively. The incidence of adverse events in all subgroups was rare (0.002%) and they were not attributed to EC because of temporal and clinical considerations. CONCLUSION: The use of the EC agent Definity is safe in hospitalized patients with PHT.