Automated detection and segmentation of pulmonary embolisms on computed tomography pulmonary angiography (CTPA) using deep learning but without manual outlining.

We present a novel computer algorithm to automatically detect and segment pulmonary embolisms (PEs) on computed tomography pulmonary angiography (CTPA). This algorithm is based on deep learning but does not require manual outlines of the PE regions. Given a CTPA scan, both intra- and extra-pulmonary arteries were firstly segmented. The arteries were then partitioned into several parts based on size (radius). Adaptive thresholding and constrained morphological operations were used to identify suspicious PE regions within each part. The confidence of a suspicious region to be PE was scored based on its contrast in the arteries. This approach was applied to the publicly available RSNA Pulmonary Embolism CT Dataset (RSNA-PE) to identify three-dimensional (3-D) PE negative and positive image patches, which were used to train a 3-D Recurrent Residual U-Net (R2-Unet) to automatically segment PE. The feasibility of this computer algorithm was validated on an independent test set consisting of 91 CTPA scans acquired from a different medical institute, where the PE regions were manually located and outlined by a thoracic radiologist (>18 years' experience). An R2-Unet model was also trained and validated on the manual outlines using a 5-fold cross-validation method. The CNN model trained on the high-confident PE regions showed a Dice coefficient of 0.676±0.168 and a false positive rate of 1.86 per CT scan, while the CNN model trained on the manual outlines demonstrated a Dice coefficient of 0.647±0.192 and a false positive rate of 4.20 per CT scan. The former model performed significantly better than the latter model (p<0.01). The promising performance of the developed PE detection and segmentation algorithm suggests the feasibility of training a deep learning network without dedicating significant efforts to manual annotations of the PE regions on CTPA scans.

Predictors of chronic thromboembolic pulmonary hypertension in patients with submassive pulmonary embolism treated with catheter-directed thrombolysis versus anticoagulation alone: A secondary analysis of the SUNSET sPE trial.

OBJECTIVE: Chronic thromboembolic pulmonary hypertension (CTEPH) after pulmonary embolism (PE) is a morbid complication with suboptimal treatment. We aimed to evaluate the biomarker profile and functional outcomes in patients with submassive PE (sPE) treated with catheter-directed thrombolysis (CDT) compared with anticoagulation alone (ACA). We performed a secondary biomarker and survey analysis of the SUNSET sPE (standard vs ultrasound-assisted catheter thrombolysis for submassive pulmonary embolism) randomized trial comparing standard CDT to ultrasound-assisted thrombolysis in patients with sPE. METHODS: As a part of the SUNSET sPE study, patients who did not receive an intervention were enrolled in the medical (ACA) arm. The biomarkers associated with CTEPH in the literature (ie, CCL2, CXCL10, PTX3, GDF-15, RAGE, BCA-1, TFPI) were collected and measured using a multiplex assay at diagnosis, discharge, and 3-month follow-up. Patients underwent a 6-minute walk test and answered quality-of-life questionnaires (pulmonary embolism quality of life; University of California, San Diego, shortness of breath questionnaire; 36-item short-form survey) at 3 months after diagnosis. Comparisons were made using the Student t test. Nonparametric tests were used when the distributions were not normal. Significance was set at P ≤ .05. RESULTS: A total of 72 patients (age, 56 ± 15 years; 40.3% women) were included in the present analysis. Of these 72 patients, 53 underwent CDT and 19 were included in the ACA arm. The baseline right ventricle/left ventricle ratios were similar between the two groups (CST, 1.8; ACA, 1.7). The survival and complication rates were similar between the two groups. At discharge, CXCL10 (768.9 ± 148.6 pg/mL vs 3032.0 ± 1201.0 pg/mL; P = .018) and PTX3 (3203.5 ± 1298.0 pg/mL vs 12,716.2 ± 6961.5 pg/mL; P = .029) were lower in the CDT group and displayed a quicker return to baseline than in the ACA group. This trend, although not significant, was also seen with the other biomarkers. At 3 months, the 6-minute walking distance and quality-of-life scores were similar between both groups. CONCLUSIONS: In patients with sPE, the biomarkers of CTEPH were lower with CDT compared with ACA. At 3 months, both groups demonstrated similar biomarker levels, 6-minute walking distances, and quality-of-life scores.

Barriers and facilitators to interhospital transfer of acute pulmonary embolism: An inductive qualitative analysis.

Background: Interhospital transfer (IHT) of patients with acute life-threatening pulmonary embolism (PE) is necessary to facilitate specialized care and access to advanced therapies. Our goal was to understand what barriers and facilitators may exist during this transfer process from the perspective of both receiving and referring physicians. Methods: This qualitative descriptive study explored physician experience taking care of patients with life threatening PE. Subject matter expert physicians across several different specialties from academic and community United States hospitals participated in qualitative semi-structured interviews. Interview transcripts were subsequently analyzed using inductive qualitative description approach. Results: Four major themes were identified as barriers that impede IHT among patients with life threatening PE. Inefficient communication which mainly pertained to difficulty when multiple points of contact were required to complete a transfer. Subjectivity in the indication for transfer which highlighted the importance of physicians understanding how to use standardized risk stratification tools and to properly triage these patients. Delays in data acquisition were identified in regards to both obtaining clinical information and imaging in a timely fashion. Operation barriers which included difficulty finding available beds for transfer and poor weather conditions inhibiting transportation. In contrast, two main facilitators to transfer were identified: good communication and reliance on colleagues and dedicated team for transferring and treating PE patients. Conclusion: The most prominent themes identified as barriers to IHT for patients with acute life-threatening PE were: (1) inefficient communication, (2) subjectivity in the indication for transfer, (3) delays in data acquisition (imaging or clinical), and (4) operational barriers. Themes identified as facilitators that enable the transfer of patients were: (1) good communication and (2) a dedicated transfer team. The themes presented in our study are useful in identifying opportunities to optimize the IHT of patients with acute PE and improve patient care. These opportunities include instituting educational programs, streamlining the transfer process, and formulating a consensus statement to serve as a guideline regarding IHT of patients with acute PE.

Pulmonary embolism response team for hospitalized patients with submassive and massive pulmonary embolism: A single-center experience.

BACKGROUND: Pulmonary embolism (PE) is a major cause of mortality with presentation varying between few or no symptoms to sudden death. This makes timely and appropriate treatment extremely important. Multidisciplinary PE response teams (PERT) have emerged to improve the management of acute PE. This study aims to describe the experience of a large multihospital single-network institution with PERT. METHODS: A retrospective cohort study of patients admitted for submassive and massive PE between 2012 and 2019 was conducted. The cohort was divided based on time of diagnosis and hospital into two groups: non-PERT included patients treated at hospitals that did not initiate PERT and patients diagnosed before the introduction of PERT (June 1, 2014); and the PERT group included those admitted after June 1, 2014, to a hospital with PERT. Patients with low-risk PE and those who had admissions in both time periods were excluded. Primary outcomes included all-cause mortality at 30, 60, and 90 days. Secondary outcomes included causes of death, intensive care unit (ICU) admission, ICU length of stay (LOS), total hospital LOS, type of treatment, and specialty consultations. RESULTS: We analyzed 5190 patients, with 819 (15.8%) being in the PERT group. Patients in the PERT group were more likely to receive extensive workup that included troponin-I (66.3% vs 42.3%; P < .001) and brain natriuretic peptide (50.4% vs 20.3%; P < .001). They also more often received catheter-directed interventions (12% vs 6.2%; P < .001) rather than anticoagulation monotherapy. Mortality outcomes were similar between both groups at all measured timepoints. Rates of ICU admission (65.2% vs 29.7%; P < .001), ICU LOS (median, 64.7 hours; interquartile range [IQR], 41.9-89.1 hours vs median, 38 hours; IQR, 22-66.4 hours; P < .001), and total hospital LOS (median, 5 days; IQR, 3-8 days vs median, 4 days; IQR, 2-6 days; P < .001) were all higher among the PERT group. Patients in the PERT group were more likely to receive vascular surgery consultation (5.3% vs 0.8%; P < .001) and the consultation occurred earlier in the admission when compared with the non-PERT group (median, 0 days; IQR, 0-1 days vs median, 1 day; IQR, 0-1; P = .04). CONCLUSIONS: The data presented here showed that there was no difference in mortality after PERT implementation. These results suggest that the presence of PERT increases the number of patients receiving a full PE workup with cardiac biomarkers. PERT also leads to more specialty consultations and more advanced therapies such as catheter-directed interventions. Further research is needed to assess the effect of PERT on long-term survival of patients with massive and submassive PE.

Surgical Management and Mechanical Circulatory Support in High-Risk Pulmonary Embolisms: Historical Context, Current Status, and Future Directions: A Scientific Statement From the American Heart Association.

Acute pulmonary embolism is the third leading cause of cardiovascular death, with most pulmonary embolism-related mortality associated with acute right ventricular failure. Although there has recently been increased clinical attention to acute pulmonary embolism with the adoption of multidisciplinary pulmonary embolism response teams, mortality of patients with pulmonary embolism who present with hemodynamic compromise remains high when current guideline-directed therapy is followed. Because historical data and practice patterns affect current consensus treatment recommendations, surgical embolectomy has largely been relegated to patients who have contraindications to other treatments or when other treatment modalities fail. Despite a selection bias toward patients with greater illness, a growing body of literature describes the safety and efficacy of the surgical management of acute pulmonary embolism, especially in the hemodynamically compromised population. The purpose of this document is to describe modern techniques, strategies, and outcomes of surgical embolectomy and venoarterial extracorporeal membrane oxygenation and to suggest strategies to better understand the role of surgery in the management of pulmonary embolisms.

Clinical outcomes and factors associated with pulmonary infarction following acute pulmonary embolism: a retrospective observational study at a US academic centre.

OBJECTIVE: Pulmonary infarction is a common clinical and radiographic finding in acute pulmonary embolism (PE), yet the clinical relevance and prognostic significance of pulmonary infarction remain unclear. The study aims to investigate the clinical features, radiographic characteristics, impact of reperfusion therapy and outcomes of patients with pulmonary infarction. DESIGN, SETTING AND PARTICIPANTS: A retrospective cohort study of 496 adult patients (≥18 years of age) diagnosed with PE who were evaluated by the PE response team at a tertiary academic referral centre in the USA. We collected baseline characteristics, laboratory, radiographic and outcome data. Statistical analysis was performed by Student's t-test, Mann-Whitney U test, Fischer's exact or χ2 test where appropriate. Multivariate logistic regression was used to evaluate potential risk factors for pulmonary infarction. RESULTS: We identified 143 (29%) cases of pulmonary infarction in 496 patients with PE. Patients with infarction were significantly younger (52±15.9 vs 61±16.6 years, p<0.001) and with fewer comorbidities. Most infarctions occurred in the lower lobes (60%) and involved a single lobe (64%). The presence of right ventricular (RV) strain on CT imaging was significantly more common in patients with infarction (21% vs 14%, p=0.031). There was no significant difference in advanced reperfusion therapy, in-hospital mortality, length of stay and readmissions between groups. In multivariate analysis, age and evidence of RV strain on CT and haemoptysis increased the risk of infarction. CONCLUSIONS: Radiographic evidence of pulmonary infarction was demonstrated in nearly one-third of patients with acute PE. There was no difference in the rate of reperfusion therapies and the presence of infarction did not correlate with poorer outcomes.

Pulmonary embolism response teams: Changing the paradigm in the care for acute pulmonary embolism.

Pulmonary embolism response teams (PERTs) have emerged as a multidisciplinary, multispecialty team of experts in the care of highly complex symptomatic acute pulmonary embolism (PE), with a centralized unique activation process, providing rapid multimodality assessment and risk stratification, formulating the best individualized diagnostic and therapeutic approach, streamlining the care in challenging clinical case scenarios (e.g., intermediate-high risk and high-risk PE), and facilitating the implementation of the recommended therapeutic strategies on time. PERTs are currently changing how complex acute PE cases are approached. The structure, organization, and function of a given PERT may vary from hospital to hospital, depending on local expertise, specific resources, and infrastructure for a given academic hospital center. Current emerging data demonstrate the value of PERTs in improving time to PE diagnosis; shorter time to initiation of anticoagulation reducing hospital length of stay; increasing use of advanced therapies without an increase in bleeding; and in some reports, decreasing mortality. Importantly, PERTs are positively impacting outcomes by changing the paradigm of care for acute PE through global adoption by the health-care community.

Interhospital Transfer for the Management of Acute Pulmonary Embolism.

BACKGROUND: There are increasing treatment options for the management of acute pulmonary embolism (PE), though many are only available at tertiary care centers. Patients with acute pulmonary embolism with high-risk features are often transferred for consideration of such therapies. There are limited data describing outcomes in patients transferred with acute pulmonary embolism. METHODS: We evaluated patients with acute pulmonary embolism at our tertiary care center from August 2012 through August 2018 and compared clinical characteristics, pulmonary embolism features, management, and outcomes in those transferred for acute pulmonary embolism to those that were not transferred. RESULTS: Of 2050 patients with pulmonary embolism included in the study, 432 (21.1%) were transferred from an outside hospital with a known diagnosis of pulmonary embolism. Patients transferred had a lower rate of malignancy (22.2% vs 33.3%; P < .001) and median Charlson comorbidity index (3 vs 4; P < .001). A higher percentage of patients transferred were classified as intermediate- or high-risk pulmonary embolism (62.5% vs 43.0%; P <.001) and more frequently received advanced therapy beyond anticoagulation alone (12.5% vs 3.2%, P < .001). Overall survival to discharge was similar between groups, though definite pulmonary embolism-related mortality was higher in the transferred group (38.5% vs 9.4%, P = .004). CONCLUSION: More than 1 in 5 patients treated for acute pulmonary embolism at a tertiary care center were transferred from an outside facility. Transferred patients had higher risk pulmonary embolism features, more often received advanced therapy, and had higher definite pulmonary embolism-related mortality. There are opportunities to further optimize outcomes of patients transferred for management of acute pulmonary embolism.

Interhospital Transfer of Patients With Acute Pulmonary Embolism: Challenges and Opportunities.

Acute pulmonary embolism (PE) is associated with significant morbidity and mortality. The management paradigm for acute PE has evolved in recent years with wider availability of advanced treatment modalities ranging from catheter-directed reperfusion therapies to mechanical circulatory support. This evolution has coincided with the development and implementation of institutional pulmonary embolism response teams (PERT) nationwide and internationally. Because most institutions are not equipped or staffed for advanced PE care, patients often require transfer to centers with more comprehensive resources, including PERT expertise. One of the unmet needs in current PE care is an organized approach to the process of interhospital transfer (IHT) of critically ill PE patients. In this review, we discuss medical optimization and support of patients before and during transfer, transfer checklists, defined roles of emergency medical services, and the roles and responsibilities of referring and receiving centers involved in the IHT of acute PE patients.

Direct oral anticoagulants for the treatment of pulmonary embolism in patients with renal impairment.

Pulmonary embolism (PE) is associated with adverse outcomes and substantial morbidity and mortality. Patients with PE often have renal impairment because of shared risk factors and close links between the renal and cardiovascular systems. Furthermore, patients with PE and renal impairment are at increased risk of recurrent thrombosis. Therefore, anticoagulation is crucial to treat the acute event, prevent recurrent venous thromboembolism (VTE), and optimize patient outcomes. However, when treated with an anticoagulant, patients with renal impairment also have an elevated risk of bleeding. Direct oral anticoagulants (DOACs) are the first-choice treatment for acute VTE in eligible patients. However, as all DOACs have a degree of renal excretion, the management of anticoagulation therapy can be more complicated in patients with renal impairment. This review provides an overview of the clinical challenges of managing anticoagulation in patients with PE and renal impairment and explores the optimal practice management of this special patient group.

Randomized Trial Comparing Standard Versus Ultrasound-Assisted Thrombolysis for Submassive Pulmonary Embolism: The SUNSET sPE Trial.

OBJECTIVES: The aim of this trial was to determine whether ultrasound-assisted thrombolysis (USAT) is superior to standard catheter-directed thrombolysis (SCDT) in pulmonary arterial thrombus reduction for patients with submassive pulmonary embolism (sPE). BACKGROUND: Catheter-directed therapy has been increasingly used in sPE and massive pulmonary embolism as a decompensation prevention and potentially lifesaving procedure. It is unproved whether USAT is superior to SCDT using traditional multiple-side-hole catheters in the treatment of patients with pulmonary embolism. METHODS: Adults with sPE were enrolled. Participants were randomized 1:1 to USAT or SCDT. The primary outcome was 48-hour clearance of pulmonary thrombus assessed by pre- and postprocedural computed tomographic angiography using a refined Miller score. Secondary outcomes included improvement in right ventricular-to-left ventricular ratio, intensive care unit and hospital stay, bleeding, and adverse events up to 90 days. RESULTS: Eighty-one patients with acute sPE were randomized and were available for analysis. The mean total dose of alteplase for USAT was 19 ± 7 mg and for SCDT was 18 ± 7 mg (P = 0.53), infused over 14 ± 6 and 14 ± 5 hours, respectively (P = 0.99). In the USAT group, the mean raw pulmonary arterial thrombus score was reduced from 31 ± 4 at baseline to 22 ± 7 (P < 0.001). In the SCDT group, the score was reduced from 33 ± 4 to 23 ± 7 (P < 0.001). There was no significant difference in mean thrombus score reduction between the 2 groups (P = 0.76). The mean reduction in right ventricular/left ventricular ratio from baseline (1.54 ± 0.30 for USAT, 1.69 ± 0.44 for SCDT) to 48 hours was 0.37 ± 0.34 in the USAT group and 0.59 ± 0.42 in the SCDT group (P = 0.01). Major bleeding (1 stroke and 1 vaginal bleed requiring transfusion) occurred in 2 patients, both in the USAT group. CONCLUSIONS: In the SUNSET sPE (Standard vs. Ultrasound-Assisted Catheter Thrombolysis for Submassive Pulmonary Embolism) trial, patients undergoing USAT had similar pulmonary arterial thrombus reduction compared with those undergoing SCDT, using comparable mean lytic doses and durations of lysis.

Impact and role of pulmonary embolism response teams in venous thromboembolism associated with COVID-19.

Venous thromboembolism associated with COVID-19, particularly acute pulmonary embolism, may represent a challenging and complex clinical scenario. The benefits of having a multidisciplinary pulmonary embolism response team (PERT) can be important during such a pandemic. The aim of PERT in the care of such patients is to provide fast, appropriate, multidisciplinary, team-based approach, with the common goal to tailor the best therapeutic decision making, prioritizing always optimal patient care, especially given lack of evidence-based clinical practice guidelines in the setting of COVID-19, which potentially confers a significant prothrombotic state. Herein, we would like to briefly emphasize the importance and potential critical role of PERT in the care of patients in which these two devastating illnesses are present together.

Direct oral anticoagulants in chronic thromboembolic pulmonary hypertension.

Chronic thromboembolic pulmonary hypertension (CTEPH) represents the later stage consequence of at least one or more unresolved episodes of acute pulmonary embolism; thus, indefinite anticoagulation is strongly recommended by current practice guidelines. Historically, vitamin K antagonists have been widely used in these patients. However, recent data indicate a shift toward direct oral anticoagulants (DOACs), despite lack of data on the safety and efficacy in this patient population. Herein, we briefly discuss the current rationale for oral anticoagulation use in CTEPH, addressing important issues and controversies involved with the use of DOACs, opening a strategy for further clinical research in the field of oral anticoagulation.

Risk Stratification in Acute Pulmonary Embolism: The Latest Algorithms.

Pulmonary embolism (PE) is a common clinical entity, which most clinicians will encounter. Appropriate risk stratification of patients is key to identify those who may benefit from reperfusion therapy. The first step in risk assessment should be the identification of hemodynamic instability and, if present, urgent patient consideration for systemic thrombolytics. In the absence of shock, there is a plethora of imaging studies, biochemical markers, and clinical scores that can be used to further assess the patients' short-term mortality risk. Integrated prediction models incorporate more information toward an individualized and precise mortality prediction. Additionally, bleeding risk scores should be utilized prior to initiation of anticoagulation and/or reperfusion therapy administration. Here, we review the latest algorithms for a comprehensive risk stratification of the patient with acute PE.

The PERT Concept: A Step-by-Step Approach to Managing Pulmonary Embolism.

Pulmonary embolism (PE) is a major source of morbidity and mortality. The presentation of acute PE varies, ranging from few or no symptoms to sudden death. Patient outcome depends on how well the right ventricle can sustain the increased afterload caused by the embolic burden. Careful risk stratification is critical, and the PE response team (PERT) concept offers a rapid and multidisciplinary approach. Anticoagulation is essential unless contraindicated; thrombolysis, surgical embolectomy, and catheter-directed approaches are also available. Clinical consensus statements have been published that offer a guide to PE management, but areas remain for which the evidence is inadequate. Although the management of low-risk and high-risk patients is more straightforward, optimal management of intermediate-risk patients remains controversial. In this document, we offer a case-based approach to PE management, beginning with diagnosis and risk stratification, followed by therapeutic alternatives, and finishing with follow-up care.

Perioperative Acute Pulmonary Embolism: A Concise Review with Emphasis on Multidisciplinary Approach.

Perioperative acute pulmonary embolism represents a relatively rare complication; however, it could be very serious and devastating in some cases. Its diagnosis could be particularly challenging, especially in the intraoperative period. Herein, we emphasize some key concepts with the aim to perform an early and appropriate risk stratification, diagnostic and therapeutic approach in a multidisciplinary fashion, a brief overview on thromboprophylaxis, with the main objective to improve outcomes and survival in these challenging patients.

Diagnosis and Treatment of Pulmonary Embolism During the Coronavirus Disease 2019 Pandemic: A Position Paper From the National PERT Consortium.

The coexistence of coronavirus disease 2019 (COVID-19) and pulmonary embolism (PE), two life-threatening illnesses, in the same patient presents a unique challenge. Guidelines have delineated how best to diagnose and manage patients with PE. However, the unique aspects of COVID-19 confound both the diagnosis and treatment of PE, and therefore require modification of established algorithms. Important considerations include adjustment of diagnostic modalities, incorporation of the prothrombotic contribution of COVID-19, management of two critical cardiorespiratory illnesses in the same patient, and protecting patients and health-care workers while providing optimal care. The benefits of a team-based approach for decision-making and coordination of care, such as that offered by pulmonary embolism response teams (PERTs), have become more evident in this crisis. The importance of careful follow-up care also is underscored for patients with these two diseases with long-term effects. This position paper from the PERT Consortium specifically addresses issues related to the diagnosis and management of PE in patients with COVID-19.

Outcomes of catheter-directed thrombolysis vs. standard medical therapy in patients with acute submassive pulmonary embolism.

BACKGROUND: Catheter-directed thrombolysis (CDL) is increasingly being used for the treatment of submassive and massive pulmonary embolism. Although this therapy has been shown to be effective at reducing right ventricle strain, the impact on clinical outcomes remains unclear. We therefore aimed to evaluate the outcomes of CDL compared to standard anticoagulation for submassive pulmonary embolism patients in a large cohort. METHODS: We conducted a retrospective observational study of consecutive patients with a primary diagnosis of submassive pulmonary embolism admitted to an intensive care unit within our health system between June 2014 and April 2016. We compared the outcome of patients treated with systemic anticoagulation (medical therapy) vs. catheter-based delivery of tissue plasminogen activator (tPA) (CDL). CDL patients were matched with medical therapy controls using a propensity-score matching algorithm based on the components of the simplified pulmonary embolism severity index (sPESI) score. RESULTS: Unadjusted mortality rates were 3.0% for CDL vs. 10.4% for medical therapy at 30 days and 8.1% for CDL vs. 22.9% for medical therapy at 1 year. In the propensity-score matched cohort, mortality rates were 3.1% for CDL vs. 6.1% for medical therapy at 30 days and 8.2% for CDL vs. 18.2% for medical therapy at 1 year. Length of stay was significantly shorter in the CDL group. The index admission bleeding and transfusion rates were not increased in the CDL group. CONCLUSIONS: In patients presenting with acute submassive pulmonary embolism who are admitted to an intensive care unit, the group treated with CDL experienced reduced mortality at 30 days and 1 year when compared to medical therapy without increase in bleeding. Further randomized studies are required to confirm these findings.