Diagnosis of pulmonary embolism with various imaging modalities

COVID-Classifier: an automated machine learning model to assist in the diagnosis of COVID-19 infection in chest X-ray images

Chest-X ray (CXR) radiography can be used as a first-line triage process for non-COVID-19 patients with pneumonia. However, the similarity between features of CXR images of COVID-19 and pneumonia caused by other infections makes the differential diagnosis by radiologists challenging. We hypothesized that machine learning-based classifiers can reliably distinguish the CXR images of COVID-19 patients from other forms of pneumonia. We used a dimensionality reduction method to generate a set of optimal features of CXR images to build an efficient machine learning classifier that can distinguish COVID-19 cases from non-COVID-19 cases with high accuracy and sensitivity. By using global features of the whole CXR images, we successfully implemented our classifier using a relatively small dataset of CXR images. We propose that our COVID-Classifier can be used in conjunction with other tests for optimal allocation of hospital resources by rapid triage of non-COVID-19 cases.

Ambulatory management of pulmonary embolism

The diagnosis of pulmonary embolism can be very difficult and elusive. It depends greatly on the use of diagnostic tests, which are in turn interpreted according to a pre-test clinical probability. These include non-specific tests such as the chest X-ray and electrocardiograph, which help exclude other conditions such as pneumonia or myocardial infarction. On the other hand, more specific tests such as computed tomography or ventilation/perfusion scanning are used to confirm or exclude the diagnosis of pulmonary embolism. The condition is potentially fatal, and in the past patients with suspected pulmonary embolism constituted a significant number of hospital admissions. Despite this, the majority were found not to have pulmonary embolism. More recently, studies have suggested that most patients with suspected pulmonary embolism who are haemodynamically stable can be safely managed on an ambulatory pathway. Therefore, there is a paradigm shift towards investigating and treating pulmonary embolism in the outpatient setting. This article discusses the ambulatory pathway of the diagnosis and treatment of pulmonary embolism.

Chest X-Ray Not Routinely Indicated Prior to the YEARS Algorithm in the Diagnostic Management of Suspected Pulmonary Embolism

Background  The YEARS algorithm was designed to simplify the diagnostic process of suspected pulmonary embolism (PE) and to reduce the number of required computed tomography pulmonary angiography (CTPA) scans. Chest X-ray (CXR) is often used as initial imaging test in patients suspected for PE. Aim  To determine if CXR results differ between patients with confirmed PE and with PE ruled out, and to investigate whether CXR provides incremental diagnostic value to the YEARS criteria that is used for selecting patients with CTPA indication. Methods  This post-hoc analysis concerned 1,473 consecutive patients with suspected PE who were managed according to YEARS and were subjected to CXR as part of routine care. The prevalence and likelihood ratios of seven main CXR findings for a final diagnosis of PE were calculated. Results  A total of 214 patients were diagnosed with PE at baseline (15%). Abnormal CXR occurred more often in patients with confirmed PE (36%, 77/214) than in patients without PE (26%; 327/1,259), for an odds ratio of 1.60 (95% confidence interval: 1.18-2.18). Only the unexpected finding of a (rib)fracture or pneumothorax, present in as few as six patients (0.4%), significantly lowered the post-test probability of PE to an extent that CTPA could have been avoided. Conclusion  The incremental diagnostic value of CXR to the YEARS algorithm to rule out PE was limited. CXR was more frequently abnormal in patients with PE than in those in whom PE was ruled out. These data do not support to perform CXR routinely in all patients with suspected PE, prior to CTPA imaging.

Infrared thermal imaging and Doppler vessel pressurization ultrasonography to detect lower extremity deep vein thrombosis: Diagnostic accuracy study

BACKGROUND AND OBJECTIVE

Infrared thermal imaging (IRTI) is a new technique for detecting deep vein thrombosis (DVT) based on DVT's infrared presentation and distribution characteristics (PDCs). A method that is singularly sensitive to DVT is needed. They, therefore, enrolled 157 subjects with suspected lower extremity DVT in a double-blind, controlled clinical trial using IRTI, and Doppler compression ultrasonography (CPUS) to verify the clinical value of IRTI.

METHODS

An IRTI system could precisely measure and store real-time thermal images. A double-blind, controlled clinical study using IRTI and detection on 157 patients with suspected DVTs, evaluating the following parameters: sensitivity, specificity, positive prescreening, negative prescreening, false positivity, false negativity, and diagnostic accordance of IRTI with CPUS for detecting DVT were conducted.

RESULTS

Of 140 subjects who underwent screening both IRTI and CPUS detect were included for analyses. According to their IRTI DVT's presentation and distribution characteristics, patients were divided into IRTI- negative (n = 59) and IRTI-positive (including suspicious IRTI positive) (n = 81) groups. CPUS identified 80 DVT-negative and 60 DVT-positive patients. The sensitivity of IRTI for detecting DVT was 88.33%, specificity 65.00%, false-positive diagnosis 11.67%, false-negative diagnosis 35.00%, positive prescreening 65.43%, negative prescreening 88.14%, diagnostic accordance rate 75.00%. IRTI results accorded with CPUS results (P = .001) except for the positivity incidence (χ²  = 39.997, P < .001).

CONCLUSIONS

IRTI could be used to supplement CPUS detection for detecting DVTs and adjunctive diagnostic screening.

The importance of MTHFR C677T/A1298C combined polymorphisms in pulmonary embolism in Turkish population

BACKGROUND AND OBJECTIVE

Pulmonary embolism (PE) is an important cardiovascular emergency with high mortality. There are still problems related to the diagnosis of PE and genetic research may play a key role on diagnosis as well as determining risk stratification. In the present study, the aim was to evaluate MTHFR C677T and A1298C polymorphisms that play a role on folate metabolism in PE patients.

MATERIALS AND METHODS

A total of 118 PE patients and 126 controls were enrolled in the current study. Genomic DNA was isolated and genotyped using polymerase chain reaction (PCR) analyses for the MTHFR C677T and A1298C polymorphisms.

RESULTS

There was no association between clinical and demographic characteristics of PE patients and both MTHFR C677T and A1298C polymorphisms. Allele frequencies showed a significant difference between patients and controls. T allele frequency was significantly higher in the patients' group than the control group. There was an association between PE and combined MTHFR C677T and A1298C polymorphisms.

CONCLUSION

We found an association between MTHFR C677T/A1298C combined mutations and PE in the Turkish population. Future genetic studies investigating combined mutations could be very helpful to identify risk population in PE.

Infrared thermal imaging as a novel evaluation method for deep vein thrombosis in lower limbs

PURPOSE

Early detection of deep vein thrombosis (DVT) is critical to prevent clinical pulmonary thromboembolism. However, most conventional methods for diagnosing DVT are functionally limited and complicated. The aim of this study was to evaluate the value of infrared-thermal-imaging (IRTI), a novel imaging detection or screening technique, in diagnosis of DVT in animal models.

METHODS

DVT model of femoral veins was established in nine New Zealand rabbits. The right hind femoral vein was embolized and the contralateral one served as a nonembolized control. Measurements of IRTI, compression ultrasonography (CPUS), and angiography under ultrasonic observation (AGUO) were performed at three time points: T1 (baseline, 10 min prior to surgery), T2 (2 h after thrombin injection), and T3 (48 h postoperatively). Qualitative pseudocolor analysis and quantitative temperature analysis were performed based on mean area temperature (Tav) and mean curvilinear temperature (Tca) of the region of interest as shown in IRTI. Temperature differences (TD) in Tav (TD(Tav)) and Tca (TD(Tca)) between the DVT and control sides were computed. Comparative statistical analysis was carried out by paired t-test and repeated measure, while multiple comparisons were performed by using Greenhouse-Geisser and Bonferroni approach. Values of P < 0.05 and P < 0.01 were considered statistically significant and highly significant.

RESULTS

Modeling of DVT was successful in all rabbits, as confirmed by CPUS and AGUO and immediately detected by IRTI. IRTI qualitative analysis of pseudocolor revealed that the bilateral temperatures were apparently asymmetrical and that there were abnormally high temperature zones on the DVT side where thrombosis formed. The results of paired t-test of Tav and Tca between DVT side and control sides did not reveal statistical difference at T1 (Tav: P = 0.817; Tca: P = 0.983) yet showed statistical differences at both T2 (Tav: P = 0.023; Tca: P = 0.021) and T3 (Tav: P = 0.016; Tca: P = 0.028). Results of repeated measure and multiple comparisons of TD(Tav) and TD(Tca) were highly different and significant differences across the T2 (TD(Tav): P = 0.009; TD(Tav): P = 0.03) and T3 (TD(Tav): P = 0.015; TD(Tav): P = 0.021).

CONCLUSIONS

IRTI temperature quantitative analysis may help further detection of DVT. Additionally, IRTI could serve as a novel detection and screening tool for DVT due to its convenience, rapid response, and high sensitivity.

Imaging of acute pulmonary embolism

Acute pulmonary thromboembolism (PE) is a cardiovascular emergency associated with significant morbidity and a 5-35 % mortality for untreated pulmonary embolism. If promptly diagnosed and treated, the mortality rate can be significantly reduced. Diagnosis of acute PE continues to be a clinical challenge, with diagnostic imaging playing an important role. This review discusses the clinical challenges of diagnosing acute PE, presents an evidence-based review of the current tests and ever-evolving imaging technology, and highlights special considerations related to radiation dose, contrast media use, and pregnant patients.

The current state of practice in the diagnosis of venous thromboembolism at an academic medical center

Evidence-based guidelines for the diagnosis of venous thromboembolism (VTE) have been recommended, yet the adoption of such guidelines into daily practice is unknown. The purpose of this study was to describe the current practices in the diagnosis of VTE. Medical records of 1161 adult patients who underwent lower extremity venous duplex scans (VDS), chest computerized tomographic (CT) angiography, or ventilation and perfusion (V/Q) scans during a 6-month period were retrospectively reviewed in an academic medical center. Patients who were first diagnosed by CT or V/Q scan still underwent a VDS. Nine patients at high risk had incomplete CT scans, yet no further tests were performed. Five pregnant patients had CT scans as the initial test instead of being screened with VDS or V/Q scanning. Inappropriate use of imaging tests was documented. The recommended guidelines of using clinical probability and D-dimer as the initial screening tests for VTE diagnosis were underused.

Medical complications of surgical treatment of adult spinal deformity and how to avoid them

STUDY DESIGN

Review article of medical complications related to adult spinal deformity surgery.

OBJECTIVE

To identify medical complications related to surgery for adult spinal deformity and suggest ways to minimize their occurrence and to avoid them.

SUMMARY OF BACKGROUND DATA

Medical complications are a major consideration in adult spinal deformity surgery. Few studies have been done to identify the medical complication rate in relation to these procedures.

METHODS

We review the literature pertaining to medical complications regarding spinal deformity surgery.

RESULTS

Urinary tract infections are the most frequently seen complication. Additionally, pulmonary complications are the most common life-threatening complication. Medical complications are a frequent occurrence with adult deformity spinal surgery.

CONCLUSIONS

Awareness of the presentation, treatment, and prevention of medical complications of deformity surgery may allow minimization of their occurrence and optimize treatment should they occur.

CT pulmonary angiography is the first-line imaging test for acute pulmonary embolism: a survey of US clinicians

RATIONALE AND OBJECTIVES

Our aim is to document current imaging practices for diagnosing acute pulmonary embolism (PE) among physicians practicing in the United States and explore factors associated with these practices.

MATERIALS AND METHODS

Between September 2004 and February 2005, we surveyed by mail 855 physicians selected at random from membership lists of three professional organizations. Physicians reported their imaging practices and experiences in managing patients with suspected acute PE during the preceding 12 months.

RESULTS

Completed questionnaires were received from 240 of 806 eligible participants (29.8%) practicing in 44 states: 86.7% of respondents believed that computed tomographic pulmonary angiography (CTPA) was the most useful imaging procedure for patients with acute PE compared with 8.3% for ventilation-perfusion (V-P) scintigraphy and 2.5% for conventional pulminary angiography (PA). After chest radiography, CTPA was the first imaging test requested 71.4% of the time compared with V-P scintigraphy (19.7%) and lower-limb venous ultrasound (5.8%). Participants received indeterminate or inconclusive results 46.4% of the time for V-P scintigraphy, 10.6% of the time for CTPA, and 2.2% of the time for PA. CTPA was available around the clock to 88.3% of participants compared with 53.8% for V-P scintigraphy and 42.5% for PA. A total of 68.6% of respondents received CTPA results in 2 hours or less (vs 37.5% for V-P scintigraphy and 22.9% for PA). CTPA also provided an alternative diagnosis to PE or showed other significant abnormalities 28.5% of the time, and these findings frequently altered management.

CONCLUSION

US clinicians unequivocally prefer CTPA in patients with suspected acute PE. Reasons for this preference include availability and timely reporting, a lower rate of inconclusive results, and the additional diagnostic capabilities that CTPA can provide.

Sensitive and quantitative, 10-min immunofluorometric assay for D-Dimer in whole blood

INTRODUCTION

Normal concentrations of D-Dimer can be used to exclude venous thromboembolism (VTE). However, methods for sensitive and quantitative D-Dimer measurements at the point-of-care (POC) are still limited.

MATERIALS AND METHODS

We developed a 10-min, non-competitive immunofluorometric assay for D-Dimer in citrated whole blood and plasma using pre-dispensed reagents dried in single assay wells. The simple, automated assay procedure comprises a 1:50 sample dilution, one-step incubation, washing, and time-resolved fluorometric measurement directly from the wet well surface.

RESULTS

The limits of detection (background + 3SD) and quantification (CV <15%) were 0.05 and 0.2 mg/L D-Dimer, respectively, and the assay was linear up to 400 mg/L. Correlations to Roche TinaQuant (r=0.726, n=200) and Biopool Auto.Dimer (r=0.190, n=149) were carried out using citrated plasma. Diagnostic sensitivity, specificity, and negative (NPV) and positive (PPV) predictive values were 98.7%, 64.4%, 99.1% and 55.1%, and 92.2%, 81.0%, 95.9% and 68.3%, respectively, using cut-off values of 0.6 and 1.0 mg/L, respectively, in outpatients with deep vein thrombosis (DVT) and/or pulmonary embolism (PE) (n=77) compared with outpatients with various other diseases (n=174). The within- and between-run CVs near the cut-off values were < or =10% in both whole blood and plasma. The 95th percentile upper range in apparently healthy individuals was 0.68 mg/L of whole blood (n=101).

CONCLUSIONS

The high sensitivity and NPV suggest that the rapid immunofluorometric assay could be valuable for rapid exclusion of VTE in outpatients. With appropriate cut-offs, the assay could potentially be used as a stand-alone test or combined with clinical probability assessment, but further studies are required.

Diagnosing pulmonary embolism: Experience with spiral CT pulmonary angiography in gynecologic oncology

OBJECTIVES

To review our experience with the diagnosis and prognosis of pulmonary embolism (PE) in gynecologic oncology patients.

METHODS

Spiral CT pulmonary angiography (CTPA) studies on gynecologic oncology patients were collected from our radiology database from 6/2001 to 6/2003. Patient charts were retrospectively reviewed. Data were abstracted relative to presenting symptoms, demographics and laboratory and diagnostic evaluations. Patient data were compared using chi-square contingency tables and logistic regression analysis. Survival was studied using the Kaplan-Meier method and the log rank test. The effect of PE on survival was adjusted using a proportional hazards regression model.

RESULTS

One-hundred and eleven CTPA studies were performed over 2 years and 25 patients were diagnosed with PE. Both PE (n = 25) and non-PE (n = 86) groups were similar for age, race, BMI and cancer diagnosis. Tachycardia (P = 0.02, OR = 3.03 [95% CI 1.16-7.94]) and leukocytosis (P = 0.04, OR = 2.93[95% CI 1.05-8.18]) were more frequent among PE patients and confirmed as independently prognostic of PE. All other clinical and laboratory findings were similar between patients with and without PE. Overall survival for patients with and without PE was 63% versus 94%, respectively, at 2 years (P = 0.02).

CONCLUSION

In a gynecologic oncology patient with high clinical suspicion for PE, our clinical pre-test probability was 23.0%. Two-year mortality rates were 6-fold higher for patients diagnosed with PE. The significant overlap in clinical presentations, multiple risk factors and higher mortality rates encourage the aggressive diagnosis and treatment of PE among this population. Further work is needed to reduce the incidence and mortality rate of PE.