Incidental pulmonary embolism in patients with cancer: prevalence, underdiagnosis and evaluation of an AI algorithm for automatic detection of pulmonary embolism.

OBJECTIVES: To assess the prevalence of reported and unreported incidental pulmonary embolism (iPE) in patients with cancer, and to evaluate an artificial intelligence (AI) algorithm for automatic detection of iPE. METHODS: Retrospective cohort study on patients with cancer with an elective CT study including the chest between 2018-07-01 and 2019-06-30. All study reports and images were reviewed to identify reported and unreported iPE and were processed by the AI algorithm. RESULTS: One thousand sixty-nine patients (1892 studies) were included. Per study, iPE was present in 75 studies (4.0%), of which 16 (21.3%) were reported. Unreported iPE had a significantly lower number of involved vessels compared to reported iPE, with a median of 2 (interquartile range, IQR, 1-4) versus 5 (IQR 3-9.75), p < 0.001. There were no significant differences in age, cancer type, or attenuation of the main pulmonary artery. The AI algorithm correctly identified 68 of 75 iPE, with 3 false positives (sensitivity 90.7%, specificity 99.8%, PPV 95.6%, NPV 99.6%). False negatives occurred in cases with 1-3 involved vessels. Of the unreported iPE, 32/59 (54.2%) were proximal to the subsegmental arteries. CONCLUSION: In patients with cancer, the prevalence of iPE was 4.0%, of which only 21% were reported. Greater than 50% of unreported iPE were proximal to the subsegmental arteries. The AI algorithm had a very high sensitivity and specificity with only three false positives, with the potential to increase the detection rate of iPE. KEY POINTS: • In a retrospective single-center study on patients with cancer, unreported iPE were common, with the majority lying proximal to the subsegmental arteries. • The evaluated AI algorithm had a very high sensitivity and specificity, so has the potential to increase the detection rate of iPE.

Vertebral compression fractures at abdominal CT: underdiagnosis, undertreatment and evaluation of an AI algorithm.

Vertebral compression fractures (VCF) are common and indicate a high future risk of additional osteoporotic fractures. However, many VCFs are unreported by radiologists, and even if reported, many patients do not receive treatment. The purpose of the study was to evaluate a new artificial intelligence (AI) algorithm for the detection of VCFs, and to assess the prevalence of reported and unreported VCFs. This retrospective cohort study included patients over age 60 years with an abdominal CT between 18 January 2019 and 18 January 2020. Images and radiology reports were reviewed to identify reported and unreported VCFs, and the images were processed by an AI algorithm. For reported VCFs, the electronic medical records were reviewed regarding subsequent osteoporosis screening and treatment. Totally, 1112 patients were included. Of these, 187 patients (16.8%) had a VCF, of which 62 had an incident VCF and 49 had a previously unknown prevalent VCF. The radiologist reporting rate of these VCFs was 30% (33/111). For moderate and severe (Grade 2-3) VCF, the AI algorithm had 85.2% sensitivity, 92.3% specificity, 57.8% PPV and 98.1% NPV. Three of 30 patients with reported VCFs started osteoporosis treatment within a year. The AI algorithm had high accuracy for the detection of VCFs and could be very useful in increasing the detection rate of VCFs, as there was a substantial underdiagnosis of VCFs. However, as undertreatment in reported cases was substantial, to fully realize the potential of AI, changes to the management pathway outside of the radiology department are imperative.

Vertebral compression fractures (VCF) are the most common osteoporotic fractures. However, they often go undetected leading to a high risk of further fractures. In this study we tested a new artificial intelligence (AI) algorithm to detect VCFs in abdominal CT scans in patients over 60 years of age, and assessed how often VCFs were missed by radiologists. We found that VCFs were underreported, with only 30% being identified by the radiologists. The AI algorithm showed promising results and had high accuracy for detecting VCFs. However, many patients with a detected VCF still did not receive treatment. The results suggests that AI could increase the detection rate of VCFs, but also highlights the need for changes beyond radiology to ensure that patients with detected fractures are appropriately treated.

Detection of acute pulmonary embolism using native repeated magnetic resonance imaging acquisitions under free-breathing and without respiratory or cardiac gating. A diagnostic accuracy study.

Objectives: Computed tomography pulmonary angiography (CTPA) is the gold standard diagnostic method for patients with suspected pulmonary embolism (PE), but it has its drawbacks, including exposure to ionizing radiation and iodinated contrast agent. The present study aims to evaluate the diagnostic performance of our in-house developed non-contrast MRI protocol for PE diagnosis in reference to CTPA. Methods: 107 patients were included, all of whom underwent MRI immediately before or within 36 hours after CTPA. Additional cases examined only with MRI and a negative result were added to reach a PE prevalence of approximately 20%. The protocol was a non-contrast 2D steady-state free precession (SSFP) sequence under free-breathing, without respiratory or cardiac gating, and repeated five times to capture the vessels at different breathing/cardiac phases. The MRIs were blinded and read by two radiologists and the results were compared to CTPA. Results: Of the 243 patients included, 47 were positive for PE. Readers 1 and 2 demonstrated 89% and 87% sensitivity, 100% specificity, 98% accuracy and Cohen's kappa of 0.88 on patient level. In the per embolus comparison, readers 1 and 2 detected, 60 and 59/61 (98, 97%) proximal, 101 and 94/113 (89, 83%) segmental, and 5 and 2/32 (16, 6%) subsegmental emboli, resulting in 81 and 75% sensitivity respectively. Conclusion: The repeated 2D SSFP can reliably be used for the diagnosis of acute PE at the proximal and segmental artery levels.

Use of a Deep Learning Algorithm for Detection and Triage of Cancer-associated Incidental Pulmonary Embolism.

Incidental pulmonary embolism (iPE) is a common complication in patients with cancer, and there is often a delay in reporting these studies and a delay between the finalized report and time to treatment. In addition, unreported iPE is common. This retrospective single-center cross-sectional study evaluated the effect of an artificial intelligence (AI) algorithm on the report turnaround time, time to treatment, and detection rate in patients with cancer-associated iPE. Adult patients with cancer were included either before (July 1, 2018, to June 30, 2019) or after (November 1, 2020, to April 30, 2021) implementation of an AI algorithm for iPE detection and triage. The results demonstrated that reported iPE prevalence was significantly higher in the period after AI implementation (2.5% [26 of 1036 studies] vs 0.8% [16 of 1892 studies], P < .001). Both report that the turnaround time (median, 0.66 hour vs 24.68 hours, P < .001) and time to treatment (median, 0.98 hour vs 28.05 hours, P < .001) were significantly shorter after AI implementation. In conclusion, the use of AI for detection and triage of iPE in clinical practice resulted in an increased detection rate of iPE and significantly shorter report turnaround time and time to treatment for patients with cancer-associated iPE. Keywords: Cancer-associated Incidental Pulmonary Embolism, Pulmonary Embolism, Artificial Intelligence, Cancer, CT Imaging © RSNA, 2023.

Unreported incidental pulmonary embolism in patients with cancer: Radiologic natural history and risk of recurrent venous thromboembolism and death.

PURPOSE: To assess the risk of recurrent venous thromboembolism (VTE) and death in patients with unreported cancer-associated incidental pulmonary embolism (iPE). MATERIALS AND METHODS: Matched cohort study on cancer patients with a CT study including the chest between 2014-01-01 and 2019-06-30. Studies were reviewed for unreported iPE, and cases were matched with controls without iPE. Cases and controls were followed for one year, with recurrent VTE and death as outcome events. RESULTS: Of the included 2960 patients, 171 patients had unreported and untreated iPE. While controls had a one-year VTE risk of 8.2 events per 100 person-years, cases with a single subsegmental iPE had a recurrent VTE risk of 20.9 events, and between 52.0 and 72.0 events per 100 person-years for multiple subsegmental iPE and more proximal iPE. In multivariable analysis, multiple subsegmental and more proximal iPE were significantly associated with the risk of recurrent VTE, while single subsegmental iPE was not associated with the risk of recurrent VTE (p = 0.13). In the subgroup of patients (n = 47) with cancer not in the highest Khorana VTE risk category, no metastases and up to three involved vessels, recurrent VTE occurred in two patients (4.7 cases per 100 person-years). There were no significant associations between iPE burden and risk of death. CONCLUSION: In cancer patients with unreported iPE, iPE burden was associated with the risk of recurrent VTE. However, having a single subsegmental iPE was not associated with the risk of recurrent VTE. There were no significant associations between iPE burden and risk of death.

High-impact loading on the skeleton is associated with a decrease in glucose levels in young men.

OBJECTIVE: The skeleton has been suggested to be involved in energy metabolism through osteocalcin (OC), an osteoblast-specific molecule. The objective of this study was to investigate whether high-impact (HI) exercise stimulating bone formation would lead to changes in glucose and lipid metabolism independent of cardiorespiratory effects and whether OC mediates this association. DESIGN: Prospective intervention study. METHODS: Fifty men aged 20-32 years were allocated to an intervention group or a control group. The intervention group completed six different types of jumps in sets of five, with the frequency of these exercises gradually increasing over 8 weeks. At baseline and after 8 weeks, glycerol concentrations were measured in fat tissue as a marker of lipolysis using microdialysis. Blood samples were assayed for OC and markers of glucose and lipid metabolism. Physical activity was measured using an accelerometer. RESULTS: After adjustment for confounders at baseline and changes in physical activity during the intervention period, the intervention was associated with a decrease in levels of glucose (P = 0·04), adrenalin (P = 0·03) and OC (P = 0·04) after adjusting for baseline levels and changes in physical activity. No other differences between the groups were significant, although the trends of the metabolic variables favoured the intervention group. CONCLUSIONS: The results of this study suggest that HI loading on the skeleton may affect glucose metabolism independent of the level of aerobic exercise.

Body composition and mortality risk in later life.

BACKGROUND: body mass index is used widely to define overweight and obesity. Both high and low body mass indices are associated with increased mortality risk during middle age, but the relationship is less clear in later life. Thus, studies on the relationships between other aspects of body composition and mortality among older subjects are needed. OBJECTIVE: to investigate associations between different aspects of body composition and mortality in older people. METHODS: the study population comprised 921 participants aged ≥65 years who underwent dual-energy X-ray (DXA) absorptiometric examination at the Sports Medicine Unit, Umeå University. The main reason for admission was clinical suspicion of osteoporosis. Total, abdominal and gynoid fat masses and lean body mass were measured by DXA absorptiometry at baseline, and the cohort was followed (mean duration, 9.2 years) for mortality events. RESULTS: during follow-up, 397 participants died. Lean mass was associated negatively with mortality in men and women (P < 0.001). Total fat mass showed a U-shaped association with mortality in men (P < 0.01) and a negative association in women (P < 0.01). A higher ratio of abdominal to gynoid fat mass increased mortality risk in women (P = 0.04), but not in men (P = 0.91). CONCLUSIONS: lean mass is associated strongly with survival in older subjects. Greater fat mass is protective in older women, whereas very low or very high fat mass increases the risk of death in men. Further research is needed to better understand the mechanisms underlying these associations.

Abdominal and gynoid fat mass are associated with cardiovascular risk factors in men and women.

CONTEXT: Abdominal obesity is an established risk factor for cardiovascular disease (CVD). However, the correlation of dual-energy x-ray absorptiometry (DEXA) measurements of regional fat mass with CVD risk factors has not been completely investigated. OBJECTIVE: The aim of this study was to investigate the association of estimated regional fat mass, measured with DEXA and CVD risk factors. DESIGN, SETTING, AND PARTICIPANTS: This was a cross-sectional study of 175 men and 417 women. DEXA measurements of regional fat mass were performed on all subjects, who subsequently participated in a community intervention program. MAIN OUTCOME MEASURES: Outcome measures included impaired glucose tolerance, hypercholesterolemia, hypertriglyceridemia, and hypertension. RESULTS: We began by assessing the associations of the adipose measures with the cardiovascular outcomes. After adjustment for confounders, a sd unit increase in abdominal fat mass was the strongest predictor of most cardiovascular variables in men [odds ratio (OR)=2.63-3.37; P<0.05], whereas the ratio of abdominal to gynoid fat mass was the strongest predictor in women (OR=1.48-2.19; P<0.05). Gynoid fat mass was positively associated with impaired glucose tolerance, hypertriglyceridemia, and hypertension in men (OR=2.07-2.15; P<0.05), whereas the ratio of gynoid to total fat mass showed a negative association with hypertriglyceridemia and hypertension (OR=0.42-0.62; P<0.005). CONCLUSIONS: Abdominal fat mass is strongly independently associated with CVD risk factors in the present study. In contrast, gynoid fat mass was positively associated, whereas the ratio of gynoid to total fat mass was negatively associated with risk factors for CVD.