Prognostic Effect of Incidental Pulmonary Embolism on Long-Term Mortality in Cancer Patients

Implementation of an AI Algorithm in Clinical Practice to Reduce Missed Incidental Pulmonary Embolisms on Chest CT and Its Impact on Short-Term Survival

OBJECTIVES

A substantial number of incidental pulmonary embolisms (iPEs) in computed tomography scans are missed by radiologists in their daily routine. This study analyzes the radiological reports of iPE cases before and after implementation of an artificial intelligence (AI) algorithm for iPE detection. Furthermore, we investigate the anatomic distribution patterns within missed iPE cases and mortality within a 90-day follow-up in patients before and after AI use.

MATERIALS AND METHODS

This institutional review board-approved observational single-center study included 5298 chest computed tomography scans performed for reasons other than suspected pulmonary embolism (PE). We compared 2 cohorts: cohort 1, consisting of 1964 patients whose original radiology reports were generated before the implementation of an AI algorithm, and cohort 2, consisting of 3334 patients whose scans were analyzed after the implementation of an Food and Drug Administration-approved and CE-certified AI algorithm for iPE detection (Aidoc Medical, Tel Aviv, Israel). For both cohorts, any discrepancies between the original radiology reports and the AI results were reviewed by 2 thoracic imaging subspecialized radiologists. In the original radiology report and in case of discrepancies with the AI algorithm, the expert review served as reference standard. Sensitivity, specificity, prevalence, negative predictive value (NPV), and positive predictive value (PPV) were calculated. The rates of missed iPEs in both cohorts were compared statistically using STATA (Version 17.1). Kaplan-Meier curves and Cox proportional hazards models were used for survival analysis.

RESULTS

In cohort 1 (mean age 70.6 years, 48% female [n = 944], 52% male [n = 1020]), the prevalence of confirmed iPE was 2.2% (n = 42), and the AI detected 61 suspicious iPEs, resulting in a sensitivity of 95%, a specificity of 99%, a PPV of 69%, and an NPV of 99%. Radiologists missed 50% of iPE cases in cohort 1. In cohort 2 (mean age 69 years, 47% female [n = 1567], 53% male [n = 1767]), the prevalence of confirmed iPEs was 1.7% (56/3334), with AI detecting 59 suspicious cases (sensitivity 90%, specificity 99%, PPV 95%, NPV 99%). The rate of missed iPEs by radiologists dropped to 7.1% after AI implementation, showing a significant improvement ( P < 0.001). Most overlooked iPEs (61%) were in the right lower lobe. The survival analysis showed no significantly decreased 90-day mortality rate, with a hazards ratio of 0.95 (95% confidence interval, 0.45-1.96; P = 0.88).

CONCLUSIONS

The implementation of an AI algorithm significantly reduced the rate of missed iPEs from 50% to 7.1%, thereby enhancing diagnostic accuracy. Despite this improvement, the 90-day mortality rate remained unchanged. These findings highlight the AI tool's potential to assist radiologists in accurately identifying iPEs, although its implementation does not significantly affect short-term survival. Notably, most missed iPEs were located in the right lower lobe, suggesting that radiologists should pay particular attention to this area during evaluations.

Development of a nomogram model to predict 30-day mortality in ICU cancer patients with acute pulmonary embolism

Cancer patients with acute pulmonary embolism (APE) admitted to the intensive care unit (ICU) face a high short-term mortality rate. The simplified pulmonary embolism severity index (sPESI) is tool for predicting adverse outcomes. However, its effectiveness in ICU cancer patients with APE remains unclear. This study aimed to validate the sPESI score and develop a predictive model for 30-day mortality in this specific patient group. We conducted a retrospective analysis using data from the MIMIC-IV database, focusing on ICU patients with cancer and APE. The primary outcome of interest was 30-day mortality. Predictors were initially selected using Least Absolute Shrinkage and Selection Operator (LASSO) analysis. A multivariable logistic regression model was then developed. The performance of the nomogram was assessed using calibration, decision curve analysis (DCA), and receiver operating characteristic (ROC) curve analysis to evaluate accuracy, clinical utility, and discrimination, respectively. A total of 286 cancer patients with APE were included in the study, with an average age of 68.9 years; the cohort comprised 137 males (47.9%) and 149 females (52.1%), and the 30-day mortality rate was 32.2%. Multivariable logistic regression analysis identified SOFA score, tumor metastasis, hemoglobin level, anion gap, weight and the prevalence of liver disease as independent predictors of 30-day mortality. The area under the curves (AUCs) of ROC for sPESI and the nomogram model were 0.568 (95% CI, 0.500-0.637) and 0.761 (95% CI, 0.701-0.821). The nomogram model had a higher predictive value for 30-day mortality in patients with acute pulmonary embolism and cancer compared to the sPESI score (P < 0.05). We developed a nomogram to predict the probability of 30-day mortality for ICU patients with acute pulmonary embolism and cancer. This nomogram demonstrated robust performance and serves as a valuable tool for clinicians to identify patients at high risk of 30-day mortality.

Added value of an artificial intelligence algorithm in reducing the number of missed incidental acute pulmonary embolism in routine portal venous phase chest CT

OBJECTIVES

The purpose of this study was to evaluate the incremental value of artificial intelligence (AI) compared to the diagnostic accuracy of radiologists alone in detecting incidental acute pulmonary embolism (PE) on routine portal venous contrast-enhanced chest computed tomography (CT).

METHODS

CTs of 3089 consecutive patients referred to the radiology department for a routine contrast-enhanced chest CT between 27-5-2020 and 31-12-2020, were retrospectively analysed by a CE-certified and FDA-approved AI algorithm. The diagnostic performance of the AI was compared to the initial report. To determine the reference standard, discordant findings were independently evaluated by two readers. In case of disagreement, another experienced cardiothoracic radiologist with knowledge of the initial report and the AI output adjudicated.

RESULTS

The prevalence of acute incidental PE in the reference standard was 2.2% (67 of 3089 patients). In 25 cases, AI detected initially unreported PE. This included three cases concerning central/lobar PE. Sensitivity of the AI algorithm was significantly higher than the outcome of the initial report (respectively 95.5% vs. 62.7%, p < 0.001), whereas specificity was very high for both (respectively 99.6% vs 99.9%, p = 0.012). The AI algorithm only showed a slightly higher amount of false-positive findings (11 vs. 2), resulting in a significantly lower PPV (85.3% vs. 95.5%, p = 0.047).

CONCLUSION

The AI algorithm showed high diagnostic accuracy in diagnosing incidental PE, detecting an additional 25 cases of initially unreported PE, accounting for 37.3% of all positive cases.

CLINICAL RELEVANCE STATEMENT

Radiologist support from AI algorithms in daily practice can prevent missed incidental acute PE on routine chest CT, without a high burden of false-positive cases.

KEY POINTS

• Incidental pulmonary embolism is often missed by radiologists in non-diagnostic scans with suboptimal contrast opacification within the pulmonary trunk. • An artificial intelligence algorithm showed higher sensitivity detecting incidental pulmonary embolism on routine portal venous chest CT compared to the initial report. • Implementation of artificial intelligence support in routine daily practice will reduce the number of missed incidental pulmonary embolism.

Interpretable Machine Learning Approach for Predicting 30-Day Mortality of Critical Ill Patients with Pulmonary Embolism and Heart Failure: A Retrospective Study

BACKGROUND

Pulmonary embolism (PE) patients combined with heart failure (HF) have been reported to have a high short-term mortality. However, few studies have developed predictive tools of 30-day mortality for these patients in intensive care unit (ICU). This study aimed to construct and validate a machine learning (ML) model to predict 30-day mortality for PE patients combined with HF in ICU.

METHODS

We enrolled patients with PE combined with HF in the Medical Information Mart for Intensive Care Database (MIMIC) and developed six ML models after feature selection. Further, eICU Collaborative Research Database (eICU-CRD) was utilized for external vali- dation. The area under curves (AUC), calibration curves, decision curve analysis (DCA), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were performed to evaluate the prediction performance. Shapley additive explanation (SHAP) was performed to enhance the interpretability of our models.

RESULTS

A total of 472 PE patients combined with HF were included. We developed six ML models by the 13 selected features. After internal validation, the Support Vector Ma- chine (SVM) model performed best with an AUC of 0.835, a superior calibration degree, and a wider risk threshold (from 0% to 90%) for obtaining clinical benefit, which also outperformed traditional mortality risk evaluation systems,as evaluated by NRI and IDI. The SVM model was still reliable after external validation. SHAP was performed to explain the model. Moreover, an online application was developed for further clinical use.

CONCLUSION

This study developed a potential tool for identify short-term mortality risk to guide clinical decision making for PE patients combined with HF in the ICU. The SHAP method also helped clinicians to better understand the model.

An age-group analysis on the efficacy of chemotherapy in older adult patients with metastatic biliary tract cancer: a Japanese cancer registry cohort study

BACKGROUND

The effectiveness of chemotherapy in older adult patients with biliary tract cancer (BTC) remains to be established, despite the fact that the majority of patients diagnosed with BTC tend to be aged ≥ 70 years. In this study, we used three databases to examine the effectiveness of chemotherapy in a large patient population aged ≥ 70 years with metastatic BTC.

METHODS

Using a large Japanese database that combined three data sources (Osaka Cancer Registry, Japan's Diagnosis Procedure Combination, the hospital-based cancer registry database), we extracted the data from patients pathologically diagnosed with metastatic BTC, between January 1, 2013, and December 31, 2015, in 30 designated cancer care hospitals (DCCHs). A cohort of patients with comparable backgrounds was identified using propensity score matching. The log-rank test was used to examine how chemotherapy affected overall survival (OS).

RESULTS

Among 2,622 registered patients with BTC in 30 DCCHs, 207 older adult patients aged > 70 years with metastatic BTC were selected. Chemotherapy significantly improved the prognosis of older adult patients, according to propensity score matching (chemotherapy, 6.4 months vs. best supportive care, 1.8 months, P value < 0.001). The number of patients receiving chemotherapy tends to decrease with age. Gemcitabine plus cisplatin (GC) and gemcitabine plus S-1 (oral fluoropyrimidine) (GS) combination therapy were frequently performed in the chemotherapy group for patients under 80 years of age (70-74 years, 61.7%; 75-79 years, 62.8%). In contrast, monotherapy including GEM and S-1 was more frequently performed in age groups over 80 years (80-84 years, 56.2%; 85-89 years, 77.7%; ≥90 years, 100%). In the chemotherapy group among older adult patients aged < 85 years, the median OS was significantly longer according to age-group analysis of the 5-year age range following propensity score matching.

CONCLUSIONS

In older adult patients with metastatic BTC who received chemotherapy, prolonged survival was observed. Chemotherapy may be a viable option for patients with metastatic BTC who are aged < 85 years.

Characteristics and 6-Month Mortality of Medical Oncology Patients With Incidental and Symptomatic Pulmonary Embolism: A Single-Institutional Retrospective Longitudinal Analysis

This study aimed to identify clinical characteristics of cancer patients with incidental pulmonary embolism (IPE) and assess the variables associated with 30-day mortality in cancer patients with PE including symptomatic pulmonary embolism (SPE) and IPE. 6-Month mortality rate in cancer patients with SPE and IPE were also compared. We retrospectively analyzed electronic medical records of cancer patients with newly diagnosed PE between January 2016 and June 2021. We compared clinical and radiological characteristics in cancer patients with IPE and SPE and identified variables associated with the overall 30-day mortality on multivariate analysis. All patients were followed up for 6 months and survival analysis was performed by use of Kaplan-Meier. Five hundred and nine eligible cancer patients with pulmonary embolism were identified during the study period. IPE is associated with lower BMI, colorectal and pancreas cancers, stage III/IV of cancer, recent antiangiogenic therapy, central venous catheter (CVC) and chronic cardiac or respiratory disease compared to SPE. The factors associated with 30-day mortality included poor performance status, lung/pleura or upper gastrointestinal cancers, stage III/IV of cancer, previous VTE, oxygen saturation < 95%, lactic acid > 2 mmol/l and bilateral PE. The overall survival in patients with IPE at 6-month follow-up was similar to those diagnosed with SPE. The present study has allowed the identification of factors associated with 30-day mortality in cancer patients with IPE and SPE. We also found similar mortality rate in cancer patients with IPE compared with patients with SPE at 6-month follow-up.

Incidentally Diagnosed With Pulmonary Embolism in Lung Cancer Patients: Comparison of Clinical Characteristics and Mortality With Symptomatic Pulmonary Embolism

The purpose of this work was to compare the clinical characteristics, rate of recurrent venous thromboembolism (VTE), bleeding complications and mortality of incidental and symptomatic pulmonary embolism (PE) detected on computed tomography in patients with lung cancer. Clinical data of lung cancer patients with PE were obtained from the Department of Respiratory and Critical Care Medicine of Ningbo First affiliated hospital of Ningbo University during January 2016 and June 2021 and were reviewed retrospectively. We compared clinical and radiological characteristics in lung cancer patients with incidental PE (IPE) and symptomatic PE (SPE) and identified variables associated with the 1-year survival on multivariate Cox analysis. All patients were followed up for 1 year to compare the risks of recurrent VTE, bleeding complications, and mortality. Survival analysis was performed by use of Kaplan-Meier. A total of 223 lung cancer patients with PE were enrolled over the period. Of these, 117 (52%) patients had symptomatic whereas 106 (48%) patients had incidental PE. Those with IPE were more likely to have adenocarcinoma, VTE history, chronic respiratory disease and chemotherapy within 30 days prior to PE, while SPE was more frequently observed in patients with squamous cancer, concomitant VTE, performance status 0-1, chronic heart disease and major surgery within 30 days prior to PE. During 1 year of follow-up, recurrent VTE was diagnosed in 10 patients (9.3%) in lung cancer patients with IPE and 13 patients (11.2%) with SPE. The 12-month cumulative recurrent VTE incidence was 9.6% for patients with incidental and 11.4% for patients with symptomatic PE (P = .61). The 12-month cumulative incidences of major bleeding complications were also comparable in the 2 groups (8.1% for incidental patients and 9.8% for symptomatic patients; P = .62). However, the respective 12-month mortality risks were 34.6% and 30.2% in lung cancer patients with IPE and SPE respectively (P = .03). On multivariate Cox analysis, we found that IPE occurrence was an independent risk factor associated with 1-year mortality in lung cancer patients complicated with PE after adjusting for age and sex (HR 1.517; 95% CI: 1.366-1.684; P = .027). Our findings suggest that lung cancer patients diagnosed with and treated for incidental PE had a similar rate of recurrent VTE, and incidence of hemorrhagic complications, but a significantly higher 1-year cumulative mortality rate after PE compared to those with symptomatic PE. IPE may be a marker of poor prognosis.

Associations Between Immune-Related Venous Thromboembolism and Efficacy of Immune Checkpoint Inhibitors: A Systematic Review and Meta-Analysis

This study aims to summarize the available data and determine if the presence of venous thromboembolism (VTE) immune-related adverse event (irAE) in patients with immune checkpoint inhibitor (ICI) therapy is associated with improved treatment efficacy and clinical outcomes, which in turn was used to help optimize patient selection for anticoagulation therapy and inform rational treatment strategies for overcoming the mechanisms of ICI resistance. PubMed, Embase, Web of Science, and Cochrane Library were searched up to March 18, 2023, for studies assessing the relationship between VTE irAE development during ICI therapy and cancer outcomes. Seven primary articles with a total of 4437 patients were included in the overall survival (OS) meta-analysis. Patients with VTE had a significant increase in overall mortality compared to patients without VTE in adjusted hazard ratios (HRs 1.36, 95% confidence interval [CI] 1.06-1.75, P  =  .02). In the studies where immortal time bias (ITB) was accounted for, patients with VTE irAE also had poor OS than those without. HR and the corresponding 95% CI values in the non-ITB group were 2.53 (1.75-3.66, P < .00001) with low heterogeneity (P  =  .17, I2  =  48%) and 1.21 (1.06-1.37, P  =  .004) in the ITB group with no heterogeneity (P  =  .95, I2  =  0%), respectively. Despite the heterogeneity identified, the evidence does suggest that VTE irAE occurrence could be served as a prognostic indicator, with higher frequencies of occurrence associated with poorer OS. However, the fundamental role of this association with clinical consequences should be further investigated in large cohorts and clinical trials.

Chemotherapy effectiveness and age-group analysis of older adult patients with metastatic pancreatic cancer: A Japanese cancer registry cohort study

INTRODUCTION

Although older adults aged ≥75 years comprise a substantial proportion of patients diagnosed with pancreatic cancer (PC), the effectiveness of chemotherapy in older adults with PC remains to be established.

MATERIALS AND METHODS

This retrospective study examined the effectiveness of chemotherapy according to age in older adult patients with metastatic PC. We used a large database that combined three data sources (the hospital-based cancer registry database, Osaka Cancer Registry, and Japan's Diagnosis Procedure Combination) and extracted data from patients pathologically diagnosed with metastatic PC between 2013 and 2015 in 31 designated cancer care hospitals in Japan. Propensity score matching (PSM) was used to identify a cohort of patients with similar backgrounds. The effect of chemotherapy on overall survival (OS) was analyzed using the log-rank test.

RESULTS

Compared with 687 younger patients (<75 years old), 276 older adult patients had significant impairments in activities of daily living and poorer prognoses (6.8 vs. 4.1 months, p < 0.001), with a lower frequency of chemotherapy (81.5% vs. 55.1%; p < 0.001). PSM of older adult patients showed that chemotherapy significantly contributed to a better prognosis (best supportive care, 2.6 months vs. chemotherapy, 5.8 months, p < 0.001). Age group analysis with PSM of five-year age ranges revealed that the median OS was significantly longer in the chemotherapy group among older adult patients aged <85 years.

DISCUSSION

Chemotherapy provides a survival benefit in older adult patients with metastatic PC, and patients aged <85 years could be promising candidates for chemotherapy.

Emergency management of incidental pulmonary embolism (IPE)

Venous thrombo-embolic (VTE) disease is a common cause of complications in patients with cancer and is the second most common cause of death in oncology patients other than the malignant disease. Whilst symptomatic VTE comprises the majority of such presentations to an emergency department (ED), incidental pulmonary embolism (IPE) is an increasingly frequent reason for attendance.

Many studies report that the consequences of IPE do not differ significantly from those with symptomatic presentations and thus most guidelines recommend using the same approach. The complexity of treatment in cancer patients due to increased prevalence of co-morbidities, higher risk of bleeding, abnormal platelet and renal function, greater risk of VTE recurrence, and medications with the risk of anticoagulant interaction are consistent across patients with symptomatic and IPE.

One of the initial challenges of the management of IPE is the design of a pathway that provides both patients and clinicians with a seamless journey from the radiological diagnosis of IPE to their initial clinical workup and management. Increased access to ambulatory care has successfully reduced ED utilisation and improved clinical outcomes in high-risk non-oncological populations, such as those with IPE.

In this clinical review, we consider IPE management, its workup, the conundrums it may present for emergency physicians and the need to consider emergency ambulatory care for this growing cohort of patients.

Venous thromboembolism: Recent advancement and future perspective

Clinicians have been more and more often encountering patients with venous thromboembolism (VTE), including pulmonary embolism and deep vein thrombosis, leading to the increased importance of VTE in daily clinical practice. VTE is becoming a common issue in Asian countries including Japan. The management strategies of VTE have changed dramatically in the past decade including the introduction of direct oral anticoagulants (DOACs). In addition, there have been several landmark clinical trials assessing acute treatment strategies including thrombolysis and inferior vena cava (IVC) filter. The current VTE guidelines do not recommend the routine use of thrombolysis or IVC filters based on recent evidence; Nevertheless, the prevalence of thrombolysis and IVC filter use in Japan was strikingly high. The novel profiles of DOACs with rapid onset of action and potential benefit of a lower risk for bleeding compared with vitamin K antagonist could make home treatment feasible and is safer even with extended anticoagulation therapy. One of the most clinically relevant issues for VTE treatment is optimal duration of anticoagulation for the secondary prevention of VTE. Considering recent evidence, optimal duration of anticoagulation should be determined based on the risk for recurrence as well as the risk for bleeding in an individual patient. Despite the recent advances for VTE management, there are still a number of uncertain issues that challenge clinicians in daily clinical practice, such as cancer-associated VTE and minor VTE including subsegmental pulmonary embolism and distal deep vein thrombosis, warranting future research. Several clinical trials are now ongoing for these issues, globally as well as in Japan. The current review is aimed to overview the recent advances in VTE management, describe the current status including some domestic issues in Japan, and discuss the future perspective of VTE.