Suspected Acute Pulmonary Embolism: Gestalt, Scoring Systems, and Artificial Intelligence

Performance and clinical utility of an artificial intelligence-enabled tool for pulmonary embolism detection

PURPOSE

Diagnosing pulmonary embolism (PE) is still challenging due to other conditions that can mimic its appearance, leading to incomplete or delayed management and several inter-observer variabilities. This study evaluated the performance and clinical utility of an artificial intelligence (AI)-based application designed to assist clinicians in the detection of PE on CT pulmonary angiography (CTPA).

PATIENTS AND METHODS

CTPAs from 230 US cities acquired on 57 scanner models from 6 different vendors were retrospectively collected. Three US board certified expert radiologists defined the ground truth by majority agreement. The same cases were analyzed by CINA-PE, an AI-driven algorithm capable of detecting and highlighting suspected PE locations. The algorithm's performance at a per-case and per-finding level was evaluated. Furthermore, cases with PE not mentioned in the clinical report but correctly detected by the algorithm were analyzed.

RESULTS

A total of 1204 CTPAs (mean age 62.1 years ± 16.6[SD], 44.4 % female, 14.9 % positive) were included in the study. Per-case sensitivity and specificity were 93.9 % (95%CI: 89.3 %-96.9 %) and 94.8 % (95%CI: 93.3 %-96.1 %), respectively. Per-finding positive predictive value was 89.5 % (95%CI: 86.7 %-91.9 %). Among the 196 positive cases, 29 (15.6 %) were not mentioned in the clinical report. The algorithm detected 22/29 (76 %) of these cases, leading to a reduction in the miss rate from 15.6 % to 3.8 % (7/186).

CONCLUSIONS

The AI-based application may improve diagnostic accuracy in detecting PE and enhance patient outcomes through timely intervention. Integrating AI tools in clinical workflows can reduce missed or delayed diagnoses, and positively impact healthcare delivery and patient care.

A machine learning model for diagnosing acute pulmonary embolism and comparison with Wells score, revised Geneva score, and Years algorithm

BACKGROUND

Acute pulmonary embolism (APE) is a fatal cardiovascular disease, yet missed diagnosis and misdiagnosis often occur due to non-specific symptoms and signs. A simple, objective technique will help clinicians make a quick and precise diagnosis. In population studies, machine learning (ML) plays a critical role in characterizing cardiovascular risks, predicting outcomes, and identifying biomarkers. This work sought to develop an ML model for helping APE diagnosis and compare it against current clinical probability assessment models.

METHODS

This is a single-center retrospective study. Patients with suspected APE were continuously enrolled and randomly divided into two groups including training and testing sets. A total of 8 ML models, including random forest (RF), Naïve Bayes, decision tree, K-nearest neighbors, logistic regression, multi-layer perceptron, support vector machine, and gradient boosting decision tree were developed based on the training set to diagnose APE. Thereafter, the model with the best diagnostic performance was selected and evaluated against the current clinical assessment strategies, including the Wells score, revised Geneva score, and Years algorithm. Eventually, the ML model was internally validated to assess the diagnostic performance using receiver operating characteristic (ROC) analysis.

RESULTS

The ML models were constructed using eight clinical features, including D-dimer, cardiac troponin T (cTNT), arterial oxygen saturation, heart rate, chest pain, lower limb pain, hemoptysis, and chronic heart failure. Among eight ML models, the RF model achieved the best performance with the highest area under the curve (AUC) (AUC = 0.774). Compared to the current clinical assessment strategies, the RF model outperformed the Wells score ( P = 0.030) and was not inferior to any other clinical probability assessment strategy. The AUC of the RF model for diagnosing APE onset in internal validation set was 0.726.

CONCLUSIONS

Based on RF algorithm, a novel prediction model was finally constructed for APE diagnosis. When compared to the current clinical assessment strategies, the RF model achieved better diagnostic efficacy and accuracy. Therefore, the ML algorithm can be a useful tool in assisting with the diagnosis of APE.

Pulmonary embolism and hemorrhage after displacement of angiographic catheter tip to pulmonary artery: A case report and literature review

Pulmonary embolism and massive hemoptysis caused by intravascular foreign bodies have rarely been reported. We report a case of an end-stage renal disease patient in which the tip of the angiographic catheter fell off into the pulmonary artery during endovascular interventional opening when the patient underwent vascular access occlusion for dialysis. During the operation, the foreign body was displaced repeatedly and finally anchored to the posterior basal segment branch of the right lower pulmonary artery. A pulmonary embolism occurred during the operation, and massive hemoptysis and hemorrhagic shock occurred after anticoagulation and thrombolytic therapy. After receiving anti-shock and symptomatic treatment, the patient gradually recovered. After six months of follow-up, no pulmonary embolism or pulmonary infarction occurred. Our case report presents an alternative approach to extracting a foreign object from the pulmonary artery by locating the foreign object within the vascular terminations, without resorting to forceful removal. This method mitigates the potential risks of pulmonary embolism and bleeding associated with forceful extraction.

Predictive Value of MPV and Plasma NT-ProBNP Combined with the Simplified Geneva Scale for the Prognosis of Acute Pulmonary Embolism

OBJECTIVE

To explore the predictive value of mean platelet volume (MPV) and plasma N-terminal probrain natriuretic peptide (NT-ProBNP) combined with a simplified Geneva scale for the prognosis of acute pulmonary embolism (APE).

METHODS

The clinical data of 68 patients with APE admitted to our hospital from October 2017 to October 2019 were collected. According to the prognosis, the patients were divided into a good prognosis group (n = 45) and a poor prognosis group (n = 23). The clinical data, laboratory clinical indexes, and simplified Geneva scale scores were recorded for the two groups. The risk factors of poor prognosis were analyzed by binary multivariate logistic regression analysis; the predictive ability of each index on the prognosis of patients with APE was analyzed by the ROC curve.

RESULTS

The incidences of deep vein thrombosis, diabetes, and hyperlipidemia in the poor prognosis group were higher than those in the good prognosis group (P < 0.05). PLT, platelet distribution width (PDW), MPV, and plasma NT-ProBNP in the poor prognosis group were higher than those in the good prognosis group (P < 0.05). The simplified Geneva scale score of the poor prognosis group was higher than that of the good prognosis group (P < 0.05). PDW, MPV, plasma NT-ProBNP, and simplified Geneva scale were all independent risk factors for the poor prognosis of APE patients (P < 0.05). The AUC of MPV in predicting the prognosis of APE patients was 0.818 (95% CI: 0.712-0.925). When the optimal cutoff value was 0.571, the sensitivity was 77.1%, and the specificity was 80.0%. The AUC of plasma NT-ProBNP in predicting the prognosis of APE patients was 0.762 (95% CI: 0.634-0.891). When the optimal cutoff value was 0.475, the sensitivity was 71.5%, and the specificity was 76.0%. The AUC of the simplified Geneva scale in predicting the prognosis of APE patients was 0.749 (95% CI: 0.618-0.879). When the optimal cutoff value was 0.469, the sensitivity was 82.9%, and the specificity was 64.0%. The AUC of MPV and plasma NT-ProBNP combined with the simplified Geneva scale in predicting the prognosis of APE patients was 0.907 (95% CI: 0.826-0.988). When the optimal cutoff value was 0.726, the sensitivity was 88.6%, and the specificity was 84.0%.

CONCLUSION

MPV, plasma NT-ProBNP, and simplified Geneva scale have a certain predictive value for the prognosis of APE. Compared with a single index, the combination of the three indexes has a significant improvement in predicting the prognosis of APE and has better clinical value.