Development and Validation of a Natural Language Processing Model to Identify Low-Risk Pulmonary Embolism in Real Time to Facilitate Safe Outpatient Management.
This study aimed to (1) develop and validate a natural language processing model to identify the presence of pulmonary embolism (PE) based on real-time radiology reports and (2) identify low-risk PE patients based on previously validated risk stratification scores using variables extracted from the electronic health record at the time of diagnosis. The combination of these approaches yielded an natural language processing-based clinical decision support tool that can identify patients presenting to the emergency department (ED) with low-risk PE as candidates for outpatient management.
Data were curated from all patients who received a PE-protocol computed tomography pulmonary angiogram (PE-CTPA) imaging study in the ED of a 3-hospital academic health system between June 1, 2018 and December 31, 2020 (n=12,183). The "preliminary" radiology reports from these imaging studies made available to ED clinicians at the time of diagnosis were adjudicated as positive or negative for PE by the clinical team. The reports were then divided into development, internal validation, and temporal validation cohorts in order to train, test, and validate an natural language processing model that could identify the presence of PE based on unstructured text. For risk stratification, patient- and encounter-level data elements were curated from the electronic health record and used to compute a real-time simplified pulmonary embolism severity (sPESI) score at the time of diagnosis. Chart abstraction was performed on all low-risk PE patients admitted for inpatient management.
When applied to the internal validation and temporal validation cohorts, the natural language processing model identified the presence of PE from radiology reports with an area under the receiver operating characteristic curve of 0.99, sensitivity of 0.86 to 0.87, and specificity of 0.99. Across cohorts, 10.5% of PE-CTPA studies were positive for PE, of which 22.2% were classified as low-risk by the sPESI score. Of all low-risk PE patients, 74.3% were admitted for inpatient management.
This study demonstrates that a natural language processing-based model utilizing real-time radiology reports can accurately identify patients with PE. Further, this model, used in combination with a validated risk stratification score (sPESI), provides a clinical decision support tool that accurately identifies patients in the ED with low-risk PE as candidates for outpatient management.
Amin KD
，Weissler EH
，Ratliff W
，Sullivan AE
，Holder TA
，Bury C
，Francis S
，Theiling BJ
，Hintze B
，Gao M
，Nichols M
，Balu S
，Jones WS
，Sendak M
... -
《-》
Maribavir treatment for resistant cytomegalovirus disseminated disease in kidney transplant recipients: A case-based scoping review of real life data in literature.
The treatment of refractory CMV is often associated with high toxicity. Maribavir (MBV) is a novel oral antiviral, known for its favourable safety profile in fragile patients. We describe a case of CMV disease with end organ damage following kidney transplantation at high risk, for recipient-donor serological mismatch. A 54-year-old female with history of obesity, hypertension, and chronic kidney disease, on prednisone and tacrolimus after kidney transplantation in November 2022, soon after developed primary CMV infection, treated with Valganciclovir and CMV Ig. In January 2023 the patient presented with fever and dyspnea. Pulmonary miliary opacities and right-upper lobe consolidation were found at CT-scan along with CMV-DNA positivity on BAL and serum. Lung biopsy confirmed CMV infection. Antiviral was switched to Ganciclovir. Despite initial benefit, fever and respiratory failure happened 8 days later, leading to intubation at day 15. Due to slow decrease serum CMV-DNA and detection of UL97 mutation, conferring resistance to valganciclovir and ganciclovir, the patient was started on foscarnet and letermovir. She was extubated after a gradual respiratory improvement and discharged from ICU to rehabilitation department with HFNC; reduction in serum CMV-DNA, but persistently elevated CMV-DNA on BAL were documented. At week 8, MBV was started and letermovir continued, for a 8 weeks course, without notable adverse effects. Respiratory function improved but soon after septic shock occurred. A bone marrow biopsy resulted in lymphoma, without indications for treatment: the patient developed coma and died 6 months after admission. MBV has recently been approved in Europe for treatment of R/R CMV in HSCT and SOT recipients. MBV showed superior rates of viraemia clearance after 8 weeks compared to SOC, demonstrating also a favourable safety profile with fewer patients discontinuing treatment and being affected by nephrotoxicity and neutropenia. Its main side effects are taste impairment, gastro-intestinal symptoms and asthenia. Based on actual promising perspectives regarding antiviral stewardship, more data are required to corroborate benefit of MBV in terms of toxicity and impact on mortality in highly fragile populations as SOT recipients. MBV received approval for the treatment of refractory or resistant CMV infections to other antiviral agents. Nevertheless, real-life data on efficacy and safety of MBV are still lacking. We conducted a narrative review of the current literature on MBV as treatment for CMV infection in kidney transplant recipients to understand clinical characteristics, safety and outcomes of MBV in this population. A search was run on the main scientific databases. 194 papers were identified, of which 188 were excluded by title and abstract evaluation. Subsequently, 6 papers were included. We performed descriptive statistics on the entire study population. The studies included in our analysis showed a higher prevalence of male subjects. The median age was 57 year. CKD was the most frequently reported comorbidity. Seven patients reported a donor/recipient mismatch (D+/R-). The case report and the cohort of patients collected from the literature show that MBV was used as an option in R/R CMV, notably for the presence or suspicion of CMV resistance to previous treatment. The clinical presentation of CMV in kidney SOT was heterogenous and varied from isolated reactivation of CMV-DNAemia, isolated fever or gastrointestinal involvement. For mild to moderate CMV disease, as with the cases reported in our review, or for proven ganciclovir, foscarnet or cidofovir resistance, MBV could be a valuable option. Outcomes of the patients treated with MBV were not reported in all the studies; however, where reported, 45.4% of the cases developed virological failure during MBV treatment with the development of specific resistance to MBV. MBV was generally well-tolerated, with low rates of toxicity, normally reversible. The introduction of new oral antivirals, such as MBV, could improve treatment, prophylaxis and preemptive treatment strategies, especially in anti-CMV treatment experienced patients.
Corcione S
，Lupia T
，Vita D
，Sidoti F
，Zanotto E
，Solidoro P
，Biancone L
，Costa C
，Balagna R
，De Rosa FG
... -
《-》
Development of a predictive nomogram for early identification of pulmonary embolism in hospitalized patients: a retrospective cohort study.
Hospitalized patients often present with complex clinical conditions, but there is a lack of effective tools to assess their risk of pulmonary embolism (PE). Therefore, our study aimed to develop a nomogram model for better predicting PE in hospitalized populations.
Data from hospitalized patients (aged ≥ 15 years) who underwent computed tomography pulmonary angiography (CTPA) to confirm PE and non-PE were collected from December 2013 to April 2023. Univariate and multivariate stepwise logistic regression analyses were conducted to identify independent predictors of PE, followed by the construction of a predictive nomogram and internal validation. The efficiency and clinical utility of the nomogram model were assessed using receiver operating characteristic (ROC) curve, decision curve analysis (DCA), and clinical impact curve (CIC).
The study included 313 PE and 339 non-PE hospitalized patients. Male gender, dyspnea or shortness of breath, interstitial lung disease, lower limb deep vein thrombosis, elevated fibrin degradation product (FDP), pulmonary arterial hypertension, and tricuspid regurgitation were identified as independent risk factors. The AUC of the predictive nomogram model was 0.956 (95% CI: 0.939-0.974), demonstrating superior performance compared with the simplified Wells score of 0.698 (95% CI: 0.654-0.741) and the modified Geneva score of 0.758 (95% CI: 0.717-0.799).
Our study demonstrated that challenges remain in the accuracy of the Wells score and revised Geneva score in assessing PE in hospitalized patients. Fortunately, the nomogram we developed has shown a favorable ability to discriminate PE cases, providing high reference value for clinical practice. However, given that this was a single-center study, we plan to expand efforts to collect data from additional centers to further validate our model.
Cao Z
，Yang L
，Han J
，Lv X
，Wang X
，Zhang B
，Ye X
，Ye H
... -
《BMC Pulmonary Medicine》
ResearchGate
(全网免费下载)
钛学术
(全网免费下载)
