Chest CT Scan Research Articles

Participant adherence in a lung cancer screening (LCS) program in a non-smoking population.

10556 Background: LCS guidelines in smoking populations includes an annual low-dose CT Chest (LDCT) scan. Historically, real-world adherence to repeat imaging following the baseline LDCT has been low at 22% (Silvestri et al. Chest 2023). Various reasons for non-adherence have been cited and can be amplified in populations where English is not the primary language, low health literacy, or logistical reasons that interfere with scheduling. We are conducting the Female Asian Nonsmoker Screening Study (FANSS), which is a pilot study for Asian women with no smoking history to provide LDCTs to this population. We describe the strategies utilized to address potential barriers to adherence and report the participant (pt) adherence observed to date for this population. Methods: FANSS is an IRB-approved trial that provides LDCTs annually for 3 years and has an interim follow-up phone call every 6 months. All aspects of the study other than the LDCT could be conducted virtually pending pt preference. All pt interactions were conducted in the pt’s requested language. LDCTs were interpreted according to Lung-RADS. Review of the LDCT results were available in-person or virtually by a nurse practitioner or the principal investigator. The timeline for the 2nd and 3rd LDCT after the baseline scan was determined as follows: pts with negative findings were recommended for a repeat LDCT in 1 year; pts with suspicious findings were reviewed at the NYU Multidisciplinary Nodule Board and recommended for a repeated LDCT in a 3 or 6 month interval. A bilingual (English and Chinese speaking) research coordinator and medical secretaries reached out to pts at their preferred contact (email, phone, or text) for scheduling the follow-up LDCT. Up to three attempts to reach pts to schedule their follow-up LDCT were made. Results: From 3/5/21 to 1/27/24, 634 subjects completed their baseline LDCTs. Language interpretation services were utilized in 30% of pts. As of 1/27/24, 215 pts were due for their 2nd LDCT: 195 (91%) completed (186) or scheduled (9) the LDCT, 5 pts withdrew their consent, and 15 did not complete the scan. The main reasons for not completing the scans were: living outside New York City, other health concerns, and lost to follow-up. As of 1/27/24, 95 pts were due for their 3rd LDCT: 87 (92%) completed (82) and scheduled (5) the LDCT, and 8 did not complete the scan due to being lost to follow-up. Conclusions: The FANSS population is a unique pt cohort comprised of all Asian women who do not qualify for current LCS guidelines. Interventions to address potential adherence issues were implemented. In our research-based setting, virtual conduct of most of the study procedures allowed pt flexibility. Pt outreach to ensure follow-up by contacting through various methods also ensured adherence of >90%. These interventions can be considered for use in other LCS programs to improve adherence to LCS follow-up.

Recruitment strategies in a lung cancer screening program for Asian women with no smoking history.

e22514 Background: The Female Asian Nonsmoker Screening Study (FANSS) is a pilot study for eligible Asian women with no smoking history to provide low-dose CT (LDCT) Chest scans for lung cancer screening annually for 3 years. To recruit for the study, we took into consideration several factors including potential language barriers, low awareness of lung cancer incidence in non-smoking populations, and participant (pt) availability. Here we describe the use of various recruitment strategies to support enrollment to the FANSS study. Methods: Multimodal recruitment strategies for enrollment into FANSS were used. A dedicated phone line answered by receptionists able to speak English and several Chinese dialects was created. Research staff are bilingual or utilized telephonic interpretation services in all pt interactions. Informational flyers available in both English and Chinese were mailed to primary care physicians serving primarily Asian communities and posted in pharmacies and storefronts in NYC Chinatown. A website was developed for interested individuals to submit their contact information for further information. Working with our institutional Epic EMR, a list of all pts with active MyChart accounts was created with criteria “Asian,” “female,” “OK to contact for Research recruitment,” “age 40-74,” and excluded anyone with a smoking history and “Cancer” in the past 5 years. From this list, pts then were sent an IRB-approved recruitment message through MyChart from 3/2023-6/2023. Interested pts who reached out through the above methods were contacted by research staff to determine eligibility. All eligible pts who agreed to participate were consented either in-person or virtually to allow for schedule flexibility to review the consent. Results: From 3/5/21 to 1/27/24, 1518 women inquired about FANSS through our website, dedicated phone line or MyChart messages and were directly contacted by our team. After determination of eligibility, 760 pts had an informed consent discussion either virtually or in-person. From 3/5/21 to 3/2023, 247 pts underwent the consent process and 229 pts had a baseline LDCT. Following the intervention of directed MyChart messaging in 3/2023, 568 pts responded to the MyChart message indicating interest, however 102 pts were not eligible due to inaccurate info in their Epic medical record (i.e. ethnicity or smoking history). Overall, from 3/2023 to 1/27/24, 513 pts underwent the consent process. Among these, 90 subjects (18%) were recruited via MyChart. Conclusions: Recruitment to a lung cancer screening program in non-smokers is feasible, and specific considerations tailored to engage minority populations can improve enrollment such as bilingual staff and translated materials. The use of directed messaging through the Epic EMR is an important tool to identify potential pts which may be applied to aid in recruitment to other clinical trials or lung cancer screening programs.

Understanding the Added Value of High-Resolution CT Beyond Chest X-ray in Determining Extent of Physiologic Impairment

BackgroundSarcoidosis staging has primarily relied on the Scadding chest radiographic system, although chest CT is finding increased clinical use. Research QuestionWhether standardized CT assessment provides additional understanding of lung function beyond Scadding stage and demographics is unknown and the focus of this study. Study Design and MethodsWe used the NHLBI study Genomics Research in Alpha-1 Anti-Trypsin Deficiency and Sarcoidosis (GRADS) sarcoidosis cases(N=351) with Scadding stage and Chest CT scans obtained in a standardized manner. One chest radiologist scored all CT scans with a visual scoring system, with a subset read by another chest radiologist. We compared demographic features, Scadding stage and CT findings, and correlation between these measures. Associations between spirometry and DLCO and CT and Scadding stage were determined using regression analysis (N=318). Agreement between readers was evaluated using Cohen’s Kappa. ResultsCT features were inconsistent with Scadding stage in about ∼40% of cases. Most CT features assessed on visual scoring were negatively associated with lung function. Associations persisted for FEV1 and DLCO when adjusting for Scadding stage, although some CT feature associations with FVC became insignificant. Scadding stage was primarily associated with FEV1 and inclusion of CT features reduced significance in association between Scadding and lung function. Multivariable regression modeling to identify radiologic measures explaining lung function included Scadding stage for FEV1 and FEV1/FVC (P<0.05) and marginally for DLCO (P<0.15). Combinations of CT measures accounted for Scadding stage for FVC. Correlations among Scadding and CT features were noted. Agreement between readers was poor to moderate for presence/absence of CT features and poor for degree/location of abnormality. InterpretationCT features explained additional variability in lung function beyond Scadding stage, with some CT features obviating the associations between lung function and Scadding. Whether CT features/phenotypes/endotypes could be useful for managing patients with sarcoidosis needs more study.

Association of ratios of visceral fat area/subcutaneous fat area and muscle area/standard body weight at T12 CT level with the prognosis of acute respiratory distress syndrome

BackgroundIt is well-known that body composition metrics can influence the prognosis of various diseases. This study investigated how body composition metrics predict acute respiratory distress syndrome (ARDS) prognosis, focusing on the ratio of visceral fat area (VFA) to subcutaneous fat area (SFA), SFA to standard body weight (SBW), VFA to SBW, and muscle area (MA) to SBW. These metrics were assessed at the level of the twelfth thoracic vertebra (T12 computed tomography [CT] level) to determine their correlation with the outcomes of ARDS. The goal was to utilize these findings to refine and personalize treatment strategies for ARDS. MethodsPatients with ARDS admitted to the intensive care units (ICUs) of three hospitals from January 2016 to July 2023 were enrolled in this study. Within 24 hours of ARDS onset, we obtained chest CT scans to measure subcutaneous fat, visceral fat, and muscle area at the T12 level. We then compared these ratios between survivors and non-survivors. Logistic regression was employed to identify prognostic risk factors. Receiver operating characteristic (ROC) curve analysis was utilized to determine the optimal cutoff for predictors of in-hospital mortality. Based on this cutoff, patients with ARDS were stratified. To reduce confounding factors, 1:1 propensity score matching (PSM) was applied. We conducted analyses of clinical feature and prognostic differences pre- and post-PSM between the stratified groups. Additionally, Kaplan–Meier survival curves were generated to compare the survival outcomes of these groups. ResultsOf 258 patients with ARDS, 150 survived and 108 did not. Non-survivors had a higher VFA/SFA ratio (P <0.001) and lower SFA/SBW and MA/SBW ratios (both P <0.001). Key risk factors were high VFA/SFA ratio (OR=2.081; P=0.008), age, acute physiology and chronic health evaluation (APACHE) II score, and lactate levels, while MA/SBW and albumin were protective. Patients with a VFA/SFA ratio ≥0.73 were associated with increased mortality, while those with an MA/SBW ratio >1.55 cm²/kg had lower mortality, both pre- and post-PSM (P=0.001 and P <0.001, respectively). Among 170 patients with pulmonary-origin ARDS, 87 survived and 83 did not. The non-survivor group showed a higher VFA/SFA ratio (P <0.001) and lower SFA/SBW and MA/SBW (P=0.003, P <0.001, respectively). Similar risk and protective factors were observed in this cohort. For VFA/SFA, a value above the cutoff of 1.01 predicted higher mortality, while an MA/SBW value below the cutoff of 1.48 cm²/kg was associated with increased mortality (both P <0.001 pre-/post-PSM). ConclusionsAmong all patients with ARDS, the VFA to SFA ratio, MA to SBW ratio at the T12 level, age, APACHE II score, and lactate levels emerged as independent risk factors for mortality.

A variety of inflammatory shadows caused by COVID-19 on chest CT that closely resembled lung cancer in annual lung cancer screening.

e23122 Background: Chest X ray (CXR) has been the most common screen test procedure for detection of lung cancer. Before COVID-19, we have shown that repeat visitors (R) had a significantly lower proportion of CXR abnormalities requiring medication than the first-time visitors (F) at annual lung cancer screening. (Kimura T. Health Prim Car, 2021). During COVID-19, we reported that the influence of large waves of COVID-19 in annual lung cancer screening. (Kimura T. abstract No. e18596, ASCO annual meeting 2023) Because of the widespread use of vaccines, the XBB variants, derived from Omicron BA.2, has mainly cold-like symptoms. These variants spreads more easily than the original or the Delta variants. In Japan, since May 2023, COVID-19 has been made less dangerous under the Infectious Disease Control Law, which loosens the restrictions on wearing masks and having close contacts. No longer visits the hospital unless there is a high fever or dyspnea. Hypothesis is that there is a difference in lung cancer screening after a COVID-19 infestation compared to during and before COVID-19. Methods: Our clinic “MedCity21” is a university outpatient clinic for medical check-ups as a part of private health screening programs. Our facility allows COVID-19 diagnosed participants (pts) 5 days after onset or 24 hours after symptoms have abated. When the abnormalities were detected on CXR, pts were notified in a week by telephone request and invited to our specialty clinic for chest CT scan as further examination. By year from 2018 to 2023, we examined the varieties of abnormal shadows on CXR and CT and compared the differences using the chi-squared tests. Results: In 2023, there were 15072pts were visited our clinic for private health screening, among them, 13451pts (F:23.8%, R:75.2%) had chest X-rays performed. The January 2022, percentage of pts with a history of COVID was 1.68%, gradually increased, reaching 46.6% in December 2023. There were 226pts (1.68%) with CXR abnormalities requiring further investigation. The rates in F and R were 3.06% and 1.23%, respectively. The distributions of CXR and CT variations on R group were consistent with our previous report. However, significantly increased rate of inflammatory changes in CT findings (16.3%) in F group compared to each previous year (3.2-6.9%). (p = 0.014) We experienced a variety of inflammatory shadows on chest CT that closely resembled lung cancer. Such shadows were confirmed to have shrunk or disappeared on CT scan 1-2 months later. Conclusions: The pts who had ever had COVID-19 gradually increased. This was accompanied by an increase in the number of inflammatory shadows that were difficult to differentiate from lung cancer. It is better to follow up patients with CT or CXR for a month instead of immediately examining them. COVID-19 may cause concomitant bacterial or viral pneumonia; COVID-19 may affect the immune mechanisms of healthy individuals.

GoogLeNet-AL: A fully automated adaptive model for lung cancer detection

As lung cancer has emerged as the top contributor to cancer-related fatalities, efficient and precise diagnostic methods are essential for efficient diagnosis. This research introduces a novel CNN architecture GoogLeNet with Adaptive Layers (GoogLeNet-AL) for lung cancer detection. The GoogLeNet-AL architecture integrates innovative features such as squeeze-and-excitation blocks, dilated convolutions, depthwise separable convolutions, group convolutions, non-local blocks, octave convolutions, inverted Residuals, and ghost convolutions in the inception layers to boost the potential of GoogLeNet-AL to capture multi-scale features efficiently. The GoogLeNet-AL model has been implemented in the PyTorch 1.8.1 platform and trained using publicly accessible datasets IQ-OTH/NCCD and Chest CT-Scan for comprehensive performance evaluation. Additionally, we employ data augmentation, stratified sampling, and fairness-aware training to enhance robustness and mitigate biases. The experimental assessment demonstrate that the GoogLeNet-AL method achieves an accuracy of 98.74 %, an F1-score of 98.96 %, and a precision of 99.74 % in lung cancer detection and also demonstrates its superior performance by outperforming traditional GoogLeNet and other baseline models. Overall, the proposed architecture enhanced the detection and categorization of lung nodules by reducing false positives and negatives, thus offering a valuable tool for combating lung cancer.

Can Tumour Antigens Act as Biomarkers for the Early Detection of Non-Small Cell Lung Cancer?

Lung cancer (LC) is one of the leading causes of cancer-related deaths. Pulmonary nodules are one of the risk factors, and their discovery rate has been increasing due to enhanced performance of chest CT scans, but more than 90% are non-malignant, causing unnecessary stress to patients and costs to healthcare providers. Early diagnosis of LC is associated with a 5-year survival rate of up to 75% following surgical resection, but LC is often diagnosed late due to a lack of symptoms and poor 5-year survival rates as low as 10%. The cost of LC diagnosis is high, with 40% of it associated with benign lesions, which are difficult to differentiate from malignant lesions. Tumour-associated antigens (TAAs) may provide one way in which LC could be diagnosed early using minimally-invasive techniques, under their association with immune responses and specificity for disease. Here we discuss the potential of cancer-testis antigens (CTAs) to act as non-invasive biomarkers for the early detection of non-small cell lung cancer.

Right sided congenital diaphragmatic hernia

Introduction: Congenital diaphragmatic hernia is a rare affection, has been classified as posterolateral, anterior or central. The posterolateral defect occurs on the left side (85%), although it may involve the right side (13%) or be bilateral (2%). Patients and methods: We report the evolution after surgical treatment of right diaphragmatic hernia in one case. Results: A male neonate, born via uncomplicated vaginal delivery at a gestational age of 10 days, weighed 3.8 kg at birth and initially presented with weak crying and a dusky skin tone. He required intubation and was placed on a ventilator. Subsequent imaging studies including chest radiography and CT scan revealed a right congenital diaphragmatic hernia, while ultrasound confirmed the presence of pulmonary hypertension. Following stabilization, the newborn underwent thoracotomy surgery, during which intraoperative exploration revealed the entire liver within the thoracic cavity along with intestinal loops. The liver was challenging to maneuver but was successfully relocated into the abdomen, and the intestinal loops were reduced. Repair of the diaphragmatic defect was accomplished using non-absorbable sutures. Following surgery, the neonate was transferred to the neonatal intensive care unit (NICU), where a postoperative chest radiograph on the fourth day showed expansion of the right lung. Over the subsequent two years, the patient's condition remained stable without the development of respiratory complications or worsening symptoms. Conclusion: Success in this difficult case is optimized by close cooperation between the neonatologist, anesthesiologist, and pediatric surgeon. Although the hospital stay was prolonged, the survival outcome is excellent in this high-risk case.

Acute Q fever pneumonia diagnosed by metagenomic next-generation sequencing.

Q fever, a zoonotic disease caused byCoxiella burnetii(C. burnetii), presents diagnostic challenges due to its clinical and radiological nonspecificity, which often mimics community-acquired pneumonia, coupled with the limitations of traditional diagnostic methods. Metagenomic next-generation sequencing (mNGS) has become an indispensable tool in clinical diagnostics for its high-throughput pathogen identification capabilities. Herein, we detail a case of acute Q fever pneumonia diagnosed with mNGS. The patient exhibited symptoms of fever, cough, expectoration, and diarrhea for three days, with the pathogen undetected in initial laboratory assessments. Bronchoscopy and bronchoalveolar lavage (BAL) were conducted, leading to the identification of C. burnetii in the lavage fluid via mNGS. Consequently, the patient was promptly initiated on a treatment regimen of 100 mg doxycycline, administered orally every 12 hours. Post-treatment, the patient's temperature normalized, and a full recovery was observed. The follow-up chest CT scan revealed complete resolution of the right lower lobe consolidation. The clinical presentation of Q fever pneumonia lacks specificity, making diagnosis based solely on symptoms and imaging challenging. mNGS offers a superior alternative for identifying elusive or rarely cultured pathogens.

A user-friendly deep learning application for accurate lung cancer diagnosis.

Accurate diagnosis and subsequent delineated treatment planning require the experience of clinicians in the handling of their case numbers. However, applying deep learning in image processing is useful in creating tools that promise faster high-quality diagnoses, but the accuracy and precision of 3-D image processing from 2-D data may be limited by factors such as superposition of organs, distortion and magnification, and detection of new pathologies. The purpose of this research is to use radiomics and deep learning to develop a tool for lung cancer diagnosis. This study applies radiomics and deep learning in the diagnosis of lung cancer to help clinicians accurately analyze the images and thereby provide the appropriate treatment planning. 86 patients were recruited from Bach Mai Hospital, and 1012 patients were collected from an open-source database. First, deep learning has been applied in the process of segmentation by U-NET and cancer classification via the use of the DenseNet model. Second, the radiomics were applied for measuring and calculating diameter, surface area, and volume. Finally, the hardware also was designed by connecting between Arduino Nano and MFRC522 module for reading data from the tag. In addition, the displayed interface was created on a web platform using Python through Streamlit. The applied segmentation model yielded a validation loss of 0.498, a train loss of 0.27, a cancer classification validation loss of 0.78, and a training accuracy of 0.98. The outcomes of the diagnostic capabilities of lung cancer (recognition and classification of lung cancer from chest CT scans) were quite successful. The model provided means for storing and updating patients' data directly on the interface which allowed the results to be readily available for the health care providers. The developed system will improve clinical communication and information exchange. Moreover, it can manage efforts by generating correlated and coherent summaries of cancer diagnoses.

COVID Pneumonia Severity Detection of Chest CT-Scan Images based on Robust Semantic Segmentation

Image segmentation has steadily grown especially for clinical usage and disease recognition in radiological research. This procedure, aimed at acquiring quantitative measurements, strives to distinguish regions or objects of interest from adjacent body tissues. To be more specific, it entails measuring the area and volume of segmented structures to extract more refined diagnostic information. The main hurdles encountered by segmentation algorithms originate from challenges like variations in intensity, artifacts, and the close juxtaposition of diverse soft tissues in the grayscale. In this paper, a robust semantic segmentation is proposed to specify the infected regions of lung images and consider the severity degree of the pneumonia caused by COVID-19 disease. The proposed model provides an accurate diagnosis of the chest CT scan image with satisfied performance with 93% accuracy and the second most important metric which is the Jaccard Index with 0.746±0.09 shows higher prediction performance than most existing systems in the literature.

DistilIQA: Distilling Vision Transformers for no-reference perceptual CT image quality assessment

No-reference image quality assessment (IQA) is a critical step in medical image analysis, with the objective of predicting perceptual image quality without the need for a pristine reference image. The application of no-reference IQA to CT scans is valuable in providing an automated and objective approach to assessing scan quality, optimizing radiation dose, and improving overall healthcare efficiency. In this paper, we introduce DistilIQA, a novel distilled Vision Transformer network designed for no-reference CT image quality assessment. DistilIQA integrates convolutional operations and multi-head self-attention mechanisms by incorporating a powerful convolutional stem at the beginning of the traditional ViT network. Additionally, we present a two-step distillation methodology aimed at improving network performance and efficiency. In the initial step, a ”teacher ensemble network” is constructed by training five vision Transformer networks using a five-fold division schema. In the second step, a ”student network”, comprising of a single Vision Transformer, is trained using the original labeled dataset and the predictions generated by the teacher network as new labels. DistilIQA is evaluated in the task of quality score prediction from low-dose chest CT scans obtained from the LDCT and Projection data of the Cancer Imaging Archive, along with low-dose abdominal CT images from the LDCTIQAC2023 Grand Challenge. Our results demonstrate DistilIQA‘s remarkable performance in both benchmarks, surpassing the capabilities of various CNNs and Transformer architectures. Moreover, our comprehensive experimental analysis demonstrates the effectiveness of incorporating convolutional operations within the ViT architecture and highlights the advantages of our distillation methodology.

#2610 Low skeletal muscle mass and low skeletal muscle quality are associated with thoracic aorta calcification in dialysis patients

Abstract Background and Aims Cardiovascular disease (CVD) is the leading cause of mortality in dialysis patients. Thoracic aorta calcification (TAC) is a common cardiovascular complication in dialysis patients and is independently associated with CVD. Sarcopenia, particularly low skeletal muscle mass, has been found to be associated with increased cardiovascular risk in dialysis patients. This study aims to explore the relationship between skeletal muscle quality and skeletal muscle mass at the first lumbar vertebra (L1) level determined by opportunistic CT scans (chest CT) and TAC, with the goal of providing valuable opportunities for identifying and intervening in high-risk CVD patients. Method We included 2514 patients for cross-sectional analysis, who underwent dialysis in four centers in China from 2020 to 2023 and all had chest CT scans including the L1 level. Additionally, we conducted a follow-up study on TAC in patients who initiated dialysis between 2014 and 2019 as part of the earlier research, including 215 patients who had undergone at least two chest CT scans for cohort analysis. At the L1 level, we assessed skeletal muscle quality [by skeletal muscle density (SMD), HU] and skeletal muscle mass [by skeletal muscle index (SMI), cm2/m2] in dialysis patients. Measurements of thoracic aorta calcification scores (TACS) and calcification scores for three segments of the thoracic aorta, including ascending aorta calcification score (ATACS), aortic arch calcification score (AoACS), and descending thoracic aorta calcification score (DTACS), were obtained in dialysis patients. Patients were divided based on their annual calcification score growth rate: those with a rate greater than or equal to the average annual increase were classified into the rapid progression group, while those with a rate less than the average were classified into the slow progression group (including those with no progression). Multivariable linear regression models were employed to assess the relationships between SMI and SMD with TACS. Multivariable logistic regression models were used to evaluate the associations of SMl and SMD with the risk of rapid progression of TACS. Results The mean (SD) age of participants was 56 (15) years, with 58.2% being male. The prevalence of TAC was 82.2%, while the prevalence of ascending thoracic aorta calcification (ATAC), aortic arch calcification (AoAC), and descending thoracic aorta calcification (DTAC) was 21.4%, 75.3%, and 68.8%, respectively. Over an average follow-up period of 3.22 years, the progression rate of TAC was 85.6%. Comparing the highest quartile of SMD to the lowest quartile, a significant inverse association was observed with TAC (beta −1.19, 95% CI −1.55— −0.83; P &amp;lt; 0.001). Similarly, comparing the highest quartile of SMI to the lowest quartile, a significant inverse association was found with TAC (beta −0.59, 95% CI −0.92— −0.26; P = 0.001). SMI and SMD, as continuous variables, were both significantly negatively correlated with TAC. Higher SMD was associated with a reduced risk of rapid progression of TAC; after full adjustment, for every 1 SD increase in SMD, the risk of TAC rapid progression decreased by 46% (aOR 0.54, 95% CI 0.32—0.91; P = 0.021). SMI showed no significant association with the rapid progression of TAC. The associations of SMI and SMD with AoAC and DTAC were consistent with their associations with TAC, except for ATAC. The ROC curve analysis indicated that incorporating SMD into the model enhanced the discriminative ability for stratifying the risk of rapid progression of thoracic aorta calcification. Conclusion After adjusting for cardiovascular risk factors and inflammatory markers, higher skeletal muscle quality and higher skeletal muscle mass were significantly associated with lower TAC. Improving skeletal muscle quality in initial dialysis patients may reduce the risk of rapid TAC progression.

Artificial Intelligence in Cardiovascular Disease Prevention: Is it Ready for Prime Time?

This review evaluates how Artificial Intelligence (AI) enhances atherosclerotic cardiovascular disease (ASCVD) risk assessment, allows for opportunistic screening, and improves adherence to guidelines through the analysis of unstructured clinical data and patient-generated data. Additionally, it discusses strategies for integrating AI into clinical practice in preventive cardiology. AI models have shown superior performance in personalized ASCVD risk evaluations compared to traditional risk scores. These models now support automated detection of ASCVD risk markers, including coronary artery calcium (CAC), across various imaging modalities such as dedicated ECG-gated CT scans, chest X-rays, mammograms, coronary angiography, and non-gated chest CT scans. Moreover, large language model (LLM) pipelines are effective in identifying and addressing gaps and disparities in ASCVD preventive care, and can also enhance patient education. AI applications are proving invaluable in preventing and managing ASCVD and are primed for clinical use, provided they are implemented within well-regulated, iterative clinical pathways.

#3033 IgA vasculitis: a unexpected diagnosis of pulmonary renal syndrome

Abstract Background IgA vasculitis is an inflammatory condition affecting blood vessels that poses a significant diagnostic and therapeutic challenge in clinical practice. Characterized by the deposition of immunoglobulin A (IgA) on vessel walls, this pathology can manifest in various ways, presenting a broad and sometimes complex clinical spectrum. Ninety percent of cases occur in the pediatric age group. Severe lung involvement, such as pulmonary hemorrhage, is rare in patients with IgAV. We present a case of a 33-year-old patient with pulmonary renal syndrome and without purpura, an atypical presentation of IgA vasculitis. Case Report We describe the case of a 33-year-old patient with no relevant medical history or regular medication, who presented to the emergency department in November 2022 with symptoms of hemoptysis, fatigue, myalgias, and pallor. On physical examination, the patient was conscious, cooperative, normotensive, tachycardic, afebrile, with bilateral axillary adenopathies, and scattered crackles on lung auscultation. Laboratory tests revealed anemia with a hemoglobin level of 5.8 g/dL, non-oliguric acute kidney injury with a creatinine level of 2.25 mg/dL, microscopic hematuria (&amp;gt;50/hpf), and proteinuria (UPCR of 2.8 mg/mg and UACR of 1.6 mg/mg). A chest CT scan showed bilateral and scattered ground-glass opacities consistent with alveolar hemorrhage. The patient was admitted to the Nephrology service, underwent 3 sessions of plasma exchange, and started therapy with methylprednisolone 1000 mg for 3 days. A renal biopsy revealed 24 glomeruli, with 3 showing segmental sclerosis and 1 with fibrocellular crescents, mild interstitial nephritis; immunofluorescence showed IgA+++, C3++, IgM, and IgG+- Oxford Classification: M1 E0 S1 T0 C1. Bronchofibroscopy showed a rosy bronchoalveolar lavage and macrophages with hemosiderin pigment deposition. The patient continued with prednisolone at 1 mg/kg. In January 2023 (after two months), there was a &amp;gt;25% reduction in albuminuria with resolution of acute kidney injury. A gradual reduction of prednisolone was initiated, and it was definitively discontinued in October 2023. In the last outpatient visit in January 2024, the patient maintained normal renal function, with no hematuria, UPCR of 100 mg/g, UACR of 70 mg/g, and no further episodes of alveolar hemorrhage. Conclusion This case stands out for its atypical presentation: an adult with alveolar hemorrhage and without other more classical manifestations of IgA vasculitis, such as purpura. This is yet another case that emphasizes the importance of the broad spectrum of diagnoses that a nephrologist should consider in the face of acute kidney injury.

Pulmonary Langerhans Cell Histiocytosis Post-Hodgkin Lymphoma Completely Resolved With Vinblastine in a Heavy Smoker: Coincidence or Causation?

The association among Langerhans cell histiocytosis, hematolymphoid malignancies, and heavy smoking has been addressed in medical literature to identify a possible potential link. Such occurrence can pose diagnostic challenges, as well as important clinical implications for disease progression and treatment approaches. We present pulmonary Langerhans cell histiocytosis instance in a 35-year-old male patient, with a 34-pack-year smoking history and nodular sclerosing Hodgkin lymphoma stage IIB who developed multiple bilateral lung nodules. The patient completed 6 cycles of doxorubicin (Adriamycin), bleomycin, vinblastine, and dacarbazine chemotherapy and radiotherapy 2 years earlier. CT chest scans revealed numerous micronodules scattered randomly throughout the upper and lower left lung lobes. Subsequent wedge resection exhibited cellular proliferation with grooved nuclei, eosinophilic cytoplasm, and surrounding inflammatory components. Immunohistochemical staining showed positive staining for S100 and CD1a confirming a diagnosis of pulmonary Langerhans cell histiocytosis. The patient responded to a 6-week treatment with vinblastine and prednisolone. A subsequent CT scan of the lungs revealed complete resolution after 3 years. This report underscores the importance of identifying pulmonary Langerhans cell histiocytosis in heavy smokers with Hodgkin lymphoma presenting with multiple nodular pulmonary lesions. For patients with Hodgkin lymphoma and a possible genetic predisposition, smoking may contribute to the overt development of pulmonary Langerhans cell histiocytosis. Therefore, smoking cessation and careful follow-up examinations are required. Further research is recommended to elucidate the underlying mechanisms of this intriguing association.

Surveying haemoperfusion impact on COVID-19 from machine learning using Shapley values.

Haemoperfusion (HP) is an innovative extracorporeal therapy that utilizes special cartridges to filter the blood, effectively removing pro-inflammatory cytokines, toxins, and pathogens in COVID-19 patients. This retrospective cohort study aimed to assess the clinical benefits of HP for severe COVID-19 cases using Shapley values for machine learning models. The research involved 578 inpatients (≥ 20years old) admitted to Baqiyatallah hospital (Tehran, Iran). The control group (359 patients) received standard treatment, including high doses of corticosteroids (a single 500mg methylprednisolone pulse, followed by 250mg for 2days), categorized as regimen (I). On the other hand, the HP group (219 patients) received regimen II, consisting of the same corticosteroid treatment (regimen I) along with haemoperfusion using Cytosorb H300. The frequency of haemoperfusion sessions varied based on the type of lung involvement determined by chest CT scans. In addition, the value function defines the Shapley value of the th feature for the query point , where the input matrix features represent individual characteristics, drugs, and history and clinical conditions of the patient. Our data showed a favorable clinical response in the HP group compared to the control group. Notably, one-to-three sessions of HP using the CytoSorb® 300 cartridge led to reduced ventilation requirements and mortality rates in severe COVID-19 patients. Shapley values were calculated to evaluate the contribution of haemoperfusion among other factors, such as side effects, medications, and individual characteristics, to COVID-19 patient outcomes. In addition, there is a significant difference between the two groups among the treatments and medications used remdesivir, adalimumab, tocilizumab, favipiravir, Interferon beta-1a, enoxaparin prophylaxis, enoxaparin full dose, heparin prophylaxis, and heparin full dose (P < 0.05). It seems that haemoperfusion has a positive impact on the reduction of inflammation markers and renal functional such as ferritin and creatinine, respectively, as well as D-dimer and WBC levels in the HP group were significantly lower than the control group. The findings indicated that haemoperfusion played a crucial role in predicting patient survival, making it a significant feature in classifying patients' prognoses.

NEW ONSET OF PULMONARY HYPERTENSION IN A PATIENT AFFECTED BY RECURRENT LUNG CANCER

Abstract 39 years old non–smoker female patient came to our observation in July 2023 complaining dyspnea on mild exertion. She had a history of lung adenocarcinoma with epidermal growth factor receptor (EGFR) positive for exon 19 deletion treated with left pneumonectomy and ipsilateral hilar mediastinal lymphadenectomy 5 years earlier, and contralateral disease progression currently treated with chemotherapy. Transthoracic echocardiogram showed circumferential prepericardial effusion requiring pericardiocentesis with transient clinical benefit. Indeed, after a month, she presented with worsening dyspnea and echocardiographic evidence of dilated and hypokinetic right ventricle and severe pulmonary hypertension associated with distal right pulmonary artery stenosis secondary to extrinsic compression by the neoplastic mass as shown by the chest CT scan (fig 1). A right heart catheterization confirmed this finding (minimum diameter of right pulmonary artery of 6 mm, maximum systolic pulmonary blood pressure of 99 mmHg) and a palliative stenting of the distal portion of the right pulmonary artery was performed with resolution of the stenosis, reduction of the pulmonary gradient (fig 2 and 3) and resolution of the dyspnea.

ALTERNATIVE STRATEGIES FOR LEFT SUBCLAVIAN ARTERY REVASCULARIZATION DURING ZONE–2 AORTIC ARCH SURGERYEMENT

Abstract Objective Anatomical extension of surgical treatment of thoracic aortic pathologies involving the aortic arch is still controversial. The adoption of distal anastomosis in aortic arch zone–2 (Z2–AAR), in order to facilitate bleeding control, has been widely recommended. In such case the revascularization of left subclavian artery (LSA) may add further concerns. Here we report our different strategy of LSA revascularization in 2 different scenario of Z2–AAR Clinical. Cases Case#1 17 yo male patient affected by Loeys–Dietz Syndrome and a previous David procedure at age of 11yo. He presented complaining chest pain and CT scan revealed a dilatation (5,8 cm) of ascending aorta and an intimal flap with preserved previous distal anastomosis. Surgical strategy #1 (Left subclavian artery in situ): Arch replacement (Zone 2 distal anastomosis) with Siena Graft 24mm and modified Elephant Trunk Tecnique (2cm distal endoluminal graft). Innominate artery and left carotid artery reimplantation. Distal Anastomosis Siena 24 (Z2). Case #2 78 yo male with a previous (6 month before) Biological AVR (Trifecta 25) + ascending aorta replacement (Jotec 30). Presented complaining acute chest pain, CT Scan revealed a residual dilatation of distal ascending aorta, dissection/rupture of distal aortic arch at level of a complicated plaque. Surgical strategy #2 (Left subclavian artery reimplanted): Arch replacement (Zone 2 distal anastomosis) with Siena Graft 30mm and Elephant trunk Teccnique (10cm distal endoluminal graft). Closure of the extended ulcera. Total epiaortic vessels de–branching 10 mm Tube on LSA – Distal Anastomosis Siena 30 (Z2). Conclusion Surgical extension of aortic arch replacement is still matter of discussion. Zone–2 approach for aortic arch replacement seems a safe and effective option. In our mind strategy for left subclavian revascularization should be tailored according patient’s anatomy and potential future scenarios.

PULMONARY VENO–OCCLUSIVE DISEASE ASSOCIATED WITH METHAMPHETAMINE ABUSE: A FIRST CASE DESCRIPTION

Abstract Background Recreational methamphetamine is widely used worldwide (about 35 million people), mainly as 3,4–Methylenedioxymethamphetamine (MDMA). A definite association has been established between methamphetamine and pulmonary arterial hypertension (PAH). This drug–associated form of PAH shares histological, clinical and hemodynamic characteristics, prognosis and treatment strategies with idiopathic PAH. However, the association between MDMA and a rarer and devasting form of PAH with concomitant venous involvement (pulmonary veno–occlusive disease, PVOD), has never been reported. Notably, initiation of PAH–specific treatment in PVOD may lead to catastrophic consequences. Case Description A 32–year–old man was fast–track referred to our PH Centre in December 2023, due to high echocardiographic probability of pulmonary hypertension (PH). After interrogation, he admitted the regular use of MDMA. No other risk factor for PAH was found. Right heart catheterization showed a pre–capillary PH (mean pulmonary artery pressure 35 mmHg; wedge pressure 12 mmHg; pulmonary vascular resistance 5.9 WU) with low cardiac output (2.2 L/min/m2) and no acute response to vasoreactivity testing. Exercise capacity was severely reduced (oxygen consumption 19.6 mL/Kg/min, 50% of predicted) due to absent stroke volume reserve, accompanied by augmented exercise hyperventilation (VE/VCO2 slope 60) and exercise–induced desaturation (SaO2 94 à 77%), this latter not explained by a right–to–left shunt. Diffusion capacity of the lung was severely reduced (DLCO 28%). Chest CT and perfusion scan excluded both thromboembolic etiology and parenchymal lung disease. A diagnosis of PVOD was made, based on the presence of pre–capillary PH, oxygen desaturation, extreme exercise hyperventilation and very low DLCO, even in the absence of pathognomonic CT features. Counselling for stopping MDMA abuse was offered. Cautious monotherapy with macitentan was started and was well tolerated. A genetic testing for EIF2AK4 is ongoing. Contact with transplant center has been performed. A follow–up RHC has been planned before careful therapy up–titration. Conclusions This is the first case reported of the potential association between methamphetamines and PVOD. Due to the large worldwide use of MDMA, this link should be considered because of its prognostic and therapeutic implications. The diagnosis of PVOD is a clinical one, needing a high index of suspicion especially in the absence of chest CT findings.