Introduction: The Safety and efficacy of DOACs is unknown in patients with left ventricular thrombus as these patients were excluded from DOAC trials. Hypothesis: The safety and efficacy of DOACs is comparable to vitamin K antagonists Methods: Databases including Medline, Scopus and Cochrane Central Registration of Controlled Trials were queried from inception to March 30 th 2022. Studies reporting efficacy and safety outcomes were selected for the analysis. Results: We included 11 studies comprising 1920 patients with left ventricular thrombus. The mean age in the DOAC group was 57.5 years (SD 12.8) and 58.6 years (SD 13.0) in the VKA group; 26.8% were females. Pooled results showed no difference in mortality (RR, 0.64 [95% CI, 0.16-2.52]) embolic events (RR, 0.94 [95% CI, 0.59-1.50]) or major bleeding (RR, 0.95[95% CI, 0.66-1.36]) in the DOACs compared to VKA groups. Event rate for DOAC group compared to VKA group was 12.7 vs 17.5 per 100 patient-years (mean follow up of 4.0 months) for mortality, 19.5 vs 26.5 per 100 patient-years (mean follow up of 8.9 months) for embolic events and 8.0 vs 10.0 per 100 patient-years (mean follow up of 9.5 months) for major bleeding. Conclusions: These data, from observational and randomized studies, demonstrate promising safety and efficacy of DOACs for treatment of left ventricular thrombus. Elevated embolic and mortality rates regardless of anticoagulant choice emphasize the need for further research to improve outcomes for patients with this complication.
Abstract 11282: Artificial Intelligence Derived Algorithm to Screen for Ebstein’s Anomaly of the Tricuspid Valve Utilizing Echocardiography
Introduction: Ebstein’s anomaly (EA) is a rare congenital anomaly of the tricuspid valve associated with heart failure and arrhythmias. Currently available imaging modalities like transthoracic echocardiography, cardiac magnetic resonance imaging (MRI), or computerized tomography (CT) are not viable for screening large asymptomatic populations. Hypothesis: A deep learning algorithm, implemented using a convolutional neural network (CNN) applied to the standard 12-lead ECG can be used as an accurate screening tool for EA in children and adults. Method: We identified 1,154 EA patients and 21,430 age- and sex-matched controls (1:20 ratio) between 1987 - 2020. A CNN was trained, validated and tested using digital 12-lead ECGs in 70%, 10% and 20% of the cohort respectively, divided by random shuffling. Results: The mean age was 26.68±19.23 years (41.8% aged < 18 years, 56.41% female) for the EA cohort and 28.36±18.65 years (37.2% aged <18 years, 55.67% female) for the control cohort. Following training and validation the area under the curve (AUC) for detecting EA in the testing cohort was 0.976 (95% CI 0.962 - 0.989) with prediction accuracy of 0.959. In subgroup analysis, the AUC was comparable in males (0.970, 95% CI 0.946-0.995) and females (0.979, 95% CI 0.964-0.994), those <18 (0.980, 95% CI 0.958-1.000) and ≥18 years old (0.972, 95% CI 0.954-0.989), as well as in those with right bundle branch block (RBBB) (0.969, 95% CI 0.950-0.989) and without RBBB (0.950, 95% CI 0.922-0.978) on ECG. Conclusion: Artificial intelligence enhanced ECG based detection of EA is possible with high diagnostic accuracy. Following further refinement and external validation, this algorithm can facilitate early detection of EA using ECGs, a widely available and inexpensive tool. Figure: Receiver operating characteristic (ROC) curve for the performance of the artificial intelligence CNN in detecting EA in the test cohort stratified by (A) age (< 18 and ≥ 18 years) and sex and (B) presence of RBBB.
Differential proteomic expression profiles in vulvar lichen planus as compared to normal vulvar tissue, vulvar lichen sclerosus, or oral lichen planus: An exploratory study
AbstractVulvar lichen planus (VLP) is a chronic inflammatory disease which adversely affects patients' quality of life. The pathogenesis of VLP is unknown although Th1 immune response has been implicated. We aimed to discover specific tissue‐based protein biomarkers in VLP compared to normal vulvar tissue (NVT), vulvar lichen sclerosus (VLS) and oral lichen planus (OLP). We used laser capture microdissection‐liquid chromatography‐ tandem mass spectrometry to assess protein expression in fixed lesional mucosal specimens from patients with VLP (n = 5). We then compared proteomic profiles against those of NVT (n = 4), VLS (n = 5), OLP (n = 6) and normal oral mucosa (n = 5), previously published by our group. IL16, PTPRC, PTPRCAP, TAP1 and ITGB2 and were significantly overexpressed in VLP compared to NVT. Ingenuity pathway analysis identified antigen presentation and integrin signalling pathways. Proteins overexpressed in both VLP versus NVT and OLP versus NOM included IL16, PTPRC, PTPRCAP, TAP1, HLA‐DPB1, HLA‐B and HLA‐DRA. This proteomic analysis revealed several overexpressed proteins in VLP that relate to Th1 autoimmunity, including IL16. Overlapping pathways, including those involving IFNγ and Th1 signalling, were observed between VLP, VLS, and OLP.
#4220 NOT JUST AIN? OTHER IMMUNE-CHECKPOINT INHIBITOR LESIONS: A SINGLE INSTITUTION'S EXPERIENCE OVER 12 YEARS
Abstract Background and Aims Immune-checkpoint inhibitors (ICI) are antineoplastic therapies that unleash the immune-system and have revolutionized cancer outcomes. Though they are a drug class with great potential, their effects are not always limited to the malignant cells and can cause a spectrum of immune-related adverse events (irAEs). Roughly 5% of patients will experience acute kidney injury (AKI) with acute interstitial nephritis (AIN) being the predominant pathologic lesion. Glomerular and vascular lesions are thought to be rare and, as a result, not well-defined. We aim to document glomerular and vascular pathology in this context at our institution. Method We performed a retrospective review of internal native renal biopsies from 2010-2022 that had known ICI treatment. Standard processing of renal biopsies included light microscopy (LM), immunofluorescence (IF), and electron microscopy (EM). We reviewed the biopsies and pathology reports, as well as clinical data from patient electronic medical records. Results Our search yielded 32 kidney biopsies; of those, most had AIN (27/32), 8 cases had glomerular pathology, and 1 case had arterial endotheliitis. Of the cases with glomerular pathology, 4 had subacute glomerular thrombotic microangiopathy (TMA). Among the cases with TMA, 2 were also treated with vascular endothelial growth factor inhibitor (VEGFi),1 with gemcitabine, and 1 with BRAF-inhibitor therapy. Further, only one of these patients had complement testing, which did not reveal definitive deficiency. One patient had proliferative glomerulonephritis with monoclonal immunoglobulin deposits (PGNMID), IgG-κ. One patient had IgA nephropathy (IgAN) and another had membranous nephropathy (MN). Most patients were biopsied for rising serum creatinine (SCr) (median: 1.6 mg/dL; range: 0.55-5.5); 1 had nephrotic-range proteinuria (median urine protein/creatinine ratio (UPCR): 0.3; range: 0.12-5.64). One, with thin basement membrane disease, had significant hematuria (>100 RBC/hpf). Five patients had irAEs in other organs. 7/9 patients died or entered hospice care (median: 14 months post-biopsy; range: 2-48 months) due to malignancy progression. Of the deceased patients, 2 were dialysis-dependent. Of the living patients, 1 has dialysis-independent chronic kidney disease (CKD). Conclusion Overall, glomerular and vascular pathology due to ICI-use appears rare though difficult to isolate since other drugs and neoplasia can cause similar lesions. In our cohort, TMA was the most common glomerular lesion, though direct causation due to ICI is difficult to prove. In all patients with TMA, we identified concurrent use of other known causative drugs. IgAN and MN have been reported in association with neoplasia. PGNMID has been reported in a variety of malignant and nonmalignant conditions, and ICI-use could be a triggering factor. In conclusion, the patterns of glomerular injury seen in our cohort may be secondary to other concurrent risk factors other than ICI use. Arterial endotheliitis appears to be a rare but significant secondary effect to ICI-use.
Thread carpal tunnel release: a retrospective review of the first 300 cases performed at a tertiary medical centre
Digital Pulmonology Practice with Phonopulmography Leveraging Artificial Intelligence: Future Perspectives Using Dual Microwave Acoustic Sensing and Imaging
Respiratory disorders, being one of the leading causes of disability worldwide, account for constant evolution in management technologies, resulting in the incorporation of artificial intelligence (AI) in the recording and analysis of lung sounds to aid diagnosis in clinical pulmonology practice. Although lung sound auscultation is a common clinical practice, its use in diagnosis is limited due to its high variability and subjectivity. We review the origin of lung sounds, various auscultation and processing methods over the years and their clinical applications to understand the potential for a lung sound auscultation and analysis device. Respiratory sounds result from the intra-pulmonary collision of molecules contained in the air, leading to turbulent flow and subsequent sound production. These sounds have been recorded via an electronic stethoscope and analyzed using back-propagation neural networks, wavelet transform models, Gaussian mixture models and recently with machine learning and deep learning models with possible use in asthma, COVID-19, asbestosis and interstitial lung disease. The purpose of this review was to summarize lung sound physiology, recording technologies and diagnostics methods using AI for digital pulmonology practice. Future research and development in recording and analyzing respiratory sounds in real time could revolutionize clinical practice for both the patients and the healthcare personnel.
ON THE DESIGN OF A NOVEL PHONOENTEROGRAM SENSING DEVICE USING AI ASSISTED COMPUTER-AIDED AUSCULTATION
Abstract Bowel sounds have been previously used to study intestinal motility and overall digestive health in various clinical settings. However, the blurred definition of bowel sounds and their subtypes, limited resources for interpretation, poor sensitivity, and low positive predictive value led to their restricted utility. Recent advances in artificial intelligence and machine learning have steered interest in developing unique tools using the phonoenterogram to analyze diverse bowel sounds. In our study, bowel sounds were recorded from eight healthy volunteers using the Eko Duo stethoscope. A novel deep-learning algorithm was designed to classify the recordings into baseline or prominent bowel sounds. A total of 11,210 data points (5,605 balanced sounds) were used to train and test the model to yield an accuracy of 0.895, a precision of 0.890, and a recall of 0.854 reflecting successful segregation of these sounds into respective groups. More extensive studies enrolling healthy and diseased subjects with a device specifically tailored to record bowel sounds are needed to generalize these results and determine their application in the patient population.
BLOOD PRESSURE PREDICTION FROM PHOTOPLETHYSMOGRAM SIGNAL USING ARTIFICIAL INTELLIGENCE
Abstract Blood pressure measurement in current medical practice relies on manual methods with the most widely used modality being sphygmomanometers. Utilizing the principle of Photoplethysmography, it is possible to provide an accurate reading of one’s blood pressure through light signals and photodetector devices. This research paper introduces a new Artificial Intelligence driven approach to predict Blood pressure levels and classify them according to the updated ACC (American College of Cardiology) criteria as Normal, Elevated, Stage I, and II Hypertension from the given PPG signal values using Machine Learning Models. This research paper aims to accurately read the Systolic and Diastolic Blood Pressure using Artificial Intelligence, place them into the correct value bins and further prove that the blood pressure values differ based on different skin tones in different light wavelengths such as red, infrared, and green. Machine Learning models such as the Support Vector Machine have shown an accuracy of 70.58% for Systolic Blood Pressure and Decision Tree with an accuracy of 74.4% for Diastolic Blood Pressure classification. The models used in this research are Support Vector Machine, Decision Tree and K-Nearest Neighbor. This research study has future applications and extensions to predict blood pressure levels for patients with different skin tones under different light radiations and PPG signal readings. Neural Network models will be developed to compare the blood predictions from this work.
ITINERARY PREDICTIVE ANALYTICS: AI BASED SOFTWARE AS A MEDICAL DEVICE TO PREDICT PATIENTS’ FIRST VISIT ITINERARY FOR HEALTHCARE ADMINISTRATION
Abstract Majority of hospitals still utilize manual methods for patient scheduling and predicting future appointments, resulting in longer wait times, hospital burnout and inadequate use of resources. A variety of avenues have been explored, including priority patient routing, tele-health, neural networks for improving ER efficiency, predicting no-shows, consultation duration variations, and optimizing operating room utilization. Addressing this issue, a study was conducted using 700 pre-visit notes of pancreatic patients to determine the requirement of endoscopic or biliary procedure. Through natural language processing and traditional or transfer learning algorithms, data could directly be sent to EPIC for nurses to assess in further decision making. Performance of the models was above average with the transfer learning method outperforming the traditional method. Although limited by less dataset and fewer circumstances to test the models on, the results exposed potential for future development with the possibility of patients reporting their chief concerns, in turn analyzed by algorithms, ultimately creating a smooth and effective patient itinerary.
Baseline neuropsychiatric symptoms and psychotropic medication use midway through data collection of the Longitudinal Early‐Onset Alzheimer's Disease Study (LEADS) cohort
AbstractIntroductionWe examined neuropsychiatric symptoms (NPS) and psychotropic medication use in a large sample of individuals with early‐onset Alzheimer's disease (EOAD; onset 40‐64 years) at the midway point of data collection for the Longitudinal Early‐onset Alzheimer's Disease Study (LEADS).MethodsBaseline NPS (Neuropsychiatric Inventory – Questionnaire; Geriatric Depression Scale) and psychotropic medication use from 282 participants enrolled in LEADS were compared across diagnostic groups – amyloid‐positive EOAD (n = 212) and amyloid negative early‐onset non‐Alzheimer's disease (EOnonAD; n = 70).ResultsAffective behaviors were the most common NPS in EOAD at similar frequencies to EOnonAD. Tension and impulse control behaviors were more common in EOnonAD. A minority of participants were using psychotropic medications, and use was higher in EOnonAD.DiscussionOverall NPS burden and psychotropic medication use were higher in EOnonAD than EOAD participants. Future research will investigate moderators and etiological drivers of NPS, and NPS differences in EOAD versus late‐onset AD.