Interpretation Of Clinical Data Research Articles

Single-Molecule Nanopore Sequencing of the CpG Island from the Promoter of O6-Methylguanine-DNA Methyltransferase Provides Insights into the Mechanism of De Novo Methylation of G/C-Rich Regions

Background: The methylation of cytosine residues at CpG sites within the O6-methylguanine-DNA methyltransferase (MGMT) promoter is a key biomarker in glioblastoma therapy. The MGMT promoter (MGMTp) contains multiple guanine-rich sequences capable of folding into G-quadruplexes (G4s), but their relevance for MGMTp methylation is poorly understood. Objectives: Our study explores the impact of potential G-quadruplex-forming sequences (PQS) in the MGMT promoter CpG island on the activity of de novo DNA methyltransferase Dnmt3a. Additionally, we investigate their influence on the accuracy of methylation pattern detection using nanopore sequencing. Methods: Nanopore sequencing was employed to analyze the methylation of 94 clinically significant CpG sites in the human MGMTp using an in vitro de novo methylation system. Circular dichroism spectroscopy was used to identify G4 structures within the MGMTp CpG island. Interactions between the catalytic domain of Dnmt3a and the PQS from the MGMTp were examined by biolayer interferometry. Results: Guanine-rich DNA strands of the PQSs in the MGMTp were hypomethylated, while the complementary cytosine-rich strands were methylated by DNA methyltransferase Dnmt3a with higher efficiency. The accuracy of detecting modified bases in the PQS was significantly lower compared to surrounding sequences. Single-stranded guanine-rich DNA sequences from the MGMTp exhibited strong binding to Dnmt3a-CD, with an affinity approximately 10 times higher than their cytosine-rich complements (Kd = 3 × 10−8 M and 3 × 10−7 M, respectively). By binding to Dnmt3a, G4-forming oligonucleotides from MGMTp effectively inhibited the methylation reaction (IC50 6·10−7 M). Conclusions: The obtained data indicate the role of PQSs in establishing de novo methylation of the MGMT promoter. They also highlight the challenges of sequencing guanine-rich regions and the impact of specific de novo methylation patterns on clinical data interpretation.

A Computer-Aided Diagnosis for Cardiovascular and Hepatic Disorders using Boosted Ensemble Deep Learning

In recent years, machine learning has gained traction as a potential tool for improving the accuracy and timeliness of illness diagnoses. The use of machine learning for the diagnosis of cardiovascular and renal disorders is critically examined in this research. To enhance patient outcomes, it is essential to diagnose cardiovascular and hepatic illnesses early and accurately. The interpretation of complicated clinical data and the identification of detailed patterns indicative of these disorders, however, may be difficult for standard diagnostic approaches. This study thoroughly tests three cutting-edge boosting algorithms: XGBoost (Extreme Gradient Boosting), CatBoost, and AdaBoost. Enabling the capture of complex nonlinear interactions and management of varied data sources, these ensemble approaches repeatedly integrate and optimize numerous weak learners. After conducting thorough experiments on massive clinical datasets, results show that the XGBoost algorithm is the best for certain types of diseases. Intelligent diagnostic tools that can reliably identify cardiovascular and hepatic diseases early on are within reach, according to the results of this study. This will lead to better patient care and disease management methods.

Virtual Control Groups in Non-clinical Toxicity Studies: Impacts on Toxicologic Clinical Pathology Data Interpretation.

One of the emerging concepts on the reduction of animal use in non-clinical studies is the use of virtual control group (VCG) to replace concurrent control group (CCG). The VCG involves the generation of a control data from historical control data to match a specific study design. This review focuses on two recently published proof-of-concept (POC) studies conducted in rats. One major issue that was consistently seen across these POC studies was the non-reproducibility of some quantitative endpoints between the CCG and the VCG, with clinical pathology parameters being the most affected. The inconsistencies observed with the clinical pathology parameters when using VCGs may lead to: (1) misconception about the accuracy and sensitivity of traditional clinical pathology biomarkers and its implications on safety monitoring in the clinic; (2) inability to correctly identify and characterize organ dysfunctions; (3) interference with the weight-of-evidence approach used in identifying hazards in toxicologic clinical pathology and toxicology studies at large; and (4) wrong interpretations and data reproducibility issues. Other alternatives to reduce animal use in toxicology studies are also discussed including blood microsampling for toxicokinetics, scientifically justified use of recovery animals, and appropriate use and continuous investments in new alternative methods.

Development of a core outcome set for psychological therapy trials on acute psychiatric inpatient wards

BackgroundConsensus on what outcomes should be included in trials of psychological therapies on acute psychiatric inpatient wards is currently lacking. Inclusion of different viewpoints, including service user perspectives, is crucial in ensuring that future trials measure outcomes which are meaningful and important. Development of a Core Outcome Set (COS), a minimum standardised set of outcomes to be measured and reported, would help improve synthesis and interpretation of clinical trial data in this area.MethodsStage 1 of the COS development involved compiling a comprehensive long-list of outcomes from key sources including i) a systematic review of outcomes from published trials, ii) online survey of key stakeholders (service users, carers, healthcare professionals, researchers, and end users of research), iii) qualitative interviews with service users and carers. Stage 2 involved stakeholder groups short-listing the outcomes using consensus methods (e-Delphi survey). The final outcome set was derived from the short-list at a consensus meeting of stakeholders, facilitated by an Independent Chair.ResultsA long-list of 68 outcomes was compiled from the systematic review (n = 30 trials), online stakeholder survey (n = 100 participants) and qualitative interviews (n = 15 participants). Fifty stakeholders took part in the e-Delphi study, where the long-list was cut down to a short-list of 12 outcomes over 2 rounds. Nine stakeholders took part in the final consensus meeting, and after some outcomes were removed and/or amalgamated, a final set of 6 outcomes was recommended for inclusion in the COS. These were Ability to Cope, Hopefulness, Quality of Life, Psychosis Symptoms, Mood, and Self-Harm Behaviours.ConclusionsWidespread future adoption of the COS will reduce research waste by ensuring that outcomes are more easily comparable across trials, and that the full range of stakeholder priorities are represented in trial outcomes. This makes it more likely that effective therapies will be identified in a timely fashion and successfully implemented in routine clinical practice. The final 6-outcome COS should be feasible to implement given the need keep participant burden to a minimum in inpatient trials. Further work is needed to make recommendations for the best outcome measurement instruments to use, including the use of patient-reported outcomes alongside clinician-rated measures.Trial registrationNot applicable.

The use of azithromycin in the treatment of inflammatory diseases of the upper respiratory tract and ear

Despite the extensive accumulated clinical experience, inflammatory diseases of the upper respiratory tract and ear still remain an important problem in the field of otorhinolaryngology, especially pediatric practice, since these diseases are associated with the risk of complications. One of the reasons for the ineffectiveness of conservative treatment is the incorrect initial antibacterial therapy. Errors in antimicrobial therapy are associated with both insufficient knowledge of clinical pharmacology by doctors and incorrect interpretation of anamnestic and clinical data, which leads to incorrect treatment of CCA. The aim of the work is to analyze the use of azithromycin in the treatment of upper respiratory tract and ear infections in children, based on pharmacological characteristics, as well as to consider current methods of antibiotic therapy in pediatric practice. An analysis of the literature and our own observations allows us to conclude that azithromycin is an effective antibacterial drug. Taking into account the low toxicity and good bioavailability, azithromycin continues to be one of the main drugs in the arsenal of doctors for the treatment of various infections, including respiratory diseases and infectious processes of ENT organs in children caused by both typical and atypical bacterial pathogens. The convenient dosage form and simple dosage regimen make this drug a popular choice in outpatient pediatric practice, which confirms the widespread use and trust in this antibacterial drug among both doctors and parents.

Peroxisome proliferator-activated receptor agonists as an adjuvant for cancer therapy: A review

Cancer is now one of the leading diseases responsible for the highest mortality rates worldwide. Cancer treatment is extremely intricate and is often associated with less targeted effects and more side effects. In the last few years, two significant revolutions in cancer treatment have altered treatment paradigms: immuno-oncology and the pursuit of actionable changes in oncogene-driven cancers. Significant obstacles continue to exist in both areas of cancer treatment. Next-generation sequencing technologies for molecular prescreening in clinical research are advancing, but their widespread clinical use is hindered by challenges related to the clinical interpretation of large genomic data. Moreover, cancer mono-chemotherapy is associated with issues such as inadequate efficacy, drug resistance, and systemic toxicity. It is not possible to administer cytotoxic drugs limitlessly. Combination therapy was developed in response to this circumstance, with the expectation of achieving high therapeutic efficacy at lower dosages of medication. Peroxisome proliferator-activated receptors (PPARs) are a group of essential lipid sensors and metabolic pathway regulators. In addition, they possess the ability to modulate immunity, inflammation, and endothelial nitric oxide synthase activation. Alongside their well-established functions, new insights into the roles of PPAR agonists in cancer research are emerging. After reviewing current research, it is evident that PPAR modulators have significant potential for managing cancer. This review aims to consolidate the functions of PPAR ligands alongside other cancer therapies. We provide a comprehensive perspective on the applicability of PPAR ligands in cancer treatment as an adjuvant.

Diagnosing Monogenic Stroke at Younger Age.

An increasing number of monogenic conditions underlying stroke are being identified. We explored the possibilities of increasing the diagnostic yield of monogenic stroke in a population under 56 years of age. Fifty probands ≤55 years at their first stroke episode were characterized clinically and investigated by whole genome sequencing. Probands had one or more of: (1) one or more first to second degree relatives with stroke under 60 years or same stroke-causing condition/disease; (2) no hypertension, hypercholesterolemia, diabetes, heart disease, or smoking; or (3) either multiple stroke episodes or multiple arterial dissections. Variants with minor allele frequency under 0.01, identified by using our stroke gene panels, were assessed. The stroke subtypes, including large artery atherosclerotic, large artery nonatherosclerotic (tortuosity, dolichoectasia, aneurysm, nonatherosclerotic dissection, or occlusion), cerebral small vessel disease, cardioembolic (arrhythmia, heart defect, or cardiomyopathy), coagulation dysfunctions (venous thrombosis, arterial thrombosis, or bleeding tendency), intracerebral hemorrhage, vascular malformations (cavernoma or arteriovenous malformations), metabolic disorders, or cryptogenic embolic, were used for genotype-phenotype correlation. In a final step, we combined genetic and clinical information to determine if the genetic variant likely was the cause of stroke in the patients. Whole genome sequencing of younger patients with stroke identified 17 clinically matching genetic variants in 15 of 50 (30%) patients, while a stronger clinical correlation with stroke was established in only 6 (12%) of them. Stroke-related genetic variants were identified in 4 of 5 (80%) patients with cardioembolic stroke subtype, 3 of 4 (75%) with intracerebral hemorrhage, 7 of 18 (39%) with cryptogenic embolic stroke, 1 of 6 (17%) with small vessel disease, and 3 of 15 (20%) of patients with nonatherosclerotic large artery stroke, including 1 of 11 (9%) with cervical dissection stroke. Careful clinical interpretation of whole genome data using stroke gene panels can detect monogenic causes of early stroke, allowing individualized follow-up and opening new possibilities for potential treatment.

Artificial intelligence machine learning based evaluation of elevated left ventricular end-diastolic pressure: a Cleveland Clinic cohort study.

Left ventricular end-diastolic pressure (LVEDP) is a key indicator of cardiac health. The gold-standard method of measuring LVEDP is invasive intra-cardiac catheterization. Echocardiography is used for non-invasive estimation of left ventricular (LV) filling pressures; however, correlation with invasive LVEDP is variable. We sought to use machine learning (ML) algorithms to predict elevated LVEDP (>20 mmHg) using clinical, echocardiographic, and biomarker parameters. We identified a cohort of 460 consecutive patients from the Cleveland Clinic, without atrial fibrillation or significant mitral valve disease who underwent transthoracic echocardiography within 24 hours of elective heart catheterization between January 2008 and October 2010. We included patients' clinical (e.g., heart rate), echocardiographic (e.g., E/e'), and biomarker [e.g., N-terminal brain natriuretic peptide (NT-proBNP)] profiles. We fit logistic regression (LR), random forest (RF), gradient boosting (GB), support vector machine (SVM), and K-nearest neighbors (KNN) algorithms in a 20-iteration train-validate-test workflow and measured performance using average area under the receiver operating characteristic curve (AUROC). We also predicted elevated tau (>45 ms), the gold-standard parameter for LV diastolic dysfunction, and performed multi-class classification of the patients' cardiac conditions. For each outcome, LR weights were used to identify clinically relevant variables. ML algorithms predicted elevated LVEDP (>20 mmHg) with good performance [AUROC =0.761, 95% confidence interval (CI): 0.725-0.796]. ML models showed excellent performance predicting elevated tau (>45 ms) (AUROC =0.832, 95% CI: 0.700-0.964) and classifying cardiac conditions (AUROC =0.757-0.975). We identified several clinical variables [e.g., diastolic blood pressure, body mass index (BMI), heart rate, left atrial volume, mitral valve deceleration time, and NT-proBNP] relevant for LVEDP prediction. Our study shows ML approaches can robustly predict elevated LVEDP and tau. ML may assist in the clinical interpretation of echocardiographic data.

Diurnal variation of serum phosphorus concentrations in intact male adult domestic cats.

Monitoring serum phosphorus concentrations is crucial in the management of chronic kidney disease in cats. The diurnal variation of serum phosphorus concentration may affect clinical assessment. Characterize the diurnal variation of serum phosphorus concentration in cats and determine the associations between changes in serum phosphorus concentration and several metabolites of phosphorus metabolism. Six apparently healthy, intact male, specific-pathogen-free cats were housed in a photoperiod, humidity, and temperature-controlled facility. Blood sampling was performed hourly for 24 hours to obtain the serum concentrations of phosphorus, ionized calcium, parathyroid hormone, and calcidiol. Results were analyzed using linear mixed-effect models to determine the significance of diurnal variation and associations between serum phosphorus concentrations and other metabolites over time. Diurnal variation in serum phosphorus concentration was noted with an apex around 11:00 followed by gradually declining concentrations to reach the nadir around 23:00. The serum phosphorus concentration again increased through the early morning on the next day. An approximately 25% difference in serum phosphorus concentration at the apex and the nadir was documented. A non-linear relationship between the serum concentrations of phosphorus and ionized calcium over time was identified. Diurnal variations of serum phosphorus concentration and associations between the trending of serum phosphorus and ionized calcium concentrations were evident in a group of clinically healthy adult cats housed in a controlled environment. These findings can help in the interpretation of clinical and research data regarding calcium and phosphorus metabolism and kidney health in cats.

Diagnosis and features of the treatment algorithm of non-lactational chronic mastitis on the example of a clinical case

Inflammatory processes in the mammary gland (MG) do not lose their relevance, the frequency of occurrence reaches 16% among all diseases of the MG. Non-lactational mastitis (NM) – inflammation in the MG outside the period of pregnancy and lactation – stands out among them [1]. With untimely and non-radical treatment of acute forms, there is a transition to chronic, with the formation of bacterial biofilm in the focus of inflammation and thick scar capsule after repeated surgical interventions, which is due to a vicious circle. The clinical picture of non-lactational chronic mastitis in most cases resembles a diffuse (mastitis-like, edematous-infiltrative) form of breast cancer (BC), which determines the differential-diagnostic difficulties in referring to a doctor both at initial treatment and at recurrence. This problem is faced by doctors of different specialties: oncologists, surgeons, gynecologists, therapists, specialists in radiation and radiological diagnostics [2, 3]. Radiation diagnostics is always the «gold standard» in the diagnosis of breast diseases, but has a number of disadvantages in the inflammatory process in the breast, and, in some cases, it is worth prioritizing the ultrasound method of investigation [4]. Through the combined interpretation of clinical data and ultrasound (USG) findings, the following parameters should be evaluated: skin thickness, pre-mammary fatty tissue, structure of glandular parenchyma of the MJ, presence and boundaries of inflammatory infiltrate/infiltrates in the MJ tissue; formation of «rarefaction» zones, microabscesses and/or already formed «draining» abscess cavities, assess the content of fluid cavities (homogeneity/homogeneity), the presence of pyogenic capsule, as well as the boundaries of inflammation/abscessing with unchanged breast tissue, taking into account possible «microfoci» outside the main mass of changes (like «satellites», «fluid spurs»). It is important to analyze the state of the ductal system of the breast (ductal diameter dilation, intraluminal content) and possible connection of ducts with abscessed areas, which may be a predictor of further spread of the process, recurrence or chronicization of the disease. Inflammation on the background of subacute and chronic process can lead to the development of fistulas [5]. However, there is not always the classic ultrasound picture of a purulent focus in the breast [6–9].

Artificial intelligence-empowered assessment of bile duct stone removal challenges

The aim of this investigation was to unravel the complexities inherent in endoscopic retrograde cholangiopancreatography (ERCP) procedures for bile duct stone removal by leveraging advanced artificial intelligence (AI) methodologies to support clinical decision-making and optimize patient outcomes. We introduced the Assessment of Stone Removal Challenges (ACRS) system, a novel integration of Data-efficient Image Transformers (DeiT) for image data analysis and eXtreme Gradient Boosting (XGBoost) for clinical data interpretation. Our study included a patient cohort of 2,129 individuals, focusing on training the ACRS system to achieve high diagnostic precision. Using logistic regression, we identified pivotal predictors affecting the complexity of bile duct stone removal. These findings were visually represented through forest plots and nomograms. Analytical and visualization processes were conducted using the Python and R programming languages, adhering to a p value significance threshold of less than 0.05. By utilizing DeiT enhanced by transfer learning and XGBoost for clinical data interpretation, the system achieved an accuracy of 0.83 and a perfect recall rate on a test set of 2,129 patients. Gradient-weighted class activation mapping (Grad-CAM) and SHapley Additive exPlanations (SHAP) provided in-depth diagnostic insights. Logistic regression was applied to identify crucial clinical predictors for stone removal difficulty, as visualized through forest plots and nomograms. These tools facilitated measurable assessments of procedural complexity, making significant strides in gastroenterology diagnostics and decision-making. By adopting causal inference techniques, the system effectively quantifies the influence of various clinical entities on stone removal difficulty, thereby augmenting both diagnostic precision and procedural strategies in ERCP.

Physics-informed neural network estimation of material properties in soft tissue nonlinear biomechanical models

AbstractThe development of biophysical models for clinical applications is rapidly advancing in the research community, thanks to their predictive nature and their ability to assist the interpretation of clinical data. However, high-resolution and accurate multi-physics computational models are computationally expensive and their personalisation involves fine calibration of a large number of parameters, which may be space-dependent, challenging their clinical translation. In this work, we propose a new approach, which relies on the combination of physics-informed neural networks (PINNs) with three-dimensional soft tissue nonlinear biomechanical models, capable of reconstructing displacement fields and estimating heterogeneous patient-specific biophysical properties and secondary variables such as stresses and strains. The proposed learning algorithm encodes information from a limited amount of displacement and, in some cases, strain data, that can be routinely acquired in the clinical setting, and combines it with the physics of the problem, represented by a mathematical model based on partial differential equations, to regularise the problem and improve its convergence properties. Several benchmarks are presented to show the accuracy and robustness of the proposed method with respect to noise and model uncertainty and its great potential to enable the effective identification of patient-specific, heterogeneous physical properties, e.g. tissue stiffness properties. In particular, we demonstrate the capability of PINNs to detect the presence, location and severity of scar tissue, which is beneficial to develop personalised simulation models for disease diagnosis, especially for cardiac applications.

Advancing Transthyretin Amyloidosis Drug Development in an Evolving Treatment Landscape: Amyloidosis Forum Meeting Proceedings.

Hereditary transthyretin amyloidosis (ATTRv, also referred to as hATTR; ORPHA 271861) and wild-type ATTR amyloidosis (ATTRwt; ORPHA 330001) are rare, progressive, systemic protein misfolding disorders with heterogeneous clinical presentations. ATTRv and ATTRwt amyloidosis are characterized by the deposition of amyloid fibrils in multiple organs including the heart, nerves, eyes, and soft tissues. The management of ATTR amyloidosis is complex because of its multisystemic nature and progression despite available treatment options. Morbidity is high and there are many unmet medical needs for patients. While contemporary ATTR amyloidosis cohorts are diagnosed earlier, have lower risk disease and lower mortality compared with the previous era, these advances coupled with the emergence of effective disease-modifying therapies have confounded the design of future prospective clinical trials and interpretation of historical control data. The Amyloidosis Forum is a public-private partnership between the US Food and Drug Administration Center for Drug Evaluation and Research and the nonprofit Amyloidosis Research Consortium ( www.arci.org ). This article summarizes proceedings from the 21 June 2023 Amyloidosis Forum on advancing drug development in ATTR amyloidosis in an evolving treatment landscape. The Forum focused on elements of clinical trial design to address these challenges and discussed their strengths and weaknesses from multiple stakeholder perspectives (i.e., patient, sponsor, statistician, clinician, and regulatory authorities). Given rapid evolution of natural history in ATTR amyloidosis, the utility of historical control data is limited. Leveraging contemporary real-world data is essential for clinical trial design. Evidence generation from clinical trials should address clinically relevant questions. Key factors in successful trial design must be informed by up-to-date data on natural history, prognostic factors, clinically meaningful thresholds, and sharing available clinical trial data. The Amyloidosis Forum includes the community of patients with ATTR amyloidosis, the physicians who treat them, and the sponsors and regulators who collectively stand ready to support further studies in order to develop novel effective therapies.

Application of Natural Language Processing in Electronic Health Record Data Extraction for Navigating Prostate Cancer Care: A Narrative Review.

Introduction: Natural language processing (NLP)-based data extraction from electronic health records (EHRs) holds significant potential to simplify clinical management and aid research. This review aims to evaluate the current landscape of NLP-based data extraction in prostate cancer (PCa) management. Materials and Methods: We conducted a literature search of PubMed and Google Scholar databases using the keywords: "Natural Language Processing," "Prostate Cancer," "data extraction," and "EHR" with variations of each. No language or time limits were imposed. All results were collected in a standardized manner, including country of origin, sample size, algorithm, objective of outcome, and model performance. The precision, recall, and the F1 score of studies were collected as a metric of model performance. Results: Of the 14 studies included in the review, 2 articles focused on documenting digital rectal examinations, 1 on identifying and quantifying pain secondary to PCa, 8 on extracting staging/grading information from clinical reports, with an emphasis on TNM-classification, risk stratification, and identifying metastasis, 2 articles focused on patient-centered post-treatment outcomes such as incontinence, erectile, and bowel dysfunction, and 1 on loneliness/social isolation following PCa diagnosis. All models showed moderate to high data annotation/extraction accuracy compared with the gold standard method of manual data extraction by chart review. Despite their potential, NLPs face challenges in handling ambiguous, institution-specific language and context nuances, leading to occasional inaccuracies in clinical data interpretation. Conclusion: NLP-based data extraction has effectively extracted various outcomes from PCa patients' EHRs. It holds the potential for automating outcome monitoring and data collection, resulting in time and labor savings.

On the problem of differential diagnosis in the detection of antineutrophil cytoplasmic antibodies

Vasculitides associated with antineutrophil cytoplasmic antibodies (ANCA) are a group of systemic autoimmune diseases characterized by necrotizing lesions of the walls of predominantly small vessels and the presence of ANCA against proteinase 3 or myeloperoxidase. However, an increase in ANCA levels can also be observed in other diseases, including autoimmune, malignant and infectious diseases, which complicates the interpretation of clinical and laboratory data and requires a differential diagnosis.

A comparative analysis of machine learning algorithms for detecting COVID-19 using lung X-ray images

Machine intelligence has the potential to play a significant role in diagnosing, managing, and guiding the treatment of disease, which supports the rising demands on healthcare to provide rapid and accurate interpretation of clinical data. The global pandemic caused by the Severe Acute Respiratory Syndrome Coronavirus (SARSCoV-2) exposed a need for rapid clinical data interpretation in response to an unprecedented burden on the healthcare system. A new healthcare challenge has arisen – post-COVID syndrome or ‘long COVID’. Symptoms of the post-COVID syndrome can persist for months following infection with SARS-CoV-2, often characterised by fatigue, breathlessness, dizziness, and pain. Despite this additional healthcare burden, no tests can diagnose, monitor, or determine the efficacy of treatments/interventions to support recovery. In this paper, an array of machine-learning algorithms is trained to evaluate and detect COVID-19-associated changes to lung tissue from X-ray images. X-ray images are classified from open sources into three categories: COVID-19 patients, patients with pneumonia, and unaffected otherwise healthy individuals using existing Machine Learning (ML) and pre-trained deep learning models. Prioritising models with the fewest false positives and false negatives assessed the performance of different models in detecting COVID-19-associated lung tissue. In addition, image pre-processing, data augmentation, and hyperparameter tuning are used to achieve the best accuracy in the models. Different ML models, including K Nearest Neighbour (KNN), and decision trees (DT), as well as transfer learning models such as Convolutional Neural Network (CNN), Visual Geometry Group (VGG-16, VGG-19), ResNet50, DenseNet201, Xception, and InceptionV3, were tested to evaluate the performance of these models for X-ray images classification. The comparative analysis indicates that VGG-19 with augmentation performed best among the ten algorithms with a training accuracy of 99%, testing accuracy of 98%, and precision of 90% for COVID-19, 90% for normal, and 100% for pneumonia. This higher accuracy for detecting COVID-19-associated lung changes on X-ray may be further developed to stratify patients suffering from post-COVID syndrome. This may enable future intervention studies to determine the efficacy of treatments or better track patients’ prognoses to be optimised.

Empowering Medical Monitors: AI-Enabled Semantic Parsing for Enhanced Clinical Data Interpretation

Empowering Medical Monitors: AI-Enabled Semantic Parsing for Enhanced Clinical Data Interpretation

Abstract 1771: NYU Langone Genome PACT - Genome Profiling of Actionable Cancer Targets (LG-PACT) for clinical patient molecular diagnostics and treatment

Abstract Next-generation sequencing (NGS) for the detection of somatic variants has become the tool of choice in a variety of molecular oncology fields and in the clinic. Its use ranges from sequencing entire tumor genomes and transcriptomes to targeted clinical diagnostic gene panels. The NYU Langone Genome PACT assay is a qualitative in vitro diagnostic test that uses targeted next generation sequencing of formalin-fixed paraffin-embedded (FFPE) tumor tissue matched with normal specimens from patients to detect gene alterations in a 607-gene panel. Indications for testing are cancer (solid tumors or hematological malignancies) where a mutational profile from multiple genes would be informative for disease stratification, prognosis, or treatment options including targeted therapies and eligibility for clinical trials. The test is intended to provide information on somatic mutations including point mutations, copy number aberrations, and small insertions/deletions (indels) for diagnostic and treatment decisions. LG-PACT is a United States Food and Drug Administration (FDA) approved diagnostic test. The clinical interpretation of sequencing data of molecular tumor markers from NGS encompasses automated variant calling tools with human interpretation. The final mostly manual review of data is intensive, involving highly trained scientists, encompassing literature review, interpretation and tier classification by pathologists, who then provide a complete molecular diagnostic report to the treating oncologists. Since January 2022 to present (October 2023) we have provided clinical genomic reports for 1029 oncological cases from 124 different cancers and their subtypes, including Brain (489 cases incl. meningioma, glioma and glioblastoma), Gastrointestinal (123), Lung (114), among others. We first present the technical challenges of validating an NGS oncological diagnostic targeted assay for appropriate clinical grade accuracy and sensitivity acceptable for patient care. We show how copy number alterations provide a more comprehensive description of the tumors genomic profile. We then outline the actionability of targeted panel sequencing for our current patient cohort. Where analysis of variant detection has led to 47% (490) of our clinical tumor samples containing known tier 1 therapeutic variants. We conclude with presenting case studies that identify both the clinical utility and informatic challenges of variant calling specific to gene panel sequencing e.g., i) the capture of potential targetable rare and novel indels and multivariant mutations in exons 19 and 20 of EGFR, and ii) a unique KIT tandem duplication event in a gastrointestinal stromal tumor (GIST). We demonstrate the value in precision oncology for multiple cancer types and how the capture of unique variants can provide better targeted treatment options to cancer patients. Citation Format: Varshini Vasudevaraja, Yiying Yang, Jonathan Serrano, Kazimierz Wrzeszczynski, Matija Snuderl. NYU Langone Genome PACT - Genome Profiling of Actionable Cancer Targets (LG-PACT) for clinical patient molecular diagnostics and treatment [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 1771.

Primary Tuberculosis in Adults: Diagnostic Errors

Primary Tuberculosis in Adults: Diagnostic Errors

Distribution of the C9orf72 hexanucleotide repeat expansion in healthy subjects: a multicenter study promoted by the Italian IRCCS network of neuroscience and neurorehabilitation.

High repeat expansion (HRE) alleles in C9orf72 have been linked to both amyotrophic lateral sclerosis (ALS) and frontotemporal dementia (FTD); ranges for intermediate allelic expansions have not been defined yet, and clinical interpretation of molecular data lacks a defined genotype-phenotype association. In this study, we provide results from a large multicenter epidemiological study reporting the distribution of C9orf72 repeats in healthy elderly from the Italian population. A total of 967 samples were collected from neurologically evaluated healthy individuals over 70 years of age in the 13 institutes participating in the RIN (IRCCS Network of Neuroscience and Neurorehabilitation) based in Italy. All samples were genotyped using the AmplideXPCR/CE C9orf72 Kit (Asuragen, Inc.), using standardized protocols that have been validated through blind proficiency testing. All samples carried hexanucleotide G4C2 expansion alleles in the normal range. All samples were characterized by alleles with less than 25 repeats. In particular, 93.7% of samples showed a number of repeats ≤10, 99.9% ≤20 repeats, and 100% ≤25 repeats. This study describes the distribution of hexanucleotide G4C2 expansion alleles in an Italian healthy population, providing a definition of alleles associated with the neurological healthy phenotype. Moreover, this study provides an effective model of federation between institutes, highlighting the importance of sharing genomic data and standardizing analysis techniques, promoting translational research. Data derived from the study may improve genetic counseling and future studies on ALS/FTD.