Multiple Disease Types Research Articles

Determining the Feasibility of a Cadmium Exposure Model to Activate the Inflammatory Arm of PANoptosis in Murine Monocytes.

A prevalence of cigarette smoking can cause the accumulation of cadmium (Cd2+) in the lungs, kidneys, and blood. The effects of exposure can cause multiple chronic disease types to emerge in the affected organ systems. The only moderately effective therapeutic option is chelation therapy; the health risks associated with this therapy have caused much criticism. The disease types associated with Cd2+ toxicity have inflammatory components and greatly impact innate immunity. These factors are affected at the cellular level and cause pathways like apoptosis, pyroptosis, and necroptosis. A development in understanding these pathways stipulates that these three pathways act as one complex of pathways, known together as PANoptosis. The inflammatory mechanisms of PANoptosis are particularly interesting in Cd2+ toxicity due to its inflammatory effects. Proteins in the gasdermin family act to release inflammatory cytokines, like interleukin-1β, into the extracellular environment. Cytokines cause inflammatory disease pathologies like fibrosis and cancer. RAW 264.7 monocytes are key in the murine immune system and provide an excellent model to investigate Cd2+ toxicity. Exposure of 0-15 µM CdCl2 was sufficient to increase expression of cleaved gasdermin D (GSDMD) and gasdermin E (GSDME) in this cell type. Cd2+ also exhibits a dose-dependent cytotoxicity in this cell type.

Targeted therapy evolution from defining a sub-population to crossing multi-indications

Targeted therapy has transformed the landscapes of medical care and pharmaceutical innovation fundamentally, due to selective efficacy on pathological tissues and minimized toxicity to normal cells particularly in oncology. As a necessary tool for implementing targeted therapy, biomarkers of pathogenesis-driven pathways were initially validated to determine the susceptible patient subgroup with a disease. Subsequently such biomarkers were also corroborated in some patients from multiple disease types, conferring a rationale to run drug development in a less risky and more affordable manner through repurpose or tissue-agnostic approval recently. To reflect the evolving trend, this article thus presents an update on the outstanding targeted medications with an extending list of clinical indications in oncology and beyond. It tends not only to shed lights on an emerging classification framework of disease according to the shared molecular pathogenesis across various organs/tissues，but also to inspire more efficient paradigms of pharmaceutic innovation in a broader medical perspective.

FSM-YOLO: Apple leaf disease detection network based on adaptive feature capture and spatial context awareness

Apple leaf disease is a key factor affecting apple yield. Detecting apple leaf diseases in unstructured environments presents a significant challenge due to the diverse early forms and varying scales of the diseases, as well as the similarity between the diseased areas and the background. To address these challenges, this paper proposes an improved convolutional neural network FSM-YOLO with adaptive feature capture and spatial context awareness. Firstly, to address the lack of feature extraction due to the complex texture structure of disease features, AFEM (Adaptive Feature Enhancement Module) with the ability of contextual information fusion and channel information modulation is proposed, which enhances the feature extraction capability for multiple disease types. Secondly, SCAA (Spatial Context-aware Attention) module with spatial relationship capture and adaptive receptive field adjustment was designed to enhance the network's ability to spatial relationship modeling and its ability to focus on disease characteristics to distinguish between disease targets and background information. Finally, MKMC (Multi-kernel mixed Convolution) is proposed to enhance multi-scale feature extraction capability by efficiently capturing and integrating information at multiple spatial resolutions to cope with different scales and shape variations of early leaf disease types. Experiments were conducted on an apple leaf disease dataset covering eight different disease types with 15,159 disease instances, and the experimental results show that compared with the baseline model YOLOv8s, FSM-YOLO improves mAP@0.5 by 2.7%, precision by 2.0%, and recall by 4.0%. Meanwhile, experimental results on the open-source apple leaf disease dataset ALDOD and plant leaf disease dataset PlantDoc show that FSM-YOLO outperforms the state-of-the-art algorithms, which validates the versatility of FSM-YOLO and confirms its excellent detection performance in various plant disease scenarios.

A hybrid deep learning skin cancer prediction framework

Skin cancer, a critical health concern, necessitates accurate early detection and classification to mitigate its impact. However, the limited availability of medical datasets and the challenge of optimizing learnable parameters in deep learning strategies for medical images pose significant hurdles. To address these challenges, we propose an innovative solution—a hybrid artificial intelligence (AI) framework for skin cancer prediction. This framework consists of two pivotal steps: firstly, a comprehensive skin cancer dataset is curated by combining diverse public datasets encompassing multiple disease types. This facilitates robust weight tuning of Convolutional Neural Networks (CNNs) by enhancing the diversity of the learning process. Subsequently, the optimization of deep learning is meticulously executed through the artificial Bee Colony (ABC) strategy, effectively mitigating the potential adverse effects of initial parameter randomness on AI model performance. Rigorous evaluation of the hybrid framework against eight prominent CNN models, including DenseNet121, InceptionResNetV2, and others, underscores its superior predictive capabilities. The optimized hybrid framework achieves exceptional results, boasting an accuracy of 93.04%, recall of 92.0%, precision of 93.0%, and an impressive F1-score of 93.12%. In summary, our proposed hybrid solution demonstrates a substantial advancement in multi-disease skin cancer classification. It outperforms existing AI models and holds promise as a pragmatic smart solution with far-reaching implications.

Abstract PO2-25-12: Production of a bespoke muscle resistance exercise (MRE) programme for use in a future clinical trial, following a detailed patient engagement program (PEP) in patients with advanced breast cancer (ABC)

Abstract Background: MRE investigations in early breast cancer have been undertaken but there has been little evaluation in ABC. Cancer guidelines suggest the use of physical activity, including MRE, to improve fatigue (National Comprehensive Cancer Network, 2.2020; European Society of Medical Oncology 2020) but improvement in other outcomes in ABC is less clear. In clinical trials, adherence to exercise intervention has been a challenge and has hampered investigation of other outcomes and little data exists evaluating the possible reasons for this poor adherence and compliance. In preparation for an exercise component as part of lifestyle intervention trial in ABC, a PEP was undertaken to evaluate an on-line web-based exercise program. Results would support continued usage of the program or creation of a new program. Methods: A commercially available program was used containing a library of exercises created for multiple disease types. There was no voice over. Using an exercise science professional, 2 sets of muscular resistance exercise programmes were created (A &B), selecting exercises for upper and lower limb major muscle groups. Set A and B differed , with A involving younger leaner demonstrators and B older, less lean. Volunteers were asked to view the sets and complete a survey. The results of the survey, involving 21 volunteers of which 43% were over 60 years and presented previously, indicated that the following main modifications were needed to a program: use of demonstrators similar to patient's habitus and use of a voice-over to guide exercises. A short test video was produced incorporating these and other visual changes and viewed by a focus group of four volunteers. Results: The focus group concluded that the new visual and audio changes would allow them to more easily perform the exercises and increase the likelihood of compliance compared to the on-line program. The group advised involvement of a more diverse demonstrator group and further improvements to the voice-over. A professionally produced video has now been made with all the above changes. Conclusions: This PEP indicates that is necessary to review exercise programmes with patients and not assume they are all suitable for use in clinical trials. We believe a PEP of this kind with the resultant bespoke video is the first produced involving patients with ABC. This video will now be evaluated in a much larger diverse PPE which will help the development of a national UK clinical trial of exercise in ABC. Citation Format: Amanda Clarke, Jennifer Glendenning, Glen Davison, Catherine Harper-Wynne. Production of a bespoke muscle resistance exercise (MRE) programme for use in a future clinical trial, following a detailed patient engagement program (PEP) in patients with advanced breast cancer (ABC) [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-25-12.

Measurement of ctDNA Tumor Fraction Identifies Informative Negative Liquid Biopsy Results and Informs Value of Tissue Confirmation.

Liquid biopsy (LBx) for tumor profiling is increasingly used, but concerns remain regarding negative results. A lack of results may truly reflect tumor genomics, or it may be a false negative that would be clarified by tissue testing. A method of distinguishing between these scenarios could help clarify when follow-on tissue testing is valuable. Here we evaluate circulating tumor DNA (ctDNA) tumor fraction (TF), a quantification of ctDNA in LBx samples, for utility in identifying true negative results. We assessed concordance between LBx and tissue-based results, stratified by ctDNA TF, in a real-world genomic dataset of paired samples across multiple disease types. We also evaluated the frequency of tissue results identifying driver alterations in patients with lung cancer after negative LBx in a real-world clinicogenomic database. The positive percent agreement and negative predictive value between liquid and tissue samples for driver alterations increased from 63% and 66% for all samples to 98% and 97% in samples with ctDNA TF ≥1%. Among 505 patients with lung cancer with no targetable driver alterations found by LBx who had subsequent tissue-based profiling, 37% had a driver, all of which had ctDNA TF <1%. Patients with lung cancer with negative LBx and ctDNA TF ≥1% are unlikely to have a driver detected on confirmatory tissue testing; such informative negative results may benefit instead from prompt treatment initiation. Conversely, negative LBx with ctDNA TF <1% will commonly have a driver identified by follow-up tissue testing and should be prioritized for reflex testing.

Pan-cancer analyses of bromodomain containing 9 as a novel therapeutic target reveals its diagnostic, prognostic potential and biological mechanism in human tumours.

Mutations in one or more genes responsible for encoding subunits within the SWItch/Sucrose Non-Fermentable (SWI/SNF) chromatin-remodelling complexes are found in approximately 25% of cancer patients. Bromodomain containing 9 (BRD9) is a more recently identified protein coding gene, which can encode SWI/SNF chromatin-remodelling complexes subunits. Although initial evaluations of the potential of BRD9-based targeted therapy have been explored in the clinical application of a small number of cancer types, more detailed study of the diagnostic and prognostic potential, as well as the detailed biological mechanism of BRD9 remains unreported. We used various bioinformatics tools to generate a comprehensive, pan-cancer analyses of BRD9 expression in multiple disease types described in The Cancer Genome Atlas (TCGA). Experimental validation was conducted in tissue microarrays and cell lines derived from lung and colon cancers. Our study revealed that BRD9 exhibited elevated expression in a wide range of tumours. Analysis of survival data and DNA methylation for BRD9 indicated distinct conclusions for multiple tumours. mRNA splicing and molecular binding were involved in the functional mechanism of BRD9. BRD9 may affect cancer progression through different phosphorylation sites or N6 -methyladenosine site modifications. BRD9 could potentially serve as a novel biomarker for diagnosing different cancer types, especially could accurately forecast the prognosis of melanoma patients receiving anti-programmed cell death 1 immunotherapy. BRD9 has the potential to serve as a therapeutic target, when pairing with etoposide in patients with melanoma. The BRD9/SMARCD1 axis exhibited promising discriminative performance in forecasting the prognosis of patients afflicted with liver hepatocellular carcinoma (LIHC) and mesothelioma. Additionally, this axis appears to potentially influence the immune response in LIHC by regulating the programmed death-ligand 1 immune checkpoint. For experimental validation, high expression levels of BRD9 were observed in tumour tissue samples from both lung and colon cancer patients. Knocking down BRD9 led to the inhibition of lung and colon cancer development, likely via the Wnt/β-catenin signalling pathway. These pan-cancer study revealed the diagnostic and prognostic potential, along with the biological mechanism of BRD9 as a novel therapeutic target in human tumours.

FlexStat: combinatory differentially expressed protein extraction.

Mass spectrometry-based system proteomics allows identification of dysregulated protein hubs and associated disease-related features. Obtaining differentially expressed proteins (DEPs) is the most important step of downstream bioinformatics analysis. However, the extraction of statistically significant DEPs from datasets with multiple experimental conditions or disease types through currently available tools remains a laborious task. More often such an analysis requires considerable bioinformatics expertise, making it inaccessible to researchers with limited computational analytics experience. To uncover the differences among the many conditions within the data in a user-friendly manner, here we introduce FlexStat, a web-based interface that extracts DEPs through combinatory analysis. This tool accepts a protein expression matrix as input and systematically generates DEP results for every conceivable combination of various experimental conditions or disease types. FlexStat includes a suite of robust statistical tools for data preprocessing, in addition to DEP extraction, and publication-ready visualization, which are built on established R scientific libraries in an automated manner. This analytics suite was validated in diverse public proteomic datasets to showcase its high performance of rapid and simultaneous pairwise comparisons of comprehensive datasets. FlexStat is implemented in R and is freely available at https://jglab.shinyapps.io/flexstatv1-pipeline-only/. The source code is accessible at https://github.com/kts-desilva/FlexStat/tree/main.

Safety and pharmacokinetics of GB1211, an oral galectin-3 inhibitor: a single- and multiple-dose first-in-human study in healthy participants

PurposeGalectin-3, a β-galactoside-binding lectin, plays a key role in several cellular pathways involved in chronic inflammation, heart disease and cancer. GB1211 is an orally bioavailable galectin-3 inhibitor, developed to be systemically active. We report safety and pharmacokinetics (PK) of GB1211 in healthy participants.MethodsThis phase 1, double-blind, placebo-controlled, first-in-human study (NCT03809052) included a single ascending-dose phase (with a food-effect cohort) where participants across seven sequential cohorts were randomized 3:1 to receive oral GB1211 (5, 20, 50, 100, 200 or 400 mg) or placebo. In the multiple ascending-dose phase, participants received 50 or 100 mg GB1211 or placebo twice daily for 10 days. All doses were administered in the fasted state except in the food-effect cohort where doses were given 30 min after a high-fat meal.ResultsAll 78 participants received at least one GB1211 dose (n = 58) or placebo (n = 20) and completed the study. No safety concerns were identified. Following single and multiple oral doses under fasted conditions, maximum GB1211 plasma concentrations were reached at 1.75–4 h (median) post-dose; mean half-life was 11–16 h. There was a ~ twofold GB1211 accumulation in plasma with multiple dosing, with steady-state reached within 3 days; 30% of the administered dose was excreted in urine as unchanged drug. Absorption in the fed state was delayed by 2 h but systemic exposure was unaffected.ConclusionGB1211 was well tolerated, rapidly absorbed, and displayed favorable PK, indicating a potential to treat multiple disease types. These findings support further clinical development of GB1211.Clinical trial registrationThe study was registered with ClinicalTrials.gov (identifier: NCT03809052).

A network approach to compute hypervolume under receiver operating characteristic manifold for multi-class biomarkers.

Computation of hypervolume under ROC manifold (HUM) is necessary to evaluate biomarkers for their capability to discriminate among multiple disease types or diagnostic groups. However the original definition of HUM involves multiple integration and thus a medical investigation for multi-class receiver operating characteristic (ROC) analysis could suffer from huge computational cost when the formula is implemented naively. We introduce a novel graph-based approach to compute HUM efficiently in this article. The computational method avoids the time-consuming multiple summation when sample size or the number of categories is large. We conduct extensive simulation studies to demonstrate the improvement of our method over existing R packages. We apply our method to two real biomedical data sets to illustrate its application.

Logistic tensor decomposition with sparse subspace learning for prediction of multiple disease types of human-virus protein-protein interactions.

Viral infection involves a large number of protein-protein interactions (PPIs) between the virus and the host, and the identification of these PPIs plays an important role in revealing viral infection and pathogenesis. Existing computational models focus on predicting whether human proteins and viral proteins interact, and rarely take into account the types of diseases associated with these interactions. Although there are computational models based on a matrix and tensor decomposition for predicting multi-type biological interaction relationships, these methods cannot effectively model high-order nonlinear relationships of biological entities and are not suitable for integrating multiple features. To this end, we propose a novel computational framework, LTDSSL, to determine human-virus PPIs under different disease types. LTDSSL utilizes logistic functions to model nonlinear associations, sets importance levels to emphasize the importance of observed interactions and utilizes sparse subspace learning of multiple features to improve model performance. Experimental results show that LTDSSL has better predictive performance for both new disease types and new triples than the state-of-the-art methods. In addition, the case study further demonstrates that LTDSSL can effectively predict human-viral PPIs under various disease types.

Design of an Ensemble Segmentation, Feature Processing &amp; Classification model for identification of Cotton Fungal diseases

Cotton fungal diseases include rust, alternaria leaf spot, fusarium wilt, grew mildew, and root rots. Identification of these diseases requires design of efficient fungi segmentation, feature representation &amp; classification models. Existing methods that perform these tasks, are highly complex, and require disease-specific segmentation techniques, which limits their scalability levels. Moreover, low-complexity models are generally observed to showcase low accuracy levels, which restricts their applicability for real-time use cases. To overcome these issues, proposed design focused on a novel ensemble segmentation, feature processing &amp; classification model for identification of cotton fungi diseases. The proposed model initially uses a combination of Fuzzy C Means (FCM), Enhanced FCM, KFCM, and saliency maps in order to extract Regions of Interest (RoIs). These RoIs are post-processed via a light-weight colour-feature based disease category identification layer, which assists in selecting the segmented image sets. These image sets are processed via an ensemble feature representation layer, which combines Colour Maps, Edge Maps, Gabor Maps and Convolutional feature sets. Due to evaluation of multiple feature sets, the model is able to improve classification performance for multiple disease types. Extracted features are classified via use of an ensemble classification model that combines Naïve Bayes (NB), Support Vector Machines (SVMs), Logistic Regression (LR), and Multilayer Perceptron (MLP) based classifiers. Due to this combination of segmentation, feature representation &amp; classification models, the proposed Model is capable of improving classification accuracy by 5.9%, precision by 4.5%, recall by 3.8%, and delay by 8.5% when compared with state-of-the-art models, which makes it useful for real-time disease detection of crops.

OS069 - Humoral and cellular immune responses to SARS-CoV-2 vaccination across multiple vaccine platforms and liver disease types: an EASL registry multicentre prospective cohort study

OS069 - Humoral and cellular immune responses to SARS-CoV-2 vaccination across multiple vaccine platforms and liver disease types: an EASL registry multicentre prospective cohort study

Abstract 1249: Development of a pan-cancer algorithm to predict homologous recombination deficiency and sensitivity to PARPi therapy

Abstract Background: PARP inhibitors (PARPi) are approved for multiple indications with ongoing trials to explore broader utility. However, identifying the right patients for these therapies across multiple disease types remains a challenge. In ovarian cancer, genomic-scar based measures for homologous recombination deficiency (HRD) are approved diagnostics (genome-wide LOH [gLOH] and genomic instability score [GIS]); however, broader utility has not been established. Methods: A pan-cancer genomic profiling dataset (n = 202,472; Foundation Medicine, Cambridge, MA) was split 70:30 for training and validation of an HRD signature using an XGB machine learning model (mlHRD). A broad set of copy number (Macintyre 2018) and indel features (Alexandrov 2020) were used to identify signatures of HRD. gLOH (Coleman 2017) and GIS (Timms 2014) were calculated using copy number profiles. Biallelic alterations were predicted using a computational zygosity algorithm (Sun, 2018). The nationwide, de-identified Flatiron Health-Foundation Medicine ovarian and prostate clinico-genomic databases (FH-FMI CGDB) were utilized for outcomes analysis. The de-identified data originated from approximately 280 US cancer clinics (~800 sites of care). Time to therapy discontinuation (TTD) was estimated with Kaplan-Meier analysis. Hazard ratios were calculated using unadjusted Cox proportional Hazard models. Results: We developed an algorithm to predict HRD status using indel and copy number features (see methods). Across the pan-cancer dataset, the rate of mlHRD was 6.4% with the highest frequency in fallopian tube (30%), ovarian (30%), peritoneal (23%), breast (16%), and prostate cancers (15%). Sensitivity to detect biallelic BRCA1/2 alterations was high across tumors [ovary (93%), prostate (87%), breast (85%), pancreas (80%)]. Beyond BRCA1/2, mlHRD positivity was associated with biallelic alterations in RAD51D (OR = 24, p&amp;lt;1E-10), PALB2 (OR = 23, p&amp;lt;1E-10), BARD1 (OR = 23, p&amp;lt;1E-10), and RAD51C (OR = 19, p&amp;lt;1E-10). In the FH-FMI CGDB ovarian cancer cohort, 150 patients were treated with PARPi (mlHRD positive = 73; negative = 77); mlHRD positivity was associated with improved TTD (median 8.9 mo v 3.9 mo; HR = 0.49 [0.34-0.71], p &amp;lt; 0.001), with similar predictive power to gLOH &amp;gt;16% (HR = 0.55 [0.38-0.79], p = 0.001) and GIS &amp;gt;42 (HR = 0.59 [0.41-0.86], p = 0.006). For 62 patients with prostate cancer treated with PARPi (mlHRD positive = 27; negative = 35), mlHRD was associated with prolonged TTD on PARPi (median 6.8 mo v 3.4 mo; HR = 0.56 [0.30-1.03], p = 0.064), trending more predictive than gLOH &amp;gt;8.29% (Sokol 2020) and GIS &amp;gt;42 (HR = 0.64 [0.29-1.40] and 0.80 [0.37-1.73], respectively; p&amp;gt;0.05). Conclusion: These findings suggest that HRD is associated with genomic scarring beyond ovarian cancer. Additional retrospective and prospective analyses in clinical datasets are needed to explore the utility of this signature. Citation Format: Emmanuel Antonarakis, Jay Moore, Dexter Jin, Tim Chen, Justin Newberg, Zoe Fleischmann, Karthikeyan Murugesan, Garrett Frampton, David Fabrizio, Russell Madison, Ethan Sokol. Development of a pan-cancer algorithm to predict homologous recombination deficiency and sensitivity to PARPi therapy [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1249.

Examining the Determinants of Patient Perception of Physician Review Helpfulness across Different Disease Severities: A Machine Learning Approach

(1) Background. Patients are increasingly using physician online reviews (PORs) to learn about the quality of care. Patients benefit from the use of PORs and physicians need to be aware of how this evaluation affects their treatment decisions. The current work aims to investigate the influence of critical quantitative and qualitative factors on physician review helpfulness (RH). (2) Methods. The data including 45,300 PORs across multiple disease types were scraped from Healthgrades.com. Grounded on the signaling theory, machine learning-based mixed methods approaches (i.e., text mining and econometric analyses) were performed to test study hypotheses and address the research questions. Machine learning algorithms were used to classify the data set with review- and service-related features through a confusion matrix. (3) Results. Regarding review-related signals, RH is primarily influenced by review readability, wordiness, and specific emotions (positive and negative). With regard to service-related signals, the results imply that service quality and popularity are critical to RH. Moreover, review wordiness, service quality, and popularity are better predictors for perceived RH for serious diseases than they are for mild diseases. (4) Conclusions. The findings of the empirical investigation suggest that platform designers should design a recommendation system that reduces search time and cognitive processing costs in order to assist patients in making their treatment decisions. This study also discloses the point that reviews and service-related signals influence physician RH. Using the machine learning-based sentic computing framework, the findings advance our understanding of the important role of discrete emotions in determining perceived RH. Moreover, the research also contributes by comparing the effects of different signals on perceived RH across different disease types.

Abstract 152: A machine learning approach to detect FFPE artefacts leads to accurate estimation of tumor mutational burden from sequencing data without a matched normal

Abstract Tumor mutational burden (TMB) is emerging as a promising predictive biomarker to select cancer patients who will benefit from immunotherapy. However, accurate TMB estimation from sequencing data remains hampered by the ability to correctly distinguish somatic variants from both germline variants and spurious base changes introduced by sample preparation and sequencing processes. The latter is particularly prevalent in poor quality FFPE material where degradation and chemical modifications of the DNA manifest as variant artefacts leading to over-estimation of TMB. One method of removing germline variants and artefacts is to compare tumor variant calls to those obtained from matched normal tissue, however inclusion of a matched normal adds significant logistical and financial challenges to clinical trial assays. Therefore, there remains a critical need to establish alternative approaches enabling accurate TMB estimation from FFPE tumor-only samples. To address these challenges, we have developed a tumor-only somatic variant calling pipeline for accurate determination of TMB from FFPE material profiled by whole exome sequencing (WES). The process is underpinned by two key features (a) enhanced germline variant filtering that uses a systematic rule-based strategy, (b) FFPE artefact removal using an ensemble machine learning model incorporating multiple variant call QC parameters. The germline filtering approach was developed on a matched fresh frozen (FF)/FFPE/blood dataset of 23 cancer patients. The FFPE artefact filtering model was built on a dataset of 59 FF and FFPE matched pairs, where FFPE artefacts were defined as variants present in FFPE but absent in the FF sample. Benchmarked against internal and TCGA datasets of somatic variant calls from &amp;gt;30 FF samples with a matched normal, our germline and FFPE filtering steps decreased false discovery rates by over 20%. This translated into improved TMB scoring performance with tumor-only pipeline estimates from three SeraCare reference standards closely matching expected TMB scores. Critically, we establish the clinical relevance of our approach on a published cohort of 98 patients treated with an immune checkpoint inhibitor. Here we observed increased association between patient response and TMB estimated from our pipeline (p=0.042) compared to a standard pipeline with no enhanced germline or FFPE artefact filters (p=0.56). Overall, our combined germline and FFPE artefact filtering pipeline results in significantly improved somatic variant detection and TMB scoring performance in FFPE samples where a matched normal is unavailable. It is applicable across multiple disease types and adaptable to other platforms. Therefore, the pipeline has utility in clinical laboratories where accurate somatic variant detection is crucial to successful deployment of predictive biomarkers such as TMB. Citation Format: Hui Sun Leong, Emma O'Connor, Nuala McCabe, Sinead Donegan, Steven M. Walker, Jayna Mistry, Karen Keating, Denis P. Harkin, Richard D. Kennedy, Laura A. Knight, James R. Bradford. A machine learning approach to detect FFPE artefacts leads to accurate estimation of tumor mutational burden from sequencing data without a matched normal [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 152.

Optimal Bayesian hierarchical model to accelerate the development of tissue-agnostic drugs and basket trials

Tissue-agnostic trials and basket trials enroll patients based on their genetic biomarkers, not tumor type, in an attempt to determine if a new drug can successfully treat disease conditions based on biomarkers. The Bayesian hierarchical model (BHM) provides an attractive approach to design phase II tissue-agnostic trials by allowing information borrowing across multiple disease types. In this article, we elucidate two intrinsic and inevitable issues that may limit the use of BHM to tissue-agnostic trials: sensitivity to the prior specification of the shrinkage parameter and the competing “interest” among disease types in increasing power and controlling type I error. To address these issues, we propose the optimal BHM (OBHM) and clustered OBHM (COBHM) approaches. In these approach, we first specify a flexible utility function to quantify the tradeoff between type I error and power across disease types based on the study objectives, and then we select the prior of the shrinkage parameter to optimize the utility function of clinical and regulatory interest. COBHM further utilizes a simple Bayesian rule to cluster tumor types into sensitive and insensitive subgroups to achieve more accurate information borrowing. Simulation study shows that the OBHM and especially COBHM have desirable operating characteristics, outperforming some existing methods. COBHM effectively balances power and type I error, addresses the sensitivity of the prior selection, and reduces the “unwarranted” subjectivity in the prior selection. It provides a systematic, rigorous way to apply BHM and solve the common problem of blindingly using a non-informative inverse-gamma prior (with a large variance) or priors arbitrarily chosen that may lead to problematic statistical properties.

Data Mining Techniques Based Diabetes Prediction

Data mining plays an important part in the healthcare sector disease prediction. Techniques of data mining are commonly used in early disease detection. Diabetes is one of the world’s greatest health challenges. A widespread chronic condition is a diabetes. Diabetes prediction is a science that is increasingly growing. Diabetes prediction at an early stage will lead to better therapy. It is necessary to avoid, monitor and increase diabetes consciousness because it causes other health issues. Diabetes of type 1 or type 2 can lead to heart disorders, kidney diseases or complications with the eye. This survey paper reflects on numerous approaches and data mining strategies used to forecast multiple diabetes disorders at an early stage. Become a chronic disease because of diabetes. The patient lives will be spared by an early prediction of this disease. By the use of data mining tools and processes, diabetes is avoided and treatment rates are reduced. The association rule mining, classification, clustering, Random Forest, Prediction as well as the Artificial Neural Network (ANN) are among the most common and important data mining technology. Different data mining methods are available to avoid diseases such as cardiac disease, cancer including kidney etc. This study examines the use of data mining methods to predict multiple disease types.

Data Mining Techniques Based Diabetes Prediction

Data mining plays an important part in the healthcare sector disease prediction. Techniques of data mining are commonly used in early disease detection. Diabetes is one of the world's greatest health challenges. A widespread chronic condition is a diabetes. Diabetes prediction is a science that is increasingly growing. Diabetes prediction at an early stage will lead to better therapy. It is necessary to avoid, monitor and increase diabetes consciousness because it causes other health issues. Diabetes of type 1 or type 2 can lead to heart disorders, kidney diseases or complications with the eye. This survey paper reflects on numerous approaches and data mining strategies used to forecast multiple diabetes disorders at an early stage. Become a chronic disease because of diabetes. The patient lives will be spared by an early prediction of this disease. By the use of data mining tools and processes, diabetes is avoided and treatment rates are reduced. The association rule mining, classification, clustering, Random Forest, Prediction as well as the Artificial Neural Network (ANN) are among the most common and important data mining technology. Different data mining methods are available to avoid diseases such as cardiac disease, cancer including kidney etc. This study examines the use of data mining methods to predict multiple disease types.

Treatment of Disorders of Tone and Other Considerations in Pediatric Movement Disorders.

Pediatric movement disorders (PMDs) consist of a heterogeneous group of signs and symptoms caused by numerous neurological diseases. Different neurological disorders in children also share overlapping movement disorders making a diagnosis of the underlying cause of the movement disorder challenging. The similarity of the symptoms across multiple disease types suggests that there may be a final common motor pathway causing the overlapping movement disorders. There are numerous disorders in children associated with disturbances in tone and involuntary movements. This chapter will focus primarily on those disorders that involve abnormalities of tone and other important considerations of pediatric movement disorders. This chapter will address rating scales and goals for treatment and will include a review of symptomatic treatment and, where possible, the treatment of the underlying disease processes. The chapter will review representative disorders, including an inborn error of metabolism, an autoimmune disorder, and a group of neurodegenerative disorders. These examples demonstrate how the disorder's underlying pathophysiology results in a specific approach to the underlying disease and the associated conditions of tone and involuntary movements. Finally, the multiple treatment options for cerebral palsy and considerations of cerebral palsy mimics will be discussed.