Search

Variant calling is a fundamental task that is performed to identify variants in an individual's genome compared to a reference human genome. This task can enable better understanding of an individual's risk to diseases and eventually lead to new innovations in precision medicine and drug discovery. However, variant calling on a large number of human genome sequences requires significant computing and storage resources. While access to such resources is possible today (e.g., through cloud computing), reducing the cost of analyzing genomes has become a major challenge. Motivated by these reasons, we address the problem of accelerating the variant calling pipeline on a large number of human genome sequences using a commodity cluster. We propose a novel approach that synergistically combines data and task parallelism for different stages of the variant calling pipeline across different sequences with minimal synchronization. Our approach employs futures to enable asynchronous computations in order to improve the overall cluster utilization and thereby, accelerate the variant calling pipeline. On a 16-node cluster, we observed that our approach was 3X-4.7X faster than the state-of-the-art Big Data Genomics software.

Background Testicular torsion is a common cause of acute testicular pain, which requires immediate investigation and treatment. We describe a unique presentation of testicular torsion, which required the operating surgeon to assess the viability of a clinically dead testis through surgical manipulation, 16 hours after onset of pain. Case Report A 19 year old male presented with a 12 hour history of pain and swelling in the left scrotum. Examination revealed the left testes was hard, swollen and tender with a palpable spermatic cord. Clinical diagnosis of testicular mass or epididymo-orchitis was suggested and scrotal ultrasound was organised. This reported no blood flow in the left testis, and so torsion was suspected. Patient was taken immediately to theatre. Examination was performed under general anaesthetic, which revealed a hard, swollen testis, with no torsion clinically. Midline scrotal incision was made. On visual examination, left testis was black and hard, but there was no obvious torsion in the cord. However, during manipulation, the testis softened and started to change colour, eventually becoming dusky. A small incision into the testis showed bright red blood, and the decision was made to replace the testis and fix both testes. The patient made an excellent recovery post-operatively. Repeat ultrasound showed return of testicular vascularity. Conclusion This case showcases the importance of considering salvage in patients who have presented even after the generally accepted 6-8 hour time window. It also highlights the value of an experienced surgeon’s judgement in unusual presentations and with unexpected events intraoperatively.

Aims The diagnosis of prostate cancer has evolved over the past 2 decades with rapid changes occurring in the last 5 years. Traditionally transrectal prostate biopsies were the standard. However due to the risk of sepsis and sub optimal diagnostic accuracy, this method has been superseded by biopsies of the prostate now being performed via the transperineal (TP) route more frequently. Our hospital was the first in our region to use the PrecisionPoint Transperineal Access system to perform TP biopsy under local anaesthetic, and here we present our experience of the first 100 cases. Aims of this study included determining cancer detection rate and MRI correlation, as well as looking at rates of complications post procedure. Method This was a retrospective study with 100 patients in our cohort. We assessed MRI and histology correlation and post procedure complication rates. Results Histology in 72% of patients was positive for prostate cancer. Correlation between MRI findings and histology were noted to be high. As Likert score decreased, so did percentage of positive biopsies. Rates of significant complications were low, with no hospital admissions required following the procedure. Conclusion Our study demonstrates TP biopsy using the PrecisionPoint transperineal access system is a safe and effective method of detecting prostate cancer, which is well tolerated by patients.

Aim Our aim was to assess FY1/FY2 doctors’ experiences and confidence in performing urethral catheterisation in a teaching hospital. Methods This was a single centre, survey based study. An anonymous online questionnaire was circulated to all foundation doctors at the trust. The survey contained 18 questions. The domains included the number of catheterisations performed, confidence levels and whether they had been signed off as competent. This was followed by a series of knowledge questions. Results The survey was sent to 71 email addresses and the response rate was 53%. The results showed that respondents’ lacked experience and confidence in urethral catheterisation. We also found that 32% trainees had not inserted a female catheter during foundation training, and 55% had failed to insert a catheter in the last year. The vast majority (71%) of respondents did not feel confident in female catheterisation. Conclusions This study shows that knowledge and competency in urethral catheterisation (which is an essential GMC requirement) amongst junior doctors is still inadequate.

In this article, we focus on the problem of learning a Bayesian network over distributed data stored in a commodity cluster. Specifically, we address the challenge of computing the scoring function over distributed data in an efficient and scalable manner, which is a fundamental task during learning. While exact score computation can be done using the MapReduce-style computation, our goal is to compute approximate scores much faster with probabilistic error bounds and in a scalable manner. We propose a novel approach, which is designed to achieve the following: (a) decentralized score computation using the principle of gossiping; (b) lower resource consumption via a probabilistic approach for maintaining scores using the properties of a Markov chain; and (c) effective distribution of tasks during score computation (on large datasets) by synergistically combining well-known hashing techniques. We conduct theoretical analysis of our approach in terms of convergence speed of the statistics required for score computation, and memory and network bandwidth consumption. We also discuss how our approach is capable of efficiently recomputing scores when new data are available. We conducted a comprehensive evaluation of our approach and compared with the MapReduce-style computation using datasets of different characteristics on a 16-node cluster. When the MapReduce-style computation provided exact statistics for score computation, it was nearly 10 times slower than our approach. Although it ran faster on randomly sampled datasets than on the entire datasets, it performed worse than our approach in terms of accuracy. Our approach achieved high accuracy (below 6% average relative error) in estimating the statistics for approximate score computation on all the tested datasets. In conclusion, it provides a feasible tradeoff between computation time and accuracy for fast approximate score computation on large-scale distributed data.

Blockchain networks have made inroads in the supply chain domains due to their transparency, security and immutable logs. For cloud providers, a typical supply chain consists of complex networks of suppliers, manufacturers, distributors, retailers, auditors, and consumers. Even though there is an increased focus on self-serve or cloud provider managed SaaS (Software-as-a-service), a portion of sales for an enterprise customer occurs the old-fashioned way with the sales department drawing up a purchase order to begin the procurement process. In many cases, there could be several disjoint suppliers who fulfill the order behind the scenes unbeknownst to the buyer. In this paper we propose C3HSB, a decentralized distributed application architecture using blockchain and smart contracts to build the supply chain. Motivated by challenges in the industry, this approach can be considered as a building block for future supply chain procurement and deployment of cloud assets. The design goal for our system was to facilitate efficient handling of enterprise-scale purchase orders and alternatives in real-time while maintaining data provenance. C3HSB streamlines complex non-repudiated transaction workflows, promotes trust, and achieves cost savings for the customer and suppliers.

Background: Myasthenia gravis (MG) is an auto-immune disease, and the mainstay of therapy is immunomodulation. Such patients are at high risk of acquiring any infections. Hence, we sought to determine the impact of the current global pandemic COVID-19 infection in MG patients.Methods: For our study, we used Cerner Real-World DataTM that was provided through Cerner’s HealtheDataLab research tool. We ran a database query from January 2019 to July 2020 in our study. To extract these patients’ data, we used ICD 9-CM, ICD-10, and SNOMED-CT codes. We report data using means, range, and prevalence rates. The p-values were calculated using the two-sample t-test and Pearson’s chi-squared test. Results:In the COVID-19 data set, a total of twenty-seven myasthenia patients were identified with a positive COVID-19 infection, and four diagnosed with an exacerbation. Male to female ratio was equal and one unknown gender (3.7%) with a mean (± SD) age of 64.33 ± 18.42 years. This study group was compared with a non-COVID-19 data set in which a total of sixty-four myasthenia patients were identified, and twenty-three had an exacerbation. Among the hospitalized patients in the two groups, the mean length of hospitalization for all the myasthenia patients in the COVID-19 data set was 8.28 days (n=7), and the non-COVID-19 set was 4.33 days (n=6), and it was statistically significant (p-value= 0.007). Conclusion: The mean length of hospital stay is prolonged in Myasthenia patients who tested positive for COVID-19.

We present a system for large-scale image retrieval on everyday scenes with common objects. Our system leverages advances in deep learning and natural language processing (NLP) for improved understanding of images by capturing the relationships between the objects within an image. As a result, a user can retrieve highly relevant images and obtain suggestions for similar image queries to further explore the repository. Each image in the repository is processed (using deep learning) to obtain the most probable captions and objects in it. The captions are parsed into tree structures using NLP techniques, and stored and indexed in a database system. When a query image is posed, an optimized tree-pattern query is executed by the database system to obtain candidate matches, which are then ranked using tree-edit distance of the tree structures to output the top-k matches. Word embeddings and Bloom filters are used to obtain similar image queries. By clicking the suggested similar image queries, a user can intuitively explore the repository.

As the kidney is an extra-nodal organ and does not have lymphatic tissues, the existence of primary renal non-Hodgkin’s lymphoma has been continuously questioned. It is very rare. However, differentiation between renal cell carcinoma and renal lymphoma is necessary in patients presenting with solitary renal mass. We present a 70-year-old-man who presented with a renal mass and was diagnosed with diffuse large B-cell lymphoma. We feel that this case report may be of benefit to clinicians who may encounter a similar scenario.

The COVID-19 pandemic has devastated the lives of millions of people worldwide and damaged the economy of many countries. While the negative impact of the pandemic on mankind is unimaginable, this pandemic has triggered new research and innovation in the use of artificial intelligence for developing solutions to better understand and mitigate the pandemic. Several valuable datasets have been made available by different organizations and research groups. In this chapter, we provide an overview of real-world COVID-19 data sources available for developing novel applications and solutions for the pandemic. We provide a comparison between them from a data science perspective. Next, we delve deep into the Cerner Real-World Data for COVID-19. We discuss the schema of the database, data quality issues, data wrangling using Apache Spark, and data analysis using popular machine learning techniques. Specifically, we provide examples of querying the database, training machine learning models, and visualization. We also discuss the technical challenges that we encountered and how we overcame them to complete multiple clinical studies on COVID-19.

Deepfakes have become a major public concern on the Internet as fake images and videos could be used to spread misleading information about a person or an organization. In this paper, we explore if deepfakes can be generated for histopathology images using advances in deep learning. This is because the field of digital pathology is gaining a lot of momentum since the Food and Drug Administration (FDA) approved a few digital pathology systems for primary diagnosis and consultation in the United States. Specifically, we investigate if state-of-the- art generative adversarial networks (GANs) can produce fake histopathology images that can trick an expert pathologist. For our investigation, we used whole slide images (WSIs) hosted by The Cancer Genome Atlas (TCGA). We selected 3 WSIs of colon cancer patients and produced 100,000 patches of 256×256 pixels in size. We trained three popular GANs to generate fake patches of the same size. We then constructed a set of images containing 30 real and 30 fake patches. An expert pathologist reviewed these images and marked them as either real or fake. We observed that the pathologist marked 10 fake patches as real and correctly identified 34 patches (as fake or real). Thirteen patches were incorrectly identified as fake. The pathologist was unsure of 3 fake patches. Interestingly, the fake patches that were correctly identified by the pathologist, had missing morphological features, abrupt background change, pleomorphism, and other incorrect artifacts. Our investigation shows that while certain parts of a histopathology image can be mimicked by existing GANs, the intricacies of the stained tissue and cells cannot be fully captured by them. Unlike radiology, where it is relatively easier to manipulate an image using a GAN, we argue that it is a harder challenge in digital pathology to generate an entire WSI that is fake.

Federated learning (FL) is a machine learning approach where the goal is to train a centralized model using a large number of clients that host private datasets. FL trains a smaller version of the model at each dataset site and then aggregates all the models at the server. In practice, clients (i.e., dataset holders) that participate in the learning process may possess corrupted or noisy datasets resulting in low accuracy models. Additionally, malicious clients may poison the data or carry out model discovery attacks.In this paper, we propose a refining algorithm called RefinedFed, to eliminate corrupted, low accuracy, and noisy models that can negatively impact the centralized model by reducing its accuracy or cause other malicious activities. Furthermore, RefinedFed reduces the uplink communication cost with the centralized server, which in return results in faster aggregation on the server side. Based on our preliminary experiments on the MNIST dataset, we observed that RefinedFed improved the global model accuracy from 84% to 91% while consuming less time for aggregation.

Water is one of the most essential natural resource, which is often costly and limiting input particularly in arid and Semi-arid. Since water is the life line for accruing desired yield levels, its time of application, method of application and quantity applied levels besides saving water. Further, there is a need for judicious use of water to reap the maximum benefit from this limiting resource. Off late, amongst irrigation methods, drip irrigation plays a vital role in economizing irrigation water, higher water use efficiency and enhancing crop yield in water scarce areas. Many research findings also confirm considerable saving in irrigation water through adoption of precise irrigation method like drip irrigation. The response of wheat to surface check basin and drip irrigation is reviewed.

Introduction FFRCT is a novel software for analysis of CT coronary angiographic images and aims to identify flow limiting disease non-invasively. FFRCT was introduced in our regular practice at ‘UHL’ in April 2018. This audit sought to assess the utility of FFRCT in evaluating the functional significance of all potentially flow limiting stenosis as seen on conventional CT. Methods We reviewed all cases which were sent for FFRCT analyses from April 2018 to December 2019. Patients with FFRCT values of >0.80 and Results A total of 222 cases were sent for FFRCT analysis to Heartflow. FFRCT was 0.80 in 100 patients in at least one coronary vessel. Invasive angiogram was performed in 59 of these patients, of which 50 had CTFFR 0.80. Of these, 35 patients had stents or were referred to surgery. Five of the patients that had revascularisation, had a CT FFR of >0.8. Conclusion We found that FFRCT has a valuable role in assessing the significance of moderate to severe stenosis on CTCA. Interpretation of FFRCT results needs to be made with caution and in conjunction with the CT angiographic images, as the quality of CT images may impact the accuracy of CT FFR values.

In this paper, we propose a system for large-scale image retrieval on everyday scenes with common objects by leveraging advances in deep learning and natural language processing (NLP). Unlike recent state-of-the-art approaches that extract image features from a convolutional neural network (CNN), our system exploits the predictions made by deep neural networks for image understanding tasks. Our system aims to capture the relationships between objects in an everyday scene rather than just the individual objects in the scene. It works as follows: For each image in the database, it generates most probable captions and detects objects in the image using state-of-the-art deep learning models. The captions are parsed and represented by tree structures using NLP techniques. These are stored and indexed in a database system. When a user poses a query image, its caption is generated using deep learning and parsed into its corresponding tree structures. Then an optimized tree-pattern query is constructed and executed on the database to retrieve a set of candidate images. Finally, these candidate images are ranked using the tree-edit distance metric computed on the tree structures. A query based on only objects detected in the query image can also be formulated and executed. In this case, the ranking scheme uses the probabilities of the detected objects. We evaluated the performance of our system on the Microsoft COCO dataset containing everyday scenes (with common objects) and observed that our system can outperform state-of-the-art techniques in terms of mean average precision for large-scale image retrieval.

We propose a tool called BigHASH for efficiently detecting tampering of big data programs (e.g., by malware) when executed in a private cluster or a public cloud environment. BigHASH produces the execution metadata of a program that precisely captures the critical internal data structures and content of the program (at runtime) using graph algorithms and homomorphic hashing. Homomorphic hashing provides two key benefits: (a) It enables parallel hash computation for efficiency. (b) It provides the ability to cope with cluster environments containing different number of servers when executing the program. BigHASH uses a blockchain network to store the execution metadata of programs as it provides a decentralized, secure, tamper-proof storage. To detect whether a program has been tampered or not during execution, BigHASH compares the execution metadata published by the owner (in a trusted environment) on the blockchain network to that produced by a user in his/her cluster environment. BigHASH is simple to use and provides automatic code instrumentation so that a programmer is not burdened to write any extra code to use BigHASH.

The U.S. Food and Drug Administration (FDA) has approved two digital pathology systems for primary diagnosis. These systems produce and consume whole slide images (WSIs) constructed from glass slides using advanced digital slide scanners. WSIs can greatly improve the work ow of pathologists through the development of novel image analytics software for automatic detection of cellular and morphological features and disease diagnosis using histopathology slides. However, the gigabyte size of a WSI poses a serious challenge for storage and retrieval of millions of WSIs. In this paper, we propose a system for scalable storage of WSIs and fast retrieval of image tiles using DRAM. A WSI is partitioned into tiles and sub-tiles using a combination of a space-filling curve, recursive partitioning, and Dewey numbering. They are then stored as a collection of key-value pairs in DRAM. During retrieval, a tile is fetched using key-value lookups from DRAM. Through performance evaluation on a 24-node cluster using 100 WSIs, we observed that, compared to Apache Spark, our system was three times faster to store the 100 WSIs and 1,000 times faster to access a single tile achieving millisecond latency. Such fast access to tiles is highly desirable when developing deep learning-based image analytics solutions on millions of WSIs.

Several inherited arrhythmias, including Brugada syndrome and arrhythmogenic cardiomyopathy, primarily affect the right ventricle and can lead to sudden cardiac death. Amongst many differences, right and left ventricular cardiomyocytes derive from distinct progenitors, prompting us to investigate how embryonic programming may contribute to chamber-specific conduction and arrhythmia susceptibility. Here, we show that developmental perturbation of Wnt signaling leads to chamber-specific transcriptional regulation of genes important in cardiac conduction that persists into adulthood. Transcriptional profiling of right versus left ventricles in mice deficient in Wnt transcriptional activity reveals global chamber differences, including genes regulating cardiac electrophysiology such as Gja1 and Scn5a. In addition, the transcriptional repressor Hey2, a gene associated with Brugada syndrome, is a direct target of Wnt signaling in the right ventricle only. These transcriptional changes lead to perturbed right ventricular cardiac conduction and cellular excitability. Ex vivo and in vivo stimulation of the right ventricle is sufficient to induce ventricular tachycardia in Wnt transcriptionally inactive hearts, while left ventricular stimulation has no effect. These data show that embryonic perturbation of Wnt signaling in cardiomyocytes leads to right ventricular arrhythmia susceptibility in the adult heart through chamber-specific regulation of genes regulating cellular electrophysiology.

An attempt was made to determine the seasonal evapotranspiration and crop coefficient of wheat during various growth stages under drip irrigation and N-fertigation scheduling in Jalgaon, Maharashtra during 2012-13 and 2013-14. The results revealed that grain and straw yield of wheat increased significantly at each higher levels of drip irrigation up to 1.0 Epan and fertigation of 120 kg N ha-1 in both the years. The mean daily ETc of wheat during its initial stage was found to be lower and almost constant and it increased continuously during vegetative stage, flowering and grain filling stage (4.75 mm day-1) and decreased during the maturity stage. The measured seasonal ETc of wheat was ranged from 294.5 to 453.5 mm. The highest seasonal ETc and ETc was recorded in surface check basin irrigation at IW/ CPE 1 and lowest in deficit irrigation schedule i.e. drip irrigation at 0.6 Epan. Each higher level of nitrogen from N0 to N160 slightly increased the seasonal ETc of wheat. Estimated crop coefficient values (0.71, 1.31, 1.34 and 0.76 at initial, crop development, mid season and late season stage) at 1.0 Epan through drip were slightly higher over the FAO Kc values.

322 Background: Natural language processing (NLP) algorithms can be leveraged to better understand prevailing themes in healthcare conversations. Sentiment analysis, an NLP technique to analyze and interpret sentiments from text, has been validated on Twitter in tracking natural disasters and disease outbreaks. To establish its role in healthcare discourse, we sought to explore the feasibility and accuracy of sentiment analysis on Twitter posts (‘’tweets’’) related to prior authorizations (PAs), a common occurrence in oncology built to curb payer-concerns about costs of cancer care, but which can obstruct timely and appropriate care and increase administrative burden and clinician frustration. Methods: We identified tweets related to PAs between 03/09/2021-04/29/2021 using pre-specified keywords [e.g., #priorauth etc.] and used Twarc, a command-line tool and Python library for archiving Twitter JavaScript Object Notation data. We performed sentiment analysis using two NLP models: (1) TextBlob (trained on movie reviews); and (2) VADER (trained on social media). These models provide results as polarity, a score between 0-1, and a sentiment as ‘’positive’’ (>0), ‘’neutral’’ (exactly 0), or ‘’negative’’ (