Summary: In genetics, many evolutionary pathways can be modeled by the ordered accumulation of permanent changes. Mixture models of mutagenetic trees have been used to describe disease progression in cancer and in HIV. In cancer, progression is modeled by the accumulation of chromosomal gains and losses in tumor cells; in HIV, the accumulation of drug resistance-associated mutations in the viral genome is known to be associated with disease progression. From such evolutionary models, genetic progression scores can be derived that assign measures for the disease state to single patients. Rtreemix is an R package for estimating mixture models of evolutionary pathways from observed cross-sectional data and for estimating associated genetic progression scores. The package also provides extended functionality for estimating confidence intervals for estimated model parameters and for evaluating the stability of the estimated evolutionary mixture models. Availability: Rtreemix is an R package that is freely available from the Bioconductor project at http://www.bioconductor.org and runs on Linux and Windows. Contact: jasmina@mpi-inf.mpg.de
Medical imaging is crucial for diagnosing, monitoring, and treating medical conditions. The medical reports of radiology images are the primary medium through which medical professionals can attest to their findings, but their writing is time-consuming and requires specialized clinical expertise. Therefore, the automated generation of radiography reports has the potential to improve and standardize patient care and significantly reduce the workload of clinicians. Through our work, we have designed and evaluated an end-to-end transformer-based method to generate accurate and factually complete radiology reports for X-ray images. Additionally, we are the first to introduce curriculum learning for end-to-end transformers in medical imaging and demonstrate its impact in obtaining improved performance. The experiments were conducted using the MIMIC-CXR-JPG database, the largest available chest X-ray dataset. The results obtained are comparable with the current state of the art on the natural language generation (NLG) metrics BLEU and ROUGE-L, while setting new state-of-the-art results on F1 examples-averaged F1-macro and F1-micro metrics for clinical accuracy and on the METEOR metric widely used for NLG.
Introduction: A major hurdle to HIV-1 eradication is the establishment of a latent viral reservoir early after primary infection. Several factors are known to influence the HIV-1 reservoir size and decay rate on suppressive antiretroviral treatment (ART), but little is known about the role of human genetic variation. Methods: We measured the reservoir size at three time points over a median of 5.4 years, and searched for associations between human genetic variation and two phenotypic readouts: the reservoir size at the first time point and its decay rate over the study period. We assessed the contribution of common genetic variants using genome-wide genotyping data from 797 patients with European ancestry enrolled in the Swiss HIV Cohort Study and searched for a potential impact of rare variants and exonic copy number variants using exome sequencing data generated in a subset of 194 study participants. Results: Genome- and exome-wide analyses did not reveal any significant association with the size of the HIV-1 reservoir or its decay rate on suppressive ART. Conclusions: Our results point to a limited influence of human genetics on the size of the HIV-1 reservoir and its long-term dynamics in successfully treated individuals.
1 February 2021 in INFORMS Journal on Applied Analytics
IBM has deployed its Predictive Analytics for Server Incident Reduction (PASIR) solution to more than 360 information technology (IT) environments worldwide since 2013. These environments, covering sectors from banking to travel to e-commerce, are serviced by IBM support groups. Incidents occurring on servers, including problem descriptions and resolutions, are documented in client account-specific ticket management systems. PASIR uses machine learning to classify the incident tickets within an IT environment and identify high-impact incidents that involve server outages by using the respective ticket descriptions and resolutions. It then correlates these high-impact tickets with server properties and utilization measurements to identify problematic server configurations. Finally, for such configurations, PASIR uses statistical multivariate analysis and simulation methods to prescribe improvement and modernization actions. In this paper, we present the results achieved from deploying this solution. We describe the PASIR approach, from ticket classification to the recommendations of remediation actions (e.g., hardware and software upgrades). We demonstrate the model’s effectiveness by comparing predictions on the impact of prescriptive actions with actual system improvements. Since 2013, we have applied PASIR to more than 840,000 client servers, resulting in more precise upgrade spending and environmental stability, thus saving our clients an estimated $7 billion.
Neural approaches have become very popular in the domain of Question Answering, however they require a large amount of annotated data. Furthermore, they often yield very good performance but only in the domain they were trained on. In this work we propose a novel approach that combines data augmentation via question-answer generation with Active Learning to improve performance in low resource settings, where the target domains are diverse in terms of difficulty and similarity to the source domain. We also investigate Active Learning for question answering in different stages, overall reducing the annotation effort of humans. For this purpose, we consider target domains in realistic settings, with an extremely low amount of annotated samples but with many unlabeled documents, which we assume can be obtained with little effort. Additionally, we assume sufficient amount of labeled data from the source domain is available. We perform extensive experiments to find the best setup for incorporating domain experts. Our findings show that our novel approach, where humans are incorporated as early as possible in the process, boosts performance in the low-resource, domain-specific setting, allowing for low-labeling-effort question answering systems in new, specialized domains. They further demonstrate how human annotation affects the performance of QA depending on the stage it is performed.