Neurodegenerative diseases are chronic debilitating conditions, characterized by progressive loss of neurons that represent a significant health care burden as the global elderly population continues to grow. Over the past decade, high-throughput technologies such as the Affymetrix GeneChip microarrays have provided new perspectives into the pathomechanisms underlying neurodegeneration. Public transcriptomic data repositories, namely Gene Expression Omnibus and curated ArrayExpress, enable researchers to conduct integrative meta-analysis; increasing the power to detect differentially regulated genes in disease and explore patterns of gene dysregulation across biologically related studies. The reliability of retrospective, large-scale integrative analyses depends on an appropriate combination of related datasets, in turn requiring detailed meta-annotations capturing the experimental setup. In most cases, we observe huge variation in compliance to defined standards for submitted metadata in public databases. Much of the information to complete, or refine meta-annotations are distributed in the associated publications. For example, tissue preparation or comorbidity information is frequently described in an article’s supplementary tables. Several value-added databases have employed additional manual efforts to overcome this limitation. However, none of these databases explicate annotations that distinguish human and animal models in neurodegeneration context. Therefore, adopting a more specific disease focus, in combination with dedicated disease ontologies, will better empower the selection of comparable studies with refined annotations to address the research question at hand. In this article, we describe the detailed development of NeuroTransDB, a manually curated database containing metadata annotations for neurodegenerative studies. The database contains more than 20 dimensions of metadata annotations within 31 mouse, 5 rat and 45 human studies, defined in collaboration with domain disease experts. We elucidate the step-by-step guidelines used to critically prioritize studies from public archives and their metadata curation and discuss the key challenges encountered. Curated metadata for Alzheimer’s disease gene expression studies are available for download. Database URL: www.scai.fraunhofer.de/NeuroTransDB.html

PICO recognition is an information extraction task for detecting parts of text describing Participant (P), Intervention (I), Comparator (C), and Outcome (O) (PICO elements) in clinical trial literature. Each PICO description is further decomposed into finer semantic units. For example, in the sentence 'The study involved 242 adult men with back pain.', the phrase '242 adult men with back pain' describes the participant, but this coarse-grained description is further divided into finer semantic units. The term '242' shows "sample size" of the participants, 'adult' shows "age", 'men' shows "sex", and 'back pain' show the participant "condition". Recognizing these fine-grained PICO entities in health literature is a challenging named-entity recognition (NER) task but it can help to fully automate systematic reviews (SR). Previous approaches concentrated on coarse-grained PICO recognition but focus on the fine-grained recognition still lacks. We revisit the previously unfruitful neural approaches to improve recognition performance for the fine-grained entities. In this paper, we test the feasibility and quality of multitask learning (MTL) to improve fine-grained PICO recognition using a related auxiliary task and compare it with single-task learning (STL). As a consequence, our end-to-end neural approach improves the state-of-the-art (SOTA) F1 score from 0.45 to 0.54 for the "participant" entity and from 0.48 to 0.57 for the "outcome" entity without any handcrafted features. We inspect the models to identify where they fail and how some of these failures are linked to the current benchmark data.

No abstract

2 Gleason score 3+4 Gleason grade: a) Primary pattern 3/5 b) Secondary pattern 4/5 a) Total Gleason score 7/10 Swillens, J. E. M., et al. "Identification of barriers and facilitators in nationwide implementation of standardized structured reporting in pathology: a mixed method study." Snoek, Annefleure, et al. "The impact of standardized structured reporting of pathology reports for breast cancer in the Netherlands.

Medical imaging research has long suffered problems getting access to large collections of images due to privacy constraints and to high costs that annotating images by physicians causes. With public scientific challenges and funding agencies fostering data sharing, repositories, particularly on cancer research in the US, are becoming available. Still, data and annotations are most often available on narrow domains and specific tasks. The medical literature (particularly articles contained in MedLine) has been used for research for many years as it contains a large amount of medical knowledge. Most analyses have focused on text, for example creating semi-automated systematic reviews, aggregating content on specific genes and their functions, or allowing for information retrieval to access specific content. The amount of research on images from the medical literature has been more limited, as MedLine abstracts are available publicly but no images are included. With PubMed Central, all the biomedical open access literature has become accessible for analysis, with images and text in structured format. This makes the use of such data easier than extracting it from PDF. This article reviews existing work on analyzing images from the biomedical literature and develops ideas on how such images can become useful and usable for a variety of tasks, including finding visual evidence for rare or unusual cases. These resources offer possibilities to train machine learning tools, increasing the diversity of available data and thus possibly the robustness of the classifiers. Examples with histopathology data available on Twitter already show promising possibilities. This article add links to other sources that are accessible, for example via the ImageCLEF challenges.

PICO recognition is an information extraction task for identifying participant, intervention, comparator, and outcome information from clinical literature. Manually identifying PICO information is the most time-consuming step for conducting systematic reviews (SR), which is already labor-intensive. A lack of diversified and large, annotated corpora restricts innovation and adoption of automated PICO recognition systems. The largest-available PICO entity/span corpus is manually annotated which is too expensive for a majority of the scientific community. To break through the bottleneck, we propose DISTANT-CTO, a novel distantly supervised PICO entity extraction approach using the clinical trials literature, to generate a massive weakly-labeled dataset with more than a million "Intervention" and "Comparator" entity annotations. We train distant NER (namedentity recognition) models using this weaklylabeled dataset and demonstrate that it outperforms even the sophisticated models trained on the manually annotated dataset with a 2% F1 improvement over the Intervention entity of the PICO benchmark and more than 5% improvement when combined with the manually annotated dataset. We investigate the generalizability of our approach and gain an impressive F1 score on another domain-specific PICO benchmark. The approach is not only zero-cost but is also scalable for a constant stream of PICO entity annotations.

Objective The aim of this study was to test the feasibility of PICO (participants, interventions, comparators, outcomes) entity extraction using weak supervision and natural language processing. Methodology We re-purpose more than 127 medical and nonmedical ontologies and expert-generated rules to obtain multiple noisy labels for PICO entities in the evidence-based medicine (EBM)-PICO corpus. These noisy labels are aggregated using simple majority voting and generative modeling to get consensus labels. The resulting probabilistic labels are used as weak signals to train a weakly supervised (WS) discriminative model and observe performance changes. We explore mistakes in the EBM-PICO that could have led to inaccurate evaluation of previous automation methods. Results In total, 4081 randomized clinical trials were weakly labeled to train the WS models and compared against full supervision. The models were separately trained for PICO entities and evaluated on the EBM-PICO test set. A WS approach combining ontologies and expert-generated rules outperformed full supervision for the participant entity by 1.71% macro-F1. Error analysis on the EBM-PICO subset revealed 18–23% erroneous token classifications. Discussion Automatic PICO entity extraction accelerates the writing of clinical systematic reviews that commonly use PICO information to filter health evidence. However, PICO extends to more entities—PICOS (S—study type and design), PICOC (C—context), and PICOT (T—timeframe) for which labelled datasets are unavailable. In such cases, the ability to use weak supervision overcomes the expensive annotation bottleneck. Conclusions We show the feasibility of WS PICO entity extraction using freely available ontologies and heuristics without manually annotated data. Weak supervision has encouraging performance compared to full supervision but requires careful design to outperform it.

Risk of bias (RoB) assessment of randomized clinical trials (RCTs) is vital to conducting systematic reviews. Manual RoB assessment for hundreds of RCTs is a cognitively demanding, lengthy process and is prone to subjective judgment. Supervised machine learning (ML) can help to accelerate this process but requires a hand-labelled corpus. There are currently no RoB annotation guidelines for randomized clinical trials or annotated corpora. In this pilot project, we test the practicality of directly using the revised Cochrane RoB 2.0 guidelines for developing an RoB annotated corpus using a novel multi-level annotation scheme. We report inter-annotator agreement among four annotators who used Cochrane RoB 2.0 guidelines. The agreement ranges between 0% for some bias classes and 76% for others. Finally, we discuss the shortcomings of this direct translation of annotation guidelines and scheme and suggest approaches to improve them to obtain an RoB annotated corpus suitable for ML.