Collaborating Authors

Analyzing COVID Medical Papers with Azure Machine Learning and Text Analytics for Health


Before making this call, you need to create TextAnalyticsClient object, passing your endpoint and access key. You get those values from cognitive services/text analytics Azure resource that you need to create in your Azure Subscription through the portal or via command-line.

Analyzing COVID Medical Papers with Azure and Text Analytics for Health


The idea to apply NLP methods to scientific literature seems quite natural. First of all, scientific texts are already well-structured, they contain things like keywords, abstract, as well as well-defined terms. Thus, at the very beginning of COVID pandemic, a research challenge has been launched on Kaggle to analyze scientific papers on the subject. The dataset behind this competition is called CORD (publication), and it contains constantly updated corpus of everything that is published on topics related to COVID. Currently, it contains more than 400000 scientific papers, about half of them - with full text.

Analytics end-to-end with Azure Synapse - Azure Example Scenarios


This example scenario demonstrates how to use the extensive family of Azure Data Services to build a modern data platform capable of handling the most common data challenges in an organization. The solution described in this article combines a range of Azure services that will ingest, store, process, enrich, and serve data and insights from different sources (structured, semi-structured, unstructured, and streaming). The analytics use cases covered by the architecture are illustrated by the different data sources on the left-hand side of the diagram. Azure Synapse Link for Azure Cosmos DB enables you to run near real-time analytics over operational data in Azure Cosmos DB, by using the two analytics engines available from your Azure Synapse workspace: SQL Serverless and Spark Pools. Using either a SQL Serverless query or a Spark Pool notebook, you can access the Cosmos DB analytical store and then combine datasets from your near real-time operational data with data from your data lake or from your data warehouse.



In this walkthrough I show how an end-to-end anomaly detection system can be implemented for IoT use cases. The scenario is intentionally kept simple for illustration purposes and to allow generalizing to different scenarios in industry. The solution is built on Microsoft's Azure stack and includes multiple cloud services that allow handling data streaming, data processing, model training/predicting, and data storage. The main component here is Batch AI, a cloud service that enables users to submit parallel jobs to a cluster of high performing virtual machines. The business problem addressed in this walkthrough is: monitoring sensor measurements of multiple devices and predicting potential anomalies that might lead to failures across these devices.

Drugs4Covid: Drug-driven Knowledge Exploitation based on Scientific Publications Artificial Intelligence

In the absence of sufficient medication for COVID patients due to the increased demand, disused drugs have been employed or the doses of those available were modified by hospital pharmacists. Some evidences for the use of alternative drugs can be found in the existing scientific literature that could assist in such decisions. However, exploiting large corpus of documents in an efficient manner is not easy, since drugs may not appear explicitly related in the texts and could be mentioned under different brand names. Drugs4Covid combines word embedding techniques and semantic web technologies to enable a drug-oriented exploration of large medical literature. Drugs and diseases are identified according to the ATC classification and MeSH categories respectively. More than 60K articles and 2M paragraphs have been processed from the CORD-19 corpus with information of COVID-19, SARS, and other related coronaviruses. An open catalogue of drugs has been created and results are publicly available through a drug browser, a keyword-guided text explorer, and a knowledge graph.