IBM Watson

IBM Watson

·    Watson is a question-answering computer system capable of answering questions posed in natural language, developed in IBM's DeepQA project by a research team led by principal investigator David Ferrucci.

·    Watson was named after IBM's first CEO, industrialist Thomas J. Watson.

·    Watson was created as a question answering (QA) computing system that IBM built to apply advanced natural language processing, information retrieval, knowledge representation, automated reasoning, and machine learning technologies to the field of open domain question answering.

·    The key difference between QA technology and document search is that document search takes a keyword query and returns a list of documents, ranked in order of relevance to the query (often based on popularity and page ranking), while QA technology takes a question expressed in natural language, seeks to understand it in much greater detail, and returns a precise answer to the question.

·    In recent years, the Watson capabilities have been extended and the way in which Watson works has been changed to take advantage of new deployment models (Watson on IBM Cloud) and evolved machine learning capabilities and optimized hardware available to developers and researchers.

·    It is no longer purely a question answering (QA) computing system designed from Q&A pairs but can now 'see', 'hear', 'read', 'talk', 'taste', 'interpret', 'learn' and 'recommend'.





Software
·         Watson uses IBM's DeepQA software and the Apache UIMA (Unstructured Information Management Architecture) framework implementation.
·         The system was written in various languages, including Java, C++, and Prolog, and runs on the SUSE Linux Enterprise Server 11 operating system using the Apache Hadoop framework to provide distributed computing
Hardware
·         The system is workload-optimized, integrating massively parallel POWER7 processors and built on IBM's DeepQA technology, which it uses to generate hypotheses, gather massive evidence, and analyze data.
·         Watson employs a cluster of ninety IBM Power 750 servers, each of which uses a 3.5 GHz POWER7 eight-core processor, with four threads per core. In total, the system has 2,880 POWER7 processor threads and 16 terabytes of RAM.
·         Watson can process 500 gigabytes, the equivalent of a million books, per second.
Data
·         The sources of information for Watson include encyclopedias, dictionaries, thesauri, newswire articles, and literary works.
·         Watson also used databases, taxonomies, and ontologies. Specifically, DBPedia, WordNet, and Yago were used.
·         The IBM team provided Watson with millions of documents, including dictionaries, encyclopedias, and other reference material that it could use to build its knowledge.
Clinical Applications

·         In January 2018, the Annals of Oncology published a study by Manipal Hospitals that found Watson for Oncology was concordant with the hospital’s multidisciplinary tumor board in 93 percent of breast cancer treatment decisions.

·         In November 2017, Acta Neuropathologica published a study by Barrow Neurological Institute that found Watson for Drug Discovery had successfully identified 5 RNA-binding proteins that had never before been associated with ALS.

·         In November 2017, the journal The Oncologist published an important study led by oncologists at the University of North Carolina’s Lineberger Comprehensive Cancer Center, who tested Watson for Genomics on 1,018 retrospective patient cases. More than 99 percent of the time, Watson agreed with the physicians, but in more than 300 cases, Watson found clinically actionable therapeutic options that the physicians had not identified.

·         In July 2017, Neurology Genetics published a study that found Watson for Genomics accurately interpreted whole genome sequencing data for a glioblastoma patient in 10 minutes vs. 160 expert human hours.

·         In June 2018, Mayo Clinic physicians presented a poster presentation at the ASCO Annual Meeting, reporting that Watson for Clinical Trial Matching boosted enrollment in breast cancer trials by 80% following implementation (to 6.3 patients/month, up from 3.5 patients/month in the immediate 18 months prior). Furthermore, enrollment was increased to 8.1 patients/month when including accruals to phase I trials with breast cancer cohorts in the experimental therapeutics program.

·         In June 2018, new data presented by Medtronic demonstrated the utility of Sugar.IQ in a real-world setting (Abstract: Real-World Assessment of Sugar.IQ with Watson—A Cognitive Computing-Based Diabetes Management Solution). The study found that people with diabetes using the Sugar.IQ app spent 36 more minutes per day in healthy glucose range compared to before they used the app. This included 30 minutes less time in hyperglycemia (>180 mg/dL) and 6 minutes less time in hypoglycemia
 

Comments

Post a Comment

Popular posts from this blog

Implementing Interoperability of Antimicrobial Resistance System

Image
Topic: Implementing Interoperability of Antimicrobial Resistance System This topic was discussed in the open spaces and the topic’s owner was Mauro Tubin. It was quite an interactive session.   The importance of Implementing an Interoperable Antimicrobial Resistance system was discussed, how they were getting about with it and the challenges they face. Accurate estimates of the burden of antimicrobial resistance (AMR) are needed to establish the magnitude of this global threat in terms of both health and cost, and to paramaterise cost-effectiveness evaluations of interventions aiming to tackle the problem. Antimicrobial resistance (AMR) is the ability of a microorganism to stop an antimicrobial from working against it. As a result, standard treatments become ineffective, infections persist and may spread to others. There should be a surveillance to get the specific data. The data needs to be mobilized regarding patients (testing and diagnostics), animals and fo...
Read more

Blockchains

Image
Blockchains What is a blockchain?  ▪A growing list of records, called  blocks , which are linked sing cryptography ▪Each block contains a cryptographic hash of the previous lock, timestamp, and transaction data ▪Invented by Satoshi Nakamoto in 2008 to serve as the public transaction ledger of the cryptocurrency bitcoin ▪Three main components: a distributed network, a shared ledger and digital transactions  Characteristics of a blockchain ▪       An open, distributed ledger that can record transactions between two parties efficiently and in a verifiable and permanent way ▪       Is resistant to modification of the data ▪       Once recorded, the data in any given block cannot be altered retroactively without alteration of all subsequent blocks Uses of blockchain ▪       Cryp...
Read more
10 COMMON APPLICATIONS OF ARTIFICIAL INTELLIGENCE IN HEALTHCARE According to a 2016 report from CB Insights, about 86% of healthcare provider organizations, life science companies, and technology vendors to healthcare are using artificial intelligence technology. By 2020, these organizations will spend an average of $54 million on artificial intelligence projects.  So what solutions are they most commonly implementing? Here are 10 common ways AI is changing healthcare now and will in the future. 1. Managing Medical Records and Other Data            Since the first step in health care is compiling and analyzing information (like medical records and other past history), data management is the most widely used application of artificial intelligence and digital automation. Robots collect, store, re-format, and trace data to provide faster, more consistent access. 2. Doing Repetitive Jobs          ...
Read more