IT as an Enabler for Translating Quality Research to Optimized Healthcare Delivery Luu Danh Anh Vu (Vu Luu) Country Manager for Technology Solutions IBM Vietnam (vuluu@vn.ibm.com) Growing data volume and complexity demands a new approach 44 zettabytes Sensors & Devices Medical Images Images/ Multimedia You are here Natural Language Enterprise Data 2010 2020 Tabulating Systems Era Programmable Systems Era Cognitive Computing Era 1900 – 1940s 1950s – Present 2011 – Cognitive systems expand the problems we can address Programmatic Systems • Leverage traditional data sources • Follow pre-defined rules (programs) • Provide the same output to all users Cognitive Systems • • • • • Are taught, not programmed Learn and improve based on experience Interpret sensory and non-traditional data Relate to each of us as individuals Allow us to expand and scale our own thinking Generation and Delivery of Evidence and Insights From population averages … • Scientific papers • Books • Guidelines Published Knowledge Knowledge-Driven Method Closing the translational knowledge gap To insights for individual patient! Observational Data • Longitudinal records • Claims, Rx, Labs • Patient reported data Data-Driven Method Personalized Insights from institutional data WATSON: A COGNITIVE SYSTEM Understands Watson can read & understand documents & data – both structured & unstructured – at a massive scale Reasons Watson searches & analyzes data, returning evidence-based recommendations Learns Decisions made by leading experts feed the engine Watson learns & improves over time Why Now? The Healthcare Disruption 24 months Frequency at which healthcare data doubles1 150+ exabytes Amount of healthcare data today2 $47 trillion 75%+ Estimated global economic impact of chronic disease by 20303 Percentage of patients expected to use digital health services in the future5 Sources: McKinsey&Company, Centers for Medicare and Medicaid Services, Centers for Disease Control and Prevention © 2016 International Business Machines Corporation A vast amount of untapped data could have a great impact on our health — yet it exists outside medical systems 60% Exogenous Factors 1100 Terabytes Generated per lifetime Volume, Variety, Velocity, Veracity 30% Genomics Factors 10% Clinical Factors Terabytes Per lifetime 0.4 Terabytes Per lifetime Rethinking Oncology By 2025, overall demand for medical oncology services will grow 42% The number of oncologists will likely grow by only 28% WATSON ONCOLOGY HELPS MEDICAL ONCOLOGISTS AND THEIR CARE TEAMS ADDRESS THESE CHALLENGES Use those attributes to find candidate treatment options as determined by consulting NCCN Guidelines Patient Case 61 y/o woman s/p mastectomy is here to discuss treatment options for a recently diagnosed 4.2 cm grade infiltrating ductal carcinoma… Guidelines Search a corpus of evidence data to find supporting evidence for each option Evidence Candidate Treatment Options Key Case Attributes Supportin g Evidence Watson Oncology Extract key attributes from a patient’s case Prioritized Treatment Options + Evidence Profile © 2016 International Business Machines Corporation • Inclusion / exclusion criteria • Co morbidities • Contraindications • FDA risk factors • MSK preferred treatments • Other guidelines • Published literature studies, reports, opinions from Text Books, Journals, Manuals, etc Use Watson’s analytic algorithms to prioritize treatment options based on best evidence 10 Natural Language Processing Diseases Medications Symptoms Modifiers We use Natural Language Processing and UMLS (Unified Medical Language System) CUIs (Concept Unique IDs) to recognize medical concepts Rethinking Genomic Medicine Watson Genomics Analytics Next-generation sequencing (NGS) data streams range between and 10 terabytes 800 Billion base pairs of DNA to analyze one brain tumor Molecular Profile Analysis Pathway Analysis Drug Analysis 16 partners WGA Content Pubmed Abstracts (23M) Ensembl.org TCGA Drugbank.ca NCI PID NCI Thesaurus Clinicaltrials.gov Clinvar NCI Drug Info Geneontology.org Genenames.org (HUGO) NCI Drug Dictionary COSMIC from Sanger Drugs@FDA Elsevier Gold Standards Uniprot.org dbNSNP Select whole text journal articles 13 Rethinking Clinical Trial Matching 30% of sites for clinical trials fail in enrolling even a single patient Approximately 3% of adult cancer patients participate in clinical trials 14 Watson Health - Vision IBM Watson Health // ©2015 International Business Machines Corporation #Watson Health 16 WATSON DISCOVERY ADVISOR Business challenge: • Researchers can’t innovate fast enough to create truly breakthrough therapies • They struggle to anticipate the safety profile of new treatments and design trials that demonstrate efficacy and safety Available External Data Watson solution: Making linkages that unlock insights Which accelerate breakthroughs in • Disease understanding • Drug discovery • Toxicity assessment (early safety) • Trial design • Comparative effectiveness • Pharmacovigilance (drug safety) Watson Corpus 12M+ chemical Chemical database structures Over 1TB of data Public genomics Over 40m documents Medical textbooks Over 100m entities and relationships Medline Other journals FDA drugs/labels Patents © 2014 International Business Machines Corporation 20,000+ genes 50+ books 23M+ abstracts 100+ journals 11,000+ drugs 16M+ patents 17 WATSON DISCOVERY ADVISOR: ACCELERATING BREAKTHROUGH INSIGHTS ACROSS LIFE SCIENCE FUNCTIONS Lead & Drug Discovery • What new ways could we target this disease pathway? Let’s look at all the genes identified in every disease that are activated by this protein Drug Repurposing • Does this drug have an effect on the pathway of another disease? There are several diseases where the same receptors that this compound binds to exist Safety & Toxicity Assessment • How can we quickly identify if this compound has a toxicity issue? Signals from internal toxicology reports and published studies suggest this compound may cause serious AEs Comparative Effectiveness / Clinical Trial Design • What populations are likely to benefit most from this intervention? Looking at all known studies of similar compounds, this is how this treatment might perform in these populations Pharmacovigilance • Are there reasons for the early safety signals that we can quickly identify? AE reports suggest that our drug is often being taken with dairy foods when this side effect is being reported Competitive Intelligence • What early studies of competitors reveal about their efficacy and safety? Animal models revealed early effectiveness and faster onset, differentiating from current products Reducing CHF readmission to improve care Seton Healthcare strives to reduce the occurrence of high cost Congestive Heart Failure (CHF) readmissions by proactively identifying patients likely to be readmitted on an emergency basis How? Utilizing natural language processing to extract key elements from unstructured History and Physical, Discharge Summaries, Echocardiogram Reports, and Consult Notes 21 Featured on Top predictors of Readmission Jugular Venous Distention (JVD ↑) Indicator Paid by Medicaid Indicator Immunity Disorder Disease Indicator Cardiac Rehab Admit Diagnosis with CHF Indicator Lack of Emotional Support Indicator Self COPD Moderate Limit Health History Indicator With Genitourinary System and Endocrine Disorders Heart Failure History High BNP Indicator 10 Low Hemoglobin Indicator 11 Low Sodium Level Indicator 12 Assisted Living 13 High Cholesterol History The Mt Elizabeth Novena ICU real time cognitive solution can proactively alert and prevent life threatening complications Phase Phase Treatment option based on ingested intensive care corpus and best practice Treatment guidelines decision Patient in ICU support and exposure of data to research and look at patient similarities - Physiologic monitor data - Laboratory results - Radiology results Stream computing provides real time analytical insights and notifications to nurses for critical trends Phase EMR will be pulled in using natural language processing and content analytics Watson will be able to identify risks along with streaming data to predict extended set of conditions MEDICAL SIEVE - RESEARCH Developing an image-guided informatic system to provide holistic summaries of patient conditions and evidence-based clinical decision support to radiologists The system • integrates clinical and imaging data • filters out irrelevant images using multimodal analytics • highlights disease depicting regions (anomalies) • flags coincidental diagnosis offers clinical decision support â 2016 International Business Machines Corporation https://www-03.ibm.com/press/us/en/pressrelease/48764.wss 24 ... 0.4 Terabytes Per lifetime Rethinking Oncology By 2025, overall demand for medical oncology services will grow 42% The number of oncologists will likely grow by only 28% WATSON ONCOLOGY HELPS... readmissions by proactively identifying patients likely to be readmitted on an emergency basis How? Utilizing natural language processing to extract key elements from unstructured History and Physical,... Safety & Toxicity Assessment • How can we quickly identify if this compound has a toxicity issue? Signals from internal toxicology reports and published studies suggest this compound may cause