Skip to main content
UploadLanguage (EN)Support
BusinessMobileSocial MediaMarketingTechnologyArt & PhotosCareerDesignEducationPresentations & Public SpeakingGovernment & NonprofitHealthcareInternetLawLeadership & ManagementAutomotiveEngineeringSoftwareRecruiting & HRRetailSalesServicesScienceSmall Business & EntrepreneurshipFoodEnvironmentEconomy & FinanceData & AnalyticsInvestor RelationsSportsSpiritualNews & PoliticsTravelSelf ImprovementReal EstateEntertainment & HumorHealth & MedicineDevices & HardwareLifestyle
GN
Uploaded byGanesan Narayanasamy
1,126 views

AI in healthcare - Use Cases

The document discusses the integration of artificial intelligence (AI) in healthcare, emphasizing the rapid advancement of AI technologies and their transformative potential across various medical fields such as genomics, diagnostics, and imaging. It highlights the challenges faced by healthcare institutions, including data overload, application chaos, and cost management, while outlining a framework for AI implementation that leverages high-performance computing and cloud infrastructure. Ultimately, the document stresses the importance of modernizing data analysis processes to enhance patient care and operational efficiency in the healthcare sector.

Technology◦
Downloaded 78 times
Powering Up AI in Healthcare Clarisse Taaffe-Hedglin Executive IT Architect IBM Garage IBM Systems clarisse@us.ibm.com
Agenda Healthcare Use cases The AI Ladder and Lifecycle AI at Scale Themes
“AI is the fastest-growing workload”* 3 *Forrester Research Inc. “AI Deep Learning Workloads Demand a New Approach to Infrastructure”, by Mike Gualtieri, Christopher Voce, Srividya Sridharan, Michele Goetz, Renee Taylor, May 4, 2018. 3 IBM IT Infrastructure / © 2021 IBM Corporation
Machine Learning Context REINFORCEMENT LEARNING TRANSFER LEARNING “AI is the automation of automation” – Jensen Huang, GCG 2020
5 Analytics Modernization: From Data to Actions 010101010101010111100010011001010111 0000000000010101010100000000000 111101011 11000 000000000000 111111 010101 101010 10101010100 Prescriptive What should we do ? Descriptive What Has Happened? Cognitive Learn Dynamically Predictive What Will Happen? ACTION DATA HUMAN INPUTS < < > < > > > delivering faster insights with greater efficiency to impact more lives
A framework for designing, deploying, growing and optimizing infrastructure for HPC, AI and Cloud, created in collaboration with world’s leading healthcare and life sciences institutions, and using Red Hat OpenShift, IBM Power Systems, IBM Storage and open API endpoints. From Data to Insight with an Optimal Reference Architecture DATAHUB High Performance Data Fabric & Catalog Capable of Handling Exabytes of Data and Trillions of Objects ORCHESTRATION High Performance Computing & AI Platform Capable of Orchestrating Thousands of Servers and GPUs APPS & MODELS Large-scale and high-throughput workloads such as HPC, AI and Cloud computing MEDICAL TASKS Genomics, molecular simulation, structural analysis, diagnostics, data fusion, manufacturing quality inspection.
Three broad categories of AI Use Cases “Structured” Data Use Cases Computer Vision Use Cases - Big Data (Rows and Columns) - Available AI Software More Accuracy ! This is sort of “Magic” - a deep learning Model is trained to detect and classify objects Natural Language Processing Use Cases - A Model learns to read, hear and “understand” language
§ BIG, COMPLEX SYSTEMS § PERSONALIZATION § AUTOMATION § SIMULATING RELATIONSHIPS § VISUAL RECOGNITION § PATTERN DETECTION § CHATBOTS § DESIGN OF EXPERIMENTS § OPTIMIZATION Thescenarios AIcansolvefor today 8 IBM IT Infrastructure / © 2021 IBM Corporation
Addressable Markets And Fields For AI RETAIL Recommendation engines, Precision marketing AGRICULTURE Crop yield, Plant disease, Remote sensing LIFE SCIENCES Sequence Analysis, Radiology UTILITIES Smart Meter analysis, Capacity planning $ FINANCIAL SERVICES Risk analysis Fraud detection CUSTOMER SERVICE Chatbots, Helpdesk, Automated Expenses LAW & DEFENSE Threat analysis - social media monitoring RESEARCH Physics Modeling Simulation optimization TRANSPORTATION Optimal traffic flows, Route planning CONSUMER GOODS Sentiment analysis HEALTH CARE Patient sensors, monitoring, EHRs MEDIA/ENTERTAINMENT Advertising effectiveness OIL & GAS Exploration, Sensor analysis AUTOMOTIVE ADAS, Maintenance MANUFACTURING Line inspection, Defect analysis AI and Autonomous Machine Learning will help revolutionized every single industry making us more productive and efficient to do things that today are impossible to do. 9 IBM IT Infrastructure / © 2021 IBM Corporation
10 Smart loves problems, and there has never been a bigger problem facing our world. Biomolecular Structure Molecular Simulation Genomics Medical Diagnostics AI Data Fusion and AI Bio-Informatics Artificial intelligence and high-performance computing have already begun to attack the virus, assisting in molecular drug discovery, genomics and medical image processing.
Data Overload Oceans of data arise from rapid digitization and instrumentation of healthcare. App Chaos Thousands of applications, workflows and models are not all following the same rules. Adoption Vertically integrated toolsets with heavy customization and vendor lock- in create work silos. Performance When scaling up or out, most institutions cannot diagnose or analyze the performance problems they face. Cost Demanding workloads require well- orchestrated infrastructure to manage, monitor and control costs. Five key challenges to progress remain despite advances
Data Insight HPC Analysis & Simulation AI Inference & Automation Sensors The Convergence of HPC and AI 12 IBM IT Infrastructure / © 2021 IBM Corporation
Optimizing Medical Imaging Enhance image identification with deep learning to assist physicians and benefit patients 1300 MRI images trained by IBM Power Systems and IBM Storage in just two hours, compared to forty hours on traditional architectures
97% Accuracy for Melanoma Detection for Dermoscopic Images Melanoma vs. Atypical & Benign Human* Deep Features Ensembles CNN DRN Doctor/ Expert ImageNet + Sparse Coding + Low-level + Auto- Encoder Deep Learning Deep Residual Learning 0.84 0.91 0.92 0.93 0.94 0.95 0.97 - 0.73 0.73 0.74 0.77 - - * Estimated human expert performance Use Case Automatic skin lesion image analysis for melanoma detection with Memorial Sloan Kettering (MSK-CC) Visual modeling techniques: § Deep Residual Networks § Conv. Neural Networks § Ensemble Models Top Performance = 97% Accuracy!!! Melanoma vs. Atypical Best 14 Think 2020 / DOC ID / Month XX, 2020 / © 2020 IBM Corporation
15 Advances in instrument design, sample preprocessing and mathematical methods have enabled high volume throughput imaging at atomic scale. Cryogenic electron microscopes generate an average of 5 TB of image data per day BIOMOLECULAR STRUCTURE Massive Data Sets Require Massive Processing Capability
Accelerating Cryo-EM Imaging Analysis Reduced time-to-completion for high resolution image analysis jobs while increasing resource utilization Using IBM AC922 cluster, more than 100 cryo-EM high resolution image workload analysis jobs running in parallel on Satori cluster BIOMOLECULAR STRUCTURE
Simulation of millions of atoms requiring large computational resources Large scale simulation includes millions of atoms • Virus molecules • Ribosomes • Bioenergy system and complex Solution • High performance computing CPU and GPUs accelerating performance • Optimal memory and network bandwidths scaling performance to hundreds of nodes • Techniques to reduce number of simulations Receptor ligand Virus molecule simulation Receptor-ligand fit Cryptic binding site prediction Binding energy prediction MOLECULAR SIMULATION
Molecular Dynamics Simulation Computational Intensity A) Using NAMD to simulate influenza B) virus (left)and Covid-19 (right) B) Drug discovery: protein receptor C) In silico prediction of protein cryptic binding site D) Predicting protein receptor ligand binding energy Receptor ligand Large scale simulation includes millions of atoms • Virus molecules • Ribosomes • Bioenergy system and complex Solution • High performance computing CPU and GPUs accelerating performance • Optimal memory and network bandwidths scaling performance to hundreds of nodes • Techniques to reduce number of simulations
Bayesian optimization accelerated workflow uses 1/3 of the calculations to achieve 4 orders of magnitude resolution increase Optimizing Molecular Modeling Achieves human level performance in days instead of months. Accelerated Force Field Tuning Intelligent Phase Diagram Exploration
Faster Better Cheaper BOA accelerates time to insight, time to value, and time to design by factors Example: IBM EDA ->100x faster than brute force BOA can find new and unknown optima in a design space because of its lack of bias and exploration algorithm Example: Infineon – 3x faster than other methods and 4 orders of magnitude better resolution Nothing is cheaper than a simulation which is never run. BOA prevents unnecessary work which reduces all kinds of costs Example: GlaxoSmithKline – reduced their screen workload from 20k experiments to 200 IBM BOA Bayesian Optimization Value 0 200 400 600 800 BOA Greedy Similarity Diversity count Search Method Comparison Drug Discovery Case - Single Objective All Data / Ties removed Conclusion: >80% of the time IBM BOA is the best method with the least regret
Optimizing Precision Genomics Reduced time-to-completion for long-running jobs while increasing resource utilization Using IBM, Sidra has completed hundreds of thousands of computing tasks comprising millions of files and directories, without experiencing system downtime.
COLLECT - Make data simple and accessible ORGANIZE - Create a trusted analytics foundation ANALYZE - Scale AI everywhere with trust & transparency Data of every type, regardless of where it lives MODERNIZE your data estate for an AI and hybrid multicloud world INFUSE – Operationalize AI across business processes The AI Ladder A prescriptive approach to accelerating the journey to AI AI AI-optimized systems infrastructure 22 IBM IT Infrastructure / © 2021 IBM Corporation
The Data: Biological Data Analytics Biological Data Analysis Biomarker Identification Biodata modeling and Statistical Analysis Biodata Visualization Medical Images Data analysis Structural Bioinformatics Genomics Sequence data analysis Biological Data Analytics q Genomic Sequence Data: an explosive growth of biodata q Sequence alignment q Variant discovery and characterization q Genomic profiling and pattern discovery q Biomarker Identification: gene expression profile, RNA-seq, ChIP- seq, microarray identification and validation, etc. q Structural Bioinformatics: identify and predict 3D biomolecule structures, such Cryo-EM data refinement, molecular dynamic simulation, NMR, x-Ray crystallographic data, etc. q Biodata Modeling & Statistical Analysis: biological pathways analysis, Gene, clinical data cohorts study, data extraction, etc. q Medical Image Processing: image segmentation, registration, statistic modeling. q Biodata Visualization: 3D molecule structures, genomics sequences visualization, etc. Ruzhu Chen @ 2019
High performance and high throughput storage hierarchy required for data loading, extraction and computation. Tertiary storage required for archive and store. Storage tools for data indexing, discovery and governance. Computation High performance and efficiency of software tools and applications for genomic variants and biomarkers analysis, drug discovery, medical image processing and molecule structure modeling, data visualization. High throughput and optimized workload pipelines to accelerate biodata analysis with highly optimal and parallel I/O, memory, CPU and GPU computations. Solutions Large volume and variety of data around genomic sequences, gene expression, images, structural biomolecules, clinical and healthcare information, personized medicine data Data Storage The Challenges: Analyzing Explosive biological data Data Explosion Ruzhu Chen @ 2019
Data Pipeline for AI in Healthcare Insights Out Trained Models, simulations Inference Data In Transient Storage SDS/Cloud Global Ingest Throughput-oriented, globally accessible Cloud ETL High throughput, Random I/O, SSD/Hybrid Archive High scalability, large/sequential I/O HDD Cloud Tape Hadoop / Spark Data Lakes Throughput-oriented Hybrid/HDD ML / DL Prep ⇨ Training ⇨ Inference High throughput, low latency, Random I/O SSD/NVMe Classification & Metadata Tagging High volume, index & auto-tagging zone Fast Ingest / Real-time Analytics High throughput SSD Throughput-oriented, software defined temporary landing zone capacity tier performance tier performance & capacity Tier performance & capacity Tier performance tier capacity tier Fits Traditional and New Use Cases EDGE COLLECT ORGANIZE ANALYZE INSIGHTS INFUSE IBM Spectrum Scale / Storage for AI / © 2020 IBM Corporation
Public data Anything data system can pull from the outside world for free through web connections, databases, IoT and sensors Proprietary data What private data from the outside world could the system be given permission to use? Purchased data What pre-trained data could the system buy or subscribe to? IBM Skills Academy / © Copyright 2018 IBM Corporation Ground truth Data used to define what the system knows from day one Domain knowledge Data resources that can be used to teach the system to understand and be an expert in a particular field Private data Unique data the creator owns and only shares internally Personal public data What unique data does the creator share with the outside world? Transaction and application data Machine, sensor data Enterprise content Image, geospatial, video Social data Third-party data Available Data Sources
2 June 2021/ © 2018 IBM Corporation • Metadata is the structured data about the unstructured object • Who, what, when, where, and why of account, container, object, stream, dir, file • Perfect for indexing and searching • Metadata may be separate from the data, stored with the data, or derived from the data • Posix inode plus extended attributes • Standard document headers (doc, ppt, mp3, dicom, pdf, jpeg, GeoTIFF) • Custom metadata tags • AI derived metadata Age, Biomarkers, Developmental Stage, Cell Surface, Markers, Cell Type/Cell Line, Disease State, Extract Molecule, Genetic Characteristics, Immunoprecipitation, antibody, Organism Biomedical Natural Language Processing Image Location Size Owner Group Permissions Last-Modified ... System Metadata Where is the data?
Metadata-Fueled Data Analysis Large Scale Data Ingest • Scan records at high speed • Live event notifications • Capture system-level tags • Automatic indexing Business-Oriented Data Mapping • Custom data tagging • Content-inspection via APIs • Policy-driven workflows Data Activation • Data movement via APIs • Extensible architecture • Solution Blueprints Data Visualization • Query billions of records in seconds • Multi-faceted search • Drilldown dashboard • Customizable reports
Common AI Data Considerations Data Compute Legacy Data Stores IoT, Mobile & Sensors Collaboration Partners New Data Ingest Inference Training Preparation Iterative Model training to improve accuracy Champion Challenge r -”Data Center” - At Edge Trained Model § Ease to Massively Scale § High Performance § Tiered / Archive § Secure § High Performance § Metadata Tagging § Single Name Space Low Latency Dev & Inference Stack - Open Source - Stable and Supported - Auditable Productivity Performance Robustness Considerations
• Ease of use • Optimize resources • Scale workload AI Frameworks / Open-Source Libraries AI Tools and Applications AI Software Landscape AI Infrastructure 30 IBM IT Infrastructure / © 2021 IBM Corporation
Anaconda Environment for Applications • Use anaconda enterprise network (AEN) to manage cryo-EM software repository on server. • Easy to use and update software Anaconda Architecture for Cryo-EM Analysis Computation Web Interface Repo Install Software Control Authentication Anaconda Server Compute Nodes Database Users
Anaconda Environment for Applications • Use anaconda enterprise network (AEN) to manage cryo-EM software repository on server. • Easy to use and update software Anaconda Architecture for Cryo-EM Analysis Computation Web Interface Repo Install Software Control Authentication Anaconda Server Compute Nodes Database Users
OpenPOWER is a technical community dedicated to expanding the the IBM Power architecture ecosystem https://github.com/open-ce Open-CE Minimize time to value for foundational ML/DL packages Provide a flexible source-to-image solution to provide a complete and customizable AI environment.
Fairness Explainability Adversarial Robustness Transparency Is it fair? Is it easy to understand? Is it secure? Is it accountable? Pillars of Trusted AI 34 IBM IT Infrastructure / © 2021 IBM Corporation
Thank You