
REGISTRATION

WELCOME
DEEP LEARNING IN HEALTHCARE: AN INTRODUCTION
Amir Tahmasebi - Enlitic
Natural Language Processing for Healthcare
With recent advancements in Deep Learning followed by successful deployment in natural language processing (NLP) applications such as language understanding, modeling, and translation, the general hope was to achieve yet another success in healthcare domain. Given the vast amount of healthcare data captured in Electronic Medical Records (EMR) in an unstructured fashion, there is an immediate high demand for NLP to facilitate automatic extraction and structuring of clinical data for decision support. Nevertheless, the performance of off-the-shelf NLP on healthcare data has been disappointing. Recently, tremendous efforts have been dedicated by NLP research pioneers to adapt general language NLP for healthcare domain. This talk aims to review current challenges researchers face, and furthermore, reviews some of the most recent success stories.
3 Key Takeaways:
*General overview of state-of-the-art NLP
*How to build a domain-specific NLP pipeline for life science applications
*Review of a few successful applications of NLP in life sciences and how the future will/should look
Amir Tahmasebi is the director of Deep Learning at Enlitic, San Francisco, CA. Before joining Enlitic, Amir was the senior director of Machine Learning and AI at CODAMETRIX, Boston, MA. He also served as a lecturer at MIT, Northeastern University, Boston University, and Columbia University. Prior to CODAMETRIX, Dr. Tahmasebi was a Principal Research Engineer at PHILIPS HealthTech, Cambridge, MA. Dr. Tahmasebi’s research is focused on innovating computer vision and natural language processing solutions for patient clinical context extraction and modeling, clinical outcome analytics and clinical decision support. Dr. Tahmasebi received his PhD degree in Computer Science from the School of Computing, Queen's University, Canada. He is the recipient of the IEEE Best PhD Thesis award and Tanenbaum Post-doctoral Research Fellowship award. He has been serving as area chair for MICCAI and IPCAI conferences. Dr. Tahmasebi has published and presented his work in a number of conferences and journals including NeurIPS, NAACL, MICCAI, IPCAI, IEEE TMI, SPIE, and RSNA. He has also been granted more than 15 patent awards.

AI IN DRUG DISCOVERY & DEVELOPMENT


Eric Milliman - Data Scientist - Berg Health
Using AI-Guided Analytics in Early Stage Clinical Trials
Eric Milliman - Berg Health
Using AI-Guided Analytics in Early Stage Clinical Trials
The Pharmaceutical and Health IT fields have struggled to analyze the high volume and diverse types of molecular and clinical data currently available. In this regard, AI informed discovery presents a potential solution over the more traditional expert guided approaches. By favoring interpretability, continued method optimization and data flexibility, Berg Analytics has developed a data-driven and hypothesis-free AI solution that has been successfully utilized to generate actionable outcomes in both clinical development and healthcare fields. In an effort to take advantage of both probabilistic and neural net-based AI technologies, Berg Analytics is currently exploring methods to augment these deep-learning methods.
Dr. Eric Milliman, Ph.D. is a Data Scientist at Berg Analytics, a division of Berg Pharma, where he works on researching, developing and applying innovative data-driven methods in the de-novo discovery of therapeutics and biomarkers. Prior to his role at Berg, Dr. Milliman was a post-doctoral fellow in the Epigenetics & Stem Cell Biology Laboratory at the National Institute of Environmental Health Sciences. Dr. Milliman holds a Ph.D. in Biology from the State University of New York at Buffalo.




Yusuf Roohani - Data Scientist - GlaxoSmithKline
Accelerating High Throughput Drug Discovery Using Deep Learning
Yusuf Roohani - GlaxoSmithKline
Accelerating High Throughput Drug Discovery Using Deep Learning
Image-based high content screening is a well-established method for discovering new compounds at high throughput using their phenotypic signatures. Current processing of these imaging assays relies primarily on tedious and often subjective manual feature extraction requiring specialized skills. We've explored the application of deep convolutional neural networks to address these concerns. Beyond algorithmic hurdles, we faced challenges around building robust production-level models as well as integrating within a pharmaceutical context. This talk will discuss our approach towards building and industrializing deep learning based image analysis workflows within the early phases of drug discovery research.
Yusuf works as a data scientist in drug discovery research at GlaxoSmithKline in Cambridge, MA. Currently, his main focus is on putting together a computer vision platform for early stage drug discovery with broad usability across use cases and imaging domains. He also has previous experience within the areas of compound screening and biomarker identification as well as in building systems that fit a healthcare context. Yusuf was previously employed at Merrimack Pharmaceuticals and received his M.S. from Carnegie Mellon in 2015.


PERSONALIZED MEDICINE AND PRECISION DIAGNOSIS


Cory McLean - Senior Software Engineer - Google Brain
DeepVariant: Highly Accurate Genomes With Deep Neural Networks
Cory McLean - Google Brain
DeepVariant: Highly Accurate Genomes With Deep Neural Networks
Deep learning has enabled dramatic advances in image recognition performance. In this talk I will discuss using a deep convolutional neural network to detect genetic variation in aligned next-generation sequencing human read data. Our method, called DeepVariant, both outperforms existing genotyping tools and generalizes across genome builds, sample preparations, and sequencing instruments. DeepVariant represents a significant step from expert-driven statistical modeling towards more automatic deep learning approaches for developing software to interpret biological instrumentation data.
Cory McLean is a Senior Software Engineer on the genomics team at Google Brain. His research interests include the development and application of machine learning methods to genomics and the biology of human health. Recent projects include efforts to use deep learning image classification methods to improve the detection of genetic variation from high-throughput sequencing data and to interpret cellular morphology and function. Before joining Google, Cory was a research scientist at 23andMe where he studied Parkinson's disease and population genetics. He received his B.S. and M.Eng. in computer science from MIT and his M.S. and Ph.D. in computer science from Stanford University.



COFFEE


Jiayi Wu Cox - PhD Candidate - Boston University
Prediction of Opioid Cessation Using Machine Learning
Jiayi Wu Cox - Boston University
Prediction of Opioid Cessation Using Machine Learning
The non-prescribed use of opioid analgesics has become a significant health and social problem. While studies had focused on opioid use disorder (OUD), a systematic inquiry of the lifestyle factors for opioid cessation has not been conducted. We performed supervised machine learning with feature selection on Yale-Penn dataset among subjects who met DSM-5 OUD criteria to predict current opioid use status. Subjects were interviewed by Semi-Structured Assessment for Drug Dependence and Alcoholism (SSADDA), a comprehensive diagnostic questionnaire. We observed moderate to high prediction efficiency using LASSO, SVM and random forest with SSADDA input alone. Future steps include using DNN and adding genetics from GWAS to see the improvement of accuracy.
Jiayi Wu Cox is a Ph. D candidate in Genetics and Genomics program at Boston University. Her research focuses on using bioinformatics and machine learning to find the genetic risk factors for a variety of diseases including addiction. In addition to her thesis, she also studies epigenetic changes in response to drug treatment and gene expression level differences due to disease phenotypes. Jiayi graduated from Tufts University with M.S degree in Pharmacology and Experimental Therapeutics. She hope her work can facilitate the development of personalized medicine, that people will be treated based on who they are genetically and the lifestyle they choose.


E-HEALTH DATA


Riccardo Miotto - Senior Data Scientist - Icahn School of Medicine
Deep Patient: Predict the Medical Future of Patients with Deep Learning and EHRs
Riccardo Miotto - Icahn School of Medicine
Deep Patient: Predict the Medical Future of Patients with Deep Learning and EHRs
The latest advances in deep learning provide new effective opportunities to model, represent, and learn from large amounts of heterogeneous medical data. Here, in this talk, we focus on applying deep learning to the electronic health records (EHRs). In particular, we review the data as well as the recent literature, we highlight limitations and needs for improved methods and applications, and we discuss the challenges to implement and deploy machine intelligence into the clinical domain. We then present Deep Patient, a general-purpose patient and phenotype representation derived from the EHRs that facilitates clinical predictive modeling and medical analysis, such as patient stratification and disease definition.
Riccardo Miotto is a senior data scientist in the Department of Genetics and Genomic Sciences at the Icahn School of Medicine at Mount Sinai in New York and a member of the Institute for Next Generation Healthcare. Riccardo’s work encompasses the design of algorithms for information retrieval and machine learning applied to clinical data for personalized medicine. Previously, Riccardo worked on clinical trial search engines through free-text eligibility criteria processing and machine learning applied to music information retrieval, in the particular semantic discovery and recommendation, automatic tagging, and cover identification. Riccardo obtained his Ph.D. in Information Engineering from the University of Padova, Italy.


NLP IN HEALTHCARE


Chen Lin - Biomedical Informatician - Boston Children's Hospital
Deep Learning-based Clinical Temporal Relation Extraction
Chen Lin - Boston Children's Hospital
Deep Learning-based Clinical Temporal Relation Extraction
The extraction of temporal relations in medical text has been drawing growing attention because of its potential to dramatically increase the understanding of many medical phenomena such as disease progression, longitudinal effects of medications, a patient's clinical course, and its many clinical applications such as question answering, clinical outcomes prediction, and the recognition of temporal patterns and timelines. We develop deep neural architectures (e.g. Convolutional or Recurrent Neural Networks) for clinical temporal relation extraction. Comparing with conventional models, which make use of heavily engineered features, neural models employ simple token features or slightly enhanced features, establishing state-of-the-art results.
Chen Lin is an Informatician in Boston Children’s Hospital Informatics Program-Natural Language Processing (CHIP-NLP) group, an Apache cTAKES developer. Chen’s work involves using machine learning in clinical NLP tasks. Topics include clinical temporal relation extraction, disease activity classification based on clinical narratives, drug-induced adverse event prediction, deep phenotyping. His main interests in computational methods include convolutional neural networks, recurrent neural networks, auto-encoder/decoder, word and syntactic embeddings, semi-supervised learning, feature selection, and kernel methods. He holds Master degree in Computer Science from Brandeis University.



LUNCH


Sadid Hasan - Senior Director of Artificial Intelligence - CVS Health
Clinical Natural Language Processing with Deep Learning
Sadid Hasan - CVS Health
AI for Care Planning Support
Effective care planning requires care managers to understand patient health status and needs to deliver appropriate patient support. The proliferation of healthcare data including massive volumes of clinical free text documents, creates a significant challenge for care managers, but a major opportunity for advanced clinical analytics. Novel Artificial Intelligence (AI)-driven solutions can help optimize care planning, reducing inefficiency and increasing focus on the most salient information, leading to improved patient outcomes. This talk will focus on various deep learning-based clinical natural language processing use cases developed as part of our advanced care planning initiatives.
Key Takeaways:
*Effective care planning requires care managers to understand patient health status and needs to deliver appropriate support
*Clinical domain has unique challenges such as massive structured/unstructured data, redundancy, limited interoperability, widespread use of acronyms etc.
*AI-augmented solutions can help optimize care planning, reducing inefficiency and increasing focus on the most salient information leading to improved patient outcomes
Dr. Sadid Hasan is a Senior Director for AI at CVS Health leading the team responsible for AI-enabled clinical care plan initiatives in Aetna. His recent work involves solving problems related to clinical information extraction, paraphrase generation, natural language inference, and clinical question answering using Deep Learning. Sadid has over 60 peer-reviewed publications in the top NLP/Machine Learning venues, where he also regularly serves as a program committee member/area chair including ACL, IJCAI, EMNLP, NeurIPS, ICML, COLING, NAACL, AMIA, MLHC, MEDINFO, ICLR, ClinicalNLP, TKDE, JAIR etc.


PREDICTING PROGRESSION


Łukasz Kidziński - Research Associate - Stanford University
Collecting Movement Data and Predicting Surgical Outcomes in the Age of Deep Learning
Łukasz Kidziński - Stanford University
Clinical Motion Lab in Your Pocket
Many neurological and musculoskeletal diseases impair movement, which limits people’s function and social participation. Quantitative assessment of motion is critical to medical decision-making but is currently possible only with expensive motion capture systems and highly trained personnel. We developed AI-based algorithms for quantifying gait pathology using commodity cameras. Our methods increase access to quantitative motion analysis in clinics and at home and enable researchers to conduct studies of neurological and musculoskeletal disorders at an unprecedented scale.
3 Key Takeaways:
*Quantitative assessment of movement enables diagnostics and treatment of many neurological disorders
*Existing methods for quantitative analysis of movement require very expensive equipment
*Deep learning models can predict common gait metrics using a mobile phone camera
Łukasz Kidziński is a co-founder of Saliency and a research associate in the Neuromuscular Biomechanics Lab at Stanford University, applying state-of-the-art computer vision and reinforcement learning algorithms for improving clinical decisions and treatments. Previously he was a researcher in the CHILI group, Computer-Human Interaction in Learning and Instruction, at the EPFL in Switzerland, where he was developing methods for measuring and improving engagement of users in massive online open courses. He obtained a Ph.D. degree at Université Libre de Bruxelles in mathematical statistics, working on frequency-domain methods for dimensionality reduction in time series.




David Ledbetter - Senior Data Scientist - Children’s Hospital Los Angeles
Predicting Individual Physiologically Acceptable States at Discharge from a Pediatric Intensive Care Unit
David Ledbetter - Children’s Hospital Los Angeles
Predicting Individual Physiologically Acceptable States at Discharge from a Pediatric Intensive Care Unit
We aim to quantify acceptable ICU-discharge vitals, compare to age-normal vitals, and develop machine learning models to predict throughout each patient’s ICU episode. Our dataset of 7,256 surviving PICU episodes (5,632 patients) collected between 2009 and 2016 at Children's Hospital Los Angeles contains 375 variables representing vitals, labs, interventions, drugs, and medical and physical discharge times. The means of each patient's heart rate, systolic blood pressure, and diastolic blood pressure between medical and physical discharge were computed as their physiologically acceptable state space (PASS), which were compared to age-normal, regression, and recurrent neural network (RNN) predictions.
Mr. David Ledbetter has an extensive and deep understanding of decision theory. He has experience implementing various decision engines, including convolutional neural networks, random forests, extra trees, and linear discrimination analysis. His particular area of focus is in performance estimation, where he has demonstrated a tremendous ability to accurately predict performance on new data in nonstationary, real-world scenarios. David has worked on a number of real-world detection projects, including detecting circulating tumor cells in blood, automatic target recognition utilizing CNNs from satellite imagery, make/model car classification for the Los Angeles Police Department using CNNs, and acoustic right whale call detection from underwater sonobuoys. Recently, David has been developing an RNN to generate personalized treatment recommendations to optimize patient outcomes using electronic medical records from 15 years of data collected from the Children's Hospital Los Angeles Pediatric Intensive Care Unit.


DEEP LEARNING IN MEDICAL IMAGING


Juan Caicedo - Post-Doctoral Researcher - Broad Institute
Image-based Morphological Profiling Using Deep Learning
Juan Caicedo - Broad Institute
Image-based Morphological Profiling Using Deep Learning
Microscopy images are widely used in biological research to understand cellular structure. Images can be used to measure multiple properties of cells, and then model the effect that treatments produce at the cellular level. These measurements can be used to discover novel relationships between treatments. We investigate whether relevant cellular features can be learned automatically from images using deep learning. In this talk, we present the results of our experiments, which indicate that deep learning features can improve the ability to identify unknown biological relationships.
Juan Caicedo is a postdoctoral researcher at the Broad Institute of MIT and Harvard, where he investigates the use of deep learning to analyze microscopy images. Previous to this, he studied object detection problems in large scale image collections also using deep learning, at the University of Illinois in Urbana-Champaign. Juan completed research internships in Google Research, Microsoft Research, and Queen Mary University of London in the past, studying problems related to large scale image classification, image enhancement, and medical image analysis. His research interest include computer vision, machine learning and computational biology.



COFFEE
Polina Golland - MIT CSAIL
From Pixels to Clinical Insight
Medical images contain a wealth of information about a patient but require a human expert to look at each image to capture relevant clinical knowledge. Computational tools that extract clinically important information from images enable development of novel biomarkers of disease, support surgical planning, and enable disease prognosis. From monitoring fetal development, to predicting stroke outcomes, this talk will discuss current challenges in extracting clinically actionable information from images.
Polina Golland is a professor of EECS at MIT CSAIL. She received her PhD from MIT and her Bachelor and Masters degree from Technion, Israel. Polina's primary research interest is in developing novel techniques for medical image analysis and understanding. With her students, she has demonstrated novel approaches to image segmentation, shape analysis, functional image analysis and population studies. Polina has served as an associate editor of the IEEE Transactions on Medical Imaging and of the IEEE Transactions on Pattern Analysis and Machine Intelligence. She is a Fellow of the International Society for Medical Image Computing and Computer Assisted Interventions.



Ahmed Hosny - Data Scientist - Dana-Farber Cancer Institute
Deep Learning Opportunities in Cancer Imaging
Ahmed Hosny - Dana-Farber Cancer Institute
Deep Learning Opportunities in Cancer Imaging
Radiographic medical images contain a vast wealth of information allowing for accurate non-invasive tumor characterization and ultimately improving cancer diagnosis and care. Recent advances in AI, deep learning in particular, promise to impact multiple facets of the radiology profession and support clinical decision making. The Computational Imaging and Bioinformatics Lab at Dana Farber Cancer Institute and Harvard Medical School is a data science lab focused on the development and application of AI methods on medical data.
In this talk, we will be presenting case studies investigating the clinical utility of deep learning in the detection, segmentation and outcome prediction of cancer tumors. We will also be presenting modelhub.ai, a repository of deep learning models crowdsourced through contributions by the scientific research community.
Ahmed Hosny is a machine learning research scientist focused on solving biomedical problems. Currently at Dana Farber Cancer institute, he trains and optimizes deep learning networks for the prognostication and treatment response prediction in lung cancer patients from CT data. In addition to regularly contributing to open-source projects including modelhub.ai and PyRadiomics, he is also intrigued by data visualization, web development, and everything UI/UX. He has previously conducted research at Brigham and Women’s hospital, Wyss Institute for Biologically Inspired Engineering, as well as MIT Media Lab’s Mediated Matter group. As an architect and computational designer in a former life, he spent 4 years working in construction with Foster+Partners in Beijing and Playze in Shanghai. He is currently working on a PhD in machine learning and medical imaging at Maastricht University after having completed a Master of Design Studies in Technology at the Harvard Graduate School of Design, and a Bachelor of Architecture at the American University of Sharjah.



PANEL: The Future Of Cancer Treatment with the Application of Deep Learning
Bill Lotter - DeepHealth
Bill Lotter is the CTO and a co-founder of DeepHeath, whose aim is to bring the best doctor in the world to every patient, through machine learning. Their first domain of focus is screening mammography, where they have developed award-winning machine learning models. Bill has a PhD in Biophysics and Computational Science from Harvard University. His thesis focused on biologically-inspired deep learning methods. Prior to Harvard, he worked as an algorithmic trader and also has served as a machine learning consultant for an NFL franchise.


Tal Schuster - MIT CSAIL
Tal Schuster is a PhD student in Computer Science at MIT and a member of the Learning to Cure team. He is developing deep learning models that help reduce the radiologists’ workload by automating some of their routine tasks, improving risk assessment, detecting cancer earlier, and preventing overtreatment. Some of these methods are already successfully being used at Massachusetts General Hospital. Tal received his MSc in CS from Tel Aviv University and his BSc in Mathematics and CS from Ben-Gurion University. He had several key positions in the IDF, including leading a team of engineers working on automating procedures.


Liz Asai - 3Derm
Liz Asai has served as CEO of 3Derm since 2013. 3Derm is a digital health company that has developed skin imaging systems paired with machine learning algorithms to triage dermatology concerns. Over the last few years, 3Derm has raised two rounds of funding, conducted three clinical trials, and obtained reimbursement for its dermatological services from several health plans. 3Derm now serves thousands of patients at health systems in the US. Liz holds a B.S. in Biomedical Engineering from Yale University and was featured in Forbes 30 Under 30.


Ahmed Hosny - Dana-Farber Cancer Institute
Deep Learning Opportunities in Cancer Imaging
Radiographic medical images contain a vast wealth of information allowing for accurate non-invasive tumor characterization and ultimately improving cancer diagnosis and care. Recent advances in AI, deep learning in particular, promise to impact multiple facets of the radiology profession and support clinical decision making. The Computational Imaging and Bioinformatics Lab at Dana Farber Cancer Institute and Harvard Medical School is a data science lab focused on the development and application of AI methods on medical data.
In this talk, we will be presenting case studies investigating the clinical utility of deep learning in the detection, segmentation and outcome prediction of cancer tumors. We will also be presenting modelhub.ai, a repository of deep learning models crowdsourced through contributions by the scientific research community.
Ahmed Hosny is a machine learning research scientist focused on solving biomedical problems. Currently at Dana Farber Cancer institute, he trains and optimizes deep learning networks for the prognostication and treatment response prediction in lung cancer patients from CT data. In addition to regularly contributing to open-source projects including modelhub.ai and PyRadiomics, he is also intrigued by data visualization, web development, and everything UI/UX. He has previously conducted research at Brigham and Women’s hospital, Wyss Institute for Biologically Inspired Engineering, as well as MIT Media Lab’s Mediated Matter group. As an architect and computational designer in a former life, he spent 4 years working in construction with Foster+Partners in Beijing and Playze in Shanghai. He is currently working on a PhD in machine learning and medical imaging at Maastricht University after having completed a Master of Design Studies in Technology at the Harvard Graduate School of Design, and a Bachelor of Architecture at the American University of Sharjah.



Conversation & Drinks

DOORS OPEN

WELCOME
STARTUP SESSION


Joe Isaacson - VP of Engineering - Asimov
Programming Living Organisms Through Targeted Machine Learning
Joe Isaacson - Asimov
Programming Living Cells for Next Generation Therapeutics
Over the past decade, there has been a rise in the usage of next generation therapeutics: biologically derived therapeutics to treat a breadth of human diseases including cancer and rare genetic diseases. The growth of treatment modalities such as antibodies, viral vectors and cell therapeutics has outpaced classic methods such as small organic molecule development. Despite this growth, methodologies for designing biological therapeutics are arcane; it can take years of research to discover a single genetic design that produces a functional therapeutic. In this talk we will walk through advances in experimental data collection and machine learning algorithms to accelerate the design of living systems to produce these next generation therapeutics.




Fernando Schwartz - Chief Data Scientist & Head of AI - Prognos
Building the Patient Tensor: The Total Is More Than the Sum of Its Parts
Fernando Schwartz - Prognos
Building the Patient Tensor: The Total Is More Than the Sum of Its Parts
As the Chief Data Scientist at Prognos, Fernando and head a 15-strong team tasked with deploying AI on the world’s largest clinical lab dataset -covering almost 200M lives in the US- with the mission of predicting the onset of disease and deliver treatment decisions at the earliest possible time. Before joining Prognos, Fernando held key leadership roles in data science at AppNexus and LiveIntent, two ad-tech companies in NYC. In a previous life, Fernando was a Tenured Professor of Mathematics & Data Science. Fernando holds a PhD in mathematics from Cornell University and undergraduate degree in Engineering from the University of Chile.




Victor Chapela - Co-Founder & CEO - Suggestic
Lifestyle-Based Human Health and Well Being, from Knowledge Representation to Knowledge Generation
Victor Chapela - Suggestic
Lifestyle-Based Human Health and Well Being, from Knowledge Representation to Knowledge Generation
Diet and lifestyle choices are known to generate or even revert clinical conditions like type 2 diabetes. Lifestyle engineering becomes a promising alternative to conventional approaches for health improvement. In this context, deep learning has emerged as a powerful tool to analyze observational data and enrich our knowledge about human physiology responses to diet, activity and environment. In Suggestic, we have adopted a two-fold approach to make technology work for wellbeing. First by encoding human knowledge about nutritional guidelines and making this knowledge actionable by rendering best-suited options for each individual. This encoding of actionable knowledge had several challenges, including nutritional content inference on restaurant menu items, or understanding meal composition from user natural language input. Deep learning has been used from the most basic aspects of nutritional knowledge representation to user interactions at restaurants through an Augmented Reality interface. Second by deciphering the nutritional and behavioral patterns to automatically generate knowledge for health improvement. This research is being conducted on top of established Markov Decision Process modeling tools and state of the art deep recurrent neural networks.
Victor Chapela is Co-founder & CEO of Suggestic, a Silicon Valley-based company whose mission is to help individuals make optimal food choices for weight loss, disease management and health improvement. Suggestic uses artificial intelligence and augmented reality to overlay and score what is best for you from a restaurant menu, at the grocery store or at home when cooking.Mr. Chapela has over 25 years of IT experience and entrepreneurship. During this time, he has founded and led 6 technology companies in the United States and Mexico. As the founder and CEO of these companies, he has mainly been involved in the design and development of software products and specialized services for the financial industry and large corporations. His latest companies: Sm4rt Security Services and Sm4rt Predictive Systems were both acquired in 2014.



Ricardo Corral - Chief Data Scientist - Suggestic
Lifestyle-Based Human Health and Well Being, from Knowledge Representation to Knowledge Generation
Ricardo Corral - Suggestic
Lifestyle-Based Human Health and Well Being, from Knowledge Representation to Knowledge Generation
Diet and lifestyle choices are known to generate or even revert clinical conditions like type 2 diabetes. Lifestyle engineering becomes a promising alternative to conventional approaches for health improvement. In this context, deep learning has emerged as a powerful tool to analyze observational data and enrich our knowledge about human physiology responses to diet, activity and environment. In Suggestic, we have adopted a two-fold approach to make technology work for wellbeing. First by encoding human knowledge about nutritional guidelines and making this knowledge actionable by rendering best-suited options for each individual. This encoding of actionable knowledge had several challenges, including nutritional content inference on restaurant menu items, or understanding meal composition from user natural language input. Deep learning has been used from the most basic aspects of nutritional knowledge representation to user interactions at restaurants through an Augmented Reality interface. Second by deciphering the nutritional and behavioral patterns to automatically generate knowledge for health improvement. This research is being conducted on top of established Markov Decision Process modeling tools and state of the art deep recurrent neural networks.
Ricardo holds a degree in Applied Mathematics and a Ph.D. in Biochemistry. He is Chief Data Scientist at Suggestic Inc. where he serves as co-inventor of 3 U.S. patents. His academic production has been the field of Computational Biology, specifically on the representation and analysis of protein molecular structures and novel approaches for peptide-based immunodiagnosis.




Mayur Saxena - Founder & CEO - Droice Labs
Deep Learning in the Health Record: Discovering Meaning in Clinical Text
Mayur Saxena - Droice Labs
Strategies for AI Adoption in Hospitals
At Droice, we use artificial intelligence to help clinicians make better decisions for individual patients. What treatment should a patient be given? Are there any potential complications? What tests need to be done? All of these (and many more) are examples of difficult, data-intensive questions that doctors must answer every day. By answering these questions, AI has the power to fundamentally transform healthcare but has been hampered by slow adoption into common clinical practice. This presentation will describe Droice Labs technology and address strategies for translating AI into deployable hospital solutions.



Tasha Nagamine - Founder and Chief of AI - Droice Labs
Deep Learning in the Health Record: Discovering Meaning in Clinical Text

COFFEE
APPLICATIONS OF DEEP LEARNING IN HEALTHCARE


Mark Michalski - Executive Director - MGH & BWH Center for Clinical Data Science
Machine Learning in the Healthcare Enterprise
Mark Michalski - MGH & BWH Center for Clinical Data Science
Machine Learning in the Healthcare Enterprise
Machine learning is an emerging technology with promise to impact a wide variety of areas throughout the healthcare enterprise. In this discussion, we’ll review advances in machine learning and their potential impact on several areas of healthcare, with special focus in diagnostic areas. In addition, we’ll discuss some of the challenges and approaches that have been taken to translate this technology at the Partners organization.
Mark H. Michalski, MD, is the Executive Director of the MGH & BWH Center for Clinical Data Science, which is focused on the application and translation of novel machine learning techniques into clinical practice. Previous to this role, Dr. Michalski held leadership and operational roles at early-stage companies in the medical software and device domain, including Butterfly Network and Hyperfine Research. Dr. Michalski held additional strategic roles in healthcare-focused efforts at Google and Genentech. Dr. Michalski completed his radiology residency training as a Holman Fellow at Yale-New Haven Hospital. He graduated with a degree in Cybernetics from the University of California at Los Angeles with multiple honors and received his medical degree from Stanford University.




Daniel Golden - Director of Machine Learning - Arterys
Lung Cancer Detection and Segmentation Using Deep Learning
Daniel Golden - Arterys
Lung Cancer Detection and Segmentation Using Deep Learning
For those of us accustomed to life’s modern automated conveniences, diagnostic radiology can seem shockingly unsophisticated. Lung cancer screening via computed tomography (CT) is an example of a common radiological procedure that is critical in ensuring that cancers are detected early so that patients have the best chance of receiving timely treatment. However, the radiological procedure for lung cancer screening is still an entirely manual affair. A given lung CT exam consists of a three-dimensional volume of data composed of a stack of hundreds of 2D slices. During screening, clinicians manually scroll through the data slice-by-slice, searching for tiny nodules that can be indistinguishable from blood vessels and other structures under most viewing conditions. Not only is this process time-consuming and tedious, but inter-reader variability among clinicians means that most patients are not receiving the best possible care. Building on the successes of our previous deep learning-based tools in cardiac MRI, we have developed a deep learning-based system that that can automatically detect and segment lung nodules in CT exams. Using the open LIDC-IDRI data set of detected and segmented lung nodules in 1018 thoracic CT exams, we have developed a pipeline that consists of three connected models: a nodule proposal system (2D U-Net-based segmentation network), a nodule classification system (2.5D ResNet-based classifier), and a nodule segmentation system (3D ENet based segmentation network). These models operate together as a complete lung nodule detection and segmentation system. The resulting system has the potential to greatly improve the speed and effectiveness of lung cancer screening. For nodules with diameter larger than 6mm (the lower limit for clinical significance), the recall of our detection model is 94% with four false positives per scan. For nodule segmentation, the mean dice coefficient is 0.83±0.10, comparable to the mean dice coefficient of expert radiologists which is 0.79±0.09. Both models operate with clinicians in the loop, requiring that clinicians review and optionally modify the initial automated results before accepting them. These deep learning-based models form the backbone of our FDA-cleared, cloud-based Oncology DL software product. In this talk, we will discuss details of the deep learning technologies behind our lung nodule detection and segmentation system. We will also discuss the method by which we demonstrated that our system is as accurate as expert radiologists in order to obtain FDA clearance.
Dan is the Director of Machine Learning at Arterys, a startup focused on streamlining the practice of medical image interpretation and post-processing. After receiving a PhD in Electrical Engineering from Stanford, he stayed for a postdoc, focusing on using machine learning to predict outcomes and disease characteristics in cancer patients. From there, he joined CellScope, where he founded a machine learning team that used the then-nascent field of Deep Learning to diagnose ear disease and streamline the process of recording ear exams at home. He moved to Arterys to found their machine learning team in 2015.




Tommy Blanchard - Data Science Lead - Fresenius Medical Care
Using Machine Learning to Improve Care of Chronically Ill Patients
Tommy Blanchard - Fresenius Medical Care
Using Machine Learning to Improve Care of Chronically Ill Patients
Providing care for chronically ill patients, like those with end stage renal disease, presents several unique opportunities for data scientists. The frequency of treatment and volume of data collected, combined with the number of health complications in the population, presents fertile ground for high-impact predictive models. At Fresenius Medical Care, we use natural language processing and machine learning models to predict which patients are likely to miss a treatment, which patients are at high risk of hospitalization, and which patients are likely to have specific conditions.
Tommy is currently Data Science Lead at Fresenius Medical Care North America. His team uses data science broadly across the organization to create predictive models and advanced analytics support for a diverse set of company needs. Central to his team’s goals is the use of machine learning to improve medical care of the many chronically ill patients Fresenius provides care for. Tommy holds a Bachelor’s in Computer Science from the University of Waterloo, completed his PhD at the University of Rochester in Brain and Cognitive Sciences, and performed his post-doctoral research at Harvard University.



LUNCH


David Richmond - Senior Data Scientist - IBM Watson Health
Developing Deep Learning-Based Solutions for Radiology
David Richmond - IBM Watson Health
Developing Deep Learning-Based Solutions for Radiology
Driven by advances in deep learning, medical image analysis offers the promise to augment and improve the workflow of radiologists. Despite this auspicious outlook, there are numerous challenges that must be overcome. I will speak about the end-to-end process of developing deep-learning based medical image analysis solutions, including: the importance of understanding clinical workflow, and how algorithm-based predictions (correct and incorrect) impact patient management; the importance of non-subjective ground truth; and research to improve transfer learning for large-scale datasets from other domains.
David Richmond is a Senior Scientist at Watson Health Imaging, IBM, where he leads algorithm development on an AI-based medical image analysis solution. Prior to this position, he was Deputy Director of the Image and Data Analysis Core at Harvard Medical School, and he received his PhD from UC Berkeley.




Ayah Zirikly - Postdoctoral Fellow - National Institute of Health
Detecting Mobility Functions in Free Text as an Indicator of Disability
Ayah Zirikly - National Institute of Health
Detecting Mobility Functions in Free Text as an Indicator of Disability
The detection of disability is of great importance in multiple medical domains and in social programs. For instance, Social Security Administration (SSA) suffers from a significant delay in disability eligibility decisions due to the expensive human resources needed to review dozens if not even hundreds of pages per applicant. In this talk, we will present a disability detection approach using LSTM models. We identify mobility mentions in text given the International Code Functionality (ICF) scheme, since mobility is one of the strongest indicators in disability. Additionally, we will discuss the impact of using in- vs. out-of-domain word embeddings and try to leverage large amount of non-medical data to enhance the performance of the LSTM model.
Ayah Zirikly is a postdoctoral fellow at the NIH working with the epidemiology and biostatics section. She focuses on identifying disability mentions in free text in both: medical specialists’ notes and patients. Additionally, she is very enthusiastic about incorporating the use of Natural Language Processing (NLP) techniques in identifying mental health issues in free text. Over the last two years in collaboration with UMD, she has been focusing on suicidal and depression prediction in social media. Currently, she is working with NIH in collaboration with Stanford University to identify suicidal ideology among the veterans. Her PhD dissertation, under the supervision of Dr. Mona Diab, focused on information extraction (specifically Named Entity Recognition) in low-resource languages, where limited training data is available.




Ayin Vala - Founder & Chief Data Scientist - Foundation for Precision Medicine
Early Detection of Alzheimer’s Disease with Deep Learning
Ayin Vala - Foundation for Precision Medicine
Early Detection of Alzheimer’s Disease with Deep Learning
The transformative impact of machine learning and AI has not been fully realized in medicine and especially personalized medicine. Complex disease processes like Alzheimer’s Disease cannot be cured by pharmaceutical or genetic sciences alone and after decades of clinical research, current treatments and therapies have lead to insignificant successes. Clinical researchers now believe that the early detection of Alzheimer’s patients is the key to a breakthrough. This talk will highlight our non-profit project funded by National Institute of Health, and our deep learning model based on 70000 Alzheimer patient records, that helps to identify Alzheimer’s Disease patients at high risk, using medication regimens, historical diagnosis, risk factors, and care programs.
Ayin is the Co-Founder and Chief Data Scientist of the non-profit organization Foundation for Precision Medicine. His research and development team works on statistical analysis and machine learning, pharmacogenetics, molecular medicine, and sciences relevant to the advancement of medicine and healthcare delivery. Ayin has several years of experience in machine learning, possessing several awards and patents in Healthcare, Aerospace, Energy, and Education sectors. He holds Master degrees in Information Management Systems from Harvard University and in Mechanical Engineering from Georgia Tech, and resides in Silicon Valley.


PANEL: How to Balance Ethics and Efficiency When Applying AI in Healthcare
Wen Dombrowski - CATALAIZE
Wen Dombrowski, MD, MBA is a geriatrics physician executive with a unique perspective bridging clinical, technical, business, design, ethics and policy expertise for social innovation. She works first hand in designing and deploying AI and digital health technologies. Prior to forming her consultancy CATALAIZE focusing on developing and scaling emerging technologies, Dr. Dombrowski was Chief Medical Information Officer (CMIO + CIO) for large healthcare organizations overseeing Enterprise IT, Digital Engagement, and Innovation portfolios. Additionally, she has been engaged in the Ethics of Science and Technology for over 2 decades – including advising tech companies on ethics, and serving on Bioethics Committees at the community, hospital, state level. She frequently speaks at national and international conferences about a range of topics including ethics issues with data, bias, and unintended consequences.


Dekel Gelbman - FDNA
As the founding CEO of FDNA, Dekel Gelbman leads the corporate and business strategy of an innovative digital health company that develops technologies and SaaS platforms used by thousands of clinical, research and lab sites globally in the clinical genomics space. Using the most advanced deep learning and artificial intelligence technologies, FDNA has created a new gold standard - next-generation phenotyping (NGP) - technologies that capture, structure, and analyze complex human physiological data to produce actionable genomic insights from next-generation sequencing data. Since its founding in 2011, FDNA has positioned itself at the forefront of AI, genomics and precision medicine, and is one of the most active and innovative startup companies in this space. Before joining FDNA, Mr. Gelbman was a practicing corporate and transactional attorney working for leading law firms, including among others, Skadden, Arps, Slate, Meagher & Flom LLP and Affiliates. Mr. Gelbman's experience includes working closely with a variety of technology and biotech companies, at all stages - from startups through growth stage companies and to mature, publicly-traded companies. Mr. Gelbman holds an LL.B and an MBA in finance.


Cansu Canca - AI Ethics Lab
Cansu is the founder and director of the AI Ethics Lab, where she leads teams of computer scientists and legal scholars to provide ethics analysis and guidance to researchers and practitioners. She has a Ph.D. in philosophy specializing in applied ethics. She works on ethics of technology and population-level bioethics with an interest in policy questions. Prior to the AI Ethics Lab, she was a lecturer at the University of Hong Kong, and a researcher at the Harvard Law School, Harvard School of Public Health, Harvard Medical School, Osaka University, and the World Health Organization.


Adrian Gropper - Patient Privacy Rights
Adrian Gropper, MD is CTO of the non-profit Patient Privacy Rights Foundation where he brings training as an engineer from MIT and physician from Harvard Medical School followed by a career as a medical device entrepreneur. His paper won a prize at ONC’s 2016 Blockchain Health competition. His current project, HIE of One Trustee, uses public blockchains, standards and open source software to enable patient-controlled independent health records that can last a lifetime. He is active in blockchain standards development for identity, credentials, and reputation.



END OF SUMMIT

Distributed Tensorflow: Scaling Model Training to Multiple GPUs - WORKSHOP
Presentation and Real-Life Use-cases

The ROI of Deep Learning Application - Is it Worth it? - PANEL DISCUSSION
Panel Discussion with Leading Experts & Practitioners

The Future of Deep Learning in the Workplace - OPEN TABLE DISCUSSION
Open Round Table Discussion with Leading Experts