BCH AI and Machine Learning Working Group

The Boston Children’s Hospital Artificial Intelligence and Machine Learning working group gives our clinicians and investigators a forum for sharing knowledge and collaborating across the many facets of artificial intelligence and machine learning.

Core objectives:

  • create a forum for Boston Children’s Hospital investigators to find like-minded collaborators
  • foster an environment of knowledge exchange
  • collaborate on funding options to improve infrastructure
  • create a unified body for industry discussions

Focus areas:

  • clinical decision making
  • image processing and interpretation
  • hospital administrative functions and capacity planning
  • basic methods
  • life sciences and drug development
  • omics research and omics-informed medicine

Participating programs and sponsors include:

We host:

  • quarterly workgroup meetings
  • seminars
  • journal clubs

Please send an email to register your interest in joining.


Previous lectures

 

Date: October 16, 2020
Speaker: Ben Reis, PhD
Event: BCH AI and Machine Learning Group Lecture
Talk title: The Age of Predictive Medicine

Dr. Ben Reis discussed recent developments in machine learning approaches to some of the grandest challenges of human health, including pandemic prediction, suicide prevention, bioterrorism detection, and drug safety prediction. The focus was on understanding both the methodological challenges involved and the ramifications of generating actionable predictions in these critical areas. The talk concluded by formulating a set of central challenges and opportunities facing the field of Predictive Medicine.

 

Date: September 9, 2020
Event: BCH AI and Machine Learning Working Group Lightning Talks

The BCH AI and Machine Learning Working Group held our first Lightning Talks session, where multiple investigators gave brief overviews of numerous Machine Learning applications at Boston Children’s Hospital to foster clinical and machine learning collaborations across the hospital. Speakers included:

  • John N. Kheir, MD, Department of Cardiology, and Mauricio Santillana, PhD, Computational Health Informatics Program: Predicting unnecessary blood testing for serum potassium in the CICU
  • Maimuna Majumder, PhD, Computational Health Informatics Program: Machine learning applications during COVID-19
  • Rudolph Pienaar, PhD, Department of Radiology: The practical reality of using AI in medical compute
  • Jess Zhang, MPH, and Guarav Tuli, PhD, Innovation Program: Using machine learning to predict food allergy risk
  • Guergana Savova, PhD, Computational Health Informatics Program: How NLP can contribute to various areas of biomedicine — translational science, disease surveillance, clinical decision making, point of care, etc.
  • Timothy Miller, PhD, Computational Health Informatics Program: Extracting useful information from clinical text with NLP
  • Amir Kimia, MD, Clinical Informatics Fellowship, Division of Emergency Medicine: A taste of NLP: Clinical domain experts — helping us to help them
  • Ata Kiapour, PhD, Orthopedic Center: Deep learning for tracking tissue healing following knee surgery
  • Ben Reis, PhD, Computational Health Informatics Program: Predicting the Future in Clinical Settings
  • Yangming Ou, PhD, Department of Radiology: AI+ Imaging to Advance Medicine
  • Mauricio Santillana, PhD, Computational Health Informatics Program: Machine learning to monitor and forecast epidemic outbreaks and patient outcomes in intensive care units
  • Alireza Akhondi-Asl, PhD, Perioperative & Critical Care Center for Outcomes Research and Evaluation: Estimation of state of cerebral autoregulation using a deep long short-term memory (LSTM) network
  • Hsin-Hsao Scott Wang, MD, MPH, MBAn, Urodynamics Program: A new analytical method to solve challenging and critical clinical studies
 

Date: August 14, 2020
Speaker: Jonathan Bickel, MD, MS, Senior Director of Clinical Health Record, Business Intelligence, and Children’s Medical Library & Archives; Ronald Wilkinson, MA, MS, CBIP; Senior Business Intelligence Program Technologist, Business Intelligence; Ashley Doherty, MS, Business Intelligence Analyst, Program Management, Analysis and Education Team, Business Intelligence
Event: BCH AI and Machine Learning Working Group Lecture
Talk Title: A Gold Mine of Potential: Predictive Analytics Using Boston Children’s Hospital’s “Children’s 360” Data Warehouse

Boston Children’s Hospital data warehouse integrates 15 years of extensive clinical and administrative data sources and more years of selected data sources. While the contents are used extensively for daily operational reporting, the potential for extensive retrospective and predictive analytics is largely untapped. Jonathan Bickel, Ashley Doherty, and Ron Wilkinson will show something of the breadth of data available in the EDW, discuss how predictive modeling tools can access the data, discuss ideas for predictive modeling applications that they think would be valuable, and explain the conditions on which access to the data can be granted.

 

Date: July 17, 2020
Speaker: Yangming Ou, PhD; Assistant Professor of Radiology; Affiliate Faculty, Computational Health Informatics Program; Faculty, Fetal-Neonatal Neuroimaging Data Science Center
Event: BCH AI and Machine Learning Working Group Lecture
Talk Title: AI in 3D Medical Images: Concepts, Milestones, and Opportunities

Dr. Ou briefly reviewed some major concepts and milestones of AI in medical images. The focus of Dr. Ou’s talk was on 3D medical images, for AI’s application in disease diagnosis, outcome prediction, early screening, neuroscience, and others. Dr. Ou then discussed some major challenges and potential opportunities, including further improving accuracy in detecting small diffuse lesions, and facilitating AI in small sample sizes.

 

Date: June 30, 2020
Speaker: Tim Miller, PhD; Assistant Professor of Pediatrics, Computational Health Informatics Program
Event: BCH AI and Machine Learning Journal Club

Dr. Miller discussed articles that he recently published on natural language processing of computerized text.

 

Date: May 8, 2020
Speaker: Arjun (Raj) Manrai, PhD; Faculty, Computational Health Informatics Program (CHIP); Director, Laboratory for Probabilistic Medical Reasoning; Assistant Professor, Harvard Medical School
Event: BCH AI and Machine Learning Working Group Journal Club
Talk Title: Machine Learning Reveals Widespread Demographic Structure in Laboratory Data

Blood laboratory measures such as glucose and hemoglobin are the basis for much of clinical decision making, yet baseline variation for many laboratory measures remains incompletely characterized across age, gender, and race groups. I will introduce foundational techniques from machine learning and statistical genetics and show how they can be applied to systematically unpack variation in blood laboratory data across population groups. These analyses reveal widespread demographic structure in blood laboratory data.