Amazon Launches HealthLake for Healthcare Orgs to Aggregate & Structure Health Data

AWS Announces Amazon HealthLake

What You Should Know:

– Amazon today announced the launch of Amazon HealthLake,
a new HIPAA-eligible service enables healthcare organizations to store, tag,
index, standardize, query, and apply machine learning to analyze data at
petabyte scale in the cloud.

– Cerner, Ciox Health, Konica Minolta Precision Medicine,
and Orion Health among customers using Amazon HealthLake.


Today at AWS re:Invent, Amazon
Web Services, Inc. (AWS),
an Amazon.com company today announced Amazon HealthLake, a
HIPAA-eligible service for healthcare and life sciences organizations. Current
Amazon HealthLake customers include Cerner, Ciox Health, Konica Minolta
Precision Medicine, and Orion Health.

Health data is frequently incomplete and inconsistent, and is often unstructured, with the information contained in clinical notes, laboratory reports, insurance claims, medical images, recorded conversations, and time-series data (for example, heart ECG or brain EEG traces) across disparate formats and systems. Every healthcare provider, payer, and life sciences company is trying to solve the problem of structuring the data because if they do, they can make better patient support decisions, design better clinical trials, and operate more efficiently.

Store, transform, query, and analyze health data in
minutes

Amazon HealthLake aggregates an organization’s complete data across various silos and disparate formats into a centralized AWS data lake and automatically normalizes this information using machine learning. The service identifies each piece of clinical information, tags, and indexes events in a timeline view with standardized labels so it can be easily searched, and structures all of the data into the Fast Healthcare Interoperability Resources (FHIR) industry-standard format for a complete view of the health of individual patients and entire populations.

Benefits for Healthcare Organizations

As a result, Amazon HealthLake makes it easier for customers to query, perform analytics, and run machine learning to derive meaningful value from the newly normalized data. Organizations such as healthcare systems, pharmaceutical companies, clinical researchers, health insurers, and more can use Amazon HealthLake to help spot trends and anomalies in health data so they can make much more precise predictions about the progression of the disease, the efficacy of clinical trials, the accuracy of insurance premiums, and many other applications.

How It Works

Amazon HealthLake offers medical providers, health insurers,
and pharmaceutical companies a service that brings together and makes sense of
all their patient data, so healthcare organizations can make more precise
predictions about the health of patients and populations. The new
HIPAA-eligible service enables organizations to store, tag, index, standardize,
query, and apply machine learning to analyze data at petabyte scale in the
cloud.

Amazon HealthLake allows organizations to easily copy health
data from on-premises systems to a secure data lake in the cloud and normalize
every patient record across disparate formats automatically. Upon ingestion,
Amazon HealthLake uses machine learning trained to understand medical
terminology to identify and tag each piece of clinical information, index
events into a timeline view, and enrich the data with standardized labels
(e.g., medications, conditions, diagnoses, procedures, etc.) so all this
information can be easily searched.

For example, organizations can quickly and accurately find
answers to their questions like, “How has the use of cholesterol-lowering
medications helped our patients with high blood pressure last year?” To do this,
customers can create a list of patients by selecting “High Cholesterol” from a
standard list of medical conditions, “Oral Drugs” from a menu of treatments,
and blood pressure values from the “Blood Pressure” structured field – and then
they can further refine the list by choosing attributes like time frame,
gender, and age. Because Amazon HealthLake also automatically structures all of
a healthcare organization’s data into the FHIR industry format, the information
can be easily and securely shared between health systems and with third-party
applications, enabling providers to collaborate more effectively and allowing
patients unfettered access to their medical information.

“There has been an explosion of digitized health data in recent years with the advent of electronic medical records, but organizations are telling us that unlocking the value from this information using technology like machine learning is still challenging and riddled with barriers,” said Swami Sivasubramanian, Vice President of Amazon Machine Learning for AWS. “With Amazon HealthLake, healthcare organizations can reduce the time it takes to transform health data in the cloud from weeks to minutes so that it can be analyzed securely, even at petabyte scale. This completely reinvents what’s possible with healthcare and brings us that much closer to everyone’s goal of providing patients with more personalized and predictive treatment for individuals and across entire populations.”

AWS, PHDA Collaborate to Develop Breast Cancer Screening and Depression Machine Learning Models

AWS, PHDA Collaborate to Develop Breast Cancer Screening and Depression Machine Learning Models

What You Should Know:

– Amazon Web Services (AWS) and the Pittsburgh Health Data Alliance (PHDA) announce a collaboration to produce more accurate machine learning models for breast cancer screening and depression.

– In work funded through the PHDA-AWS collaboration, a research team led by Shandong Wu, an associate professor at the University of Pittsburgh Department of Radiology, is using deep-learning systems to analyze mammograms in order to predict the short‐term risk of developing breast cancer. 

– A team of experts in computer vision, deep learning,
bioinformatics, and breast cancer imaging, including researchers from the
University of Pittsburgh Medical Center (UPMC), the University of Pittsburgh,
and Carnegie Mellon University (CMU), are working together to develop a more
personalized approach for patients undergoing breast cancer screening.


Last August, the Pittsburgh Health Data Alliance (PHDA)
and Amazon Web Services (AWS)
announced a new collaboration to advance innovation in areas such as cancer
diagnostics, precision medicine, electronic health records,
and medical imaging. One year later: AWS collaboration with Pittsburgh Health
Data Alliance begins to pay dividends with new machine learning innovation.

Researchers from the University of Pittsburgh Medical Center
(UPMC), the University of Pittsburgh, and Carnegie Mellon University (CMU),
who were already supported by the PHDA,  received additional support
from  Amazon Research Awards to use machine learning
techniques to study breast cancer risk, identify depression markers, and
understand what drives tumor growth, among other projects.


Accurate Machine Learning Models for Breast Cancer Screening
and Depression

In work funded through the PHDA-AWS collaboration, a
research team led by Shandong Wu, an associate professor in the University of
Pittsburgh Department of Radiology, is using deep-learning systems to analyze
mammograms in order to predict the short‐term risk of developing breast
cancer.  A team of experts in computer vision, deep learning,
bioinformatics, and breast cancer imaging are working together to develop a
more personalized approach for patients undergoing breast cancer screening.

Wu and his colleagues collected 452 de-identified normal
screening mammogram images from 226 patients, half of whom later developed
breast cancer and half of whom did not. Leveraging AWS tools, such as
Amazon SageMaker,
they used two different machine learning models to analyze the images for
characteristics that could help predict breast cancer risk. As they reported in
the American Association of Physicists in Medicine, both
models consistently outperformed the simple measure of breast density, which
today is the primary imaging marker for breast cancer risk,  The team’s
models demonstrated between 33% and 35% improvement over these existing
models, based on metrics that incorporate sensitivity and specificity.


Why It Matters

“This preliminary work demonstrates the feasibility and promise of applying deep-learning methodologies for in-depth interpretation of mammogram images to enhance breast cancer risk assessment,” said Dr. Wu. “Identifying additional risk factors for breast cancer, including those that can lead to a more personalized approach to screening, may help patients and providers take more appropriate preventive measures to reduce the likelihood of developing the disease or catching it early on when interventions are most effective. “


Tools that could provide more accurate predictions from screening images could be used to guide clinical decision making related to the frequency of follow-up imaging and other forms of preventative monitoring. This could reduce unnecessary imaging examinations or clinical procedures, decreasing patients’ anxiety resulting from inaccurate risk assessments, and cutting costs.

Moving forward, researchers at the University of Pittsburgh
and UPMC will pursue studies with more training samples and longitudinal
imaging data to further evaluate the models. They also plan to combine deep
learning with known clinical risk factors to improve upon the ability to
diagnose and treat breast cancer earlier.


Second Project to Develop Biomarkers for Depression

In a second project, Louis-Philippe Morency, associate
professor of computer science at CMU, and Eva Szigethy, a clinical researcher
at UPMC and professor of psychiatry, medicine, and pediatrics at the University
of Pittsburgh, are developing sensing technologies that can automatically measure
subtle changes in individuals’ behavior — such as facial expressions and use of
language — that can act as biomarkers for depression.

These biomarkers will later be compared with the results of
traditional clinical assessments, allowing investigators to evaluate the
performance of their technology and make improvements where necessary. This
machine learning technology is intended to complement the ability of a
clinician to make decisions about diagnosis and treatment.  The team is working with a gastrointestinal-disorder
clinic at UPMC, due to the high rate of depression observed in patients with
functional gastrointestinal disorders.

This work involves training machine learning models on tens
of thousands of examples across multiple modalities, including language (the
spoken word), acoustic (prosody), and visual (facial expressions). The
computational load is heavy, but by running experiments in parallel on multiple
GPUS AWS services have allowed the researchers to train their models in a few
days instead of weeks.

A quick and objective marker of depression could help
clinicians more efficiently assess patients at baseline, identify patients who
would otherwise go undiagnosed, and more accurately measure patients’ responses
to interventions. The team presented a paper on the work, “Integrating
Multimodal Information in Large Pretrained Transformers”, at the July 2020
meeting of the Association for Computational Linguistics.


“Depression is a disease that affects more than 17 million adults in the United States, with up to two-thirds of all depression cases are left undiagnosed and therefore untreated,” said Dr. Morency. “New insights to increase the accuracy, efficiency, and adoption of depression screening have the potential to impact millions of patients, their families, and the healthcare system as a whole.”


The research projects on breast cancer and depression
represent just the tip of the iceberg when it comes to the research and
insights the collaboration across PHDA and AWS will ultimately deliver to
improve patient care. Teams of researchers, health-care professionals, and
machine learning experts across the PHDA continue to make progress on key
research topics, from the risk of aneurysms and predicting how cancer cells
progress, to improving the complex electronic-health-records
system
.