Gari Clifford is the tenured chair of the Department of Biomedical Informatics at Emory University and a professor of biomedical engineering at Georgia Institute of Technology. Clifford, an Amazon Research Award recipient, is seen here speaking at Emory University.
Gari Clifford is the tenured chair of the Department of Biomedical Informatics at Emory University and a professor of biomedical engineering at Georgia Institute of Technology. He is seen here speaking at Emory University.
Steve Nowland/Emory University

Using machine learning to reduce costs, increase accuracy, and improve access in healthcare

Gari Clifford, the chair of the Department of Biomedical Informatics at Emory University and an Amazon Research Award recipient, wants to transform healthcare.

Gari Clifford is an academic who keeps his eyes fixed on real-world problems. His work in machine learning and signal processing is centered on improving some of the world's most burdensome and overlooked healthcare issues.

Clifford, now the tenured chair of the Department of Biomedical Informatics at Emory University and a professor of Biomedical Engineering at Georgia Institute of Technology, got his start in theoretical physics. But near the end of his master’s degree in the mid 90’s, his interests began to change. Conway’s Game of Life spurred him to think about ways to actually measure complex biological systems. Neural networks seemed like the most reasonable answer.

Finding a group working on neural networks in the ‘90s wasn’t easy. But once he made his way to Oxford in 1998, where he pursued a biomedical engineering PhD, Clifford found himself learning and working at the epicenter of British artificial intelligence. He gained steady experience — not just in building neural networks, but also in processing the data properly.

Oxford is also where Clifford “became profoundly interested in solving real-world problems.” At first, his research focused on using machine learning to predict cardiovascular events and critical care needs in hospitals. “That’s where all the data was,” he explains.

Transforming healthcare

After graduate school, Clifford started to get excited about new areas, particularly neuropsychiatry and maternal-fetal health.

“These were the biggest areas where I could have the biggest effect,” Clifford said. “And they’ll have the biggest effect in low- to middle-income countries, which is where I’m most interested in making a difference.”

Edge machine learning is going to transform healthcare.
Gari Clifford

He’s since held research and faculty positions at MIT, Oxford, and more recently Emory and Georgia Tech, the latter two because he wanted to be more embedded in healthcare systems. He describes his lab as “applying machine learning to whatever problems doctors come up with.” But, he explains, his “secret agenda,” is to see it change healthcare entirely. And for that to happen, edge machine learning — machine learning done in real time and on edge devices — is the key, he said.

“Edge machine learning is going to transform healthcare,” Clifford predicts. Rather than processing data in the cloud, edge machine learning relies on smart devices that use deep machine learning algorithms to process data locally and in real time.

The cloud is still essential to collect the initial data and train the model. Scaling this work requires a large vendor like AWS, Clifford said. Only once the ML model is trained on the cloud can it then be run off the edge sensors in real time. Edge sensors continue to update the model locally, and the data only needs to be pushed to the cloud periodically to prevent model drift and share local updates across all sensors. “The models are much smaller than the data,” Clifford said. “So not only does this reduce the energy and bandwidth needed, but it can preserve the privacy of the patient.”

Monitoring patient environments

Currently, the Clifford Lab — now in its twelfth year and supporting 12 graduate students and six postdoctoral scholars — is using edge machine learning to monitor patient environments. While today’s healthcare system doesn’t ignore a patient’s social support system, such as their interactions with friends, relatives or care providers, it also doesn’t record them, Clifford explained.

A complete picture of an individual’s support system could inform their care, he adds. For instance, decreased interaction with others, changes in their social circle or word choices, and decreased daily travel can all indicate a worsening of the patient’s condition. And they can be easily measured with a smartphone app running edge technology. This strategy is particularly important for the maternal and neuropsychiatry patient populations Clifford is working with, because “traditional healthcare is quite limited for these patient groups,” he said.

In 2018, Clifford received an Amazon Machine Learning Research Award for this work. The funding from Amazon allowed Clifford’s team to develop prototypes and partially funded two PhD students working on the project. They developed audio and Bluetooth algorithms that can run on Raspberry Pis to track who is going in and out of a patient’s hospital care environment. Using the audio and Bluetooth data as a diagnostic tool, the team hopes to understand whether a patient is degenerating quickly and what might be the cause.

“Based on the data, maybe we can come up with interventions — like a sleep intervention — that would reduce deterioration,” Clifford said.

“We started by developing [this technology] for in-hospital use because it allows for rapid development. The hospital is like an experimental environment that's easier to control. It’s much more difficult to do that in someone's home,” he added. But that’s the direction in which his team is moving.

Helping patients stay at home longer

One project Clifford’s group is working on uses the same Raspberry Pis with added sensors to monitor patients with a range of neuropsychiatry issues, including schizophrenia, Alzheimer’s, mild cognitive impairment, Parkinson’s disease, and postpartum depression.

Zifan Jiang, a PhD candidate in machine learning and graduate research assistant at Emory University, is seen here testing a device while wearing sterile gloves and a mask.
Zifan Jiang, a PhD candidate in machine learning and graduate research assistant at Emory University, is seen here testing a device in the Clifford Lab.
Courtesy of Gari Clifford

The strategy is to deploy Raspberry Pi devices in these patients’ home environments to monitor their interactions, movement and who comes and goes. Monitoring and managing the patient environment — such as how often they see a healthcare provider, their sleeping patterns, or how often they communicate with others — could help patients live in their homes longer (as opposed to hospitalization) and improve quality of life, Clifford said.

Most importantly for Clifford, the low cost of the tiny Raspberry Pi devices means this strategy is cost-effective. It can be rapidly scaled and deployed in middle- and low-income countries, places where mental and maternal health create an enormous burden but go largely unmanaged.

“It’s an exciting phase,” Clifford said. But many challenges are ahead, like acceptance of the technology. “As we expand sensors and tech, people are obviously concerned about privacy,” he noted. A 2019 study by Pega found that only 30% of respondents felt comfortable with businesses that use artificial intelligence to interact with them.

The importance of developing with inclusivity

As this technology develops, it’s critical to pull underrepresented groups into the process, Clifford explains. Artificial intelligence as an industry tends to be very homogeneous, he notes, and building trust will require that people from different cultures and backgrounds have a hand in its development.

Comfort levels with this technology are not likely to be any higher in the healthcare realm. “There is systemic distrust of this kind of technology, especially in disparity populations,” Clifford said. “And a history of the medical research community exploiting minority populations.”

Clifford’s lab invests significant time trying to build that trust.

In a collaboration with the Morehouse School of Medicine, the team built an app with Amazon Web Services (AWS), leveraging cloud-based computing and infrastructure resources to measure young African Americans’ exposure to different factors that affect cardiovascular disease, such as exercise, healthy food, and air pollution. Community engagement leaders in Atlanta facilitated the data collection, and several interested community members were trained and brought on to the development team. The aim is “to build the infrastructure for them and with them,” Clifford said. The app has just been made open source and “the hope is we have built a substrate the community could build companies out of.”

[The midwives] have fully taken ownership, and they don’t need us anymore. That was the best end result I’ve had with my research, ever.
Gari Clifford

In Guatemala, a midwife organization Clifford’s group has been collaborating with to predict maternal-fetal health outcomes has completely taken ownership of the technology. The strategy collects inputs like low-cost ultrasound data and pictures of daily blood pressure, and the data, once computed via AWS (Clifford’s team utilized AWS tools like Elastic Cloud Compute, Elastic Load Balancing, Relational Database Service, and GuardDuty, among others) can help predict fetal health.

Next up, Clifford is in search of funding to put that algorithm on the ultrasound device so the computing can be done locally. But in the meantime, the midwives have adopted the technology as the standard of care and reported that they hadn’t lost a single patient in the deployment area over last year.

“They have fully taken ownership, and they don’t need us anymore,” Clifford said. “That was the best end result I’ve had with my research, ever.”

Related content

US, WA, Seattle
The Global Media Entertainment Science team uses state of the art economics and machine learning models to provide Amazon’s entertainment businesses guidance on strategically important questions. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Python is necessary, and experience with SQL and UNIX would be a plus. These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, scientists, and product managers. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement. Roughly 85% of previous cohorts have converted to full time scientist employment at Amazon. If you are interested, please send your CV to our mailing list at econ-internship@amazon.com. Key job responsibilities
US, CA, Palo Alto
The Amazon Search team creates powerful, customer-focused search solutions and technologies. Whenever a customer visits an Amazon site worldwide and types in a query or browses through product categories, Amazon Product Search services go to work. We design, develop, and deploy high performance, fault-tolerant distributed search systems used by millions of Amazon customers every day. Our Search Relevance team works to maximize the quality and effectiveness of the search experience for visitors to Amazon websites worldwide. The Search Relevance team focuses on several technical areas for improving search quality. In this role, you will invent universally applicable signals and algorithms for training machine-learned ranking models. The relevance improvements you make will help millions of customers discover the products they want from a catalog containing millions of products. You will work on problems such as predicting the popularity of new products, developing new ranking features and algorithms that capture unique characteristics, and analyzing the differences in behavior of different categories of customers. The work will span the whole development pipeline, including data analysis, prototyping, A/B testing, and creating production-level components. Joining this team, you’ll experience the benefits of working in a dynamic, entrepreneurial environment, while leveraging the resources of Amazon.com (AMZN), one of the world’s leading Internet companies. We provide a highly customer-centric, team-oriented environment in our offices located in Palo Alto, California. Please visit https://www.amazon.science for more information
US, WA, Seattle
To ensure a great internship experience, please keep these things in mind. This is a full time internship and requires an individual to work 40 hours a week for the duration of the internship. Amazon requires an intern to be located where their assigned team is. Amazon is happy to provide relocation and housing assistance if you are located 50 miles or further from the office location. Do you have a strong machine learning background and want to help build new speech and language technology? Amazon is looking for PhD students who are ready to tackle some of the most interesting research problems on the leading edge of natural language processing. We are hiring in all areas of spoken language understanding: NLP, NLU, ASR, text-to-speech (TTS), and more! A successful candidate will be a self-starter comfortable with ambiguity, strong attention to detail, and the ability to work in a fast-paced, ever-changing environment. As an Applied Science Intern, you will develop and implement novel scalable algorithms and modeling techniques to advance the state-of-the-art in technology areas at the intersection of ML, NLP, search, and deep learning. You will work side-by-side with global experts in speech and language to solve challenging groundbreaking research problems on production scale data. The ideal candidate must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. Amazon has positions available for Natural Language Processing & Speech Intern positions in multiple locations across the United States. Amazon fundamentally believes that scientific innovation is essential to being the most customer-centric company in the world. Please visit our website to stay updated with the research our teams are working on: https://www.amazon.science/research-areas/conversational-ai-natural-language-processing
US, WA, Seattle
To ensure a great internship experience, please keep these things in mind. This is a full time internship and requires an individual to work 40 hours a week for the duration of the internship. Amazon requires an intern to be located where their assigned team is. Amazon is happy to provide relocation and housing assistance if you are located 50 miles or further from the office location. The Research team at Amazon works passionately to apply cutting-edge advances in technology to solve real-world problems. Do you have a strong machine learning background and want to help build new speech and language technology? Do you welcome the challenge to apply optimization theory into practice through experimentation and invention? Would you love to help us develop the algorithms and models that power computer vision services at Amazon, such as Amazon Rekognition, Amazon Go, Visual Search, etc? At Amazon we hire research science interns to work in a number of domains including Operations Research, Optimization, Speech Technologies, Computer Vision, Robotics, and more! As an intern, you will be challenged to apply theory into practice through experimentation and invention, develop new algorithms using mathematical programming techniques for complex problems, implement prototypes and work with massive datasets. Amazon has a culture of data-driven decision-making, and the expectation is that analytics are timely, accurate, innovative and actionable. Amazon Science gives insight into the company’s approach to customer-obsessed scientific innovation. Amazon fundamentally believes that scientific innovation is essential to being the most customer-centric company in the world. It’s the company’s ability to have an impact at scale that allows us to attract some of the brightest minds in artificial intelligence and related fields. Amazon Scientist use our working backwards method to enrich the way we live and work. For more information on the Amazon Science community please visit https://www.amazon.science.
US, WA, Seattle
To ensure a great internship experience, please keep these things in mind. This is a full time internship and requires an individual to work 40 hours a week for the duration of the internship. Amazon requires an intern to be located where their assigned team is. Amazon is happy to provide relocation and housing assistance if you are located 50 miles or further from the office location. The Research team at Amazon works passionately to apply cutting-edge advances in technology to solve real-world problems. Do you have a strong machine learning background and want to help build new speech and language technology? Do you welcome the challenge to apply optimization theory into practice through experimentation and invention? Would you love to help us develop the algorithms and models that power computer vision services at Amazon, such as Amazon Rekognition, Amazon Go, Visual Search, etc? At Amazon we hire research science interns to work in a number of domains including Operations Research, Optimization, Speech Technologies, Computer Vision, Robotics, and more! As an intern, you will be challenged to apply theory into practice through experimentation and invention, develop new algorithms using mathematical programming techniques for complex problems, implement prototypes and work with massive datasets. Amazon has a culture of data-driven decision-making, and the expectation is that analytics are timely, accurate, innovative and actionable. Amazon Science gives insight into the company’s approach to customer-obsessed scientific innovation. Amazon fundamentally believes that scientific innovation is essential to being the most customer-centric company in the world. It’s the company’s ability to have an impact at scale that allows us to attract some of the brightest minds in artificial intelligence and related fields. Amazon Scientist use our working backwards method to enrich the way we live and work. For more information on the Amazon Science community please visit https://www.amazon.science.
CA, ON, Toronto
To ensure a great internship experience, please keep these things in mind. This is a full time internship and requires an individual to work 40 hours a week for the duration of the internship. Amazon requires an intern to be located where their assigned team is. Amazon is happy to provide relocation and housing assistance if you are located 50 miles or further from the office location. Are you a Masters student interested in machine learning, natural language processing, computer vision, automated reasoning, or robotics? We are looking for skilled scientists capable of putting theory into practice through experimentation and invention, leveraging science techniques and implementing systems to work on massive datasets in an effort to tackle never-before-solved problems. A successful candidate will be a self-starter comfortable with ambiguity, strong attention to detail, and the ability to work in a fast-paced, ever-changing environment. As an Applied Science Intern, you will own the design and development of end-to-end systems. You’ll have the opportunity to create technical roadmaps, and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists, and other science interns to develop solutions and deploy them into production. The ideal scientist must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. Amazon Science gives insight into the company’s approach to customer-obsessed scientific innovation. Amazon fundamentally believes that scientific innovation is essential to being the most customer-centric company in the world. It’s the company’s ability to have an impact at scale that allows us to attract some of the brightest minds in artificial intelligence and related fields. Our scientists use our working backwards method to enrich the way we live and work. For more information on the Amazon Science community please visit https://www.amazon.science.
CA, ON, Toronto
To ensure a great internship experience, please keep these things in mind. This is a full time internship and requires an individual to work 40 hours a week for the duration of the internship. Amazon requires an intern to be located where their assigned team is. Amazon is happy to provide relocation and housing assistance if you are located 50 miles or further from the office location. Are you a PhD student interested in machine learning, natural language processing, computer vision, automated reasoning, or robotics? We are looking for skilled scientists capable of putting theory into practice through experimentation and invention, leveraging science techniques and implementing systems to work on massive datasets in an effort to tackle never-before-solved problems. A successful candidate will be a self-starter comfortable with ambiguity, strong attention to detail, and the ability to work in a fast-paced, ever-changing environment. As an Applied Science Intern, you will own the design and development of end-to-end systems. You’ll have the opportunity to create technical roadmaps, and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists, and other science interns to develop solutions and deploy them into production. The ideal scientist must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. Amazon Science gives insight into the company’s approach to customer-obsessed scientific innovation. Amazon fundamentally believes that scientific innovation is essential to being the most customer-centric company in the world. It’s the company’s ability to have an impact at scale that allows us to attract some of the brightest minds in artificial intelligence and related fields. Our scientists use our working backwards method to enrich the way we live and work. For more information on the Amazon Science community please visit https://www.amazon.science.
US, WA, Seattle
To ensure a great internship experience, please keep these things in mind. This is a full time internship and requires an individual to work 40 hours a week for the duration of the internship. Amazon requires an intern to be located where their assigned team is. Amazon is happy to provide relocation and housing assistance if you are located 50 miles or further from the office location. We are looking for Masters or PhD students excited about working on Automated Reasoning or Storage System problems at the intersection of theory and practice to drive innovation and provide value for our customers. AWS Automated Reasoning teams deliver tools that are called billions of times daily. Amazon development teams are integrating automated-reasoning tools such as Dafny, P, and SAW into their development processes, raising the bar on the security, durability, availability, and quality of our products. AWS Automated Reasoning teams are changing how computer systems built on top of the cloud are developed and operated. AWS Automated Reasoning teams work in areas including: Distributed proof search, SAT and SMT solvers, Reasoning about distributed systems, Automating regulatory compliance, Program analysis and synthesis, Security and privacy, Cryptography, Static analysis, Property-based testing, Model-checking, Deductive verification, compilation into mainstream programming languages, Automatic test generation, and Static and dynamic methods for concurrent systems. AWS Storage Systems teams manage trillions of objects in storage, retrieving them with predictable low latency, building software that deploys to thousands of hosts, achieving 99.999999999% (you didn’t read that wrong, that’s 11 nines!) durability. AWS storage services grapple with exciting problems at enormous scale. Amazon S3 powers businesses across the globe that make the lives of customers better every day, and forms the backbone for applications at all scales and in all industries ranging from multimedia to genomics. This scale and data diversity requires constant innovation in algorithms, systems and modeling. AWS Storage Systems teams work in areas including: Error-correcting coding and durability modeling, system and distributed system performance optimization and modeling, designing and implementing distributed, multi-tenant systems, formal verification and strong, practical assurances of correctness, bits-IOPS-Watts: the interplay between computation, performance, and energy, data compression - both general-purpose and domain specific, research challenges with storage media, both existing and emerging, and exploring the intersection between storage and quantum technologies. As an Applied Science Intern, you will work closely with Amazon scientists and other science interns to develop solutions and deploy them into production. The ideal scientist must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. A successful candidate will be a self-starter with strong attention to detail and the ability to thrive in a fast-paced, ever-changing environment who is comfortable with ambiguity. Amazon believes that scientific innovation is essential to being the world’s most customer-centric company. Our ability to have impact at scale allows us to attract some of the brightest minds in Automated Reasoning and related fields. Our scientists work backwards to produce innovative solutions that delight our customers. Please visit https://www.amazon.science (https://www.amazon.science/) for more information.
US, WA, Seattle
To ensure a great internship experience, please keep these things in mind. This is a full time internship and requires an individual to work 40 hours a week for the duration of the internship. Amazon requires an intern to be located where their assigned team is. Amazon is happy to provide relocation and housing assistance if you are located 50 miles or further from the office location. We are looking for PhD students excited about working on Automated Reasoning or Storage System problems at the intersection of theory and practice to drive innovation and provide value for our customers. AWS Automated Reasoning teams deliver tools that are called billions of times daily. Amazon development teams are integrating automated-reasoning tools such as Dafny, P, and SAW into their development processes, raising the bar on the security, durability, availability, and quality of our products. AWS Automated Reasoning teams are changing how computer systems built on top of the cloud are developed and operated. AWS Automated Reasoning teams work in areas including: Distributed proof search, SAT and SMT solvers, Reasoning about distributed systems, Automating regulatory compliance, Program analysis and synthesis, Security and privacy, Cryptography, Static analysis, Property-based testing, Model-checking, Deductive verification, compilation into mainstream programming languages, Automatic test generation, and Static and dynamic methods for concurrent systems. AWS Storage Systems teams manage trillions of objects in storage, retrieving them with predictable low latency, building software that deploys to thousands of hosts, achieving 99.999999999% (you didn’t read that wrong, that’s 11 nines!) durability. AWS storage services grapple with exciting problems at enormous scale. Amazon S3 powers businesses across the globe that make the lives of customers better every day, and forms the backbone for applications at all scales and in all industries ranging from multimedia to genomics. This scale and data diversity requires constant innovation in algorithms, systems and modeling. AWS Storage Systems teams work in areas including: Error-correcting coding and durability modeling, system and distributed system performance optimization and modeling, designing and implementing distributed, multi-tenant systems, formal verification and strong, practical assurances of correctness, bits-IOPS-Watts: the interplay between computation, performance, and energy, data compression - both general-purpose and domain specific, research challenges with storage media, both existing and emerging, and exploring the intersection between storage and quantum technologies. As an Applied Science Intern, you will work closely with Amazon scientists and other science interns to develop solutions and deploy them into production. The ideal scientist must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. A successful candidate will be a self-starter with strong attention to detail and the ability to thrive in a fast-paced, ever-changing environment who is comfortable with ambiguity. Amazon believes that scientific innovation is essential to being the world’s most customer-centric company. Our ability to have impact at scale allows us to attract some of the brightest minds in Automated Reasoning and related fields. Our scientists work backwards to produce innovative solutions that delight our customers. Please visit https://www.amazon.science (https://www.amazon.science/) for more information.
US, WA, Seattle
To ensure a great internship experience, please keep these things in mind. This is a full time internship and requires an individual to work 40 hours a week for the duration of the internship. Amazon requires an intern to be located where their assigned team is. Amazon is happy to provide relocation and housing assistance if you are located 50 miles or further from the office location. Help us develop the algorithms and models that power computer vision services at Amazon, such as Amazon Rekognition, Amazon Go, Visual Search, and more! We are combining computer vision, mobile robots, advanced end-of-arm tooling and high-degree of freedom movement to solve real-world problems at huge scale. As an intern, you will help build solutions where visual input helps the customers shop, anticipate technological advances, work with leading edge technology, focus on highly targeted customer use-cases, and launch products that solve problems for Amazon customers. A successful candidate will be a self-starter comfortable with ambiguity, strong attention to detail, and the ability to work in a fast-paced, ever-changing environment. You will own the design and development of end-to-end systems and have the opportunity to write technical white papers, create technical roadmaps, and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists, and other science interns to develop solutions and deploy them into production. The ideal scientist must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. Amazon Science gives insight into the company’s approach to customer-obsessed scientific innovation. Amazon fundamentally believes that scientific innovation is essential to being the most customer-centric company in the world. It’s the company’s ability to have an impact at scale that allows us to attract some of the brightest minds in artificial intelligence and related fields. Amazon Scientist use our working backwards method to enrich the way we live and work. For more information on the Amazon Science community please visit https://www.amazon.science