As healthcare professionals are facing massive pressure not only to ensure the quality of care, but also to come up with new solutions, cures and treatments, they are becoming increasingly dependent on advanced technologies like artificial intelligence (AI) and machine learning (ML).
But it is hardly a smooth partnership. The issues of skills shortages at the entry-level and of “messy data” in leveraging patient records at the high end are merely book-ends for a range of challenges that span these fields.
Last week’s annual Amazon Web Services Re:Invent conference, one of the largest cloud-focused events in the world, saw the launch or demonstration of a range of new cloud-based tools that are ideal for health research and treatment. ML, defined as computer algorithms that improve automatically through experience, was at the heart of these.
The tools raised two key questions in terms of global and local relevance, namely how messy data is addressed, and how relevant these are to South Africa.
We asked a man at the heart of AWS’s health initiatives, Shez Partovi, AWS director of worldwide business development for healthcare, life sciences, and genomics. It all starts with ML, he says.
“In South Africa, we have seen how providing access to advanced technologies such as ML is vital to stopping the spread of COVID-19 and helping individuals quickly find medical help when they fall ill. GovChat, South Africa’s largest citizen engagement platform, launched a COVID-19 chatbot in less than two weeks using Amazon Lex, an AI service for building conversational interfaces into any application using voice and text.
“The chatbot provides health advice and recommendations on whether to get a test for COVID-19, information on the nearest COVID-19 testing facility, the ability to receive test results, and the option for citizens to report COVID-19 symptoms for themselves, their family, or household members.”
ML in particular is being roped in globally to address the massive volumes of data being gathered from a variety of unrelated sources, he says.
“ML has the potential to serve as an assistive tool for healthcare professionals, providing the support they need to process and analyse the increasing amount of data generated by doctors, hospitals, researchers, and organisations, including structured data like Electronic Health Record forms, as well as unstructured data, such as emails, text documents, and even voice notes.
“ML is being used in a variety of tasks such as analysing medical images to advancing precision medicine. Tools that leverage natural language processing, pattern recognition, and risk identification are also fuelling new models for predictive, preventive, and population health and have the potential to help providers identify gaps in care and improve the health of individuals and communities.”
Go to the next page to read about how Amazon’s latest machine learning tools can read a doctor’s handwriting.
One of the new tools already in use, Amazon Comprehend Medical, is already proving itself. Partovi describes it as “a highly accurate natural language processing service for medical text, which uses machine learning to extract disease conditions, medications, and treatment outcomes from patient notes, clinical trial reports, and other electronic health records”.
The beauty of Comprehend Medical is that requires no ML expertise, no complicated rules to write, no models to train, and it is continuously improving.
It is in use at the Fred Hutchinson Cancer Research Centre, home to three Nobel laureates, where interdisciplinary teams of world-renowned scientists seek new ways to prevent, diagnose and treat cancer, HIV/AIDS and other life-threatening diseases.
Matthew Trunnell, chief information officer at the institution, gives a powerful perspective on its use: “Curing cancer is, inherently, an issue of time. For cancer patients and the researchers dedicated to curing them, time is the limiting resource. The process of developing clinical trials and connecting them with the right patients requires research teams to manually sift through mountains of unstructured medical records to look for treatment insights. Amazon Comprehend Medical can reduce this time burden from hours to seconds. This is a vital step toward getting researchers rapid access to the information they need when they need it so they can find actionable insights to advance lifesaving therapies for patients.”
In South Africa, the Department of Health is working to create paperless hospitals in the country.
Partovi spells out the clear benefits: “Paper-based clinical records in healthcare facilities result in extended patient waiting times – sometimes between 60 and 80 minutes; reduced quality of care due to files being lost in overcrowded filing rooms; and increased litigation costs. Using Amazon Comprehend Medical, regional public hospitals implemented indexing systems for easier retrieval of scanned patient records.
“Called Hybrid e-scripting, the solution enables electronic data storage without typing, an e-sketch pad for electronically accessible medical diagrams, and easy-to-use automated pharmacy labelling to reduce medication dispensing time. The impact to implementing this solution was a 90% reduction in patient wait time for fulfilling prescriptions, a 10% reduction in patient hospital wait time, and a cost savings of R1- million in software licenses.”
And then there is the Covid-19 pandemic and the massive challenge of tracking exposure. History may well record this as one of the great triumphs of AI and ML. For example, South African developer A2D24, was in just three days able to develop and deploy an automated AI platform using Amazon Lex for a private hospital group, to inform anyone who has been in one of their hospitals of possible exposure to a confirmed COVID-19 patient.
The system automatically sends an alert message and conducts an SMS based triage where, each day, patients are asked questions about the type of symptoms they are experiencing and, based on the responses, the chatbot recommends what to do, and whether to seek further medical help.
“This application has helped provide critical care to thousands of patients and staff across the country, and potentially prevent many new infections,” says Partovi.
The fundamental issue of messy patient data remains, however, he says.
“A challenge to fully realising the potential of ML in healthcare is health data locked in unstructured medical text, which makes applying ML time consuming, costly, and sometimes impossible. Having patient medical data consolidated into a secure data lake, organized in a standard format, and properly indexed with key entities identified, is key to making this vast amount of information searchable and ready for applying ML learning on top, to derive insights and relationships for improving patient care.”
Get that right, and the long-term potential is incalculable.
Says Partovi: “We’re seeing a renaissance in healthcare as more of our customers leverage ML technologies to uncover new ways to enhance patient care, improve health outcomes, and ultimately save lives.”
- Arthur Goldstuck is founder of World Wide Worx and editor-in-chief of Gadget.co.za. Follow him on Twitter and Instagram on @art2gee