Earlier this year, we wrote about the influx of tech companies entering the healthcare space. Amazon, Apple, Facebook, Google, IBM, Microsoft, even Nokia. Recently, we learned that Amazon is going a step further with its latest Amazon Web Service (AWS) solution — called Amazon Comprehend Medical (ACM). This latest AWS tool can analyze unstructured text in doctor’s notes, clinical trial reports, and electronic health records to identify information like a patient’s medical condition, procedures, and medications and dosages. Mining critical information from these reports is a tedious and inefficient process that typically requires data entry by healthcare providers (HCPs) or teams of developers writing custom code. ACM’s use of natural language processing will address these issues.
Amazon states, “In a nutshell, this Natural Language Processing service provides simple real-time APIs for language detection, entity categorization, sentiment analysis, and key phrase extraction.”
In its announcement, Amazon also noted that Comprehend Medical is HIPAA-eligible, can identify protected health information like name, age, and medical record number, while also adhering to the European Union’s standards for General Data Protection Regulation.
Amazon is already working with companies like Deloitte and Pricewaterhousecoopers, as well Seattle’s Fred Hutchinson Cancer Research Center and Roche Diagnostics to rapidly process unstructured data to find lifesaving insights, personalize healthcare, enable decision support and population analytics, and more.
As we said earlier this year, tech is moving fast, and pharma needs to keep up. One way to do that is being open to more partnerships with tech giants like Amazon and others.
Why is ACM an important development?
ACM is expected to give HCPs and health economics/outcomes researchers the ability to share and analyze data sets that were previously not practical to analyze due to the disparate nature of healthcare data and unstructured patient-specific notes. Simplified, streamlined access to healthcare data is critical to assessing geographic disparity of care, identifying predicators of disease, assessing new therapies, identifying best practices, fine-tuning treatment guidelines and evaluating current therapies and procedures. Additionally, the fact that ACM enables personal information to be removed effectively addresses confidentiality requirements.
Why does this matter?
Driving efficiency in the clinical trial process …
It is critical that appropriate selection criteria are quickly identified to recruit patients for trials. Given that ACM understands and identifies complex medical information in unstructured text, indexing and searching is easier. By using these insights, identification of appropriate patients for trial recruitment becomes much more efficient from a time and cost perspective. The potential benefits for researchers, biopharma research sponsors and patients in fielding research, analyzing data, reporting results and bringing new therapies to market is clear.
Making the most appropriate clinical decisions …
By utilizing ACM, early warning systems can be built to help identify individuals at risk of debilitating diseases by extracting diagnosis, and signs and symptoms from more than hundreds of thousands of clinical notes. By providing a singular view into patient histories, HCPs will be able to make more informed, proactive clinical decisions that can impact progression of disease, thus improving patient outcomes and driving cost-effective care.
In summary, by enhancing the ability to more effectively access, analyze and apply healthcare data; patients, HCPs, researchers and health plans will benefit in several ways, many of which are yet to be determined. It remains to be seen how quickly this service and others like it will be adopted. It is likely that consortiums will be formed to represent stakeholder group interests and ensure that all voices are heard through the evolution.
Mike Motto is Senior Vice President, Market Access at Intouch Solutions.