What are you working on in 2021? So far, I’ve spent my New Year reading through articles with predictions for the top healthcare technology trends of 2021. Not surprisingly, each article began by acknowledging how the pandemic has accelerated digital transformation at every level of healthcare.
For decades, the industry has promised to become more “patient-centered” but only the harsh demands of COVID-19 have forced massive changes. In a TechRepublic article, Ian McCrae, CEO of Orion Health described COVID-19 as “ushering in the long-overdue transformation of the healthcare system and, finally, a move to patient-centric health.”
Other prognosticators heralded the advent of AI and machine learning, looking forward to amazing improvements in diagnostic medicine and even the ability to predict a person’s healthcare needs in advance.
Sound too good to be true? You are correct. We’re not quite there yet. There remain several stumbling blocks on the path to this nirvana of patient-centric healthcare.
In this blog, we will look at two of the most persistent technology problems – (1) mining the wealth of medical data, and (2) interoperability between Electronic Health Record (EHR) systems – and explore how Intelligent Document Processing (IDP) can help to solve them in 2021 and beyond.
First of all, interoperability will be a huge priority for public and private healthcare organizations and companies in 2021, according to Scott Galbari, Lyniate Chief Technology Officer as referenced in the Tech Republic. Galbari anticipates that the new presidential administration will prioritize interoperability with reinvestment in and modernization of the IT infrastructures of federal and state public health agencies, to better position and prepare the US healthcare system for future public health crises.
But here’s the problem with that. In 2019, Forbes published a troubling report about the problems of the effort to implement EHR systems across the USA healthcare industry. After some $36 billion of taxpayer money was spent on EHR software for thousands of healthcare providers, these proprietary systems made by over 700 vendors routinely do not talk to one another.
Remarkably, this means that doctors still resort to printing out then rescanning medical documents and transferring it to other providers via fax and CD-ROMs! Patients, meanwhile, still struggle to access their own records—and sometimes, just plain can’t. You can read more about this startling report on the Parascript blog page.
The pandemic has done nothing to fix the interoperability problem. We reported last year how this dramatically affected the CDC’s ability to collect COVID-19 case reports. Because hospitals use incompatible proprietary EHR software, the COVID case reports must be printed out first, faxed and then re-entered by public health authorities. This outdated, ancient process is wasting valuable time and leading to potentially harmful transcription errors. Forms faxed between hospitals and laboratories often are missing critical information, leading to delays in contacting patients and identifying the people with whom they had close contact.
IDP Can Bridge the Gap
Companies such as Parascript who make IDP software have proven their value and integrity in automating the data collection from faxed healthcare forms such as the Coronavirus Case Report Form. IDP software sits between the originating EHR system and the receiving system. Using advanced machine learning algorithms and computer vision, the software opens and reads the fax document, extracts the data needed, and sends that data into the receiving system.
Mining Data from Medical Records
Secondly, the Forbes healthcare tech council believes that “actionable big data” is one of the top five trends for 2021. EHR systems provide a wealth of data to create patterns and predictability models for health treatment plans. Well-educated patients who have access to their own medical records can help to create a shift toward patient-centered delivery systems.
Collecting Relevant Data
The problem is how to collect all the relevant data. EHR/EMR-based data is generally available, though as shown above it is hard to collect because of the lack of interoperability. More importantly, a treasure store of qualitative data is trapped within the complex structure of medical charts, each made-up of different medical records that rarely have needed data, which is uniformly located in the same position.
Analysis of the data in medical charts requires treating each medical record as a separate entity. However, many charts exist as single monolithic PDF files containing many discrete records. So not only is there a challenge with accessing data from each record, but there is the challenge of separating each chart file into individual records.
New Miner’s Tool
Using machine learning algorithms, IDP software can be trained on medical charts to identify key characteristics of each individual medical record. Different algorithms are often employed that evaluate various attributes such as presence of graphical information (e.g., logos), textual data (e.g., facility names and addresses), and even spatial information such as the distance between different dates on a page and use of specific language related to those dates.
All these attributes are then analyzed to identify the most reliable way to identify and separate one record from another. Once separated, data extraction can then be employed with the final step being to employ Intelligent Capture to further identify specific patterns in the text that can reveal various problems and conditions not only with a single patient, but across a patient population.
Into the Future
The future is bright for digital healthcare initiatives, provided that the industry addresses the problems of interoperability and data collection. IDP software powered by AI and machine learning can help. For 2021, it is an essential tool to have in every healthcare IT toolkit.