EHRs: The Good and the Bad
In the past, medical transcription used to be easier. A doctor dictated exam outcomes on the fly, and a transcriptionist typed it into the patient record immediately. This allowed doctors to focus on patients while still recording data.
Then, electronic health records (EHRs) came into the picture. EHRs were intended to be a way to better track health data for hospitals, payers and physicians. Although they have good intentions, they often end up causing more problems than they solve.
According to a study by Northwestern University, physicians who have EHRs in their exam rooms spend around 33% of their time looking at their computer screens, while doctors who use paper charts spend only 9% of their time looking at screens.
Also, EHRs can store massive amounts of data, which is a double-edged sword because though data is important, the structure of that data creates challenges. On one hand, it is too limiting. Doctors can enter information about a patient's medical history, medications and procedures--but only through constrained check boxes that don't capture nuances and complexities.
While unstructured "notes" sections can be included in comment boxes, there is no standard format for how these should be written, and it is hard to pull insights without diving into detail. Furthermore, this data is often copied and pasted repeatedly into different areas within the EHR, resulting in a phenomenon called "note bloat," when there's so much information it's difficult to make good use of it.
Where Does Blockchain Technology and AI Come In?
Blockchain technology (and apps built on a blockchain) can make data organized and easily accessible, while artificial intelligence makes it possible to extract intelligent insights from vast amounts of data that no human could ever analyze.
Blockchain is a digital ledger that records and shares transactions and interactions in chronological order, providing security and interoperability for healthcare providers and their patients. In healthcare, for example, each patient visit, diagnosis, prescribed treatment, outcome and other key data that goes in the EHR are considered the transactions. Various providers, payers and pharmacies all record this information on the same ledger for a given patient, and they can access the data put there by each other. For example, medications can be noted, assessed and managed to prevent contradictions or misuse.
The apps that can be built on the blockchain further help with parsing and reading data that is logged but with details stored separately--in a PDF, for example. It's worth noting that blockchains for health data can and should be created as a permissioned ecosystem of trusted collaborators with additional controls that protect personally identifiable information while allowing anonymized sharing of personal health information.
Using the database, providers and specialists who see patients for the first time can rest assured that the data regarding previous tests, diagnoses and treatments is accurate. Having highly reliable patient data on the ledger means providers can spend less time on repetitive data entry tasks, prevent catastrophic misdiagnoses and provide better predictive solutions to patients. Furthermore, this data is now much more consumable by intelligent algorithms.
For example, California-based startup PokitDok is using blockchain to develop application programming interfaces (APIs) for the healthcare industry in areas such as identity management, claims and pharmacy in order to create a more secure network for accessing and sharing patient data. It also uses machine learning to analyze large amounts of data and speed up processes--for instance, it's able to run an eligibility check on an insurance claim in just seconds rather than days, saving healthcare providers time and money.
Once the data is organized in a transparent and fully reliable way on a blockchain, machine learning and eventually artificial intelligence (AI) can learn from the patterns in the data and execute analyses very quickly.
Digital Reasoning is a startup that's using AI to help healthcare professionals make better decisions. It uses complex algorithms to organize data into graphs and detect patterns, helping machines "think more like people do." As a result, doctors are able to see a clearer picture of a patient's health and make more informed decisions based on all that information.
Complications Within Interoperability
The industry mindset around sharing data has typically been very conservative, even antagonistic. However, over the past two years, new standards like fast healthcare interoperability resources (FHIR) are leading to more sharing--35% of U.S. hospitals plan to use open APIs within the next year, and that data is their competitive advantage. In order to truly provide value to patients, though, this trend needs to continue and extend to all players in the continuum of patient care.
Healthcare systems experts understand the importance of providers being able to collaborate, even when they don't know one another. The trouble is that interoperability in healthcare is complicated by a variety of factors.
Because providers all operate within their own systems, identifying who previously treated a patient, as well as when and where treatment took place, can be difficult. Also, EHRs may be moved into health information exchanges, but they are still controlled by data silos. Patients cannot choose what specific data of theirs is shared. To prevent unwanted access, they may put a blanket denial on any of their health information being shared.
Together, these factors (and many others) make interoperability a vital but difficult-to-achieve goal for healthcare systems. Therefore, one of the biggest reasons blockchain is becoming such a popular healthcare buzzword is because it may be the solution to making safe and efficient interoperability possible. And from there, with the application of AI, major innovation will accelerate.
The Challenges to Implementing Blockchain and AI
Despite all the problems blockchain and AI can solve for doctors, hospitals and patients, they're not without their challenges. Blockchain must resolve problems related to scalability, and AI faces the challenge of getting doctors on board.
With AI, doctors will need to believe in the technology and trust that it's analyzing the data accurately. Doctors will still be the ones diagnosing patients and providing treatment plans, but if they don't trust the information they're receiving from AI technology, they won't be able to do their jobs to the best of their ability.
At the end of the day, humans want to be cared for by other humans--not robots. But doctors are spending far too much time inputting information into EHRs rather than spending time with their patients. Blockchain and AI won't be able to take over all of doctors' responsibilities, but they can help them get back to what they love: helping people be healthy and heal.
Source: Modern Medicine Network (View full article)
Posted by Dan Corcoran on January 15, 2018 07:21 AM
Post a comment