Lab Soft News

Amazon Launches New Medical Record Language Processing Service

One of the most significant factors in extracting information from EHR record is the use of natural language processing (NLP) which I have referred to in a number of previous  notes (see, for example: EMRs and the Data Entry Paradox; Same Concept Not Applicable in the LIS World; Assessing Drugs Using "Real World Evidence" in Addition to Clinical Trials; AI Allows Computers to "Read" EHR Records and Make Predictions). A recent article discussed why one should "care" about Amazon's new medical language processing service (see: Why Should You Care About Amazon's New Medical Language Processing Service). Below is an excerpt from it:

Keeping track of your medical records can be a complex task....One of the significant challenges of handling medical records is that for each patient there is a variety of types of "notes" entered over time by health care professionals. These may include prescriptions, observation and administration of drugs and therapies, test results, x-rays, CT-scans, heart rate measured over months, surgical history, immunization history and family history. So the data type can be anything from a string, or a time-series data to an image or a very high definition video.The second challenge of handling data is accessibility. Although there is a generic set of rules in the US under Health Insurance Portability and Accountability Act (HIPAA) governing access to medical records, that states that the patient and the health-care providers directly involved in delivering care have the right to view the record.

The patient, however, may grant consent for any person or external entity to access the record. Given the complexity of handling and managing medical record, the holy grail of health records is perhaps a global electronic health directory that has both interoperability and liability built into it...Amazon [has] announced a new service called AWS Comprehend Medical...that can potentially impact the whole medical records ecosystem. Although electronic health records (EHR) exist for more than a decade, the majority of historical patient data is still stored today as unstructured medical text, such as medical notes, prescriptions, audio interview transcripts, and printed pathology and radiology reports. Extracting meaningful information from these is still a time-consuming process, and either requires data entry by high skilled medical experts, or teams of developers writing custom code. Comprehend Medical leverages Amazon’s AI technology to build a health record industry-specific solution, that uses natural language processing (NLP) to extract health-related text and data from virtually any medical record. 

Here's a key passage from the Amazon Comprehend Medical landing page about its services:

You can use the extracted medical information and their relationships to build applications for use cases like clinical decision support, revenue cycle management (medical coding), and clinical trial management. Because Amazon Comprehend Medical is HIPAA eligible and can quickly identify protected health information (PHI), such as name, age, and medical record number, you can also use it to create applications that securely process, maintain, and transmit PHI. You pay only for what you use, and there are no minimum fees or upfront commitments.

It's no surprise that Amazon singles out clinical trial management as a suitable use case for the company's new language processing service. For patients enrolled in clinical trials, EHR notes are extremely important. Pharmaceutical companies spend billions on such trials and will not be bothered by the costs involved in using such a service. I will be sure to track the future activities of this new company.

Walmart Shapes Its Own Primary Care, Unbundling Strategy

Walmart is establishing its own version of a primary care, unbundling healthcare strategy (Walmart Care Clinics) that is both similar and different to CVS-Aetna. The details were discussed in a recent article (see: Walmart Health: A Deep Dive into the $WMT Corporate Strategy in Health Care)

...[R]eports [have emerged] that Walmart is in merger talks with Humana, a health insurer with a $37B market cap [to] make Walmart look more like an integrated health care delivery system with every passing day. On top of Walmart’s existing health care offerings, these two acquisitions would functionally give Walmart the following:

• Risk-aligned health insurance plans that incentivize the expansion of low-cost retail primary care clinics in underserved geographies.
• A distribution footprint that places outpatient primary care clinics within 15 minutes of 90% of the US population.
• A seamless online pharmacy with home medication delivery funneling into a robust e-commerce offering.

Here are two reasons why outpatient primary care is ready to be unbundled from traditional health care delivery systems, i.e. hospitals, for two reasons: (see: Walmart Health: A Deep Dive into the $WMT Corporate Strategy in Health Care):

1. Most patients that visit primary care physicians don’t need the resources of an expensive medical center on-hand for each visit, and would be better served by an experience that emphasized price, convenience, and attention.
2. Reimbursement rates for most primary care services, e.g. a blood pressure checkup or physical exam, are much lower than specialty care (imaging, biopsies, intensive procedures, etc) and thus provide a lower short-term return on invested capital.

Like CVS-Aetna, Walmart is seeking to integrate its healthcare business with a health insurance company, currently Humana. Walmart also has a web-based prescription drug program. By way of contrast to its CVS-Aetna competitor, Walmart is emphasizing the following aspects of its primary care program:

• A low-cost, rural-aligned retail program in underserved areas,
• Some emphasis on chronic care and medical referrals, at least in its web marketing materials (see: Walmart Care Clinics).
• High profile prescription program offering some drugs with a $4 prescription price tag.

Virtual Scribe Vendors Remotely Generate EHR Notes and Coding

The use of scribes to act as intermediaries between a clinician and a patient is now common practice in outpatient healthcare settings (see, for example: Shift of Hospital EMR Data Entry Tasks from MDs to Scribes; The Emergence of EMR Scribes as a New Category of Hospital Employees; The Explosive Growth of EHR Scribes; Back to the Future). This use of scribes relieves the clinician of the laborious responsibility of entering data into the EHR. The clinician only interacts with the patient and the scribe extracts the necessary and appropriate EHR information from the conversation without any cues from the clinician. Disadvantages of the use of scribes is that they add to the expense of patient visits and are also expensive to recruit and train. Another scribe option is now available -- virtual scribe services (see: How a scribe tool linked to Epic EHR is helping ease physician burnout). Below is an excerpt from an article on this topic:

Chief among those administrative burdens [ cited by physicians and leading to burnout] was documenting in the electronic health record. Many physicians were spending two hours or more after each clinical session documenting in the EHR. As a result, they were missing family events and staying up late at night typing clinical notes. And in the office, they were too burdened to add new patients to their panels or focus on improving care and outcomes of their existing patients....[Massachusetts General Hospital] already had a relationship with vendor IKS Health, which had demonstrated success in allowing physicians to delegate and centralize clinical tasks – in that case, transferring medications from the legacy EHR to the current Epic system. Building on the vendor's clinical delegation abilities, Massachusetts General Physicians Organization engaged IKS Health to implement its virtual scribe technology, dubbed Scribble. Scribble provides a hybrid technical-human system where a physician uses a secure device to obtain an encrypted audio recording of the patient encounter, with the patient's consent. The recording is accessed by an IKS Health physician partner, who then synthesizes a complete, concise clinical note in the EHR, ready for the Mass Gen physician to review, edit if necessary, and sign. In addition, IKS Health coders review the documentation and provide billing and coding guidance. "....There are many scribe technology vendors on the market. These vendors include iScribeMD, Physicians Angels, Scribe America, Scribe Healthcare Technologies, Scribe Technology Solutions and Skywriter MD.

The virtual scribe technology consists of the clinician launching a digital audio recorder of the patent encounter with the patient's consent. The virtual scribe vendor then makes this recording available to one of its employees (physician or trained scribes) who listens to it and enters the encounter summary into the hospital EHR. This latter document can subsequently be edited by the responsible physician who interacted with the patient. As noted above, a vendor health coder can also review the same document and provide billing and coding guidance. This latter is non-trivial because it provides a double check on these data entries.

Although more expensive, the work of a scribe accompanying a physician in the examining room will often be of a higher quality, particularly as the scribe learns the habits and pace of the his or her physician. In the early years of medical scribes, they tended to be assigned to speciality physicians who generated higher revenue for the hospital. However, it has become the norm for more clinicians to be assigned scribes. The cost of virtual scribes is undoubtedly less expensive because the work lends itself to mass production. The lesser cost allows the hospital to provide such services to a larger swath its physician employees. 

eConsult System Designed to Optimize Hospital Specialty Referrals

NYC Health & Hospitals has developed and deployed e-consult software that is both EHR linked and web-based. It has been shown to be a valuable tool for reducing wait time for speciality care appointments and to enable PCPs to improve the quality of care (see: eConsult proves valuable tool for NYC Health+Hospitals in cutting wait times, speeding referrals). Below is an excerpt from it:

The [web-based, EHR integrated] eConsult tool allows primary care providers and specialists to communicate more effectively and co-manage patients when appropriate, as well as allowing them to connect patients to specialty care. The system is integrated through NYC Health + Hospitals' electronic health record systems, which helps with documentation. The eConsult system pilot began in August 2018 with two hospitals....September 2018 marked a milestone of 52,000 referrals reviewed and triaged thus far. The eConsult system helps streamline the referral process by allowing for rapid messaging and responses between providers when a primary care provider's patient has a health concern that would typically be treated by a specialist....Sometimes the communication is simply guidance that will allow the PCP to better treat the patient. Other times, when a specialist visit is necessary, the specialty clinic contacts the patient directly to schedule an appointment....NYC H+H said eConsult has helped to cut wait times for specialty care, showing that for patients referred for an in-person specialty care visit, the median wait time decreased from 50 days before eConsult to 28 days in June 2017.  

Here's another link to a related article about the development of this same software (see: Improving Access to Specialist Expertise via eConsult in a Safety-Net Health System) and below is an excerpt from it about the lessons learned in the process:

• Primary care providers consistently review eConsult responses and follow up with patients as needed.
• Specialty clinic staff schedule only those referrals that have been triaged appropriately.
• Specialists use the eConsult process as an opportunity for ongoing education for referring providers and for co-managing patients.
• Patients expect to be contacted by the specialty clinic if an appointment needs to be made.

There is a long history in the formerly paper-dominant healthcare world in which PCP referrals to medical specialists were largely a one-way street. This process was often inefficient and wasted resources. The e-consult software described here helped to correct this imbalance and enabled a dialogue between the PCPs generating referrals and speciality personnel. As noted in the quotes above, the software also provides guidance that enables the PCP's to better treat their patients and creates an opportunity for training and improved patient co-management. Because of this enhanced communication, median wait time for speciality appointments in the health system was  reduced by almost half since the final software deployment. 

Blurring of Definition of Big Medicine; Corporatization of Healthcare

Eight years ago I posted a note referring to an article in the New York Times (see: More Doctors Giving Up Private Practices) about the emergence of "Big Medicine" (see: Physician Private Practice Declines; the Last Barrier to Emergence of "Big Medicine"). In that note, Big Medicine was defined as being composed of the following organizations: (1) Big Pharma, (2) Big Payers (i.e., the U.S. government and large insurance companies); and (3) Big Providers (i.e., large consolidated regional health systems). A related concept now occurring in Big Medicine is its corporatization. As a result, physicians working in hospitals are now commonly referred to as providers and patients as customers. Here is a quote from a recent blog note that discusses the corporatization of medicine (see: Here’s what the corporatization of medicine is doing).

....[T]he “corporatization of medicine,”...[occurs when] the principles of depersonalized mass production — highly effective in retail business models — ...[are] imposed on health care systems, replacing the sacrosanct doctor-patient relationship with that of a commodity and consumer. Why is this happening? In the first three quarters of 2017, the top-five insurance companies made a record $6 billion in profit, with their executives getting handsome salaries and bonuses. The top CEOs of health care systems make seven- and eight-figure salaries. And their executives make equally large sums of money. When you receive that $25,000 ER bill, keep these exorbitant salaries in mind.

Another shift that is occurring in Big Medicine is that large retail drug companies such as CVS and Walgreens are becoming significant providers of the first tier of healthcare and Big Payers such as health insurance companies have become the employers of many thousands of physicians in competition with large health systems. In other words, there is a blurring of the originally conceived categories. I discussed this phenomenon in a recent blog note (see: OptumHealth, One of the Largest Employer of MDs, Pursues Telemedicine):

The largest employer of physicians in the country, OptumHealth is emphasizing virtual care. It is a division of the largest health insurance company in the country, UnitedHealth Group (see: Top 5 Largest Health Insurance Payers in the United States). UnitedHealth Group is also pursuing virtual care with its NowClinic subsidiary.....The third largest health insurance company in the country, Aetna, has now merged with CVS which is one of largest purveyors of walk-in primary care with its MinuteClinics (see: CVS Health and Aetna merger closes). These major health insurance companies may thus control at some point in the future a substantial portion of the first tier of healthcare as well as medical referrals associated with patients seen in their clinics.

Although I believe that value-based care needs to be substituted for fee-for-service with emphasis on outcomes of care, I believe that this goal may result in a lower quality of care in this depersonalized and increasingly corporatized healthcare environment.