Lab Soft News

Retail Clinics May Provide What Patients Want; Moving Away from Hospital Campuses

Have you been wondering what sort of businesses will lease at least part of the space vacated by Sears and other large retails chains that are vacating their mall space. One possibility will be large health systems that are placing selected outpatient services in mall spaces. Details were provided in a recent article (see: Retail clinics have what patients, healthcare execs want). Below is an excerpt from it:

Dana-Farber Cancer Institute plans to lease about 34,000 square feet of space at Patriot Place, a shopping and entertainment center in Foxborough, Mass., where it will offer both cancer treatment and hematology services....Oncology and infusion are among next generation of specialties predicted to shift into retail settings, along with the management of chronic diseases like diabetes, asthma and hypertension....There were an estimated 2,800 medical clinics in retail space in the U.S. in 2017....That includes a 47% jump in the last three years alone....Changing dynamics in healthcare reform, technological advances, demographic shifts and consumer preferences are driving healthcare providers to adopt new locations in retail centers....In 2018, 73% of healthcare construction was happening off of hospital campuses, compared with just 56% in 2014....In response, health systems are working to evolve their organizations to rely more on outpatient revenue and less on inpatient. Dallas-based Baylor Scott & White Health recently reported its admissions fell 7% and outpatient surgeries grew 7% year-over-year in the nine months ended March 31. Even as that happens, its operating margin is well above the national average among not-for-profit health systems....

[R]etail settings were designed to deliver exactly the kind of experience healthcare executives are now trying to create for patients: convenient, accessible locations, consistent branding and high visibility. They also offer parking and have easily accessible entrances....[This] trend will accelerate with the influx of inexpensive, vacant retail space as companies like Dressbarn shutter hundreds of stores....The losers, however, are health systems currently spending hundreds of millions of dollars on medical office buildings and healthcare real estate investment trusts....Dana-Farber won't be the only medical provider in a sea of dress pants and frozen yogurt [at Patriot Place]. Brigham and Women's/Mass General already has a clinic there that provides urgent care, cardiology, dermatology, pain management, gastrointestinal surgery and rehabilitation, among other things.... Patriot Place also has a CVS pharmacy and a handful of fitness studios.

Oncology infusion services have been leading the movement from inpatient to outpatient locations and now to retail space. This is all about an increased attention on the part of hospital executives to consumerism in healthcare, a large part of which consists of accommodating to the opinions of consumers. It's worth emphasizing the details of the "experience" that healthcare executives are trying to create as noted above: (1) convenient accessible locations; (2) consistent branding; (3) high visibility; and (4) easy, free parking. 

In this same spirit, hospital lab blood drawing centers as well as remote hospital labs with point-of-care analytic instruments also need to be deployed in malls to accompany these retail clinical facilities. At the very least, blood draws can be completed in association with clinical visits if not the actual test performance. Moreover, I also think that necessary and appropriate lab studies could and should be ordered and performed prior to clinic visits. How can this be accomplished? The current practice is for the physician determine the necessary blood tests after a visit with a patient. I think that predictive analytics and common sense can be used to order lab tests before a visit. This is true particularly for tests that are ordered on regular basis for a patient.

What Trends Can We Anticipate as Digital Capitalism Reshapes Healthcare?

The digital revolution entails the application of digital technology to all types of human enterprise. Capitalism is a system whereby the means of production are privately or corporately owned; development occurs through the accumulation of investment and profits gained in a free market. Healthcare is obviously one of the major business sectors in the U.S., accounting for nearly 18 per cent of the GDP and thus a major focus for investment under capitalism (see: Health Care Spending in the United States and Other High-Income Countries). Digital capitalism is the process by which digital technology is used in an industry such as healthcare to improve the quality of care and reduce human work input to enhance the quality care and profits. This note will briefly focus on the consequences of digital capitalism in healthcare.

There have been two recent significant financial changes that have occurred in healthcare. One of them has been the increased number of M&A's involving large healthcare systems (see: Hospital Merger and Acquisition Deals Got Bigger in 2018). This pursuit of mega-corporation status has been fueled by a quest for fiscal and operational efficiencies. Another financial trend has been the purchase and consultation of urgent care facilities by venture capitalists and private equity firms (see: Why Private Equity Loves Retail Healthcare; Private equity infuses healthcare with $63B investment). The most recent and significant trend in healthcare digital capitalism has been the deployment of electronic health records (EHRs), driven largely by subsidies from the federal government (see: The Federal Government Has Put Billions into Promoting Electronic Health Record Use: How Is It Going?). Although the goals was greater clinical efficiency, the results has been mixed (see: 7 EHR usability, safety challenges—and how to overcome them).

The most significant current opportunity for digital capitalism on healthcare is the broad deployment of AI (see: HOW AI IS TRANSFORMING THE FUTURE OF HEALTHCARE). It will lower the amount of human inputs and improve the quality of care by error avoidance in all types of processes ranging from the automating appointments to predicting what illnesses will befall a patient (predictive analytics). Although healthcare executives have driven the M&A initiatives in healthcare, they will have little input in terms of defining and deploying algorithms in healthcare processes. These decisions need to be made at lower levels of the organizations.

Here are some general future-oriented statements about the future of healthcare with a nod to digital capitalism:

• For the most part, inpatient admissions will continue to decline (see: Trends in Hospital Inpatient Stays in the United States, 2005-2014). That the reason bedless hospitals are being built (see, for example: The Case of the "Disappearing Hospital Beds"; Implications for Pathologists; Some Details about Hospital-at-Home (HaH) Services for Selected ER Patients). An open question is how health systems will repurpose their inpatient facilities. 
• Ambulatory care is differentiating into that provided by large health systems and, for the future, home care/home health monitoring, largely under the control of consumers. This is the sector where AI will have the largest effect (see: The Future for Pathology Informaticians Inexorably Linked to Analytics).
• Big Tech companies like Apple, Google, and Microsoft are currently collaborating with large health systems to gain access to EHR records to develop the software to support the various types of analytics. I don't think that these companies will have any appetite to work closely with health systems in the long term -- it will involve too much bureaucracy and too little enthusiasm for healthcare consumerism.

More Thoughts About HistoQuery: a Tool for Crowd-Sourcing Surgical Pathology Cases

In a recent note, I discussed HistoQuery, a crowd-sourcing web site to which surgical pathology case images can be uploaded (see: A New Tool for Obtaining Crowd-Sourced Diagnoses for Pathology Images). It was developed by Dr. Ulysses Balis and colleagues at the University of Michigan Medical School and intended as a pathology teaching resource. It seems to me that, in addition to such an audience, surgical pathologists from around the world could potentially use the site to obtain a consensus diagnosis for cases from his or her daily workload. The question then arises as to what type of cases would be uploaded to the web site to seek a crowd-sourced diagnosis for a case.

For me, it seems clear that such cases would most likely be those for which the submitting pathologist is leaning in a particular direction for the diagnosis and then seeking a validation, albeit crowd-sourced and therefore not attributable to any one named colleague or consultant. Contrast this with a challenging case encountered by a pathologist who then seeks a consultation from an eminent pathologist or pathology department. Here such a case would certainly be sent to specific consultant (see: "Eminence-Based" Surgical Pathology and the Digital Pathology Department). In return, the submitting pathologist receives a signed report from an expert (generally) with a specific diagnosis. On to the next case!

In addition, I need to give more thought to the question of the appropriateness of physicians in developing countries with an acute shortage of pathologists uploading surgical pathology images to HistoQuery. In such countries, there may be an insufficient number of qualified pathologists to whom such cases could be sent or it may take many weeks to obtain a surgical pathology report. Is a crowd-sourced diagnosis better than none at all? In addition, images submitted from another country would be beyond the reach of U.S. regulatory authorities. However, we need to focus here on what is ethically correct. Is a crowd-sourced consensus from unnamed parties superior to no diagnosis at all for a patient?

CVS's Grand Strategy for HealthHUBs and Aetna Becoming Apparent

In a previous blog note, I reported that CVS was launching a new type of retail health facility in Houston called a HealthHUB (see: CVS Expands Its Healthcare Presence with Its New HealthHUB Stores). The first store has now opened in Houston and was discussed in detail in a recent article (see: CVS Wants to Make Your Drugstore Your Doctor). These facilities are designed to offer a greatly expanded set of health services including wellness. Below is an excerpt from the Fortune article. It's very long so I can cover only a portion of it.

[CVS] CEO Larry Merlo is working to transform CVS into a wellness pioneer—far from its origins as a drugstore.Today the master plan is to combine Aetna’s claims data and analytics that identify which of its 22 million members are at risk for, say, developing diabetes or cardiac disease (see: CVS Health Completes Acquisition of Aetna, Marking the Start of Transforming the Consumer Health Experience), with CVS’s capacity to guide them to testing and treatment before the disease progresses, at the pharmacies and HealthHUBs. That formula is targeted to generate big savings by curbing readmissions to hospitals and getting patients to adhere to their drug regimens....[Part of the plan consist of] recruiting CVS’s biggest customers, mostly other insurers, to adopt a fresh model that gives CVS a share of the potentially giant savings to come from counseling and screenings at their corner clinics that keep patients out of operating and emergency rooms....

[I]n a May  1 conference call in which CVS announced better-than-expected results, Merlo discussed plans to make HealthHUBs the cornerstone of the new CVS..... [The company] operates 9,900 drugstores, standing in a virtual tie with Walgreens as the nation’s largest drugstore owner....The new CVS is focusing on where the money is: managing chronic conditions. Between 50% and 60% of all adults suffer from one or more of the top five: diabetes, hypertension, cardiac disease, depression, and asthma. Those conditions account for 80% of America’s $3.5 trillion in annual health care spending. The new model’s Rx is to hand Aetna’s data on every detail of its members’ health—including hospitalizations, lab tests, and doctors’ diagnoses—to the pharmacists and wellness specialists who encounter those folks in person far more often than anyone else in their health care orbit.

Stay tuned as to whether CVS and its CEO Larry Merlo can execute this grand strategy. On the face of it, this seems to be the company's new health model: (1) numerous convenient locations; (2) the analytics capability of a large health insurance company; (3) an emphasis on wellness; (4) an emphasis on the treatment of chronic diseases which some health systems treat piecemeal using multiple specialists and often without coordination. I don't think that most of the large health systems can or will be able to respond to this CVS challenge in a coordinated way. Most of them have engaged in only a half-hearted way to wellness (see: New National Patient Survey Reveals 84% Would Increase Provider Loyalty with More Holistic Health and Wellbeing Support).

A New Tool for Obtaining Crowd-Sourced Diagnoses for Pathology Images

Below is an announcement from Dr. Ulysses Balis, Professor of Pathology and Director of Pathology Informatics at the University of Michigan Medical School in Ann Arbor, Michigan:

The University of Michigan Department of Pathology, Division of Pathology Informatics is very pleased to introduce a new educational tool for the global Pathology Community: www.Histoquery.org.

With use of this new crowd-sourcing tool, following a simple and fast user registration process, users will be able to post educational cases to the site (comprised of one or more pathology images and an associated diagnostic question), and then be able to receive a crowd-sourced answer in a matter of seconds. Similarly, users can log on to the site as a crowd-sourcing participant, with the option of either providing a new answer or providing a vote on an already-submitted answer. Every respondent gets one vote, which may be changed as needed (but, no ballot stuffing is possible).

An example of how this educational tool might be helpful would be: seeking consultation from your colleagues on a particularly difficult case in a weekly slide teaching set. Simply post an image or two along with any salient history (but no protected health information, please) and simply wait for the flow of answers and their associated histogram to appear, in real time. Result answers and counts are tabulated in real time for all to see, as a dynamically updated histogram and consequently, no web page updates or refreshes are ever required.

Just as much fun as submitting questions is the opportunity to respond to them! Users may assist in the answering of as many questions as they would like, in the sub-specialty or specialties of their interest. In responding to submitted questions, you become an important and essential component of the crowd-sourced equation! Background: The site is designed with the latest audience-participation, real-time web architecture and will easily accommodate hundreds of concurrent users without skipping a beat. When registering, you will have the choice of selecting as many pathology sub-specialties as you would like, for case monitoring purposes.

Cases may be submitted at any time to any available sub-specialty board, independent of the monitoring board elections that you have previously logged. An all-board-monitoring category is also available, for those who feel confident in assisting with any type of inbound question. Please forward all user support questions to me directly, at: ulysses@med.umich.edu There is no fee to use this educational service and I very much look forward to hearing back from you on your initial experiences with the use of this new class of educational tool.

I think that this is an incredibly useful idea by Ul and his colleagues. We all know about the value of crowd-sourced knowledge. As noted in the note above, the web site will serve as a valuable education tool for residents and fellows as well as practicing pathologists.

Need for More Verbal Communication Between Pathologists and Radiologists

I first discussed the merits of collaboration (or even merger) between the specialties of pathology and radiology in October, 2006 (see: Ten Reasons for Merging Pathology/Lab Medicine with Radiology). Since that time, I have commented on this same topic from time to time as well as how to improve pathology/radiology reports (see, for example: Radiologists and Pathologists as Information Specialists; Merger of the Specialties?; Making Surgical Pathology and Radiology Reports More Patient-Friendly; Pathology and Radiology Collaborate with a Concordance Conference). I recently came across a longish article encouraging pathologists to communicate verbally with radiologists when certain findings are encountered. Below is an excerpt from it:

Discordance between radiology and pathology studies compounds...[the problem or arriving at the correct diagnosis]. As good practice, frequent verbal communications between pathologists and radiologists ensure that we recognize and minimize potential diagnostic confusion prior to issuing the pathology report. The radiologist-pathologist conversation may provide valuable feedback to the radiologist (because the pathologic findings may add to their understanding of imaging findings and improve interpretive skills), and to the pathologist (who may develop a better appreciation of the clinical question asked with the biopsy and provide a more relevant pathologic answer).....Importantly, the radiologist...[is] able to convey the degree of suspicion for malignancy much more thoroughly to the pathologist in direct conversation than in the biopsy requisition, which has only limited ability for nuanced communication.....

When should a pathologist contact the radiologist? We propose the following situations: (1) negative/benign biopsy result, (2) surprising/unexpected finding on the biopsy, (3) clarification of specific requests for the biopsy, and (4) insufficient material on the biopsy. We define a negative biopsy as one that “is negative for any pathologic process or contains only nonspecific findings.” In this setting, sampling during the biopsy may have missed the intended lesion, or the findings may reflect a process that is not the radiographic lesion of concern (for instance, inflammation adjacent to a malignancy). Additionally, the biopsy may have been performed on an atypical or unusual radiographic presentation of a typically benign process with a lower level of suspicion for malignancy, such as an apical cap or rounded atelectasis. Without an assured radiologic-pathologic correlation comment, the patient may be subjected to an additional, unnecessary needle biopsy or even a more invasive surgical biopsy....

Suggested Reading

J Sorace et al., “Integrating pathology and radiology disciplines: an emerging opportunity?”, BMC Med, 10, 100 (2012). PMID: 22950414.

AS Oh et al., “Imaging-histologic discordance at percutaneous biopsy of the lung”, Acad Radiol, 22, 481–487 (2015). PMID: 25601302.

National Academies of Sciences, Engineering, and Medicine, Improving Diagnosis in Healthcare. The National Academies Press: 2015.

The suggested readings above may be of value but, unfortunately, there is not a large literature on this topic. The most important steps to take to improve pathology-radiology communications would be to develop specific guidelines when oral communication is required for a case, as discussed above, and the launching of a periodic hospital diagnostic concordance conference (see: Pathology and Radiology Collaborate with a Concordance Conference).

Grail Picks Specific Method for Liquid Biopsy Clinical Trials

I have blogged about the liquid biopsy for about eight years (see, for example, Rapid Adoption of the Term "Liquid Biopsy" on the Web; Continuing Discussion about the "Liquid Biopsy"; "Liquid Biopsy" Used to Refer to Detection of Any Serum Cancer DNA). Initially, the test involved the isolation of circulating cancer cells from a blood sample, a daunting task due to their rarity, and the subsequent analysis of the DNA of them. Liquid biopsy research has evolved since then to the collection and analysis of cell-free circulating DNA and RNA. A recent article discussed how Grail, the apparent leader in the commercialization of the technology, has selected what it deems to be the best method for cancer detection in the blood (see: Grail, the liquid biopsy startup, picks an approach for its cancer test). Below is an excerpt from the article:

Grail, the company that has raised $1.6 billion to develop a blood test to detect cancer early, announced Monday that it has settled on a method for its test and enrolled 115,000 patients in two large clinical trials. A third study, with 50,000 patients, has already begun. The San Francisco-based startup, spun out of DNA sequencing giant Illumina in 2016, previously presented data on three different approaches to detect cancer using DNA circulating in the blood. One used DNA sequencing to look at specific regions of genes; a second used the technology to sequence the entire genomes of cells floating in patients’ bloodstreams; and a third looked at methylation, an epigenetic change across the whole genome. Grail said in a statement that it has settled on the third method, which uses methylation to detect cancer and identify where in the body it started.....The company also said that it had received a special “breakthrough device” designation from the Food and Drug Administration that could expedite the test’s eventual review. 

Here's a paragraph from the Grail landing page about how to analyze cancer signals in blood:

An increasing body of evidence suggests tumors release cell-free nucleic acids (cfNAs) into the bloodstream. cfNAs are small fragments of DNA and RNA, and reflect the genomic features of the tumor from which they originated. cfNAs are thought to be a direct measure of cancer and can be detectable in the bloodstream of people with cancer, potentially even before symptoms present.

All of this seems promising. Grail certainly has generous funding and is enrolling large numbers of patients in its clinical trials. However, I suspect that, even with its “breakthrough device” classification by the FDA, we won't have good answers about this technology for several years. Here's a brief description of the science of DNA methylation patterns (see: DNA Methylation and Its Basic Function):

In the mammalian genome, DNA methylation is an epigenetic mechanism involving the transfer of a methyl group onto the C5 position of the cytosine to form 5-methylcytosine. DNA methylation regulates gene expression by recruiting proteins involved in gene repression or by inhibiting the binding of transcription factor(s) to DNA. During development, the pattern of DNA methylation in the genome changes as a result of a dynamic process involving both de novo DNA methylation and demethylation. As a consequence, differentiated cells develop a stable and unique DNA methylation pattern that regulates tissue-specific gene transcription.

Watson's Patient Synopsis Tool, a Partial Solution for Physician Burnout?

As far as I can tell, IBM's Watson has not lived up to the expectations of many healthcare providers which was probably predictable, given the exuberance of its marketing campaign. Too many promises. However, a recent article about its use in creating a Patent Synopsis caught my eye. This would appear to be a potentially useful tool given the complexity of EHRs and the inability of users to often extract usable information from it (see: IBM Watson is taking on EHR qualms with a new AI tool). Below is an excerpt from this article:

AI-enabled programs that help parse through data have the potential to minimize physicians' headaches with EHRs and ultimately slash costs. Patient Synopsis simplifies data extraction, which can help minimize medical errors resulting from physician burnout. Patient Synopsis pulls out clinically relevant information from a patient's EHR in seconds — including current illnesses, medications, and medical history — and organizes it into 12 categories....By eliminating the need for doctors to dig through mounds of patient data, hospitals could avoid these errors and save a huge amount of money....The tool could also help doctors expedite treatment plans and clamp down on unnecessary testing. Patient Synopsis offers comprehensive, easy-to-access patient summaries, which could grant physicians a clearer view of the best plan of action for treatments and more quickly send patients onto the road of recovery. This could also help prevent doctors from ordering tests that might not be needed to guide effective treatment....

Watson...struggled to retain major hospital clients in 2018, citing softening demand....But its AI-enabled solution for EHRs could help the tech titan lay claim to more healthcare partners, considering 92% of regular hospitals in the US have implemented EHR systems and likely all share in the struggle of managing the burdensome content they contain. Landing Patient Synopsis in Hardin Memorial Health puts IBM in competition with other tech giants offering solutions to combat EHR-related troubles. Leading cloud vendors...have all jumped in to offer solutions to EHR woes: For example, Microsoft's Healthcare Next program seeks to mitigate the burden of inputting EHRs for physicians, and Google's Cloud for Healthcare platform is designed to simplify the process of pulling insights from patient data stored in the cloud to improve clinical decision-making....[IBM] joined forces with other tech leaders last August to tackle interoperability issues plaguing the healthcare system, which often stem from difficulties in sharing EHR data among providers. Now that IBM's doubling down on curbing EHR troubles, it will likely eye more hospital partnerships to emerge as a front-runner in the crowded market.

Although it may not be obvious to all observers, the goal of IBM's Patient Synopsis project, extracting clinically relevant information from the EHR "soup", is a daunting task. Clinical documentation with EHRs is commonly entered using drop-down menus with a controlled vocabulary, making computerized synopsis relatively easy. A similar story pertains to medications and numerical data from the labs. However, surgical pathology and radiology reports, although labeled with diagnostic codes, may harbor subtleties in text that can be important. Such textual reports require computerized natural language processing (NLP) to extract meaning. I have posted a number of previous notes about this topic (see, for example, Assessing Drugs Using "Real World Evidence" in Addition to Clinical Trials; AI Allows Computers to "Read" EHR Records and Make Predictions; Amazon Launches New Medical Record Language Processing Service). Because the EHR record for an individual patient can be complex, the risk of the creation and availability of a patient synopsis generated by Watson is that clinicians may come to depend on it and miss some of the information contained in the larger EHR record. Hence and at least initially, the Patient Synopses will probably be published with a warning label.

Six-Lead, Consumer-Facing ECG Device Close to Release to Market

I have previously blogged about AliveCor's three-lead ECG device in particular and cardiology in general as examples of cardiology being a "collision point" between consumer IT and the healthcare system (see: Three New Studies Confirm Clinical Utility of AliveCor’s KardiaMobile Device and AI Algorithms; Cardiology as a "Collision Point" between Consumer IT and the Healthcare System). The company is now testing a a six-lead ECG instrument (see: AliveCor previews next product: A 6-lead smartphone ECG). Here is an excerpt from this article:

AliveCor, which has offered an smartphone-connected ECG since 2012 and a wristworn version since 2016, revealed...the company’s next direction: a six-lead ECG compatible with a smartphone.....The device is not yet cleared by the FDA...[and] codenamed Project Triangle, looks similar to AliveCor’s existing Kardia Mobile device....But in addition to the two electrodes on the front of the device, there’s an additional one on the back. The user places on thumb on each of the top electrodes and places the bottom electrode on their left knee. This formation — known in cardiology as an Einthoven Triangle after Willem Einthoven, the inventor of the electrocardiograph — allows cardiologists to view electronic activity in the heart from six angles, or leads. With these, the device can potentially catch the warning signs of an upcoming heart attack.....Both AliveCor’s existing products...are single-lead ECGs, as are most similar devices on the market.

Here's a tweet from Dr. David Albert from May 10, 2019 about this new six-lead device:

I am proud that our new @AliveCor KardiaMobile 6L provides a new level of diagnostic cardiac rhythm information. Thanks to Dr. Topol for helping us evaluate and validate this new clinical capability.

This consumer-facing ECG instrument is a good example of the development arc of such products over the period of about seven years in the case of KardiaMobile. It's a story of increasing diagnostic functionality to the point, now or in the near future, when it will loop back to even be deployed by cardiologists in certain clinical settings. Cardiologists may find it more efficient to use the device in their office or ED rather than the standard instrument to obtain an answer quickly. In some developing countries, it may be the only ECG instrument available because of cost. A similar story applies to portable ultrasound devices that utilize the screen of a smart phone (see: Wireless Portable Ultrasound). Here's my note on the topic of portable ultrasound devices from almost thirteen years ago (see: Portable Ultrasound Devices Introduced into Medical School Curriculum). It should be emphasized that the KardiaMobile devices are equipped with AI to interpret the tracings for consumers. This AI feature obviously will not be required by the cardiologists who use it.

Sonic Use Lab Data and Analytics to Provide Important Information to Patients

Sonic Healthcare USA is the world’s third largest pathology/laboratory medicine company with operations in eight countries. A recent article discussed how the company is now using lab test data generated in its labs for predictive analytics focusing on patients with neglected diabetes. The various laboratories then directly contacted these patients, urging them to seek medical treatment  (see: Sonic Healthcare Uses Test Data to Create Shared Savings Opportunities for Clinical Laboratory and Providers). These actions, in turn, reduced medical costs by this early intervention. Below is an excerpt from the article:

Using integrated financial and clinical analytics, Sonic is developing technologies to build clinical decision support tools for its provider and health plan clients. The providers and health plans use those tools to engage patients and help them manage their health....Sonic uses lab test results and financial data to show providers how some low-cost patients over time can become high-cost patients....Sonic [then] uses lab test data to help physicians identify low-cost patients who may need certain interventions before they become high-cost patients. Providers have opportunities to intervene with patients who have renal failure, congestive heart failure, ischemic heart disease, diabetes, and other conditions....

Over several years, Sonic has worked with one client provider group to identify patients who would benefit the most from interventions to prevent their healthcare costs from rising sharply....Sonic found that about two-thirds of high-cost patients were in the low-cost group just one year earlier.....[T]he reason they were low cost the year before was not because they were healthy. Instead, it was because they did not engage with the healthcare system for their chronic disease management.....Sonic used its iMorpheus data analytics system to show that 26.5% of the low-cost patients had diabetes, but that they had not seen their physician in the previous 12 months....[T]he company developed an automated interactive voice response system to call the patients. Sonic recorded the patients’ physicians and then had the system place the calls. Of the patients who received the calls, 44% responded and visited their physicians.

I have posted a number of previous notes about predictive/diagnostic analytics (see, for example: Diagnostic and Predictive Analytics and Their Possible Link to the Future of the LIS; Three Examples of Predictive Analytics in Clinical Practice). However, I was pleasantly surprised to discover via the cited article above that a global laboratory company had both developed a proprietary data analytics system, iMorpheus, and was then using the system to predict/diagnose disease. Ultimately, the patients were alerted about this finding with an automated telephone system using their physician's voice.

All of this is both admirable and highly unusual. Although clinical labs enable clinicians to make myriad diagnoses with lab test results, they seldom take a proactive role in predicting and diagnosing disease in patients. Sonic's program provides early insight into the potential value of  various types of analytics software installed in the labs. In a recent note, I also discussed how analytics will play a critical role in the future for the professional career of pathology informaticians (see: The Future for Pathology Informaticians Inexorably Linked to Analytics). This fascinating news from Sonic reinforces this same idea.