Two years ago, the American Society of Clinical Oncology (ASCO) announced the launch of an initiative to build a big data platform, called CancerLinQ, as a database that provides oncologists with growing amounts of real-world cancer information. The CancerLinQ platform was designed to connect and analyze cancer data from electronic records to provide data to cancer providers in order to assist them with making more informed decisions about patient care. The CancerLinQ platform was co-developed with SAP utilizing the SAP Connected Health platform that runs on SAP HANA, a flexible, in-memory data management and application platform.
In October, CancerLinQ announced a significant milestone with more than 1 million patient records now in the system. Additionally, there are now 71 oncology practices in 39 states and the District of Columbia participating in CancerLinQ, representing more than 1,500 oncologists. The aim of this big data initiative is to enable cancer providers to improve the quality and value of care by analyzing millions of cancer patient medical records, uncovering patterns and trends, and measuring their care against that of their peers and recommended guidelines.
Recently, Healthcare Informatics Assistant Editor Heather Landi spoke with Robert Miller, M.D., medical director at CancerLinQ, about the progress, to date, to build the research data network. Miller, who is a board-certified medical oncologist and informaticist, also shared his perspectives about how CancerLinQ is helping to break down data silos, how big data initiatives can help move the needle toward better cancer care, and the continuing challenges that oncologists and informaticists face in this area.
What are some of the challenges that oncologists are facing that CancerLinQ was specifically developed to address?
The American Society of Clinical Oncology (ASCO) board of directors identified the fact that only a small percentage of adult cancer patients actually participate in clinical trials for their care [about 3 percent]. So what that means is that for 97 percent of cancer patients, they are receiving the best care as determined by their local oncologist, but that knowledge of what happens to them as a result of the everyday care experience is largely lost, because the data is trapped in electronic health records (EHRs), or in some remaining cases paper records. So, the problem that ASCO was hoping to impact was to try to make all these data interoperable, to allow learning to occur from the care experiences of every cancer patient. So, they came up with this idea of creating a database whereby EHR data would feed into a single, aggregated database, and it would have to be de-identified for privacy protections, and that database could then be accessed by the broader cancer community, or what they call a learning health system. ASCO wanted to build a learning health system for the field of oncology and that’s what we are doing.
Robert Miller, M.D.
As of today, CancerLinQ has 71 participating practices in the U.S., and the way the program works is that our technology teams and informaticists connect the EHRs at the back end to the CancerLinQ database through a direct software connection and then using either pull technology or push technology, the protected health information data is moved from the EHRs into the CancerLinQ database where it’s aggregated. There is an initial data dump at the time of connection, and then there’s nightly incremental updates, so the data is refreshed every single day. Several weeks ago, we had crossed the point where we had 1 million patient records in the data lake. These are not all processed records yet, but a million records that have been brought on board from a percentage of the 71 practices that are participating.
Who is able to access these patient records in the database?
Right now, as of today, access is restricted to the subscribing practices that are themselves contributing data to CancerLinQ. However, we are in the process of finalizing, probably in the next few weeks, the third-party access policy. From the very beginning of this whole initiative, ASCO has anticipated that this database would have great interest and value to the larger cancer community, and so, once those policies are in place, and it will probably be operational by the first quarter of next year, then really anyone, whether that’s an academician, government agency or a commercial interest, anyone with a legitimate interest in CancerLinQ data would have the ability to apply for access. There will be an approval process and the request will have to be consistent with ASCO’s mission and for the good of the cancer community, but we anticipate a broad swath of interested parties will start to use CancerLinQ in the not-too-distant future.
What does CancerLinQ enable cancer providers to do?
It’s still fairly early days as we’re bringing practices on and the number of practices that are fully live and operational is still relatively small, as it’s not all 71 just yet. However, there are two main parts of the service that every subscriber gets. One is they have access to electronic clinical quality measures, so these are clinical quality measures that are based on other quality measures that ASCO has already created for other quality programs that really reflect the quality of the care that providers are delivering in their offices. CancerLinQ is in these multi-faceted dashboards and provides [the oncologist] with their own quality performance on a real-time basis—which is something that, heretofore, had been retrospective, and now this is real-time and prospective. So they have access to that and that has an immediate potential impact on improving quality of care. And the second is a tool within CancerLinQ that’s based on SAP technology, CancerLinQ Insights (CLQI), and this is a data exploration tool where any subscriber can drill down into the aggregated de-identified data set looking for new patterns or increasingly smaller cohorts of patients to really answer pressing clinical questions. So, an example of that might be, a rare cancer type, something that there’s really not good guidelines on and which clinical trials generally don’t address very effectively. An individual subscriber can drill down into the data to see how the last 100 patients with this unusual cancer type were treated in the database and that can impact care by being able to offer some suggestions. It’s not the same thing as guidelines or a clinical trial, but it’s still data that would otherwise not be available to most people.
Do you think big data initiatives like CancerLinQ are helping to move the needle toward better cancer care?
This is a way of enabling physicians to use electronic tools, to use the power of computers, particularly supercomputers that can handle big data, at the frontlines. What I mean by that is our current electronic tools, the EHRs that oncologists and other doctors use, there’s no mystery that there is a lot of dissatisfaction with them, that they don’t perform as well as many specialists like them too. While CancerLinQ is not an EHR in and of itself, within the system, this is something that oncologists are designing for other oncologists so there are dashboards, tools and programs that give an oncology-specific view of the patient timeline and presents oncology-specific quality measures, things that really matter to oncologists, and this is something that is just not available, for the large part, in many of the electronic systems and many environments that most cancer doctors are familiar with now.
How does CancerLinQ support Vice President Biden’s Cancer Moonshot effort?
CancerLinQ has been very visible with the Vice President, we have personally met with Mr. Biden on several occasions, and spoken with him about his vision and how we can help his vision become a reality. He’s talked largely about research and compressing progress, achieving 10 years of progress in five years. Where I think CancerLinQ can be effective is, number one, data sharing. The norm is that doctors care for cancer patients in their own clinics and own cancer centers, and the data is sitting in their EHRs and it’s rarely accessed and certainly not shared across institutions. Through the CancerLinQ technology, we now have the ability to have this much larger aggregated dataset that everyone can benefit from, and with the third-party access opening up soon, cancer care will improve in that regard.
There is a lot of discussion about the need to break down data silos. Does the CancerLinQ platform create a new paradigm for sharing data?
I think the primary way CancerLinQ is helping to break down data silos is the main construct of the system which is that we’re bringing in data from practices throughout the U.S., and I’ll add that, probably next year, to international practices as well, and we’re not restricted to any one particular EHR or any one type of practice. We have something like 15 different EHRs that are currently connected or will be connected soon to CancerLinQ. Our practices represent the full spectrum of oncology care throughout the U.S., including small, single specialty practices, larger regional integrated delivery networks, such as Intermountain Healthcare in Utah, and also all the way up to academic medical centers, University Hospitals in Cleveland and Rush University and several others, and at the other end, there are some safety net hospitals which are in the process of signing with us. I think the one of the complaints about data silos is that any one site represents the types of patients and practice in that site, but with CancerLinQ, all of the data from these different types of sites can be blended into one dataset that everyone can access.
When we started this, we didn’t know for sure if oncologists were going to prioritize this or whether they would be comfortable with this idea of sharing their patients’ data. We wondered whether there would be grave reservations, from a privacy and security standpoint, or at the other end of the spectrum, there are concerns that some have raised that the larger centers may want to hang onto their data, to monetize it or use it for other purposes, but what we found was virtually none of that. The response of the oncology community has been overwhelming. We have several hundred practices more in the pipeline. This construct that we’ve come up with seems to resonate.
What role does the CancerLinQ initiative play in moving toward personalized medicine?
Right now, CancerLinQ is largely bringing in what we call phenotypic data, so this is the data from EHRs, for the large part, and it doesn’t include a lot of genetic information or personalized molecular information just yet. But we will, in the near future, start to bring in some solutions to capture genomic data, and when we bring in this genomic data—which tells us what happened to this patient’s cancer, the patient’s experience with the treatment, what were the outcomes, what side effects did they experience as a result of a particular drug—we can then link our data with genomic data from other sources, and that’s largely tumor sequencing data. So, more and more cancer patients are undergoing next generation sequencing of their tumors, so there are these rich genomic profiles being created. That data is just exploding right now, but people don’t know what to do with it just yet, and the reason is, there hasn’t been enough effort yet to match the specific genomic alterations of the tumor to what happens to the patient. So, what CancerLinQ can do is provide the answer to what happens to the patient, what is their cancer like, and what was their treatment, and how does that break down based on what specific markers are present in their tumor? I think this is a very important role and I think this area will only accelerate in the next 12 and 24 months.
What are some of the biggest challenges that CancerLinQ is facing right now?
There’s challenges that we’re facing, and there’s challenges that cancer care is facing. I think what oncologists are facing is that this is a very complex time to practice on many levels—the number of therapeutic options is exploding, the need to understand genomics and other molecular medicine is huge in oncology, and that is something that’s a real challenge for many who see multiple types of cancer patients. In addition, because of the title wave of changes in reimbursement, practitioners have to demonstrate that they are practicing quality care by participating in registries and other requirements and this is a challenge for them.
I think what we face from the CancerLinQ side is really just trying to integrate all these data sources and make sure that the data quality is as good as possibly can be. The data that comes from real world practice is never as clean as the somewhat artificial datasets that are generated in the context of the clinical trial, where the conditions are very controlled. So what we’ve taken on is basically trying to fix all that on the backend. So as we grow and diversify, that challenge is never going to go away. We have the backing of SAP as a technology partner to innovate with us and to build new solutions for these types of data challenges. That’s my day job right there. Trying to figure out some of these things.
You mentioned expanding to international providers in the next year. What are some other future plans for CancerLinQ?
Currently, we’re somewhere in the ballpark of having about one in seven or one in eight U.S. oncologists participate in CancerLinQ through their practice. I think by the end of next year, it could very well be one in three, and probably by 2019, it may be one in two. So growth is one of the things we see happening and certainly we’re on pace for that right now. The second is the diversification of the data. Right now we bring EHR data in from practices, but that’s not the only source of data—there is claims data, cancer registry data and genomic datasets and large laboratory datasets and, very importantly, there’s patient-generated data. The patient reports of their outcomes is a critical aspect of what’s really happening to cancer patients and there are apps, webpages, mobile devices and other tools that can be used to gather those data points from patients and all that can be brought into CancerLinQ. So we intend to diversify our data input to some of these other sources, which again, will enrich the overall database that we’re building.