The previous section of this article paused during a discussion of the accuracy and uses of devices. At a panel on patient generated data, a speaker said that one factor holding back the use of patient data was the lack of sophistication in EHRs. They must be enhanced to preserve the provenance of data: whether it came from a device or from a manual record by the patient, and whether the device was consumer-grade or a well-tested medical device. Doctors invest different levels of trust in different methods of collecting data: devices can provide more objective information than other ways of asking patients for data. A participant in the panel also pointed out that devices are more reliable in the lab than under real-world conditions. Consumers must be educated about the proper use of devices, such as whether to sit down and how to hold their arms when taking their blood pressure.
Costantini decried the continuing silos in both data sharing and health care delivery. She said only half of doctors share patient data with other doctors or caretakers. She also praised the recent collaboration between Philips and Qualcomm to make it easier for device data to get into medical records. Other organizations that have been addressing that issue for some time include Open mHealth, which I reviewed in an earlier article, and Validic.
Oozing into workflow
The biggest complaint I hear from clinicians about EHRs–aside from the time wasted in their use, which may be a symptom of the bigger problem-is that the EHRs disrupt workflow. Just as connected health must integrate with patient lives as seamlessly as possible, it should recognize how teams work and provide them with reasonable workflows. This includes not only entering existing workflows as naturally as capillary action, but helping providers adopt better ones.
The Veterans Administration is forging into this area with a new interface called the Enterprise Health Management Platform (eHMP). I mentioned it in a recent article on the future of the VA’s EHR. A data integration and display tool, eHMP is agnostic as to data source. It can be used to extend the VistA EHR (or potentially replace it) with other offerings. Although eHMP currently displays a modern dashboard format, as described in a video demo by Shane Mcnamee, the tool aims to be much more than that. It incorporates Business Process Modeling Notation (BPMN) and the WS-Human Task Specification to provide workflow support. The Activity Management Service in eHMP puts Clinical Best Practices directly into the workflow of health care providers.
Clinicians can use eHMP to determine where a consultation request goes; currently, the system is based on Red Hat’s BPMN engine. If one physician asks another to examine the patient, that task turns up on the receiving physician’s dashboard. Teams as well as individuals can be alerted to a patient need, and alerts can be marked as routine or urgent. The alerts can also be associated with time-outs, so that their importance is elevated if no one acts on them in the chosen amount of time.
eHMP is just in the beginning stages of workflow support. Developers are figuring out how to increase the sophistication of alerts, so that they offer a higher signal-to-noise ratio than most hospital CDS systems, and add intelligence to choose the best person to whom an alert should be directed. These improvements will hopefully free up time in the doctor’s session to discuss care in depth–what both patients and providers have long said they most want from the health care field.
At the Connected Health symposium, I found companies working on workflow as well. Dataiku (whose name is derived from “haiku”) has been offering data integration and analytics in several industries for the past three years. Workflows, including conditional branches and loops, can be defined through a graphical interface. Thus, a record may trigger a conditional inquiry: does a lab value exceed normal limits? if not, it is merely recorded, but if so, someone can be alerted to follow up.
Dataiku illustrates an all-in-one, comprehensive approach to analytics that remains open to extensions and integration with other systems. On the one hand, it covers the steps of receiving and processing data pretty well.
To clean incoming data (the biggest task on most data projects), their DSS system can use filters and even cluster data to find patterns. For instance, if 100 items list “Ohio” for their location, and one lists “Oiho”, the system can determine that the outlier is a probably misspelling. The system can also assign data to belonging to broad categories (string or integer) as well as more narrowly defined categories (such as social security number or ZIP code).
For analysis, Dataiku offers generic algorithms that are in wide use, such as linear regressions, and a variety of advanced machine learning (artificial intelligence) algorithms in the visual backend of the program–so the users don’t need to write a single line of code. Advanced users can also add their own algorithms coded in a variety of popular languages such as Python, R, and SQL. The software platform offers options for less technically knowledgeable users, pre-packaged solutions for various industries such as health care, security features such as audits, and artificial intelligence to propose an algorithm that works on the particular input data.
Orbita Health handles workflows between patients and providers to help with such issues as pain management and medication adherence. The company addresses ease of use by supporting voice-activated devices such as Amazon Echo, as well as some 250 other devices. Thus, a patient can send a message to a provider through a single statement to a voice-activated device or over another Internet-connected device. For workflow management, the provider can load a care plan into the system, and use Orbita’s orchestration engine (similar to the Business Process Modeling Notation mentioned earlier) to set up activities, such as sending a response to a patient’s device or comparing a measurement to the patient’s other measurements over time. Orbita’s system supports conditional actions, nests, and trees.
CitiusTech, founded in 2005, integrates data from patient devices and apps into provider’s data, allowing enterprise tools and data to be used in designing communications and behavioral management in the patient’s everyday life. The company’s Integrated Analytix platform offer more than 100,000 apps and devices from third-party developers. Industry studies have shown effective use of devices, with one study showing a 40% reduction in emergency room admissions among congestive heart failure patients through the use of scales, engaging the patients in following health protocols at home.
In a panel on behavior change and the psychology of motivation, participants pointed out that long-range change requires multiple, complex incentives. At the start, the patient may be motivated by a zeal to regain lost functioning, or even by extrinsic rewards such as lower insurance premiums. But eventually the patient needs to enfold the exercise program or other practice into his life as a natural activity. Rewards can include things like having a beer at the end of a run, or sharing daily activities with friends on social media.
In his keynote on behavioral medicine, the Co-founder & CEO of Omada Health, Sean Duffy, put up a stunningly complex chart showing the incentives, social connections, and other factors that go into the public’s adoption of health practices. At a panel called “Preserving the Human Touch in the Expanding World of Digital Therapies”, a speaker also gave the plausible advice that we tell patients what we can give back to them when collecting data.
The next section of this article offers some memorable statements at the conference, and a look toward the symposium’s future.