|TRA’s Innovence™ Pulse software highlighted in trade journal
|A number of large health systems and insurers around the country are using cloud-based software to make sense of the huge amounts of clinical and claims data collected and stored in their various departments, outpatient settings, and physician practices. The very best software combines these disparate data sets to look for patterns or early indicators of clinical trouble among patients, thus enabling risk managers to take preventive action.
Innovence™ Pulse, developed by The Risk Authority Stanford, is enabling insurer Beazley to comb through its vast database of nearly 900,000 unique loss records to understand where precisely in the hospital a claim occurred, and how claims cluster along the continuum of care. Beazley says TRA’s software is helping it create a far richer, nuanced picture of claims trends.
As Health Data Management noted in a recent feature, TRA’s risk management software analyzes varied data sets such as incident reports, loss runs, patient complaints, and net patient revenue to give users a comprehensive clinical and financial picture.
“It uses machine learning and natural language processing to read the unstructured free text of an event, and then categorizes that event through our Stanford Risk Lexicon, which provides accurate risk classifications, descriptions, and reports that make information actionable,” says Randall Smith, product manager for Innovence™ Pulse.
For instance, in case of an infection threatening a certain unit of a hospital, the software can detect the emerging risk and alert caregivers to intervene in a timely fashion. It is a tool that collects and analyzes empirical data in real time, and prioritizes results of most interest to risk managers, hospital leadership, insurers, and large customers.
Health Data Management says what makes such predictive software especially appealing is that it is cloud-based – users don’t have to invest in hardware or software or keep up with servers running databases. In this model of software delivery – known as SaaS (software as a service) – all the heavy lifting is done by the software vendors. Clients need only a device with an Internet connection to receive and access the information.
Another attractive feature of cloud-based predictive software is that it can integrate data from various electronic health records systems. For instance, as Health Data Management reports, Beth Israel Deaconess Care Organization in Massachusetts includes eight hospitals and 2,600 physicians and among them they use 40 different EHRs.
The software used by Beth Israel pulls real-time data from all the EHRs in the network. As one Beth Israel official explains it, “we get that data nightly in a batch process, and we pull it into our population health platform, which gets married with claims data as well as scheduling information and [admission, discharge and transfer] to give a real picture to our care teams of what’s going on in the network with our patients.”
Risk managers are also pleased with cloud-based analytic software because it can read and make sense of unstructured data contained in raw clinical documentation, such as that found within EHRs. Eric Sullivan, senior vice president of innovation and data strategies at Inovalon, a cloud-based data analytics vendor, noted to Health Data Management that more than two-thirds of what is really clinically relevant is embedded in unstructured text and uncodified fields.
“If you can have a machine scroll through a 300-page medical record in a fraction of a second and identify five potential places where the physician is indicating that they may have some diabetes complications, that is incredibly more efficient than having a human try to identify those areas,” he says.