Patient safety is always a priority. Detecting early signs of clinical risk and disease gives us a greater chance of a successful outcome. Many clinical risk models that predict patient outcomes rely on a mixture of structured and unstructured data. However, timely use of clinical risk models to identify high-risk patients requires either real-time mining of the mountains of unstructured data, or diligent continued monitoring of data flowing into EHRs every day.

The real-time solution

Linguamatics platform provides a real-time NLP processing engine to highlight at-risk individuals. This combination of technology allows clinical risk models to be applied for immediate patient benefit. Examples of how the technology can be used include:

• Identify early signs of lung cancer by mining radiology reports for mentions of pulmonary nodules, so these at-risk patients can be identified for follow-up
• Extract signs and symptoms of Sepsis to support predictive risk models

Continual monitoring ‘batch’ solution

Linguamatics NLP can also provide monitoring for those instances of safety that don’t require immediate attention. In the hustle and bustle of healthcare the immediate problems always come first. Don’t let things like re-prioritization and changing shifts cause important information to be forgotten. Linguamatics NLP can be deployed as part of your continual monitoring ‘batch’ solution for your patients safety-net for those patients at risk.

• Assess Social Determinants of Health (SDoH) to help patients ‘at home’ risks

Food insecurities, ambulatory status, social support, living situations can all indicate risk to a patient. See how MUSC utilized Linguamatics NLP to determine social isolation in patients with prostate cancer.

“When people go to the doctor, they do talk about social isolation and other determinants of health. But you won’t find that in the coded data. You have to look at the clinical notes – that’s where the information is embedded. It would take a human many months to sort through the notes looking for mentions of social isolation. In contrast, the [Linguamatics] NLP software combed through the 55, 516 clinical notes comprising 150,990 documents from 3138 prostate cancer patients in the training data set in just eight seconds.”

Vivienne Zhu, M.D., M.S., MUSC Biomedical Informatics Center (BMIC)

• Help meet Joint Commision Patient Safety Goals

Behavioral health risk monitoring helps determine which patients have higher risk behaviors such as smoking status, drug and alcohol use, feelings of hopelessness

• Close information gaps, allowing closure of care gaps

Manual chart review wastes valuable nursing time and skills. Linguamatics NLP can help reduce the time required to find care gaps and improve identification of chronic conditions. At one ACO, prior to adopting Linguamatics NLP, a manual review of 1,000 charts only identified a single care gap. After implementing NLP, the ACO reduced manual review to only 6 charts for each successful care gap identified. Ultimately the ACO leveraged NLP to identify 92 patients who were documented in the narrative as having chronic obstructive pulmonary disease or congestive heart failure, but whose conditions were not entered into a structured format. These patients became eligible for the ACO’s population-based disease management programs and the quality of care was enhanced as chronic disease-related care gaps were closed. To read more click here.​

Webinar: Operationalizing NLP to support value-based care at Atrius Health

ACCESS WEBINAR

For more information on how Linguamatics NLP can help you with quality and safety, download our white paper below.