KAID Health Technology demonstrates the value of natural language processing to improve preoperative care

BOSTON-(BUSINESS WIRE)–KAID Hi, an AI-based platform for healthcare data analytics and provider engagement, announced the results of a study confirming the potential benefit of natural language processing (NLP) technology to improve provider efficiency and quality of care. The peer-reviewed physician vs. artificial intelligence paper found that KAID Health’s NLP technology was highly consistent with clinician reviewers when completing a preoperative checklist, and was also able to identify 16.6% of cases where the presence or absence of a specific condition was not established by the anesthesiologist. The study was conducted at the UCSD Department of Anesthesiology, Division of Perioperative Informatics. The authors of the manuscript are Harrison S. Suh, BS, Jeffrey L. Tully, MD, Minhthy N. Meineke, MD, Ruth S. Waterman, MD, MS, and Rodney A. Gabriel, MD, MAS.

“We have demonstrated that NLP technology can help identify critical medical conditions relevant to pre-anesthetic assessment. The key to this was KAID Health’s ability to use input unstructured free text from the electronic medical record (EMR) to flag critical medical conditions for anesthesiologists,” explained researcher and senior author Dr. Rodney Gabriel. “This research shows that NLP can be a useful tool to assist preoperative anesthesia providers in screening and evaluating surgical patients.”

For each of the 93 patients in the study, researchers collected all relevant free-text notes from the EMR. The free-text notes were then processed by a named object recognition pipeline that incorporates an NLP machine learning model developed by KAID Health. The model recognizes and labels sections of text that correspond to medical concepts. Medical concepts were then mapped to a list of medical conditions of interest for preanesthetic assessment. The most common conditions that NLP caught that the anesthesiologist did not include cardiac arrhythmias, angina pectoris, anticoagulation, peripheral vascular disease, obstructive sleep apnea, and neuromuscular disease.

“We are proud that leading academic institutions such as UCSD partner with KAID to ensure that our NLP and AI models meet the exacting standards of accuracy and usability demanded by the industry,” said Kevin Agatstein, CEO of KAID Health. “KAID Health’s NLP technology played a vital role in this study to identify relevant pre-anesthetic history to optimize performance for anesthesiologists. Our model showed that NLP has the potential to reduce clinician workloads, improve cost-effectiveness and, most importantly, make surgery safer.

The International Society for the Study of Anesthesia published the study, “Identifying elements of preanesthetic history using a natural language processing machine,” in its journal, Anesthesia and analgesia, one of the leading anesthesiology journals in the world. To read the study, please click here.

About KAID Health

KAID Health makes care delivery more effective, efficient and profitable for providers and their payers and accountable care organization partners. It is Analysis of the entire chart the platform extracts all relevant data from electronic medical records, including structured data and text, using artificial intelligence and natural language processing. The solution identifies the patient care interventions providers need to achieve their clinical, financial or operational goals. In parallel, KAID Health provides payers with a comprehensive view of member health by combining claims and EMR data. Today, KAID Health’s technology is used by leading providers, health systems, academic medical centers and payers to automate a variety of workflows, including coding accuracy, quality measurement, prior authorization support and preoperative assessment. The company was founded by a veteran team of innovators in the field of information technology in healthcare and population health. It is based in Boston, Massachusetts. To learn more, visit www.kaidhealth.com.

Leave a Comment