KAID Health Technology Demonstrates the Value of Natural Language Processing to Improve Preoperative Care

Boston –(Business Wire)–Kade Health, An AI-driven healthcare data analytics and provider engagement platform, announced the results of a study that validated the potential utility of its natural language processing (NLP) technology in improving provider efficiency and quality of care. The peer-reviewed “Physician vs. Physician Artificial Intelligence” paper found that KAID Health’s NLP technology was highly consistent with clinician reviewers in completing preoperative checklists and was able to identify 16.6% of cases where anesthesiologists did not detect the presence of a particular condition or does not exist. The study was conducted in the Department of Perioperative Informatics, Department of Anesthesiology, UC San Diego. 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 shown that NLP technology can help identify key medical conditions associated with pre-anaesthesia assessments. The key is KAID Health’s ability to utilize unstructured free-text input from electronic medical records (EMRs) to flag serious medical conditions for anaesthetists,” Researcher and senior author Dr. Rodney Gabriel explained. “This study suggests that NLP may be a useful tool to help preoperative anesthesia providers screen and evaluate surgical patients.”

For the 93 patients in the study, the researchers collected all relevant free-text annotations from the EMR. The free text annotations are then processed by a named entity recognition pipeline that incorporates an NLP machine learning model developed by KAID Health. The model identifies and labels text ranges that correspond to medical concepts. Medical concepts are then mapped to a list of medical conditions of interest for pre-anesthesia evaluation. The most common conditions for anesthesiologists captured by the NLP pipeline did not include arrhythmias, angina, anticoagulation, peripheral vascular disease, obstructive sleep apnea, and neuromuscular disease.

“We are proud that leading academic institutions such as UCSD have partnered with KAID to ensure our NLP and AI models meet the demanding standards of accuracy and usability required by the industry,” said Kevin Agatstein, CEO of KAID Health. “KAID Health’s NLP Technology Played a crucial role in this study to identify relevant pre-anesthesia history to optimize the efficiency of the anesthesiologist. Our model shows that NLP has the potential to reduce clinician workload, increase profitability, and most importantly, enable The potential for safer surgery.”

The International Association for the Study of Anesthesia published the study in its journal, “Identification of Pre-Anesthesia History Elements Through a Natural Language Processing Engine,” Anesthesia and Analgesia, one of the world’s leading journals of anesthesiology. To read the study, click here.

About CapitaLand

KAID Health delivers more efficient, effective and profitable care to providers and their payer and responsible care organization partners.its Full graph analysis The platform uses artificial intelligence and natural language processing to extract all relevant data from electronic medical records, including structured data and text. The solution identifies the patient care interventions that providers need to achieve their clinical, financial or operational goals. At the same time, KAID Health extends a comprehensive view of member health to payers by combining claims and EMR data. Today, leading providers, health systems, academic medical centers, and payers use KAID Health’s technology to automate a variety of workflows, including coding accuracy, quality measurements, prior authorization support, and preoperative assessments. The company was founded by a veteran team of healthcare information technology and population health innovators. It is located in Boston, Massachusetts. To learn more, visit www.kaidhealth.com.

Leave a Comment

Your email address will not be published.