Kahun, an evidence-based clinical reasoning tool for physicians, announces the publication in the International Journal of Medical Informatics (IJMI) of a first-of-its-kind study assessing the data-gathering function of currently available chatbot symptom-checkers. Out of eight symptom-checkers-K Health, Babylon, ADA, Buoy, Kahun, Mediktor, Symptomae, and Your.MD-Kahun demonstrated the best overall performance in finding the most pertinent insights in a simulated patient conversation.
Population growth and aging, overuse of medical services, and the COVID-19 pandemic have put immense strain on healthcare systems. Big-data driven self-assessment tools, otherwise known as symptom checkers, have gained momentum and popularity with patients but haven't assisted counter the strain on healthcare systems because they start and end with patients, and aren't being used by healthcare providers. So far, such symptom checkers haven't eased the burden healthcare providers are experiencing because they fail to produce an output that is professional enough and explainable enough for providers to trust. Additionally, symptom checkers are designed to be used by patients rather than physicians making diagnoses.
Kahun's XAI-driven (explainable AI) clinical reasoning and clinical assessment solution tackles this challenge by simulating the physician's thought process and explaining its algorithmic decisions. Its engine performs clinical reasoning at scale by basing its decisions on the company's proprietary map of more than 30 million evidence-based medical insights. The tool has the potential to ease the burden on healthcare systems by digitally mimicking the medical-interview process, making it more efficient and accurate, while saving precious time for trained personnel. This process helps healthcare providers handle large volumes of patients through standardization and digitization.
IJMI's study aims to ensure the useful and safe integration of AI-based tools in healthcare. Even though such tools have great potential to assist with healthcare challenges, there has yet to be a mass adoption because physicians can't blindly trust an algorithm. Kahun's clinical reasoning solution can be understood and trusted because its insights are referenced and backed by links to originating medical knowledge. Its algorithmic engine utilizes Kahun's knowledge graph in real time to generate clinical insights tailored to each specific patient.
To this day symptom checkers were designed for consumers as an alternative to asking Google. Hundreds of studies have been conducted to find which one of them is best for diagnosing, but the uniqueness of this study demonstrates that Kahun successfully established the quality of its data gathering in a way that makes sense clinically, allowing it to be widely adopted by medical providers instead of just patients.
"We are extremely proud of the IJMI study results," says Eitan Ron, Co-Founder and CEO of Kahun. "However, we don't look at ourselves as a symptom checker tasked with merely guessing the right diagnosis. Our explainable AI is designed to conduct clinical reasoning in the same manner a physician would. This study demonstrates that this approach is superior to others already on the market, and I'm convinced that as our model improves, its usefulness for physicians will only become more apparent."
RELATED ARTICLE : Kahun Secures $8M Round for its 'XAI' Engine for Clinical Reasoning
