Home     About Us     Team     Products     News     Contact     FAQ     Account

H.O.L.M.E.S.

Sherlock B. Swan is ACG's corporate pet and is the virtual property of H.O.L.M.E.S.

Directed Machine Learning-Evidence-based Algorithms H.O.L.M.E.S. was developed to solve some of the same problems as the first U.S. medical libraries. The purpose of those first medical libraries was to enable individuals, families, and communities to take greater responsibility for their health while advancing medical research, teaching, and patient care. H.O.L.M.E.S.’ mission is to organize the world’s medical knowledge and data. H.O.L.M.E.S.’ vision is to do the right thing for the patient. H.O.L.M.E.S.’ ancestry can be traced back to the 13th century polymath, Ramon Llull, also known as Doctor Illuminatus. Llull was known for organizing scientific knowledge in his Arbor Scientiae that included systems of organizing concepts using devices such as trees as classification systems. Llull was a pioneer of computation theory upon which H.O.L.M.E.S. is based and Llull’s tree of knowledge has become ACG’s corporate symbol. H.O.L.M.E.S. was first conceived in a patent application in 2002. The work started in a medical office in Palatka, FL that is known for a nearby paper mill – a true skunk works. A new computer language (PALATKA-C) and Medical Algorithmic Platform were invented to map the massive amount of information needed to generate, in hours NOT years, the millions of lines of code that builds H.O.L.M.E.S.’ computer generated clinical decision tree algorithms. H.O.L.M.E.S. stands for Human Observation Logic Machine and Educational System. While H.O.L.M.E.S. started in Florida, H.O.L.M.E.S. grew up in a server farm in Palo Alto, CA, and now resides in the cloud. One can see from this link all of the places the infant version of H.O.L.M.E.S. has been accessed around the world. H.O.L.M.E.S.’s logic engine and thought processes are based on Holmesian Deduction that draws from the word deduce, which implies to subtract. In a way, Holmesian Deduction is all about shaving off the excess until you're left with the essential pieces. In Sir Arthur Conan Doyle’s stories, Sherlock Holmes speaks of his “science of deduction” and the two key components: observation and deduction. Holmes then finds meaning in the clues based on a specialized knowledge and from there, deduces the facts of the case. The vast and specialized knowledge that Sherlock Holmes possesses makes the process work. In the same sense, H.O.L.M.E.S. solves the problem that the patient and provider may not have the specialized knowledge needed to make sense of what they observe. H.O.L.M.E.S. organizes that knowledge as vast three-dimensional clinical decision logic trees in which H.O.L.M.E.S. guides the user down each branch by a series of questions to deduce medical necessity, coding, diagnosis, and treatment as the fruit that one finds at the end of the branch. Why has it taken nearly 700 years for Llull’s logic and knowledge organization to come to medicine in the form of H.O.L.M.E.S.? First of all, ACG’s team had to invent the knowledge mapping technology and associated logic platform. Until recently, systems on a chip were not powerful enough and web runtimes were not efficient enough. Medical libraries previously were not fully electronic and web developers were not experienced enough. Most importantly, development and knowledge teams to create and teach H.O.L.M.E.S. medicine were not physician led. H.O.L.M.E.S. is made of thousands of individual knowledge modules and has achieved an intelligence that is a combination of the next generation of clinical documentation and coding logic that is the key to revenue cycle management and data. For population health analytics, H.O.L.M.E.S. comprehensive knowledge based algorithms and logic engine generate clean clinical documentation that mirrors claims data in an ICD-10 based CDC data model. H.O.L.M.E.S. provides the right information (& the right questions) for the right care everywhere in 80 different languages via massive computer generated clinical decision trees with real time error checking, diagnostic, and treatment logic. This ICD-10 CM based data model represents a SIM card for interoperable healthcare data. H.O.L.M.E.S. is compatible with any EMR, revenue cycle system, or registry. H.O.L.M.E.S. has been taught family medicine, ER medicine, pediatrics, obstetrics/gynecology, urology, and psychiatry among many other medical specialties. H.O.L.M.E.S. learned to code in ICD-10 CM in 2 weeks – ICD-10 PCS in another 2 weeks. H.O.L.M.E.S. learned the orthopaedic knowledge base in 4 weeks. Sir Arthur Conan Doyle described his character as "a calculating machine." Like Babbage's Difference Engine, there is no personality or bias involved, only the application of a method. "He was," says Watson, "the most perfect reasoning and observing machine that the world has seen." Simplifying medical knowledge into logic trees makes H.O.L.M.E.S. easy to use and requires no training. H.O.L.M.E.S. should have a huge impact on medical education and medical practice in general, not just in the United States, but worldwide. H.O.L.M.E.S. Intelligence Platform meets the needs of the data based clinician in every way. H.O.L.M.E.S. is an elegant system for doing the right thing for the patient and for those who pay for that care. H.O.L.M.E.S. integrates all of the elements of care, payment, and data at the nexus of care to control risks, errors, and costs. H.O.L.M.E.S is a distributive solution to the problems of difficult health issues fraught with gaps of knowledge and care. H.O.L.M.E.S. is so intuitive as to require no training to use, code, document medical necessity, and normalize data while operating on nearly any mobile device in multiple languages. Only H.O.L.M.E.S. has the patented and patent pending technology to organize, integrate, and map the world's medical knowledge, coding databases, clinical guidelines, and outcome data analytics for use at the nexus of care. Only H.O.L.M.E.S. safely and efficiently reduces administrative costs and the burden of inappropriate and excessive care on a worldwide scale.

Copyright 2006-2022 Automated Clinical Guidelines, LLC. All rights reserved.