✖
Ingine Inc
Ingine Inc - Enabling Large Data Driven Evidence Based Learning Health System
The Bioingine - Probabilistic Thinking Reasoning and Learning System
Large Data Driven Evidence Based Medicine Achieving Higher Levels of Clinical Efficacy
Probabilistic Knowledge
The Bioingine.com approach thus more fundamentally reflects the nature of probabilistic knowledge in the real world, which has the potential for taking account of the interaction between all things without limitation, and ironically this more explicitly makes use of Bayes rule far more than does a Bayes Net.
Deep Learning
It also allows more elaborate relationships than mere conditional dependencies, as a probabilistic semantics analogous to natural human language but with a more detailed sense of probability. To identify the things and their relationships that are important and provide the required probabilities, the Bioingine.com scouts the large complex data of both structured and also information of unstructured textual character.
Suspends Cognitive Bias
It treats initial raw extracted knowledge rather in the manner of potentially erroneous or ambiguous prior knowledge, and validated and curated knowledge as posterior knowledge, and enables the refinement of knowledge extracted from authoritative scientific texts into an intuitive canonical “deep structure” mental-algebraic form that the Bioingine.com can more readily manipulate.
Implicate Order Modeling
Extracting Medical Knowledge Existing Deeply Encysted In The Health Ecosystem

Implicate Order and Explicate Order are concepts coined by David Bohm to describe two different frameworks for understanding the same phenomenon or aspect of reality. He uses these notions to describe how the same phenomenon might look different, or might be characterized by different principal factors, in different contexts such as at different scales. For instance, Macro vs Micro overcoming Cartesian Dilemma. In the healthcare context, macro is the population health and micro is the patient health. The implicate order, also referred to as the "enfolded" order, is seen as a deeper and more fundamental order of reality. In contrast, the explicate or "unfolded" order include the abstractions that humans normally perceive. This leads into deeper learning uncovering knowledge deeply encysted in the system. ‘Implicate Order’ attempts to describe those phenomenon which are beyond the limitations of Euclidian Geometry and also the Cartesian Co-ordinate System, Boolean Algebra, Classical Descriptive Statistics, Frequentist Inference, Regression Techniques, Neural Nets etc. Both Euclidian and the Cartesian system are based on determinism associated among the ‘objects’, and describes the mechanistic causality. ‘Implicate Order’ attempts to step beyond such views to account for the holistic phenomenon that defies reductionism. Cartesian system in its very structure attempts to capture ‘everything else’ in the world as that can be laid out following the classification scheme, such as set theory. Although, classification scheme has played a vital role for describing everything else in the universe, it is devoid of the inner knowledge about how a certain peculiar behavior manifests. This is where ‘Implicate Order’ emerges as an ontological scheme encoded with the prior knowledge, especially the process that directs the behavior that is about to manifest. 

Hyperbolic Dirac Net Fulfilling Implicate Order
New Kind Of Data Science - The Theory Of Everything - Enabling Probabilistic Reasoning and Clinical Decision Making

The BioIngine Platform is based on a New Kind of Data Science derived from “The Dirac Notational Algebra”. The method allows for modeling “Implicate Order” as a probabilistic semantic system thus creating a scheme or ontology for making inferences from zillions of possibilities from otherwise complexity ridden irreducible system. The mechanism derived from Dirac Notation (Bra-Ket) for making Inference based on a n-dimensional vector state computational method is called “Hyperbolic Dirac Net” (HDN).

David Joseph Bohm (1917 – 1992) was a leading American theoretical physicist that who contributed to the philosophy of mind and natural language based on his thinking about quantum mechanics.  Attractive features of practical mathematics that can be derived from his system for applications to Big Data in the everyday world include the notions of (a) implicate order based on (b) hidden explanatory variables, (c) facts of knowledge asserted as stable truths but nonetheless to be continually tested as refutable, and (d) more elaborate fields of pervading influence that are not confined to inference networks such as the Bayes Net that are based on, for example, directed acyclic graphs rather than the general graph of knowledge interactions . To link these ideas to knowledge and communication he noted that our subject noun phrase, verb, object noun phrase languages as in “The cat chases the mouse”, which we might see today as a “semantic triple”, mirror the worldview of classical physics. Bohm saw everything in terms of verbs as operators describing process and transformation.  He conceived a new way of representing natural languages and knowledge that he called the rheomode – from the Greek ‘rheo-’ to flow, arguing that the syntax and grammatical form of language could be changed to give the basic role to the verb rather than the noun.  While these aspects may seem abstractly philosophical, we would hold that make perfect sense for a probabilistic semantics in the notation and algebra of Paul A. M. Dirac (1002 – 1984), whose mathematical system does not demote the importance of things and states, but places them on a dynamic conceptual interchange in a system that holds itself up by its own bootstraps.  For example, <A|B><C|D> has a subject <A|, “verb” |B><C| and object |B> (but also encodes for subject <D|  “verb” |B><C| and object |A>). Nonetheless, <A|, |B>, <C| and |D> are all each separate things, descriptions of state of something, all capable of forming matrices as process and transformation, and yet the above can equally be seen as the products of probability amplitudes <A|B> and <C|D> as entities, each of which describes a conditional, causal, or transitional relationship between A and B, and between C and D. All these perceptions are equally valid, and no one view that eliminates the others is valid.

The BioIngine Algorithm - Ensemble of Mathematical Techniques
QUANTUM MECHANICS MACHINERY FOR BIG DATA DRIVEN MEDICINE
Q-UEL
Quantum Universal Exchange Language (Q-UEL) Is an algebraic notational language derived from the Dirac Notation, the mathematical machinery that defines quantum mechanics and a long and widely accepted standard in physics. Its concept endures as a powerful architectural principle, managing the problem of the interchange and merging of medical data and knowledge from a variety of formats and ontologies.
Zeta Theory
A combined information theory and number theory approach that can, first developed as a theory of expected information in bioinformatics that handles high dimensional problems and sparse data and can be combined with Dirac’s approach. The information measures readily convert to probabilities called zeta probabilities optionally including subjective prior probabilities that can be used in the HDN and other QUEL approaches. With ample data, the probabilities behave classically, with less, there is less information.
Hyperbolic Number
Dirac’s algebra also includes the hyperbolic imaginary number h, rediscovered by Dirac and described in various guises. It belongs to particle physics and did not appear in Schrödinger’s earlier wave mechanics. The purely h-complex algebra is the algebra required by the HDN and Q-UEL to give familiar descriptions about the everyday world when we are not interested in inference about waves.
Information Theory
The information theory aspects are explicit in the use of the partially summated Riemann zeta function as a measure of expected information in both sparse and extensive data. They are also implicit in the use of similarity and novelty or unusualness measures expected to be helpful in identifying anomalous records.
The BioIngine Capability - MARPLE
The Medical Automated Reasoning Programming Language Environment
Hyperbolic Dirac Net
Is a data science approach that employs breakthrough mathematical technique that brings the power of mathematical framework designed to describe Quantum Mechanics. The algorithmic technique is an ensemble of techniques borrowed from several disciplines and notably from late Prof Paul A M Dirac's Quantum Mechanics (QM). The mathematical framework derived from QM, is based on Dirac Notation for knowledge inference and is called Hyperbolic Dirac Net (HDN).
HDN as Hypothesis independent Unsupervised Machine Learning Approach
Employs unsupervised machine learning algorithmic approach based on Hyperbolic Dirac Net (HDN) that allows creation of inference nets that are a general graph (GC), including cyclic paths, thus surpassing the limitation in the Bayes Net that is traditionally a Directed Acyclic Graph (DAG) by definition. It is a long standing, peer reviewed, and well-proven concept. Basically HDN is an advanced version of Bayesian Inferential Statistics, and actually does make use of the famous Bayes equation while a traditional Bayes Net, paradoxically, does not.
HDN as Supervised Machine Learning approach
Employs supervised machine learning algorithmic that automatically builds HDNs composed of up to millions of tags, verifies the consistency of probabilities used, returns the estimate of probability value requested based on all those tags, and does pattern discovery to help explain the quantitative findings. Builds the largest possible inference net (HDN) based on odds (probability ratios) and does automatically with many automatic cross-checks and corrections.
HDN as a Semantic method Extracting and Learning from World Wide Web
Is a unsupervised unstructured web searching tool that employs Dirac Notation having strong relationship with the Semantic Structure used in the Semantic Web. The tool can quickly generate many millions of statements of knowledge. The extracted knowledge as semantic triples and semantic multiples are placed in the Knowledge Representation store.