Month: January 2016

Journey from Gutenberg Printing Press to 2nd Order Probabilistic Semantics :- Thinking Web WW4 Achieving Medical Ontology for Medical Reasoning

 Bioingine.com | Ingine Inc

1. 1452, Printing Press Revolutionized Professional Knowledge Distribution

Johannes Gutenberg (c. 1398 – February 3, 1468) was a German blacksmith, goldsmith, printer, and publisher who invented the first printing press. Gutenberg’s printing press revolutionised the creation of books and helped make them affordable, ushering in a new era of affordable books and literature.
1452, with the aid of borrowed money, Gutenberg began his famous Bible project. Two hundred copies of the two-volume Gutenberg Bible were printed, a small number of which were printed on vellum. The expensive and beautiful Bibles were completed and sold at the 1455 Frankfurt Book Fair, and cost the equivalent of three years’ pay for the average clerk. Roughly fifty of all Gutenberg Bibles survive today.

The Gutenberg Bible is the first substantial book printed in the West with moveable metal type. Before its printing in 1454 or 1455, books were either copied by hand or printed from engraved wooden blocks—processes that could take months or years to complete. Johann Gutenberg invented a printing press that revolutionized the distribution of knowledge by making it possible to produce many copies of a work in a relatively short amount of time. Learn more about the Gutenberg Bible through the links below.

bibliagutenberg

Printing Press:- By giving all scholars the same text to work from, it made progress in critical scholarship and science faster and more reliable.

2. WWW :- Introduced non-linear linking or information across systems.

In March 1989, Tim laid out his vision for what would become the Web in a document called “Information Management: A Proposal”.Believe it or not, Tim’s initial proposal was not immediately accepted. In fact, his boss at the time, Mike Sendall, noted the words “Vague but exciting” on the cover. The Web was never an official CERN project, but Mike managed to give Tim time to work on it in September 1990. He began work using a NeXT computer, one of Steve Jobs’ early products.

sir_tim_berners-lee

“In those days, there was different information on different computers, but you had to log on to different computers to get at it. Also, sometimes you had to learn a different program on each computer. Often it was just easier to go and ask people when they were having coffee…”, Tim says.

Tim thought he saw a way to solve this problem – one that he could see could also have much broader applications. Already, millions of computers were being connected together through the fast-developing Internet and Berners-Lee realized they could share information by exploiting an emerging technology called hypertext.

3.A – 1999, Tim Berners-Lee described the Semantic Web vision in the following terms

I have a dream for the Web [in which computers] become capable of analysing all the data on the Web, the content, links, and transactions between people and computers. A Semantic Web, which should make this possible, has yet to emerge, but when it does, the day-to-day mechanisms of trade, bureaucracy and our daily lives will be handled by machines talking to machines. The intelligent agents people have touted for ages will finally materialise. (1999)

3.B – 1st Order Semantics :- Knowledge Engineering and the Web of Data – Harald Sack is Senior Researcher at the Hasso Plattner-Institute for IT-Systems Engineering (HPI) at the University of Potsdam

https://player.vimeo.com/external/95279410.hd.mp4?s=746c2b595f18bd581dcb5444db5901c61b259ae3&profile_id=113&oauth2_token_id=60919992

4. 2014 2nd Order Semantics :- Adding Probabilistic Semantics to better Reasoning employing Knowledge Engineering 

4.A – Bayesian Reasoning from The Uncertainty on Web

Paulo Cesar G. da Costa, Kathryn B. Laskey , Kenneth J. Laskey

Uncertainty is ubiquitous. If the Semantic Web vision [1] is to be realized, a sound and principled means of representing and reasoning with uncertainty will be required. Existing Semantic Web technologies lack this capability. Our broad objective is to address this shortcoming by developing a Bayesian framework for probabilistic ontologies and plausible reasoning services. As an initial step toward our objective, we introduce PR-OWL, a probabilistic extension to the Web ontology language OWL.

4.B :- 2014 – Dr. Barry Robson proposed using quantum mechanics as a basis for heuristics with the design and implementation of inference nets.

Split-Complex Numbers And Dirac Bra-Kets

Dr. Steven Deckelman ·  Dr. Barry Robson

Physical analogy and intuition has a long and distinguished tradition as a source of inspiration and deep mathematical insights. Take, for example, Jean Bernoulli’s ingenious solution to the brachistochrone problem, based on the path light takes through an inhomogeneous stratied medium as described in or the original solution of the Dirichlet problem based on physical reasoning for a physical electrical potential being determined by the laws of electrostatics given a charge distribution on the boundary. Or recall P.A.M. Dirac’s delta function  from the early days of quantum mechanics δ(x),  is a generalized function, or distribution, on the real number line that is zero everywhere except at zero, with an integral of one over the entire real line. Dirac delta function is a typical example of how a physicist’s unerring mathematical intuition can go beyond the level of the mathematics of his time. Or consider Wiener’s development of stochastic processes based on trying to model physical Brownian motion.We could, of course, go on and on. Recently Barry Robson has proposed using quantum mechanics as a basis for heuristics with the design and implementation of inference nets. The resulting net, called a Hyperbolic Dirac Net (HDN), is based on split-complex numbers. Inference nets, a topic in artificial intelligence, are very important in bioinformatics, data mining and biomedical analytics as well as having many other applications. An example from biomedical informatics would be a patient record database. The science of designing and implementing such nets in a computationally tractable way is a nontrivial problem in computer science.

Dr. Barry Robson

2014 :- Q-UEL – Probabilistic Semantic achieving, a WW4 for Medicine

Probabilistic Medical Ontology for Medical Reasoning by HDN Inference

4.B 1 Q-UEL The Dirac Notational Language :- To represent High Dimensional Data and Multi-lateral Subject

Q-UEL (Quantum – Universal Exchange Language), a web-based universal exchange and inference language for healthcare and biomedicine . It is extended to the more traditional domain of public health analysis including general population health sampling, healthcare quality surveys, and screenings. The techniques used can include or extend to cross-sectional studies, cohort studies, and other similar investigations including, to some extent, clinical trials.

4.B 2 HDN The Knowledge Model :- To represent 2nd Order Semantics

HDN – Medical Ontology for Medical Reasoning

  1. Hyperbolic Dirac Net (HDN) developed for medical inference overcoming the limitation of acyclic modeling in Bayes Net (BN), which leads into Directed Acyclic Graph (DAG). Motivating being that, while the traditional Bayes Net (BN) is popular in medicine, it is not suited to that domain.
  2. Medical domain, as such has many interdependencies, owing to high dimensionality of the data and multi-lateral nature of the subject, such that any “node” can be ultimately conditional upon itself.
  3. A traditional BN is a directed acyclic graph by definition, while the HDN is a bidirectional general graph closer to a diffuse “field” of influence. Cycles require bidirectionality; the HDN uses a particular type of imaginary number from Dirac’s quantum mechanics to encode it. Comparison with the BN is made alongside a set of recipes for converting a given BN to an HDN, also adding cycles that do not usually require reiterative methods. This conversion is called the P-method. 

The obvious problem here is that any knowledge network prepared to realistically model the world must allow for cyclic pathways that can be traced through the connections (edges) of the network (graph). To the extent that we can think of nature as a graph at all, it must be a general graph, but because relationships can potentially exist between any node and every other node but present as matters of degree, it can be further objected that the ideal picture is not even a general graph with cycles, but something closer to a continuous field of interactions between things. This perception also relates to the employ of conditional probabilities.

Meaning as ubiquitously and diversely seen in street, highway, train and subway maps, family ―trees, biochemical pathways, schematics in medical student‘s lecture notes, flowcharts, Feynman diagrams and path integrals (important for HDN philosophy) and not least the concept of the Semantic Web. With the interesting exception of such as physical, chemical, biological and computational processes that necessarily imply a probabilistic basis for transitions, their ubiquitous and confident use is obviously due to the fact that the relationships are held as being certain, not probabilistic. Intuitive probability calculation can be highly misleading as discussed in this report, but it is hard even for the human brain to make a mess of estimating overall probability when all the multiplied probabilities are assumed to be 1.

HDN – Inference Nets to :-

  1. “Observe” – mine data
  2. “Evaluate” – compute a very large number of the more significant probabilities and render them as tags,
  3. “Interpret” – use a proposed inference net as a query to search amongst the probabilities represented by those tags, but only looking for those relevant to complete the net and assign probabilities to it, assessing what is available, and seeing what can be substituted, and
  4. “Decide” – compute the overall probability of the final inference net in order to make a decision
Advertisements

IoT + Cognitive Computing :- Interoperability + Clinical Knowledge Management – Clinical Care Transformation

Clinical Tacit Knowledge – Represents Clinical Pathways

Slide1

Interoperability Health ecosystem includes

To achieve efficacy in Clinical Care, it means a design strategy around Clinical Care Redesign. The outcomes is Tacit Knowledge (Clinical Pathways) driven improvement in the overarching architecture involving PCMH, CI, and ACO

The article below by Sarah O’Hara discusses the Care Transformation as a consequence of improvement in PCMH, CI, and ACO.

What’s the difference between CI, ACO, and PCMH? | The Advisory Board Company

 

IoT coupled with Cognitive Computing has a huge potential in driving the Clinical Care Improvement efforts.

IoT +

Knowledge Management :- Discharge Planning

https://www.advisory.com/research/care-transformation-center/care-transformation-center-blog/2014/09/deciphering-the-reform-alphabet

Bioingine.com; Cognitive Computing Platform 

Addressing Clinical Care Improvement driven by algorithms that extract Tacit Knowledge from the Health ecosystem involving PCMH, CIN and ACO / HIE.

http://www.scirp.org/journal/PaperInformation.aspx?paperID=33250

We extend Q-UEL, our Quantum – universal exchange language for interoperability and inference in healthcare and biomedicine, to the more traditional fields of public health surveys. These are the type associated with screening, epidemiological and cross-sectional studies, and cohort studies in some cases similar to clinical trials. There is the challenge that there is some degree of split between frequentist notions of probability as

(a) classical measures based only on the idea of counting and proportion and on classical biostatistics as used in the above conservative disciplines, and

(b) more subjectivist notions of uncertainty, belief, reliability, or confidence often used in automated inference and decision support systems. Samples in the above kind of public health survey are typically small compared with our earlier “Big Data” mining efforts.

An issue addressed here is how much impact on decisions should sparse data have. We describe a new QUEL compatible toolkit including data analytics application (DiracMiner) that also delivers more standard biostatistical results, DiracBuilder that uses its output to build Hyperbolic Dirac Nets (HDN) for decision support, and HDNcoherer that ensures that probabilities are mutually consistent. Use is exemplified by participating in a real word health-screening project, and also by deployment in a industrial platform called the BioIngine, a cognitive computing platform for health management.

Bioingine.com employs algorithmic approach based on Hyperbolic Dirac Net that allows 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.

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.

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.

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.

Bioingine :- Multivariate Cognitive Computing Platform – Distributed Concurrent Computing by Dockerized Microservices

HDN_Cognitive_Computing

Employ of Dockerized Apps Opens a Vistas of Possibilities with Hadoop Architecture. Where, the Hadoop’s traditional data management architecture is extended beyond data processing and management into Distributed Concurrent Computing.

 

Data Management (Storage, Security,  MapReduce based Pre-processing) and Data Science (Algorithms) Decoupled.

Microservices driven Concurrent Computing :- Complex Distributed Architecture made Affordable

Conceptual View of Yarn driven Dockerized Session Management of  Multiple Hypothesis over Semantic Lake

Notes on HDN (Advanced Bayesian), Clinical Semantic Data Lake and Deep Learning / Knowledge Mining and Inference 

 

 

Hyperbolic Dirac Net (HDN) + Data Mining to Map Clinical Pathways (The Tacit Knowledge)

 

Bioingine.com employs algorithmic approach based on Hyperbolic Dirac Net that allows 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.

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.

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.

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.

Discussion on employing HDN to map Clinical Pathways (The Tacit Knowledge)

Screenshot 2016-01-05 21.04.17

In the below referenced articles on the employ of Bayesian Net to model Clinical Pathways as probabilistic inference net, replace Bayesian Net to achieve stress tested Hyperbolic Dirac Net (HDN) which is a non-acyclic Bayesian resolving both correlation and causation in both the direction; etymology –> outcomes and outcomes –> etymology

1. Elements of Q-UEL 

Q-UEL is based on the Dirac Notation and associated algebra The notation was introduced into later editions of Dirac’s book to facilitate understanding and use of quantum mechanics (QM) and it has been a standard notation in physics and theoretical chemistry since the 1940s

a) Dirac Notation

In the early days of quantum theory, P. A. M. (Paul Adrian Maurice) Dirac created a powerful and concise formalism for it which is now referred to as Dirac notation or bra-ket (bracket ) notation

<bra vector exprn* | operator exprn* | ket vector exprn*> 

[ exprn* is expression]

It  is an  algebra for observations and measurements, and probabilistic inference from  them

 QM is a system for representing observations and measurements, and drawing probabilistic inference from them.

In Dirac’s notation what is known is put in a ket, “|>” . So, for example, “|p >” expresses the fact that a particle has momentum p. It could also be more explicit: |p = 2> , the particle has momentum equal to 2; | x = 1.23 , the particle has position 1.23 |Ψ > represents a system in the state and is therefore called the state vector. 

The ket |> can also be interpreted as the initial state in some transition or event.

The bra <| represents the final state or the language in which you wish to express the content of the ket

Hyperbolic Dirac Net, has ket |> as row vector, and bra <| as column vector

b) hh = +1 Imaginary Number

QM is a system for representing observations and measurements, and drawing probabilistic inference from them. The Q in Q-UEL refers to QM, but a simple mathematical transformation of QM gives classical everyday behavior. Q-UEL inherits the machinery of QM by replacing the more familiar imaginary number i (such that ii = -1), responsible for QM as wave mechanics, by the hyperbolic imaginary number h (such that hh=+1). Hence our inference net in general is called the Hyperbolic Dirac Net (HDN)

In probability theory A, B, C, etc. represent things, states, events, observations, measurements, qualities etc. In this paper we mean medical factors, including demographic factors such as age and clinical factors such as systolic blood pressure value or history of diabetes.

They can also stand for expressions containing many factors, so note that by e.g.

P(A|B) we would usually mean that it also applies to, say, P(A, B | C, D, E). In text, P(A,B, C,…) with ellipsis ‘…’ means all combinatorial possibilities, P(A), P(B), P(A, C), P(B, D, H) etc.

2) Employing Q-UEL  preliminary inference net as the query can be created.

“Will my female patient age 50-59 taking diabetes medication and having a body mass index of 30-39 have very high cholesterol if the systolic BP is 130-139 mmHg and HDL is 50-59 mg/dL and non-HDL is 120-129 mg/dL?”.

This forms a preliminary inference net as the query, which may be refined and to which probabilities must be assigned

The real answers of interest here are not qualitative statements, but the final probabilities. The protocols involved map to what data miners often seem to see as two main options in mining, although we see them as the two ends of a continuum.

Method (A) may be recognized as Unsupervised (or unrestricted) data mining and post-filtering, and is the method mainly used here. In this approach

we (1) mine data (“observe”),(2) compute a very large number of the more significant probabilities and render them as tags and maintained as Knowledge Representative Store (KRS) or Semantic Lake (“evaluate”), (3) use a propose inference net as a query to search amongst the probabilities represented by those tags, but only looking for those relevant to complete the net and assign probabilities to it, assessing what is available, and seeing what can be substituted (“interpret”), and (4) compute the overall probability of the final inference net in order to make a decision (“decide”). Unsupervised data mining is preferred because it generates many tags for an SW-like approach, and may uncover new unexpected relationships that could be included in the net.

Method (B) uses supervised (or restricted) data mining and prefiltering. Data mining considers only what appears in the net. The down-stream user interested in inference always accesses the raw database, while in (A) he or she may never see it.

The advantage of (B) is that mining is far less computationally demanding both in terms of processing and memory. Useful to computing HDN for a specified Hypothesis.

The Popular Bayes Net BN Compared with our Hyperbolic Dirac Net HDN.

Each probabilities of any kind can also be manipulated for inference in a variety of ways, according to philosophy (which is a matter of concern ). The BN is probably the most popular method, perhaps because it does seem to be based on traditional, conservative, principles of probability. However, the BN is traditionally (and, strictly speaking, by definition) confined to a probability network that is a directed acyclic graph (DAG).

In general, reversibility, cyclic paths and feedback abound in the real world, and we need probabilistic knowledge networks that are general graphs, or even more diffuse fields of influence, not DAGs. In our response as the Hyperbolic Dirac Net (HDN), “Dirac” relates to use of Paul A. M. Dirac’s view of quantum mechanics (QM).

QM is not only a standard system for representing probabilistic observation and inference from it in physics, but also it manages and even promotes concepts like reversibility and cycles. The significance of “hyperbolic” is that it relates to a particular type of imaginary number rediscovered by Dirac. Dirac notation entities, Q-UEL tags, and the analogous building blocks of an HDN all have complex probabilities better described as probability amplitudes. This means that they have the form x + jy where x and y are real numbers and j is an imaginary number, though they can also be vectors or matrices with such forms as elements.

Q-UEL is seen as a Lorentz rotation i → h of QM as wave mechanics. The imaginary number involved is now no longer the familiar i such that ii = -1, but the hyperbolic imaginary number, called h in Q-UEL, such that hh = +1.

This renders the HDN to behave classically. A basic HDN is an h-complex BN.

Both BN and basic HDN may use Predictive Odds in which conditional probabilities (or the HDN’s comparable h-complex notions) are replaced by ratios of these.

Discussions on Employing Bayesian Net to Model Clinical Pathways (Replace BN by HDN to achieve Hyperbolic BN)

Development of a Clinical Pathways Analysis System with Adaptive Bayesian Nets and Data Mining Techniques 

D. KOPEC*, G. SHAGAS*, D. REINHARTH**, S. TAMANG

 

Pathway analysis of high-throughput biological data within a Bayesian network framework

Senol IsciCengizhan OzturkJon Jones and Hasan H. Otu

Are Standardized Clinical Pathways Stymying Drug Innovation?

HDN :- Need for Agile Clinical Pathways that do not impede Drug Innovation

Oncologists Say Clinical Pathways Are Too Confining

Creating fixed plans for treating common malignancies promises to make the work of nurses and other staff more predictable and practiced, increasing efficiency and reducing errors that could lead to poor outcomes and hospitalization. For payers, pathways also gave them another way to insert awareness of costs directly into the examining room.

“The way the pathways are constructed does promote consideration of value-driven practice, which is to say that the pathways vendors all take into account cost of care, but only after considering efficacy and toxicity,” said Michael Kolodziej, MD, national medical director of oncology solutions at Aetna, and a former medical director at US Oncology. “So there is an element here of reduction of cost of care, by trying to encourage physicians to consider the relative value of various treatment options. This has now become the mantra in oncology.”

Studies found that using pathways can indeed cut costs substantially without hurting outcomes.