2. Abstract
We have always made tools and machines that eventually would end up doing something we did well, do better than us. That is because our creativity is inspired by what we do and what surrounds us but also because we recognise that ultimately, we (our living bodies) are all just tools in our own existence. Our drive for self-improvement can, in a sense, be understood as the pursuit of Self-obsolescence.
A data-technical proposal for a method to achieve real-time predictive healthcare, using a novel approach for Personal Healthcare data management, based on Shannon data entropy-, and Black-Scholes-Merton derivative modelling.
Dr Stefaan Vossen MSc. (Chiro), Angela Vossen MSc. (PPPE)
Introduction to the paper p. 15, Method 23, Structure 30, Discussion 32, Conclusions 36
Abstract:
In this paper we present one idea: that of recording the change in people’s behavioural pattern to predict what they should receive as treatment or undertake as habits to help them be(come) health(y)ier. The argument is broken down logically, computationally and mathematically. Mathematical modifications are suggested and computational and logical consequences are presented.
The idea repurposes multiple existing computational frameworks to superimpose the data that represent them in a novel way (through a novel function in the proposed modifications of the Spinor) to successfully enable prediction of real-world, human, lived-experience factors. The premise has significant consequences in theoretical physics and computation of the human experience of the world.
It is one idea that consists of a way of recombining multiple, individually simple, but logistically complex, already existing, systems. The way of recombining these ideas mathematically and logically also has an impact on computer science, the application of math and forms a proof in physics (which is why this paper is written the only way it could be: to the slight dissatisfaction of all).
Each of these multiple, “simple”, concepts are functionally related through multiple inter-relationships, some of which have unusual properties. (Publicly) poorly understood concepts such as “AI”, “Quantum computing” and “blockchain cryptography” being positioned as natural bedfellows may be novel to some readers.
The idea is to create a digital record of the shape of a human’s movement (an avatar) and use that record to do two things:
create a individualised data-object (a representation of it as a physical location in a real-world representative data-matrix or “geo-tagging” it) and
identify and record as and when there are correlations between the data object moves, behaves and the way they feel.
(1) The first repurposing idea is that of “surface-mapping” an individual (like a shop that has its location and past performance details mapped out by popular search engines) combining objective and visual, location-based data, with subjective and performance data and thereby making them “Real” as a data point in a calculable data-matrix (of a good or bad restaurant (QoL metrics) in the area within your search criteria).
The second (2) is to observe and correlate how the way they walk/move (including micro-expressions) changes when the way they “feel” changes. Or at least how they say/are reported to say they feel.
Finding a place in the world with such clean and structured records showing both those things could be hard to find but the healthcare setting is essentially a place where they make records of what was done to make people feel different (treatment pathway, diet, exercise pathway, APIs) all the time, and seems like a good and natural place to start. This paper explains that this also offers an incredible opportunity to safely release AGI computational power to the public domain's benefit.
The “how” of this idea is by comparing your data-file's key-traits with other data-file holders (people) that are “most-like you”.
The “why it’s safe” is because healthcare only ever asks what would be best for you and is inherently benevolent.
This paper doesn’t go into the details of how to produce a 3-dimensional map of individuals with an associated database. Or how to “Google-map people”, this is current technology and not innovation.
The innovation in this paper is to present a “pure logical” argument for a change in conceptualisation of Spinor mathematics to mathematico-logically support the use-case that complies with current observational evidence, to conclude that combining these various high-complexity systems in the method suggested is sound and calculationally cannot but work if current scientific evidence is to be believed.
To do this in practical terms is simple to execute with existing technology: as an idea it is about comparing the way in which people’s movement patterns change when they are made to feel differently (via treatment, lifestyle modification and home advice).
The application of this logic in healthcare is logical. Healthcare holds data, lots of it, about how people feel. And it is a valuable industry with a great need for improvement.
Progressing that connection successfully has always been extremely valuable and affects every aspect of today’s world. It also represents the gradual pursuit of total, coherent computational entanglement. An experiment Theoretical Physicists and Computer Scientists have been looking for.
Using data on “the way people move”, and statistically correlating that data to the data on “how they feel”, would logically create an objective parameter to link clinical treatment processes to objective behavioural data. This paper suggests this parameter conceptually and mathematically and offers a logical execution of it, using semi-familiar existing technologies from mathematics, the world of finance and theoretical physics to explain a bigger opportunity:
the introduction of true AGI computing to benefit human health.
This paper demonstrates a logical and practical route and does so by invoking thermodynamic computation of the suggested data-particle relationships (infodynamics) of Quantised datasets. In doing so it does two things: establish a computationally entangled relationship between the unique individual (subject under clinical evaluation) and the gargantuan database already available in the wider clinical, ethnographic and populational healthcare data-pool.
In this paper, we outline a novel mathematical and computer-logical data-management and data super-imposition model for the confident entanglement of distally associated data points and their resulting, predictive computational capability in Healthcare.
The usage of existing computational models from financial systems in healthcare, and the translation of stock and company values to human experiences such as health and quality of life may seem transactional yet “naturally analogous” and offers useful, readily made applications in healthcare.
In one sense, effective healthcare could, when translated into fiscal/economic terms, be thought of as a naturally emerging and globally combined effort to:
optimise human individual “stock and strike-value" (Quality of Life Metrics)
optimise pressure-fluctuations in ongoing interest rate-changes (Environmental and socio-economic metrics)
undertake volatility management, by creating stable markets with healthy internal fluctuation primarily driven by innovation and human adaptation (Policies, Politics and Socio-cultural narratives)
This, so to speak, to maximise derivative “call option value” as analogy to improving Quality of Life (QoL).
This paper presents that the analogy holds more broadly and enables us to use existing computational models from the financial markets. These mathematical tools, repurposed into healthcare terms, can be used to predict, guide and maximise individual quality of life metrics as a means to deliver a novel, cost-effective and -efficient, healthcare model.
Healthcare is very much based on natural phenomena having predictable effect and repeatability. By creating relevant data-loops using avatar-based archetypes, real-time advice and guidance can be produced for both patient and clinician alike from other, most-like data-pools.
This is in equal measure in the interest of governments, organisations, households and individuals alike. Note; this, in equal measure, but in different ways (methods/expressions).
From an analytical point of view, we can evaluate the datapoints that comprise those 3 areas (QOL/ Environmental and Cultural narratives) equally, whether at global, organisational or individual level, and observe their interactions and lags for emerging patterns and coalescences. Yet at individual level they operate within their own dataset, only occasionally releasing changes in other functionally linked datasets.
These various analyses are currently produced as policy-impact reports, socioeconomic-/ clinical research, and individual clinical files. Computational models are in use in the financial markets with derivatives and integrals. Their topological evaluation reveals various patterns and predictive relationships of interest for further analysis and prediction.
Projecting the various data meshes onto each other and identifying correlations by this method has previously demonstrated high-confidence predictions in all branches of medicine and is well-used in science.
This paper’s proposal is a method to reveal correlating patterns for predictive and evaluatory purposes in a new healthcare data-management strategy. It is aimed at promoting health-positive behaviours and improving care and self-care delivery, as well as the use and development of more effective care pathways. This, in some contrast to the predominant clinical healthcare-research policy that is aimed at improving delivery of sickness-care processes for the restoration to a theoretical, statistical “normal”.
Both statistical approaches toward risk have individual merits under differing circumstances. This approach seeks to improve performance in the prevention field to reduce strain on the latter sickness-care field. It also reveals significant computational potential in other fields by integration with its method.
Limited by data-sharing restrictions, the success associated with quantum/data-processing methods used in the financial sector has so far been elusive in healthcare. This proposal is to create a localised computational “digital form” of the movement patterns and changes in movement patterns of “the individual” (a file analogous to the data representing the “health of a company”).
There, it compares movement patterns representing the notion of the “changing-self” to that of the changing-self-of- “others”. From this, archetypical response-patterns are identified and classified. The extra data needed for construction of this avatar is acquired on-site from material freely available through CCTV. From there, several significant and emerging predictive functions arise from the creation of this localised form.
This can be done using simple visualisation technology to develop an understanding of fluctuation of individual movement surface-patterns in response to treatment (TKM or Topological Kinesiomorphology) with public and private keys (identifiers) held in a blockchain wallet for 3rd party analysis. In essence, this process makes the relative and subjective information of the individual’s health status have reference in the real world. It also makes it useful data by quantising the individual’s reaction to environmental changes/stimuli. This paper outlines this concept theoretically and suggests several analogous mathematical and financial tools already in use today which can be recombined to form a theoretically effective computational model for the successful prediction of health-positive behaviours and actions.
If considered successful, this computational re-evaluation would readily translate into changes in perspectives in math, physics and other sciences. These are beyond the scope of this paper; seeing the alternative could be unnecessarily complex and confusing to the goal of this paper.
Some ideas solve a problem, some change the way we solve it. This one, aims to do both.
Keywords:
healthcare, AI/AGI, emergence, modelling, infodynamics, LLLM, blockchain, HIPAA, topology, Lidar, derivatives, integrals, Web3.0.
