ICT-CIO: Clinical Informatics Outlet via Neural Networks for

Inclusive, Contextual, and Tractable eHealth

Sheldon Liang

1,* a

and Henry Whitlow

2,**

Department of Computer Science, Lane College, Jackson TN, U.S.A.

Department of Management, Clark Atlanta University, Atlanta GA, U.S.A.

Keywords: CIO-Clinical Informatics Outlet, OLAP-Online Archival Analytical Processing, CARE - Cloud Archival

Repository Express, DATA - Digital Archiving & Transformed Analytics, UnIX-Universal Interface &

User-Centered experience.

Abstract: Studies on Ageing Well and eHealth aim to improve health-related quality for well being life in AWE that

applies Information & Communication Technologies to Clinical Informatics as Outlets to help people stay

healthier, and more independent and active at work or in their community. The Clinical Informatics Outlet

has emerged from information-driven technologies in which the neural network plays a key role in applied

artificial intelligence and machine learning (AIM) for the effective use of information and data technology in

healthcare to improve patient outcomes, streamline clinical workflows, and enhance the delivery of care. This

paper presents N

ICT-CIO acting as a clinical informatics outlet (platform) that aims for the use of digital

technologies and electronic communication tools to support and improve healthcare services with inclusivity,

contextuality and tractability. Where the ICT can be redefined from a service perspective via AIM and Neural

Networks characterized through inclusivity via inclusive design for equitable services that are accessible,

usable, and enjoyable; contextuality for charming user experience in a contextual, individual and assemblable

approach to help other people consider something in its context; and tractability is to propel handlings of

situations with ease. The novel CIO (N

ICT-CIO) represents a revolutionary step forward in healthcare

delivery, leveraging advanced technologies. Designed to address inefficiencies, improve patient portfolio, and

enhance security and collaboration across healthcare systems, it can be built as a cohesive platform able &

capable to integrate these technologies around core pillars: neural networks, universal interactivity, resilient

enhancement, and self-adaptive automation (Magic G.I.F.T). As a result, N

ICT-CIO, based on the previous

inventive work of wiseCIO, prioritizes generative criteria for equity of eHealth service regardless of their

abilities, such as age, background, or circumstances, contextualizes dynamical portfolio optimization to user-

centered experience, and most important, synergizes CARE (for content management & delivery), DATA

(for OLAP), and UnIX (universal interface & experience) as a whole to promote cloud-based orchestrated

Anything-as-a-Service (XaaS) with Magic G.I.F.T characterized via dynamically Grouping, Indexing,

Folding & Targeting for eHealth services available at the user’s fingertips.

1 INTRODUCTION

Studies on Ageing Well and eHealth aim to improve

health-related quality for well being life in AWE that

apply Information & Communication Technologies

to Clinical Informatics as Outlets to help people stay

healthier, and more independent and active at work or

in their community. The Clinical Informatics Outlet

https://orcid.org/0009-0002-7191-0346

* Also, the paper was supported by the US NSF / iUSE

grant (ID# 2142514)

** Henry’s Interview on Digital Twin by Dr. Liang,

https://youtu.be/sbtlWLMySnU

has emerged from data-driven technologies in which

the neural network plays a key role in applied

artificial intelligence and machine learning (AIM) for

the effective use of information and data technology

in healthcare to improve patient outcomes, streamline

clinical workflows, and enhance the delivery of care.

Inclusivity ~ Traditional systems design and

development pursue a “one-size-fits-all" solution,

248

Liang, S. and Whitlow, H.

N2ICT-CIO: Clinical Informatics Outlet via Neural Networks for Inclusive, Contextual, and Tractable eHealth.

DOI: 10.5220/0013280400003938

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health (ICT4AWE 2025), pages 248-258

ISBN: 978-989-758-743-6; ISSN: 2184-4984

which is optimal and general, but may probably

introduce unpredictable “digital biases” to the

community-based diverse mass users - a specific

group of people may feel biased because of various

abilities, such as ages, backgrounds, and/or

circumstances. More biases could be introduced by

“sophisticated” design that may be stiff, and make

users stuck without dynamical portfolio optimization

(Gunjan and Bhattacharyya, 2022), such as linguistics

in menu, layout for outcomes, the algorithmic

processing approach, etc., which makes the user

inconvenient, incapable, and inequitable while using

them. The paper’s goal is to use neutral networks to

make the hidden layer eclectic and turn out “smiley

face” (without biasing anybody) in which

personalized usage of the service would be

dynamically as part of the input so as to rid digital

biases. Innovation with artificial intelligence and

machine learning (AIM) helps humanize eHealth

services and turn “digital biases” into a “digital

mentor” aligning with diverse individuals on their

needs (Whitlow and Liang, 2024). Ideally, the

inclusive “digital twin” is generalized by creating

products, services, or environments that are

accessible, usable, and enjoyable for as many people

as possible, regardless of their abilities, such as age,

background, or circumstances

Contextuality ~ smart computing abilities are

required to help other people consider something in

its context or the situation within which it exists or

happens. In favor of “multifacetedness-in-one”, or

“multifacets-in-one”, systematic contextuality means

understanding and embracing various facets,

behaviors, or outcomes based on their interactions

within a specific system or environment. It is

systematic contextuality that helps the effective use

of information and data technology in healthcare to

improve patient outcomes, streamline clinical

workflows, and enhance the delivery of care. On

another hand, “digital biases” may not be so wrong,

but could be “pre-planted” strategic decisions,

systematic contextuality assists the “digital mentor”

by providing multifaceted, eclectic and elastic

scenarios for eHealth services.

Tractability ~ informative abilities are needed to

effectively address, manage, and solve health-related

problems or challenges. Ensuring tractability without

biases means developing solutions that are accessible,

fair, and effective for all patients, regardless of

background, socio-economic status, or other

individual factors. As part of clinical informatics

outlets, informative tractability embodies data-driven

decisions with diverse representation, transparency in

methodology and outcomes, and the most important,

equitable access to treatment and resources that

should be unbiased.

The novel CIO represents a revolutionary step

forward as a Clinical Informative Outlet in

healthcare, leveraging advanced technologies such as

Artificial Intelligence & Machine learning (AIM),

blockchain, cloud computing, big data analytics and

neural networks, smart contracts, and digital twins

(mentor to individuals). Designed to address

inefficiencies, improve patient portfolio, and enhance

security and collaboration across healthcare systems,

it can be built as a cohesive platform able & capable

to integrate these technologies around core pillars:

neural networks, universal inclusivity for unbiased

use with ease, resilient enhancement for

contextualized user experience, informative

tractability for accessibility, fairness, and

effectiveness for all patients, and self-adaptive

automation to promote cloud Anything-as-a-Service

(XaaS) with Magic G.I.F. T (Liang and Miller, 2024)

characterized via dynamic ally Grouping, Indexing,

Folding & Targeting for eHealth available at the

user’s fingertips.

From the view of AIM, to humanize eHealth

services of inclusivity, contextuality and tractability,

the N

ICT-CIO may involve two types of data sets

that can be migrated as knowledgebase from

experiential and expertise in the industrial sector:

large datasets, and arbitrary & unstructured data

streams that collaborate through CIIA (contextual,

interoperable & intelligent aggregation) for clinical

portfolio management. OLAP (Microsoft Azure

Analysis Services, 2025) represents a category of data

processing that enables users to perform complex

archived analytical queries on large datasets quickly

and interactively, which is widely used for business

intelligence and decision support because it allows

users to analyze data from multiple perspectives (such

as time, location, and product) by structuring it into

multi-dimensional "cubes." Neural Networks are

used to deal with arbitrary or unstructured data that

are strongly associated with portfolio content

normalization and optimization. They can also

innovate with traditional existing websites to be more

presentable to help ensure user-centered experience

in the cloud computing environment with low/no

coding.

Strategic Impact ~ the N

ICT-CIO platform

offers a transformative approach to healthcare,

addressing key challenges such as data

fragmentation, administrative inefficiencies, and lack

of personalized care. By integrating AIM,

blockchain, cloud computing, and other technologies,

it enables healthcare providers to deliver efficient,

N2ICT-CIO: Clinical Informatics Outlet via Neural Networks for Inclusive, Contextual, and Tractable eHealth

249

secure, and patient-centered care. Major contribution

of the paper on the self-adaptive CIO eclectically &

elastically combes OLAP with Neural Networks to

considerably aim for Inclusive, Contextual, and

Tractable eHealth, all of which is reflected with

following benefits:

▪ Personalized, Real-Time Care: AI-driven

insights and adaptive learning enable

healthcare providers to tailor treatments to

individual patient needs, improving accuracy

and outcomes.

▪ Secure and Transparent Data: Blockchain

ensures the privacy and security of patient data

while enabling transparent and trusted sharing

among healthcare stakeholders.

▪ Automation and Efficiency: The use of smart

contracts automates administrative tasks,

reducing the burden on healthcare providers

and streamlining patient interactions with

healthcare systems.

▪ Collaboration and Scalability: Cloud

computing facilitates collaboration between

healthcare professionals, supporting the

integration of diverse care providers and

ensuring that patient care is coordinated across

multiple settings.

▪ Proactive Healthcare Delivery: Predictive

analytics powered by big data allows for early

identification of health risks, enabling

healthcare systems to move from reactive care

to proactive, preventive care.

The paper is organized with following aspects:

Sec-2. Overview of N

ICT-CIO

Sec-3. Pillars for Clinical Informatics Outlet

Sec-4. RNNs for contextual enhancement

Sec-5. Case Study for better Applied Outcomes

Lastly, the conclusion will be drawn to

summarize.

2 OVERVIEW OF N

ICT-CIO

ICT-CIO addresses key challenges such as data

fragmentation, administrative inefficiencies, and lack

of personalized care, functions as the clinical

informatics outlet, a cloud-based platform that

considerably offers “digital & clinical mentorship

through a transformative approach toward Inclusive,

Contextual, and Tractable eHealth. It is the novel CIO

platform that enables healthcare providers to deliver

efficient, secure, and patient-centered care by

integrating AIM, blockchain, cloud computing,

distributed data center, and other technologies,

illustrated in Figure 1.

Figure 1: Clinical Information Outlet for eHealth.

According to Figure 1, The N

ICT-CIO serving

as a clinical informatic outlet platform for eHealth

can be modeled in a three-layered framework: 1)

digital clinical mentorship, or digital twins - a virtual

replicas of patients, liaising with human serving for

the HIA community; 2) the central gear represents

AIM embodied via information-driven eclectic

automata (Liang and Miller, 2024) endorsed by

MLKb, so that patient-centered care can be offered

via ICT characterizes Inclusivity, Contextuality, and

Tractability achievable by Neural Networks for high

flexibility & adaptability; 3) two types of distributed

resources utilized for iDEA: the domain-specific data

sets via OLAP, and arbitrary data streams via RNNs

(Stryker, C. IBM, 2025). eHealth promises a digital

revolution for better care by effective use of

information and data technology in healthcare to

improve patient outcomes, streamline clinical

workflows, and enhance the delivery of care.

A multi-document represents functional features

the CIO pursues, and Recurrent Neural Networks

(RNNs) denote a deep neural network trained on

sequential or time series data to create a machine

learning (ML) model that can make sequential

predictions or conclusions based on. MLKb plays a

key role in both OLAP and RNNs through data

mining, analytical processing, information retrieval,

and pattern recognition. MLKb supports robotics

automation with low or no coding.

2.1 The Future of eHealth: A Digital

Revolution for Better Care

As we stand on the brink of a technological

renaissance in healthcare, eHealth emerges as a

ICT4AWE 2025 - 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health

250

transformative force poised to revolutionize how care

is delivered, accessed, and experienced. With

advances in digital twins, artificial intelligence (AI),

blockchain, cloud computing, and machine learning,

we are entering an era where healthcare becomes not

only more efficient but also more inclusive,

personalized, and proactive. The N

ICT-CIO could

be a domain-specific CIO (clinical informatics

outlet), a digital revolution for better care, and helps

to lead to the future of eHealth as follows:

▪ A New Era of Inclusivity and Personalization ~

One of the most promising aspects of eHealth is

its ability to make care equitable and adaptive.

For too long, healthcare has struggled with

disparities based on geography, socio-economic

status, and systemic inefficiencies. But imagine

a world where digital twins—virtual replicas of

patients—enable personalized care plans that

adapt dynamically to an individual’s unique

needs. These digital models, combined with AI,

offer unprecedented opportunities to predict

outcomes, optimize treatments, and prevent

complications.

▪ The Power of Collaboration and Real-Time

Insights ~ Healthcare has long been hindered by

data silos and fragmented systems. However,

platforms like the N

ICT-CIO offer a glimpse

into a future where collaboration becomes

seamless. By integrating blockchain for secure

data sharing and cloud computing for real-time

accessibility, these platforms enable physicians,

specialists, and caregivers to work together as

never before.

▪ Empowering Aging Populations ~ The challenge

of caring for aging populations is one of the 21st

century’s defining healthcare issues. eHealth

technologies are uniquely positioned to address

this challenge. IoT devices, such as wearables,

continuously monitor vital signs, mobility, and

other health indicators, feeding data into AI-

powered systems that predict and prevent

potential emergencies.

2.2 Digital CARE for eHealth

As an example of a previous inventive work, wiseCIO

(Liang, Lebby and McCarthy, June, 2020) has

embraced a good number of dedicated and intelligent

parts for industrialized content management and

considerate delivery (“CMD”), such as CARE for

well-archived content management and delivery,

MLKb for algorithmic machine learning that

implements data mining of arbitrary / unstructured

data streams via pattern recognition, DATA for

digital archiving & transformed analytics.

ICT-CIO platform considerably offers a

transformative approach to Inclusive, Contextual, and

Tractable eHealth by addressing key challenges such

as data fragmentation, administrative inefficiencies,

and lack of personalized care. Central to the N

ICT-

CIO platform is (a) DCM (digital-clinical

mentorship) being grounded on (b) MLKb with AIM

to embrace (c) RNNs (for deep learning from

unstructured data streams) and (d) OLAP (for

digitally-archived data sets). The DCM via Clinical

Informatics Outlet coordinates the N

ICT of

Inclusivity, Contextuality, and Tractability in support

of the HIA Community that is healthier, independent

and Active, mentors patients and clinical staff

members in healthcare to improve patient outcomes,

streamline clinical workflows, and enhance the

delivery of care, and discoveries their behavioral

preference, and care-specific routines for the sake of

better mentorship. In particular, the N

ICT platform

is open to orchestrate Anything-as-a-Service with

AIM that assembles various technologies, such as

blockchain, cloud computing, and other technologie,

with low or no coding, for healthcare providers are

enabled to deliver efficient, secure, and patient-

centered care.

2.3 Core Pillars of CARE for eHealth

There are following pillars that make the Clinical

Informatics Outlet transformative to Inclusive,

Contextual, and Tractable eHealth as follows:

▪ Inclusive Digital Twins via DCM (digital-

clinical mentorship) as virtual replicas of patients

to liaise inclusively with eHealth service for the

HIA community. Wherein portfolio normalizer

via MLKb to embrace AIM to synergize

dynamical portfolio optimization as a powerful

strategy for maximizing customer value,

improving customer satisfaction, and driving

profitability.

▪ Contextual Collaborator for digitally-archived

data sets able to contextualize current

technologies, such as blockchain, big data

analytics (OLAP) and neural networks

(RNNs),smart contracts, together with previous

inventive works residing on wiseCIO (Liang,

Lebby and McCarthy, 2020), such as CARE

(Liang, Hall, Pogge and Van Str,y 2022),

DATA(Liang, McCarthy and Van Stry, 2021),

and UnIX as dedicated par ts from which N

ICT-

CIO is composed as a whole for Clinical

N2ICT-CIO: Clinical Informatics Outlet via Neural Networks for Inclusive, Contextual, and Tractable eHealth

251

Informatics Outlet through Orchestrated XaaS

for Inclusivity, contextuality tractability by

harnessing cloud-based Anything-as-a-Service

(XaaS) for a wide range of service delivery over

the internet rather than through traditional

means.

▪ Tractable Allowance-Made-For the HIA

Community & eHealth via information-driven

elastic automata (iDEA) to tractably collect

workflows of tasks that are eclectic & elastic to

the individuals, and target via Magic G.I.F.T

Among inclusivity, contextuality, and tractability,

portfolio normalization transitions from inclusivity to

contextuality, and orchestrated XaaS from

contextuality to tractability. Thorough discussions

will be conducted in the next section.

3 CORE PILLARS FOR

CLINICAL INFORMATICS

OUTLET

The clinical informatics outlet (CIO) emerges from

eclectic and elastic cloud archival repository express

(CARE) in combination with OLAP and RNNs as a

whole for inclusive, contextual, and tractable

eHealth. There are five core pillars that streamline via

iDEA the effective use of information and data

technology in healthcare to improve patient

outcomes, harness clinical workflows, and enhance

the delivery of care, as illustrated as Figure 2.

Figure 2: iDEA: information-driven Eclectic Automata.

According to Figure 2, it is depicted that the

neural network is made robotic consisting of layers of

nodes, or artificial neurons. The subscribers (Subs),

such as patients and medical providers, liaise with the

input layer (portfolio) through several hidden layers,

such as Contextual Collaboration, Digital Twins, and

Orchestrated XaaS, and the output layer Tractable

Allowance made for eHealth services (Svc). Central

to the network is Inclusive digital twins that are

virtual replicas of patients to liaise with eHealth

service for the HIA community. Each pillar acting as

a node connects to others, and has its own associated

“weight” and “threshold” throughout iDEA that

refers to the MLKb via OLAP and RNNs. If the

output of any individual node within the pillar is

above the specific threshold value that node is

activated, sending data to the next pillar of the

network. Otherwise, no data is passed along to the

next pillar of the network.

3.1 Intelligent & Optimal CIO

Intelligent and optimal CIO - clinical informatics

outlet - can actually provide virtual replicas of

patients that are responsible to liaise inclusively with

eHealth service for individual members of the HIA

community. One of the most promising aspects of

eHealth is its ability to make care equitable and

adaptive. For too long, healthcare has struggled with

disparities based on geography, socio-economic

status, and systemic inefficiencies. But imagine a

world where digital twins enable personalized care

plans that adapt dynamically to an individual’s unique

needs. These digital models, combined with AI, offer

unprecedented opportunities to predict outcomes,

optimize treatments, and prevent complications.

For example, an elderly patient with multiple

chronic conditions can benefit from a digital twin that

simulates the effects of various treatment options.

This allows clinicians to choose the safest and most

effective path, reducing hospitalizations and

enhancing quality of life. This technology also

democratizes care, ensuring that rural and

underserved populations gain access to the same

high-quality healthcare as those in urban centers.

3.2 Rule-Based CIO via Portfolio

Normalization

Portfolio normalization innovates to normalize and

synergizes dynamic portfolio optimization that

supports comfortable and trustful eHealth service

through the “digital mentorship” that can be

individualized as a powerful strategy for maximizing

customer value, improving customer satisfaction, and

driving profitability. Portfolio is a collection of

drawings, documents, etc. that represent a person's

work and tracks, such as clinical workflow, historical

prescriptions and so on. The PON helps the service

get smarter through Algorithmic machine learning.

With PON the learning process can get rid of GIGO,

or garbage-in-garbage-out.

ICT4AWE 2025 - 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health

252

3.3 Collaborative CIO with

Interoperability

The collaborative CIO is empowered by

Collaboration and Real-Time Insights. Healthcare has

long been hindered by data silos and fragmented

systems. However, platforms like the N

ICT-CIO

offer a glimpse into a future where collaboration

becomes seamless. By integrating blockchain for

secure data sharing and cloud computing for real-time

accessibility, these platforms enable physicians,

specialists, and caregivers to work together as never

before.

Picture a global network where a general

practitioner in Atlanta can consult with a specialist in

Geneva in real-time, sharing patient data securely and

instantly. This interconnected ecosystem is not only a

boon for individual patients but also a game-changer

for tackling global health crises, enabling faster, data-

driven responses to pandemics, and resource

shortages.

3.4 Orchestrated CIO Empowering

Aging Populations

The challenge of caring for aging populations is one

of the 21st century’s defining healthcare issues.

eHealth technologies are uniquely positioned to

address this challenge. IoT devices, such as

wearables, continuously monitor vital signs, mobility,

and other health indicators, feeding data into AI-

powered systems that predict and prevent potential

emergencies.

Meanwhile, telemedicine, bolstered by the

Anything-as-a-Service (XaaS) model, brings care to

patients wherever they are. An elderly individual can

consult a doctor from the comfort of their home,

supported by real-time data insights and secure digital

records. This integration of technology enhances

independence and dignity for aging individuals while

easing the burden on caregivers.

3.5 Tractable CIO Making Allowance

for Digital Innovation

Tractable CIO represents iDEA the collected

workflows of tasks will be eclectic to the individuals,

which acts as the DCM. It is the iDEA whose core is

digital innovation that helps with the effective use of

information and data technology in healthcare to

improve patient outcomes, streamline clinical

workflows, and enhance the delivery of care. Let’s

imagine, there are a certain number of tasks in clinical

services, the combinational would be huge against

individuals. Here not pursuing "one-size-fits-all"

solution that could bring out “digital biases”, We are,

instead, promoting “multifaceted-in-one” in

individual “digital mentorship” with inclusivity. The

clinical workflows can be streamlined according to

individuals’ special needs. Magic G.I.F.T is

considered a great AI tool in e-service digital

innovation with plenty of content deliverable

dynamically through Grouping, Indexing, Folding &

Targeting for eHealth services available at the user’s

fingertips.

As we stand on the brink of a technological

renaissance in healthcare, eHealth emerges as a

transformative force poised to revolutionize how care

is delivered, accessed, and experienced. With

advances in digital twins, artificial intelligence (AI),

blockchain, cloud computing, and machine learning,

we are entering an era where healthcare becomes not

only more efficient but also more inclusive,

personalized, and proactive.

4 NEURAL NETWORKS FOR

CONTEXTUAL

ENHANCEMENT

A neural network is a machine learning model that

makes decisions in a manner similar to the human

brain, by using processes that mimic the way

biological neurons work together to identify

phenomena, weigh options and arrive at conclusions.

Specifically neural Networks are introduced to

deal with arbitrary or unstructured data streams that

are strongly associated with portfolio content

normalization and optimization via CIIA (contextual,

interoperable & intelligent aggregation). They can

also innovate with traditional existing websites to be

more presentable, so that “CIIA” helps ensure user-

centered experience in the cloud computing

environment with low coding or no coding.

Contextuality is derived from the subscribed portfolio

about user experience under a specific circumstance

where the user’s focus would be. That is, the

circumstance is “renovated” for individuals without

appearing with the same interfacing content to cause

the loss of his focus / concerns.

4.1 Eclectic Collaborative CMD

Collaborative Content Management & Considerate

Delivery (CMD) could only be achieved via neural

networks. Considerate delivery to the individuals

should be inclusive without digital biases. So we

N2ICT-CIO: Clinical Informatics Outlet via Neural Networks for Inclusive, Contextual, and Tractable eHealth

253

introduce Recurrent Neural Networks (RNNs,

Stryker, C. IBM, 2025) as an eclectic and elastic

solution to CMD. RNNs denote a deep neural

network trained on sequential or time series data to

create a machine learning (ML) model that can make

sequential predictions or conclusions based on It

makes sense with RNNs that sequential inputs from

the given subscriber can assist sequential predictions

or conclusions.

The neural network is made robotic consisting of

layers of nodes, or artificial neurons. The subscribers

(Subs), such as patients and medical providers, liaise

with the input layer (portfolio) through several hidden

layers, and the output layer for eHealth services

(Svc). Each node acting as a node connects to others,

and has its own associated “weight” and “threshold”

throughout iDEA that refers to the MLKb via OLAP

and RNNs. If the output of any individual node is

above the specific threshold value that node is

activated, sending data to the next pillar of the

network. Otherwise, no data is passed along to the

next pillar of the network.

MLKb plays a key role in both OLAP and RNNs

through data mining, analytical processing,

information retrieval, and pattern recognition. MLKb

supports robotics automation with low or no coding,

as illustrated in Figure 3.

Figure 3 shows you the subscribers (Subs as

input), and the eHealth service (Svc as output), and in

between is the processing (hidden) layer where

neutral networks are built based on dynamically-

normalized portfolio. There are various computing

approaches toward the implementation of portfolio

optimization. The solution to the N

ICT-CIO

platform is the MLKb (machine learning

knowledgebase) that intelligently supports and

generates contextual neural networks with low/no

coding. That is to say, the “pathway” as indicated

above for an individual, is intelligent for reasoning-

about.

Figure 3: Contextual neural networks for user experience.

Amazingly, the customizable context through

contextual neural networks would prioritize the

primary on top at user’s fingertips, and in the

meantime, a group of associative content is suggested

available and accessible at the most convenience.

According to iDEAL-CIO (Liang and Miller, 2024),

a “magic lamp” is provid ed with hundreds up to

thousands web blocks that can be made available and

accessible in the context, which is enabled with

Magic G.I.F.T. for top presentation of the web block

plus dynamically grouping, indexing, folding and

targeting through associative accessibilities.

4.2 Descriptive RNNs with Low Coding

Descriptive RNNs support rule-based Machine

Learning automata so that the RNNs can be

implemented recurrently with dynamic rule

distribution to drive the automata. Descriptive RNNs

are composable for iDEA that signals divergent nodes

connecting each other lead to “sinking output”, one or

zero outlet. The descriptive RNNs can strategically be

fulfilled through structurality, spontaneity,

smoothness and synthetics as a JIT (Just-in-Time)

output. A variety of means by which the inclusive

section via the clinical informatics outlet is to be

composed and delivered from the collective portfolio

segments at runtime. For example, a clinical module

can comprise sections, sessions, and (hierarchical)

segments. Adherence to composable rules as

constituents within an expert system (Parente, Rizzuti

and Trerotola, 2025) serve to cohere or “glue” them

under the module.

Figure 4: Rule-based descriptive knowledge for RNNs.

Figure 4 gives four definitions to neural logic

flows that can be implemented as semantic graph in

the MLKb:

▪ Logical sequence ~ in a given neural network, a

node connects to another, the performing logic is

from one to another, which could be understood

in clinical treatments, intake of pills, then

monitor

▪ Logical selection ~ a node selectively connects

to more than one node, but the performing logic

is randomly selective, which could be understood

in choice meals in a hospital.

▪ Logical at simultaneousness ~ a node connects

multiple nodes and performs logic to transition

ICT4AWE 2025 - 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health

254

from the current to all the adjacent nodes at

exactly the same time, but there must be a

merging point, whoever researches at the point

first causes others to cancel with no data.

▪ Logical Composite ~combinational priority.

With imaginary diagrams in Figure 3, the

contextual neural networks can be described in above

mentioned descriptive RNNs

4.3 iDEA over Descriptive RNNs

We have created an iDEA(Liang, and Cox, 2024) by

using instructional information to drive an eclectic

automata for diverse learners. The smart use of plenty

of inclusive learning sections as neural network nodes

generates three levels of learning modules: initial

junior, senior. The sampled portfolio factors do help

with the hidden processing layer in the RNNs. When

each learning section is assigned with a value that

marks as initial, junior and senior, etc. It was a work

in progress for educational equity, but we can adapt

the model here for N

ICT-CIO for eHealth service.

Figure 4: RNNs via info-Driven Elastic Automata.

In Figure 4, it is illustrated that the fulfillment of

ICT-CIO is composed of four parts: portware,

descriptive neutral network, diverse outcomes, and

iDEA through MLKb. In a domain-specific field,

there is generally a complete closure from a

mathematical perspective, for instance, a complete

closure for human marriages is [male, female]

traditionally. 1) Portware is defined as the “complete

closure” for eHealth affairs related portfolio

components, such as patient outcomes, streamlined

clinical workflows, and enhanced delivery of care,

etc. where the “complete closure” is relatively

complete but it could be enhanced, just like same-sex

marriages, …2) descriptive neural networks,

reflecting combinatorial possibilities, in order to

target inclusivity, … 3) diverse outcomes against

individuals’ needs, and 4) info-driven eclectic

automata over MLKb.

4.4 Innovative eHealth for Portware

The innovative eHealth represents an approach on re-

engineering traditional existing web content done for

years, which turns out as associative, useful and

usable with algorithmic machine learning in low or no

coding. The idea of eHealth Digital Innovation is to

innovate with or renovate the traditionally existing

healthcare related websites by retrieving content in

support of clinical informatics outlets (CIO). A piece

of Portare, known as portBox (portfolio box), generally

consists of an image (as an icon), a caption, and brief

description, and a URL beneath that to access the

original website, shown as below Figure 5.

As part of portfolio normalization, a portBox is

innovated from existing websites ( wiseCIO-renovated

TeV, 2022; Hatfield , 2023) and automata beneath is

the solution of RNNs describable with MLKb. There

are charming intelligent features that can be automated

and attached to the portBox, such as language set for

auto-translation (via a dropdown list).

Figure 5: Innovated prtBoxes from existing websites.

Table 1: Descriptive RNNs for pattern recognition.

Explaining

Descriptive RNNs in MLKb

A useful icon / image

could be tag <img …>,

so by its src, the icon can

be extracted for portBax.

There may be multiple

paths to succeed with a

retrieval. …

'website…':

{ // j=-hcc/tlnz

'pic': "icon-path>img:>src[]p2[] p3"

,'clk': "url-path>a :>href [] p2 [] p3"

,'cap': "cap-path>h2:>text()[]path"

,'des': "desc-path > p :>text()"

};

Machine Learning Knowledge (MLK) represents

the possible highlights of RNNs (over arbitrary data

streams) applied to eHealth Digital Innovation through

iDEA, robotic processing automation. Following table

is used to describe the RNNs for deep learning, and

drive pattern recognition to retrieve core ingredients

for protBoxes (icon, desc, url, caption, etc.):

Ideally, if some informative ingredients could be

figured out through simplified NLP(Stryker and

Holdsworth, IBM; DeepLearning.AI, 2023), such as

categories, series, authors, or something as

collectives, Magic G.I.F.T. can apply for rapid lookup

N2ICT-CIO: Clinical Informatics Outlet via Neural Networks for Inclusive, Contextual, and Tractable eHealth

255

and precise access via dynamically Grouping,

Indexing, Folding, and Targeting, which offers a

user-centered experience with no coding at all. We

will discuss it in the section of Case Study.

5 CASE STUDY FOR BETTER

OUTCOMES

Applied Clinical Informatics Outlet comes out from

the N

ICT whose back sketch is: Interactivity,

Contextuality and Tractability as a whole in support

of quality of eHealth service.

The eHealth can be made as an intelligent CIO via

ICT, or digital twins along with Just-in-Time magic

G.I.F.T. as shown in Figure 6. The objective of

eHealth is information / intelligence and the means of

better service is enable including inclusivity,

contextuality, and tractability by applying artificial

intelligence and machine learning (AIM) for the

effective use of information and data technology in

healthcare to improve patient outcomes, streamline

clinical workflows, and enhance the delivery of care.

As the case study, we are to present four

categorized intelligent features, different from

traditional websites, such as dashboard, locator,

grouping, and folding, all of which are low coding or

no coding because of iDEA: information-driven

eclectic automata.

5.1 Context-Sensitive Dashboard

Layouts of rich web content usually consist of

multiple parts , so a heading bar is presented as the

top menu whose items may include a sub-menu.

When so many parts are presented, it would confuse

the user unless he is so used to it. A big drawback is

that any changes of menu items would mess up the

user's ability to find the right entries for his further

operation. With well categorized services, there is no

need for a menu to appear on the webpages, but a

dynamic dashboard is provided to track the user’s

interest while she / he goes into the category, for

instance, music, science, arts, … etc.

Context-sensitive dashboard is intelligently

tracking the path that the individual user went into a

category. With or without appearing onto a dynamic

dashboard, a part tracks on statistical popularity. For

more information, please refer to UnIX-CARE(

Liang,Van Stry,and Liu, 2022).

5.2 Rapid Locator with no Scrolling

There is usually a lengthy list for web blocks

(portBox) after being renovated from the original

websites, and each block includes an illustrative

image, a title, and brief description and associated

actionable buttons, or anchors. Traditionally, a user

can scroll down / up the listed web blocks, a “quick

pickup” dropdown is of great help as part of the

automated contextual locator.

The TeVA, Tennessee Virtual Archive has been

highly praised with high professional and diligent

work on. The renovated outcomes are even greater

than the original website because of the excellence of

UnIX. Amazingly, a user can stay without needing to

swap webpages from one to another, which reflects

what it means “centeredness of user experience”.

Also, such kind of valuable long-term information

service could be more globalized with multi-

linguistic translations, from which, contextuality

really means what it does for better web service (e.g.,

healthcare) outcomes.

5.3 Keyword-Grouped Activator

Lots of long-term websites provide wonderful online

resources (and we believe some in the healthcare

field), however, the traditional organization strategy

applied to organizing complex information services

that make rapid access impossible because of an ideal

number of items are allowed in the layout so the

numbered pages from tens up to hundreds are used to

manage big amount of web content blocks. Similarly,

the websites can be renovated through algorithmic

machine learning to collect all the blocks onto a single

webpage, and each block includes an illustrative

image, a title, and brief description and associated

actionable buttons, or anchors. Traditionally, a user

can scroll down / up the listed web blocks, but what

if the number of blocks is up to 800. Magic GIFT has

introduced grouping for better services dynamically.

Renovated by wiseCIO, the number of web blocks

up to hundreds is still a big problem. The keyword-

categorized grouping activator offers magic GIFT, a

dynamic strategy to make dynamic groupings at

user’s fingertips ( Hatfield, 2023).

By pattern recognition, there are several keyword

based activators that allow dynamical grouping

alternatively, such as image-basis (the same image

indicating the series of the topic), subject-basis (the

same subject may have multiple sessions),

speaker/host-basis (speaker on topics or subjects),

associative topics (similar topics as recommended),

and search-basis (keyword to group).

ICT4AWE 2025 - 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health

256

Figure 6: Dynamic button set for Magic G.I.F.T.

As shown in Figure 6, Applying “Topic-basis” to

the originally collected up to 800 blocks, it turns out

with Magic GIFT to form 25 groups of the same

topics, which really can help users to see more (by

collecting all from hundreds of webpages), and

choose only a few (his interest within some topics).

More details can be found in iDEAL-CIO.

5.4 Dynamic Folding to Dedicate Users

As a companion to the keyword-categorized grouping

operation, Magic GIFT is applied to promote

keyword grouping (say, topic-basis) and will present

all the grouped blocks within a folder. A user, if his

interest in that folder, can be contextually

concentrated in his category without swapping even a

single webpage.

The “just-in-time” activator for Magic GIFT

offers not just lookup (prompted by some hints), but

presents look-down (information-driven processing)

within specific folders so that he can really

experience what he is interested in, and he can

eclectically get his needs to be met.

6 CONCLUSION

ICT-CIO sets a new standard for the future of

healthcare by combining cutting-edge technologies

into an integrated platform that addresses the

evolving needs of healthcare providers and patients

alike. By embracing personalization, security,

efficiency, and collaboration, the platform positions

itself as a crucial enabler of smart healthcare systems

globally. As eHealth systems face increasing pressure

to innovate and improve outcomes, Clinical

Informatics Outlet (CIO) offers a path forward

through a data-driven, patient-centric, and automated

approach to care.

Five pillars have been more or less in practice

with plentiful web content blocks from the renovated

traditional websites, industrialized content

management & delivery, so the platform can be

grounded up to be able to considerably orchestrate

and capable of synergizing Anything as a Service

(XaaS) through intelligent connectivity and

interactivity. The N

ICT-CIO is positioned as a

technology- driven ecosystem that aims to empower

aspiring people in communities and regions, and

nation-wide with the skills, resources, and networks

needed to build individuals' entrepreneurial,

professional and educational success.

6.1 Strategic Impact

The N

ICT-CIO platform offers a transformative

approach to healthcare, addressing key challenges

such as data fragmentation, administrative

inefficiencies, and lack of personalized care. By

integrating AI, blockchain, cloud computing, and

other technologies, it enables healthcare providers to

deliver efficient, secure, and patient-centered care

(Whitlow and Liang, 2024).

The platform’s adaptability makes it well-suited

for diverse healthcare environments—from large

hospitals to telemedicine networks—providing a

scalable solution that is both cost-effective and

capable of meeting the growing demand for data-

driven healthcare services. Additionally, the platform

supports healthcare systems in achieving greater

transparency, operational efficiency, and

collaboration across disciplines, fostering a new era

of digital healthcare.

What has been achieved (?): wiseCIO was

invented in Vancouver, Canada, and it was firstly

presented at the Computing Conference, London,

UK, July, 2020 aiming for universal interface & user-

centered experience with low coding for

industrialized content publishing (quick, precise, and

instant); DATA was established by preparing

complex content with digital archive, and intelligent

connectivity promoted via analytical processing,

Magic GIFT was introduced for large-scale website

renovation, UnIX-CARE was thoroughly developed

for digital innovation on digital libraries, iDEAL-CIO

was inspired for educational equity through advanced

distributed learning.

N2ICT-CIO: Clinical Informatics Outlet via Neural Networks for Inclusive, Contextual, and Tractable eHealth

257

How to transition successes from productive

CMD to eHealth service (?): Content Management

& Delivery needs to collect more materials to enrich

the content for Healthcare outcomes; how to tie the

individual users’ feedback, and normalize it into the

MLKb so that individual’s experience can be

customized and individualized, which would be a big

part of the N

ICT-CIO.

To conclude, N

ICT-CIO sets a new standard for

the future of healthcare by combining cutting-edge

technologies into an integrated platform by

embracing personalization, security, efficiency, and

collaboration, the platform positions itself as a crucial

enabler of smart healthcare systems globally. As

healthcare systems face increasing pressure to

innovate and improve outcomes, N

ICT-CIO offers a

path forward through a data-driven, patient-centric,

and automated approach to care.

REFERENCES

Gunjan, A. and Bhattacharyya, S. (2022). A brief review of

portfolio optimization techniques. Published online:

https://www.researchgate.net/publication/363583850_

A_brief_review_of_portfolio_optimization_techniques

Whitlow, H. and Liang, S. (2024). HBCU franchising

Business Model Branding – Digital Twins.

Workshop/Seminar on intelligent Platforms

Liang, S. , Miller, P., et al (2024). iDEAL-CIO: instant

Digital Express Advocated “Magic Lamp” for Cloud

Intelligence Outlet. Intelligent Information

Management (IIM), Vol. 16, No.1,. January, 2024. doi:

10.4236/iim.2024.161004.

Microsoft Azure Analysis Services (2025). Online

analytical processing (OLAP). https://learn.microsoft.

com/en-us/azure/architecture/data-guide/relational-dat

a/online-analytical-processing

Stryker, C. (Editorial Lead, AI Models, 2025). What are

Recurrent Neural Networks (RNN)? https://www.ibm.

com/topics/recurrent-neural-networks

Liang, S. Lebby, K. and McCarthy, P. (June, 2020).

wiseCIO: Web-Based Intelligent Services Engaging

Cloud Intelligence Outlet. SAI 2020: Intelligent

Computing, Vol. 1, 169-195. doi: 10.1007/978-3-030-

52249-0_12

Liang, S., Hall, C., Pogge, J. and Van Str, M. (2022).

CARE: Cloud Archival Repository Express via

Algorithmic Machine Learning. Intelligent Information

Management, Vol. 14, No. 4, 133-156. doi:

10.4236/iim.2022.144010

Liang, S., McCarthy, P., and Van Stry, M. (2021). DATA:

Digital Archiving and Transformed Analytics.

Intelligent Information Management (IIM), Vol. 13, 70-

95. doi: 10.4236/iim.2021.131004

Parente, M, Rizzuti, L. and Trerotola, M. (2025). A

profitable trading algorithm for cryptocurrencies using

a Neural Network model. Expert Systems with

Applications. Journal homepage: www.elsevier.com/lo

cate/eswa

Liang, S., Cox, W., et al (2024). intelligent Distributed

Educational Advocated for Sustainable Learning

Outlet. Journal of Information System & Systems

Science (SCIREA). Vol.8(3), June 2024, PP 103-128

DOI: 10.54647/isss120351

wiseCIO-renovated TeVA (2022), the Tennessee Virtual

Archive. Experimental portBox renovated by wiseCIO

from TeVA. https://teva.contentdm.oclc.org/

Hatfield, R., wiseCIO-Renovated TLN (2025). The light

network of Christian podcast, https://thelightnetwork.

tv/

Stryker, C. (Editorial Lead, AI Models), and Holdsworth, J.

(Writer). What is NLP? https://www.ibm.com/topics/na

tural-language-processing

DeepLearning AI (2023). A Complete Guide to Natural

Language Processing. https://www.deeplearning.ai/

resources/natural-language-processing/.

Liang, S, Van Stry, M. and Liu, H. (2022/chapter) UnIX-

CARE: Universal Interface & Experience via

Collaborative Archive Repository Express. Edited by

Dr. Kyeong Kang, IntechOpen Publisher, London, UK.

PRINT ISBN: 978-1-80356-572-9

We hope you find the information in this template useful in

the preparation of your submission.

ICT4AWE 2025 - 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health

258