Never doubt that a small group of thoughtful committed individuals can change the world. In fact, it's the only thing that ever has."
Counterview to above in the link below illustrates the broader meaning of cision and de-cision (expanded again further down): https://www.
Introduction
to our team and human centered clinical decision making lab:
Our team consists of full time educators and practitioners of clinical decision making with a special interest in developing creative skills in learners and online users while tackling clinical decision making issues utilising current AI tools and descriptive models that not only create a case based medical informatics ecosystem but also promote explainability and trust among humans.
The above mug is available here: https://www.etsy.com/in-en/listing/270900314/theory-and-practice-funny-statement-mug?ref=elp_anchor_listing&sts=1
Our team is currently working on:
Among other things such as daily clinical decision making with our patients, a book on the same topic, named "Troubleshooting Humans in the Age of AI: A Playbook for Multidisciplinary, Participatory, Medical Cognition," and we are looking for potential chapter authors and elective trainees who will also enjoy this journey of clinical decision making to trouble shoot humans in our blended learning ecosystem in the coming months.
More about it here: https://userdrivenhealthcare.
More about our team members past and present here : https://medicinedepartment.
Case based medical informatics descriptive database:
Session learning Goals:
Short term: brief hands on interactive exposure to descriptive models of clinical decision making in the pre AI and current AI era and challenges posed toward explainability and trust in blended learning ecosystems
More here:
Descriptive or predictive? https://sites.
Changing the game: http://www.pitt.edu/~
Long term: collaborate to potentially develop a special group of human centered healthcare managers trained in AI driven clinical decision making that takes into account an individual patient's internal medicine (anatomy physiology, pathology, organ systems) and external (organisational, public health, environmental exposure and community medicine) drivers to optimise their overall healthcare outcomes using tools such as creative critical realist heutagogy.
More here:
Understanding clinical complexity in organ and organizational systems: https://pubmed.ncbi.
Narketpally syn (critical realist heutagogy) : https://pubmed.ncbi.nlm.nih.
Session learning objectives:
1) Discuss briefly the evolution of clinical decision making pre and post AI
2) Demonstrate a hands on approach to AI driven clinical decision making utilising past cases as well as cases from the floor shared by the audience
3) Discuss issues around how to bridge the inferential gap between multiple stakeholders in clinical decision making such as patients, their relatives, health professionals and policy makers through AI driven explainability
4) Discuss how to gain and maintain trust between multiple stakeholders through judicious optimization of intelligence driven explainability.
Evolution of clinical decision making
pre and post AI
What is cognition?
What is dual processing theory of cognition?
Speakers thoughts: https://
What is decision?
Word picture:
Imagine you are "Cutting a vegetable with a knife" and imagine what is the next step in your cooking once cutting is over?
Cision is the process of cutting originated from Proto-Indo-European language as *skh1-ie, *skh1-io
Looks like Europeans added an s to the beginning of khid in Sanskrit aka caed in Latin and then subsequently removed the d when they used cutting as a metaphor for science!
The word science is derived from Proto-Indo-European language as *skh1-ie, *skh1-io
So imagine some of the cutting instruments you know of and check out their names:
Nouns: scissors, sickle,
Verbs: incise, size up, cut to size
Also part of: abscise; avicide; biocide;
Needless to say, not everything ending with cise means cutting such as the words "exercise" and "exorcise" apparently have no connection to cutting: https://www.
Image with CC licence: https://commons.m.
And the image of the sickle and science is contained in an important writing tool for science! The question mark is a very important instrument of scientific scepticism:
Creative commons license: https://en.m.
To reach a de cision is to stop cutting and stop questioning further! As in de addiction or de escalation, which means to stop addiction or stop escalation!
In other words going with the cutting edge pictorial cooking analogy above, one simply moves to the next phase of cooking once the cutting of it's ingredients is over.
Decision etymology:
https://www.reddit.com/r/
What is intelligence?
Animal intelligence vs plant cognition?
Speakers thoughts
and Rhetoric:
Rhetoric:
There is nothing called artificial or real intelligence.
What exists is just "intelligence" that is embedded in all manifest beings in this Earth right from apparently inanimate plants to animate humans including embedded artificial systems that humans appear to be currently developing because of their own intelligence deficiency.
This human intelligence deficiency (requirement) is primarily memory because of which humans have been cursed with their penchant for dimensionality reduction resulting in asynchronous intelligence aka primordial AI.
This is the reason modern humans have become more and more academic as academics is largely all about communicating and learning through a two dimensional interface, be it early cave paintings or current day xy axis mobile screens!
More thoughts here:
What was clinical decision making like in the pre AI LLM era just few years back?
Video demo of our patient centered, clinical decision making lab:
https://youtu.be/ZKoljY2UBHI?
https://youtu.be/xvE5b8Xk3vM?
Video demo of a single patient's decision making:
https://youtu.be/csF8VQbOYRo?
Hands on demonstration:
Explaining the user interface for clinical decision making with AI in the loop:
Image above: Current AI driven clinical decision making workflow as well as user interface and medical cognition engine.
Rhetoric : The above interface has essentially evolved from a felt need toward dimensionality reduction leading to what is aka academic flatlands that hides multiple hidden layers, which can pose issues with explainability at a machine level.
Image CC licence: https://commons.m.
Rhetoric: Human animals invented AI beginning with asynchronous intelligence through their ability to use cave painting tech to convert multidimensional real life data into two dimensional data in an xy axis cave wall that later evolved to paper and electronic media so that they could eventually manage their lives better as artistic modelling was easier in a two dimensional virtual plane than a multi dimensional real plane!
Let's look at where we have come all the way from primordial AI (aka asynchronous intelligence) to modern AI that models primordial AI to produce some currently interesting results particularly if the data capture is asynchronously hyperlocal.
Unquote: https://
A layered approach to clinical decision making:
Explainability, trust and layers of clinical decision making in pre and current AI LLM era:
Machine layer and AI dominance with humans in the loop:
How useful is AI in the loop of humans and how crucial are humans if placed in the loop of AI?
Analytical scientific and EBM layer: This layer is where our clinical decision making lab appears to be largely engaged in although the other two layers are no less important.
We have already shared something around this layer in our previous demos particularly our two video links shared above.
Human layer: This is the most important layer where clinical decision making actually happens at multiple human stakeholder levels:
We are all apprentices in a craft where no one ever becomes a master.
Ernest Hemingway, The Wild Years
Human, Scientific and Machine layers :
Anatomy of cognitive layers:
Physiology of cognitive layers in clinical decision making: enter Bloom's taxonomy!
RUAAEC
ApRUAECAp
More here on the bloom game of learning cognition: https://sites.pitt.
Bloom's taxonomy image copyright as well as an enlightening write up: https://www.niallmcnulty.
Our single click entry user interface:
Workflow in brief:
Workflow theory generalized: https://
Workflow theory individualized:
Workflow theory simplified:
AI and human looped clinical decision making:
The human layer and Ux interface
- "Sometimes the smallest things take the most room in your heart." —
- Winnie the Pooh
- Above was Winnie the Pooh translating the Chandogya Upanishad:
- छान्दोग्य उपनिषद् ८.१.३*अथ य एषोऽणिमैतदात्म्यमिदं सर्वम्।तत् सत्यम्। स आत्मा। तत् त्वम् असि श्वेतकेतो इति।
How do we deidentify as per HIPAA, the entire data that is captured into our system 2 healthcare data processing ecosystem?
Can missing the smallest things sometimes take up the most room in our workflow?
Are the smallest things, sometimes the smallest pieces in the puzzle, most rewarding in terms of learning and illness outcomes?
Is the work of AI LLMs as just a machine translator in our multilingual workflow small enough?
Consent form: Machine translation provides an added feature to our informed patient consent form that allows a single click translation to any global language!
Let me know if the konkani seems right!
In case it's not we have a manual back up here used routinely for majority of our patients:
The above is one layer of explainability and raising awareness about patient rights including right to privacy.
Assignment: Get your LLMs to go through the consent forms linked above and check if they are DPDP compliant and if not ask for a better draft of the above consent form to make it DPDP compliant.
In a human centered learning ecosystem, with AI in the loop, manual translation is more common?
Above is a layer of manual human to human translation as well as intermittent problems in an otherwise complex patient with comorbidities (will discuss again in the next layer of AI driven analysis)
Again this patient does have comorbidities related to his metabolic syndrome such as heart failure but then intermittent simple human requirements of explainability manifest in his daily sharing through his advocate such as the one here that manifests in his sleep and meta AI helps not just to translate it but also explain it well.
The role of AI driven infographics in explainability:
Speaker's thoughts: A picture speaks more than a thousand words!
A video can be time consuming though!
Assignment: Ask your LLMs to gather all the patient data from the case report linked above and rearrange it using AI driven removal of exactly dated time stamps and replacement with unidentifiable event timelines comprising labels such as Day 1,n season of year 1,n.
This patient is an example how human simple explainability backed by scientific evidence can provide a new lease of life to a patient of myocardial infarction who travelled the long distance to our college just for that explainability to strengthen his prior trust in us!
Past published work on similar patient:
LLM textual explanation followed by translation and then text to voice file for the patient's advocate who like most of us also suffers from TLDR:
Also demonstrates AI driven support for insulin dose calculation through human learning around carb counting, accounting for insulin correction or sensitivity factor and insulin to carb ratios to decide the total insulin pre meal dose with scientific accuracy.
The Scientific analytical cutting layer:
What is the sensitivity, specificity of a CT abdomen in a woman with chronic mild intermittent regular pain abdomen and a vague lump in her abdomen?
Are most drug efficacies simply of marginal benefit to patients?
And AI driven decision support for the whole patient:
Dynamic version of the case report here: https://pajrcasereporter.blogspot.com/2024/12/44f-diabetes-nud-ccf-wb-pajr.html?m=1
Explainability, trust and layers of clinical decision making in pre and current AI LLM era:
EBM layer: This layer is the one our clinical decision making lab is largely engaged in although the other two layers are no less important.
We have already shared something around those in our previous demos particularly our two video links shared above.
Human layer: This is the most important layer where clinical decision making actually happens at multiple human stakeholder levels:
Below are recent examples of the limits of scientific explainability and it's effect on human trust.
How much Trust building can one achieve through Human clinical decision making with AI in the loop?
Human mistrust due to persistent uncertainty due to scientifically limited explainability ?
Images of subclinical hypothyroidism patient data:
Human full trust inspite of persistent uncertainty due to scientifically limited explainability
Can AI act as a guard rail for human mistrust due to lack of communication and explainability?
And last but not the least!
Machine layers:
The machine algorithm will see you now?
Amazon "Help me Decide"!
👆 Quantitative AI driven clinical decision making is currently here?
Is this analogous to clinical decision making:
Key takeaways:
Help Me Decide uses AI to analyze your browsing history (patient's clinical history) and preferences (check out the word preferences in Sackett's classic definition of EBM) to recommend the right product (diagnostic and therapeutic, lab or imaging as well as pharmacological or non pharmacological therapy) for you with just one tap.
The tool helps customers pick the right product, quickly.
(System 2 decision making fast tracked to system 1 and closer to tech singularity)?
Personalized recommendations include clear explanations of why a product is right for you based on your specific needs and preferences.
Personalized precision medicine with explainability to gain trust!
Who owns the data that trains these algorithms? Did patients consent to its use? Can we trace how a prediction was made, or who’s responsible when it’s wrong?
DPDP Act is — a national trust charter?
The Act’s intent isn’t to burden innovation; it’s to humanize it,?
It recognizes that in a connected nation, trust is infrastructure.
