How We Achieved ~100% Accuracy in Medical Diagnosis, Election/Marketing Campaigns, Customer Analytics, …?
The Thing About Medical Diagnostics
Medical diagnosis (abbreviated Dx or Ds) is the process of determining which disease or condition explains a person’s symptoms and signs. It is most often referred to as diagnosis with the medical context being implicit. The information required for diagnosis is typically collected from a history and physical examination of the person seeking medical care. Often, one or more diagnostic procedures, such as medical tests, are also done during the process. Sometimes posthumous diagnosis is considered a kind of medical diagnosis.
Diagnosis is often challenging, because many signs and symptoms are nonspecific. For example, redness of the skin (erythema), by itself, is a sign of many disorders and thus does not tell the healthcare professional what is wrong. Thus differential diagnosis, in which several possible explanations are compared and contrasted, must be performed. This involves the correlation of various pieces of information followed by the recognition and differentiation of patterns. Occasionally the process is made easy by a sign or symptom (or a group of several) that is pathognomonic.
Diagnosis is a major component of the procedure of a doctor’s visit.
The Most Important Point To Note — It Boils Down To One Simple Thing ‘Classification’
All of the theory and practice of Medical Diagnosis boils down to one thing and just one thing ‘Classification’
Lets See The History of Claims Being Made About A.I. (???) or basically Deep Learning
Writing in the Lancet Digital Health, Denniston, Liu and colleagues reported how they focused on research papers published since 2012 — a pivotal year for deep learning.
An initial search turned up more than 20,000 relevant studies. However, only 14 studies — all based on human disease — reported good quality data, tested the deep learning system with images from a separate dataset to the one used to train it, and showed the same images to human experts.
Dubious Claims: While all Deep Learning Announcements Claim 90% or even 99% Accuracy. How come only 14 of 20000 studies used a separate test dataset than the one on which the Deep Learning Network was trained on?
The team pooled the most promising results from within each of the 14 studies to reveal that deep learning systems correctly detected a disease state 87% of the time — compared with 86% for healthcare professionals — and correctly gave the all-clear 93% of the time, compared with 91% for human experts.
However, the healthcare professionals in these scenarios were not given additional patient information they would have in the real world which could steer their diagnosis.
Healthcare Professionals use a whole lot of information from patient history, medication, anatomy, physiology, epidemics, food and diet, habits, family history etc. to reach a ~100% diagnosis in most cases, eventually after a few consultations and/or tests, or observations.
Prof David Spiegelhalter, the chair of the Winton centre for risk and evidence communication at the University of Cambridge, said the field was awash with poor research.
“This excellent review demonstrates that the massive hype over AI in medicine obscures the lamentable quality of almost all evaluation studies,” he said. “Deep learning can be a powerful and impressive technique, but clinicians and commissioners should be asking the crucial question: what does it actually add to clinical practice?”
Dr Raj Jena, an oncologist at Addenbrooke’s hospital in Cambridge said “If you are a deep learning algorithm, when you fail you can often fail in a very unpredictable and spectacular way”.
AI equal with human experts in medical diagnosis, study finds
Artificial intelligence is on a par with human experts when it comes to making medical diagnoses based on images, a…
The Best Efforts By Top Companies So Far
Efforts by IBM
Doctors are losing faith in IBM Watson’s AI doctor
After utterly crushing it on “Jeopardy!” IBM wanted to shift focus with its artificial intelligence division, Watson…
Did IBM overhype Watson Health’s AI promise?
In recent weeks, IBM has changed leadership at its Watson Health division and announced a new business strategy for…
Efforts By DeepMind
The algorithm was fairly accurate at predicting the most severe forms of AKI. It correctly predicted 90 per cent of the cases in which the patient’s kidney function deteriorated so severely that they eventually required long-term dialysis.
However, the algorithm was far less accurate for all forms of AKI, correctly predicting only 55.8 of all episodes, with a ratio of two false alerts for one correct prediction.
The difficulty of testing the effectiveness of AIs in medicine is that there could be serious consequences if they get things wrong — a false negative could mean a missed cancer diagnosis, while a false positive may lead to unnecessary treatment.
Clinicians might be hesitant to take the advice of such an algorithm if it doesn’t provide clinical reasons for a prediction, says John Prowle at the Queen Mary University of London
It’s too soon to tell if DeepMind’s medical AI will save any lives
Artificial intelligence trained on health records can now detect kidney injury up to two days before it occurs. The…
So What Is Our Solution And How Does It Work?
- Our Solution can be used to Create ~100% Accurate Digital Models/Clones of Systems/Machines.
- It has been tested for performance with ~1000 variables.
- The Algorithm is of O (N³)
- The Implementation is Distributed and can be Scaled Linearly
- It utilizes Categorical & Numerical Data
- Currently it only uses Structured Data and NOT Unstructured Data
- It is a Deterministic Algorithm and NOT a Heuristic or an Approximation. This is by far The Best we can get Theoretically.
Medical Diagnosis requires evaluating 1000’s of variables if not more. We hope to support the capability of ~1m variables in generated universal models by our solution.
Our solution has comprehensively delivered The Holy Grail of Medical Diagnosis and can implicitly accommodate a comprehensive suite of variables and models of arbitrary complexity.
If we see clearly then Customer Analytics and Marketing Campaigns especially Election Campaigns also utilize 1000’s to ~1m variables. And require the same kind of inferencing and causality reasoning. Our solution has been tested on limited scale Customer Analytics and Marketing/Election Campaigns till now, purely due to unavailability of resources. And not because of any inherent limitations in our solution. A Situation we hope to remedy very soon.
You can read more about the Millennium Breakthroughs here…
This is our Website http://automatski.com