Gustavo Lacerda

Interacting with the real world (especially doctors) often makes me want to create expert systems.

Here's an idea for diagnosing allergy/cold/flu complaints. It should be fairly easy to set up a booth on campus, and collect data from volunteers (using Excel and a digital camera); call up 10 doctors, and have them diagnose the profiles given to them. Trying to get the ground truth would be more expensive, since that might involve blood tests (if that works!).


INPUTS (roughly ordered by presumed importance)

photograph of:
* face
* throat
* nose, ears, eyes

* complaints (possibly null)

* answer to "how long have you felt this way?", "do you have seasonal allergies?", and other relevant questions

* time of year, time of day when the data was collected

* biographical info: age, sex, height/weight, race




OUTPUT:

* probability distribution over {nothing, allergy, virus, post-nasal drip, sleep apnea, other} (optionally, allow multiple conditions)


We can control which inputs are given to doctors. My goal is to do machine learning, to automate the diagnostic process, by learning a function from the inputs (images and text) to the diagnosis.

I'm 99.9% sure that studies like this have been done before. How well did the system work?

Other possible applications of the statistics computed from this:
* help individual doctors correct their biases
* help individual doctors correct their incoherences
* help doctors make quicker decisions
* help patients select doctors who are good at diagnosing people with their type of profile
* for patients who want second opinions, help find an optimal pair of doctors (e.g. pairs whose biases would cancel out)

In an act of desperation / curiosity, I just pushed a Q-tip inside the depths of my right nostril, compressing my very swollen turbinate mucosa, to see if this would free up my airway. It works! Not perfectly, but it does make my passage freer than without the cotton swab. Am I the first person to find the mechanical solution chronic turbinate hypertrophy?

Now I just need someone in a machine shop to make me insertable plastic tubes. Can you refer anyone?

Lots of people have problems breathing for the same reason (my guess is that at least 10% of people have it occasionally). Please go ahead and make your millions! The idea is for free.

And no, I am not a doctor.

See http://www.optimizelife.com/wiki/index.php/My_Breathing#Causal_Processes

All the pieces finally fall into place:

Causal diagram of Chronic Rhinitis

Solid lines mean positive influence (+), i.e. more of the source tends to cause more of the target.
Dashed lines mean negative influence (-), i.e. more of the source tends to cause less of the target.


N.B.: I don't suffer from all causes or all symptoms above.

I could add a node for "vasoconstrictor" (e.g. Afrin) right next to "fluticasone", having a negative (e.g. health-positive) effect on "amount of blood in mucosa", but the problem is that vasoconstrictors have a short-term effect that rebound, becoming a positive (e.g. health-negative) effect.

Thanks WikiTex/Wikisophia, for providing me with a sandbox! Wiki code is behind the cut.

Fluticasone appears to be effective in the long run. But if I end up needing to use it for the rest of my life, then I'll go for a ~50% partial turbinectomy (under the knife, since laser seems to damage mucociliary function).

I am interested in the semantics of these diagrams, and how they relate to argument maps and formal proofs.

semantics of diagrams

* Say we want to instantiate a particular allergen and a particular individual: what kind of graph rewriting will we need to do?

* What about expressing the distinction between independent and dependent influences (e.g. conjunction, synergy)?

* What about tagging nodes with information about which leaves are controllable?

* Some effects have preconditions: snoring requires sleeping. Sleeping requires lying down. So we have an implicit relationship in the graph: the consequence is that turbinate enlargement will be worse during sleep. Could conclusions of the kind be drawn automatically, by simply adding to the implicit information to the current representation?


( Read more... )

I just received a photocopy of the results of that blood allergy test (immunological) that I did in February.

It says:

                     63.8951 1     EENHEID  REF.W.
----------------------------------------------Immunologie----------------------------
IgE totaal   (BL)           36     kIU/l    0-100
Phadiatop.   (BL)          NEG(*)


Opmerkingen:

"eenheid" = "unit" (the unit seems to be kiloUI / liter)
"totaal" = "total" (the IgE total seems to be 30 kiloUI / liter, whatever that means)
"opmerkingen" = "remarks" (it's blank)

Can anyone tell me what this means, what it has to do with my being allergic to stuff?

Xylometazoline works wonderfully to unblock my nose. Turns out there was a little bit of mucus stuck in my system, but probably mostly swollen tissues in the nose.

I've been using it every night for almost a week, and now I started getting symptoms during the day too. I remembered reading about people who become dependent on nose drops. So I read up and decided that I can't continue using it:

Rhinitis medicamentosa is an iatrogenic condition where rhinitis has developed as a result of inappropriate use of vasconstrictor nasal drops to relieve nasal congestion.

Sympathomimetic decongestants cause vasoconstriction of the nasal mucosal blood vessels providing relief from the symptom of nasal congestion. However, as their effects wear off, secondary vasodilatation occurs causing the sense of congestion to return. This prompts further application of the decongestant and a vicious circle of use develops.

In this condition, rhinitis is thought to be a consequence of tissue hypoxaemia from reduced mucosal blood flow.

Of the sympathomimetrics, ephedrine is the safest to use topically. Agents with more potent vasoconstrictor activity such as oxymetazoline and xylometazoline are more likely to cause a rebound effect. All should be avoided in patients receiving monoamine oxidase inhibitors because of the risk of provoking a hypertensive crisis.

(Afrin falls in the same category, being based on oxymetazoline HCl)

Thanks Google. No thanks to Dr. Quack, who gave me this medication without any warnings. I could have become an addict. (see here for a nicotine-patch approach to quitting)

This vasoconstrictor effect seems to be exactly what I need. But how can I achieve it without causing this rebound effect? ice?


Other Things I Could Try:

* daily steroid sprays (e.g. Fluticasone), which I thought didn't work, but maybe I didn't keep it up long enough. It's doubtful it could be helpful, since I apparently don't have allergic rhinitis, but either vasomotor 1 2 or irritative rhinities + maybe deviated septum. (note to self: ask the hospital for copies of my exam results)


* daily saline wash (which I've already begun)

* laser resection surgery of the nasal turbinates to make more room in there 1 2

I was just sleeping with my left side down, and I woke up with my right nostril totally blocked. It was somewhat alarming.
I just spent 10 minutes trying to clean it, and there weren't significant amounts of mucus (unless it's *really hard* mucus).
It's still about 70% blocked. I think that sleep makes everything more swollen.

I'm thinking of getting an emergency consultation (it's Sunday, I'm tired, and I'm afraid that when I go back to sleep, both passages may get blocked).

Yesterday I went through a lot of pollution, as was apparent from my clearasil pad (skin cleansing).