- This topic has 14 replies, 6 voices, and was last updated 7 years, 9 months ago by
.
-
Posts
-
I’m pretty surprised this hasn’t already been posted yet.
I’d love to hear other people’s thoughts on the possibility of developing a model which would give people the ability to test MDMA existence and concentration in any given sample (powder, capsule, pill, etc). According to this DEA approved laboratory that assists people in testing their drugs (http://www.ecstasydata.org/stats.php), a large percentage of the samples provided to them have contaminates in them. Furthermore, they are prohibited from publishing the exact concentrations and can only present them as a ratio due to regulations. Ideally we would want models for the commonly found substances in material they have tested (http://www.ecstasydata.org/stats_substance_by_year.php) so that when a sample is scanned it can return what exactly is in it. But to start, surely there is a use case for estimating how much MDMA is in a given sample.
What do you think SCIO, is this something you all have explored?
Hi John,
Generally speaking, illicit drugs can be identified using SCiO. However, an important factor to be taken into consideration are the concentration levels of the components within the drugs, as SCiO’s detection threshold varies by material, and is typically 0.1%-1%, and thefore unable to detect any components which are below its 0.1% detection threshold.
Please also note that SCiO is NOT a medical device and should not be used as such.
We have proven feasibility for pill differentiation with our pharmaceuticals application. However, we have not developed an illicit drug database and do not plan to do so in the foreseeable future. There is a vast combination of substances that can be present in various drugs and in order to build a working model an almost endless database of illicit drug combinations would need to be built. Moreover, if the substance were in a compressed powder form, it is quite possible that SCiO may miss the active ingredient if that part of the sample wasn’t scanned.
As with all potential applications, feasibility testing would need to be completed along with development of the corresponding molecular sensing models and a corresponding app.
To develop such an application will require a complete sample collection – which we will not be able to supply. Such an application may be developed by you, the developers community, using our SCiO Development ToolKit (DevKit).
Ayelet
The Consumer Physics Team
Thanks for the quick response. I’ve been testing a classification model with some over the counter medication as a test and I’m optimistic with the results given a very poor model.
A detection threshold of even 1% would definitely prove to be useful for this use case. The multitude of combinations that exist out there will definitely be problematic (but hey, that’s why we have a community to help!), but a more immediate and feasible use case would be to test if given sample is pure. Any deviation from the well-tested model would throw an alert.
Have you guys made any more progress with returning a confidence threshold from a scan so a yes/no decisions can be made? In the meantime, this application could have an “advanced view” that could show the user what the “ideal” spectra for pure MDMA powder is (we could ignore capsules and pills for now) and let the them decide if they want to further test the sample (with a chemical test, for example).
1) Is a confidence % against a model from a scan even feasible?
2) Also, will there come a point where we can share our models with each other in the community? I’d imagine any such repositories would have rules in place needed to adhere to a strict standardized method of collecting data.
Thanks!
Hi John,
1. Confidence level value will be available in future versions.
2. Currently the samples and scans you collect for application development are your proprietary data.
The data collection is located in cloud based environment and you cannot access other developers collections.
However, once an application is developed, it can be published by SCiO developers and purchased via the app store.
Ayelet
Hey John,
I was curious about this idea too, but was also skeptical about the multitude of combinations. Have you purchased a developer kit? I could help you collect data 🙂 and mayyyyybe use my web developer skills to crank out an app with ya. Hit me up @NerdVolpe if you are feeling adventurous.
Hey team,
I have access to a lab who can confirm the control groups when collecting these samples. They can provide results from their gas spectrometer of any sample provided. I have tested my application on over the counter Aspirin with some success.
However, all efforts surrounding harm reduction MUST NOT CONTINUE until Consumer Physics is capable of providing a confidence interval. Trying to develop an application like this without such a metric available is reckless and nobody should attempt it until this is in place.
Consumer Physics: how long until such a feature is ready? What are some of the challenges you are encountering trying to develop this? Unless I’m missing something here, I’d imagine pretty much most other applications cannot continue until the SDK is capable of returning a “no such sample found” response.
Hey Nick,
Yes, I have multiple developer kits to ensure that there does not exist any wild discrepancies between SCIO devices.
I am also disappointed there is no collaborative features to share scans with others in the community. This endeavor will require participation in different locations around the country and world to be effective. I’m not sure how we could collaborate on sample processing if consumer physics is hoarding all the scans and preventing collectors from sharing with one another.
Finally, I wanted to a build a global submission program that worked like this:
1) Aquire a sample (we’d start with powder only – no capsules or tablets).
2) Scan it with the SCIO given a well defined and reproducible set of instructions of how to do it.
3) Anonymously mail the sample to the laboratory with an ID and publish the ID to a collaborative website. Labrotory will publish the results with the ID from its gas chromatograph along with it’s opinion of what it is.
4) After discussion on the sample, if it’s pure, the sample is included in the training model.
Consumer physics: is there a way step 4 works with your platform? We could solicit a massive amount of help from the community, both in terms of samples and donations to perform the laboratory scans. My understanding is this would not work because there is no way to gain access to the raw scan data and share it with others. Is this accurate?
Hi John,
The confidence level value calculation is high prioritized task for our software team.
As for sharing the database: before the application development, scans may be shared with others by asking us to copy the data from your account to other accounts. In addition, access to the raw spectrum is possible using the Researcher kit.
I hope that answered your question.
Ayelet
I would like to add my support to John’s request for a method of sharing the collections, where co-workers can add their scans, but not be able to change the attribute set. It would need an additional Attribute of “Contributor” so that the extra scans can be easily QC’ed.
Only the Collection owner and Support should be able to add Contributors.Thanks for the quick response!
Question:
– Is there a timeline when this feature might be available? This thread is nearly 3 months old now with the same response. 🙁
– Will scans/models created today be compatible with future versions of the SDK when this feature is rolled out?
Definitely am glad to hear there is a way to share scans.
Thanks!
Hi John,
Thank you for you ideas and feedback.
Confidence level is now available is SCiO Lab Mobile when you test your model, you will see the model’s response and a number in brackets. That number is the confidence level of the answer – 0 means no confidence (theoretically should never happen), and 100 means full confidence.
In addition to the confidence level, you can train the model to disregard scans that look significantly different than the scans used to train the model (the response will be “null” in that case).
To activate the “outlier detection” feature, use the expert mode, click on the settings button (cog wheel on the right), and check the “outlier detection” option.
About sharing and collaboration – we are very much in favor of creating it in the future, at this point we can help by copying and merging collections from different users. Please contact us at dev@consumerphysics.com if you have a specific request in mind (some developers already have shared the collections with each other).
Hello Everybody!
I just purchased the SCiO primarily with this exact purpose in mind. Not sure what all will be required, but I am intending to develop something to identify street samples of Methamphetamine, black tar Heroin, and Crack/Powdered Cocaine for purity, as well as adulterants. I understand someone will need to provide pure reference samples, and if that person happens to see this message, PLEASE contact me at somnitek@gmail.com! I really, really would like to talk to or work with you! I do have some background as an amateur chemist, and let’s just say that a murky associate, we’ll call him Mr. S, is more than able to provide a plethora of varying street samples over time.
Let me be the first to admit I really have a limited idea of what I’m getting into here, but I am motivated. I have had a number of friends die from heroin overdoses (partly due to varying purity levels), and my own brother who has a horrendous Meth problem recently went into acute liver failure after he relapsed, due in large part to the adulterants in a recent batch going around my area. He’s recovering alright now, and hopefully he’ll get another big chunk of clean time at least out of this. The need for this feature is definitely there. I very much want to see this function fully developed and fleshed out, so please, if this is your interest too, let’s talk!
I’m not a programmer, although I am very willing to learn if necessary, along with any other necessary skills. I’m currently studying Information Technology right now, so I do have a decently strong tech background, and like I said, I love to study Chemistry in my free time, so if there’s any way to contribute, even if it’s just adding scan profiles to a database, I’m all in!
I posted this in the other hard reduction thread as well. Let’s do this!
- You must be logged in to reply to this topic.