[HN Gopher] AI can diagnose childhood autism from retinal photos
       ___________________________________________________________________
        
       AI can diagnose childhood autism from retinal photos
        
       Author : bookofjoe
       Score  : 56 points
       Date   : 2023-12-22 20:13 UTC (2 hours ago)
        
 (HTM) web link (petapixel.com)
 (TXT) w3m dump (petapixel.com)
        
       | FirmwareBurner wrote:
       | What's the difference between AI and just pattern matching here?
       | 
       | I mean, you take a data set of how people with X health condition
       | look like, train your model on that set, then the model can, with
       | a certain probability threshold, tell you if other people have X
       | condition as well. But to me, a non-AI average joe programmer,
       | that's more pattern matching, and less AI.
       | 
       | That kind of application was something I remember some colleagues
       | in university were working on over 10 years ago in OpenCV and
       | Tensorflow, using labeled sets of X-rays and CT scans to pattern
       | match conditions for aiding in diagnostics for radiology lab
       | techs, well before the AI explosion.
       | 
       | What am I missing here?
        
         | Racing0461 wrote:
         | AI (LLMs etc) exhibits "emergent behavior" properties. things
         | like reasoning and other higher order effects. It could be
         | mimicry (parrotting or cargo culting) but it seems like there
         | is something that that isn't in a bunch of if/else statements
         | or pattern matching.
        
           | FirmwareBurner wrote:
           | If this is remotely like my experience with ChatGPT, doesn't
           | that run the risk of hallucinating? Versus pattern matching
           | just telling you "This X-ray shows a 75% chance this person
           | has condition X".
           | 
           | Can you at least interact with it and have it explain to you
           | its reasoning like "so my diagnostic is based on seeing a
           | lump in the lower right hand corner"? That would be an
           | innovation indeed.
        
           | therobot24 wrote:
           | > AI (LLMs etc) exhibits "emergent behavior" properties.
           | things like reasoning and other higher order effects.
           | 
           | I would disagree with this statement. The model is
           | _reasoning_ via the method of processing the data since the
           | weights are informed from the relationships of prior similar
           | information, but at its heart the model is still just doing
           | pattern matching. The primary distinction and what I disagree
           | with in your statement is that these AI models are closer to
           | AGI because there aren't a bunch of if/else statements or
           | basic pattern matching.
        
         | lokar wrote:
         | What is AI, or what counts as AI, has always had a large
         | element of "things seem hard must be AI"
         | 
         | For years most people agreed that a computer beating the best
         | human at chess would be "real" AI. Then they managed it, but
         | people said "not that does not count, you just brute forced
         | it".
         | 
         | What you describe, the automatic construction of classification
         | models was textbook AI for over 20 years (using a whole range
         | of methods), now it's often just seen as "data science".
        
         | itsoktocry wrote:
         | > _What am I missing here?_
         | 
         | Perhaps _how_ the pattern matching is performed?
         | 
         | Whether this is "AI" or not, I don't know. But dismissing it as
         | mere "pattern-matching" grossly simplifies the technology and
         | it's potential usefulness.
         | 
         | > _I remember colleagues in university were working on over 10
         | years ago_
         | 
         | Yes, this is how we get better technology, by continuing to
         | work on problems.
        
         | delecti wrote:
         | The history of AI research has been one of moving goalposts.
         | Technologies only stay "AI" until they're shown to be useful.
         | At various points in the past, computing in general, self-
         | modifying code, search algorithms, computer vision, chat bots,
         | neural networks, stable diffusion, large language models, and
         | more, have all been considered "AI" at various points in their
         | development. Occasionally, people will demonstrate that a topic
         | in "AI" has a broader usefulness, and the specific name will be
         | used, and people will argue online whether it's " _really_ AI
         | ".
         | 
         | About 15 years ago I learned about several of those topics in
         | an AI course in college, and now they're all frequent
         | occurrences in debates about whether they're _really_ AI.
        
       | alach11 wrote:
       | While there's prior associations between retinal photos and
       | autism, I'm by default very skeptical of any AI algorithm
       | purporting "100% accuracy". It smells like data leakage.
       | 
       | I would bet that even physicians aren't 100% consistent in their
       | diagnosis of autism. If that's the case, then it should be more
       | or less impossible for any other diagnostic approach to be 100%
       | consistent with the physician diagnoses.
       | 
       | Edit: After reading the study closer, this criticism might be a
       | bit harsh. In their autism subjects, they excluded those with
       | mild/moderate autism. Limiting to severe cases should mean
       | there's a higher degree of confidence/consistency in the
       | diagnoses.
        
         | karaterobot wrote:
         | I'm not actually sure where the Petapixel article authors are
         | getting the phrase "100% accuracy", as it does not show up in
         | the article they are writing about, nor does it appear in the
         | only other article they link to. Putting it in quotes makes it
         | seem like a claim the model creators are making about their
         | model, but I don't see them making that claim in general. They
         | say the model matched all the sample data in this case, not
         | that it's 100% accurate--presumably for the same reasons you
         | are hesitant to do so. Unless I'm missing something, Petapixel
         | should correct their headline.
        
           | reqo wrote:
           | You can see the results if you download the pdf from [0].
           | 
           | [0] https://jamanetwork.com/journals/jamanetworkopen/fullarti
           | cle...
        
         | Eisenstein wrote:
         | > I would bet that even physicians aren't 100% consistent in
         | their diagnosis of autism.
         | 
         | That's because autism is diagnosed by using the DSM. You can
         | take an x-ray of an arm and see the fracture, but in order to
         | diagnose autism you have to determine 'persistent deficits in
         | social communication and social interaction across multiple
         | contexts'.
         | 
         | It is all dependent on how society defines things, and is fluid
         | (and IMO, somewhat dubious).
        
           | tastyfreeze wrote:
           | The whole DSM is dubious. Nothing more than a made up tool to
           | pathologize normality and sell more drugs.
           | 
           | https://youtu.be/6JPgpasgueQ?si=dn3muYeOe-cSSKM2
        
       | bitshiftfaced wrote:
       | I couldn't find any confirmation that they tested on out of
       | sample ASD populations.
        
         | hervature wrote:
         | From TFA:
         | 
         | "" The data sets were randomly divided into training (85%) and
         | test (15%) sets. We used 10-fold cross-validation to obtain
         | generalized results of model performance. Data splitting was
         | performed at the participant level and stratified based on the
         | outcome variables. Because the data classes were imbalanced for
         | symptom severity (ADOS-2 and SRS-2), we performed a random
         | undersampling of the data at the participant level before
         | conducting data splitting. """
         | 
         | 100% indicates a major case of data leakage. Particularly,
         | "When we generated the ASD screening models, we cropped 10% of
         | the image top and bottom before resizing because most images
         | from participants with TD had noninformative artifacts (eg,
         | panels for age, sex, and examination date) in 10% of the top
         | and bottom." tells me that there are known issues with the
         | photos. Quite possible the photos of the groups were taken on
         | distinct days and/or times and the lighting conditions is
         | enough to distinguish the groups. Possibly, the background for
         | the ASD candidates have a different background or a different
         | camera sensor.
        
       | DrStartup wrote:
       | FTP: Findings - In this diagnostic study of 1890 eyes of 958
       | participants, deep learning models had a mean area under the
       | receiver operating characteristic curve of 1.00 for ASD screening
       | and 0.74 for symptom severity. The optic disc area was also
       | important in screening for ASD.
       | 
       | https://jamanetwork.com/journals/jamanetworkopen/fullarticle...
        
       | n-e-w wrote:
       | I try not to immediately call BS on these types of studies...but
       | in this case there are some concerns.
       | 
       | "The data sets were randomly divided into training (85%) and test
       | (15%) sets. We used 10-fold cross-validation to obtain
       | generalized results of model performance. Data splitting was
       | performed at the participant level and stratified based on the
       | outcome variables. Because the data classes were imbalanced for
       | symptom severity (ADOS-2 and SRS-2), we performed a random
       | undersampling of the data at the participant level before
       | conducting data splitting. Moreover, we examined different split
       | ratios (80:20 and 90:10) to assess the robustness and consistency
       | of the predictive performances across diverse splitting
       | proportions."
       | 
       | * undersampling is problematic here and probably introduced some
       | bias. These imbalanced class problems are just plain hard.
       | Claiming one hundred percent on an imbalanced class problem
       | should probably cause some concern. * data split at the
       | participant level has to be done really careful or you'll over
       | fit * multiple comparisons bias by testing multiple split ratios
       | on the same test data. Same with the 10-fold cross Val. * not
       | sure if they validated results on any external test data *
       | outcome variable stratification also has to be done really
       | carefully or it will introduce bias; seems particularly sensitive
       | in this case * using severity of symptoms as class labels is
       | problematic. These have to really have been diagnosed the same
       | way / consistently to be meaningful.
       | 
       | I also note a long time history in collection of these images (15
       | years iirc). Hard to believe such a diverse set of images
       | (collection, equipment etc) led to perfect results.
       | 
       | ML issues aside, super interested in the basic medical concept. I
       | wasn't aware retinal abnormalities could be indicative of issues
       | like ASD.
        
         | Closi wrote:
         | Another potential issue:
         | 
         | > The photography sessions for patients with ASD took place in
         | a space dedicated to their needs, distinct from a general
         | ophthalmology examination room. This space was designed to be
         | warm and welcoming, thus creating a familiar environment for
         | patients. Retinal photographs of typically developing (TD)
         | individuals were obtained in a general ophthalmology
         | examination room. Each eye required an average of 10-30 s for
         | photography, although some cases involved longer periods to
         | help the patient calm down, sometimes exceeding 5-10 min. All
         | images were captured in a dark room to optimize their quality.
         | Retinal photographs of both patients with ASD and TD were
         | obtained using non-mydriatic fundus cameras, including EIDON
         | (iCare), Nonmyd 7 (Kowa), TRC-NW8 (Topcon), and Visucam NM/FA
         | (Carl Zeiss Meditec).
         | 
         | So two questions:
         | 
         | 1. Are we positive that the difference in rooms does not effect
         | these images?
         | 
         | 2. If we are in a dark room, and ASD patients are in it for
         | 5-10 minutes longer, are we sure this doesn't effect the
         | retina?
         | 
         | 3. Were all cameras used for both ASD and TD images?
         | 
         | Want to make sure the AI is being trained to detect autism, and
         | wasn't accidentally trained to identify camera models, length-
         | in-dark-room or room-welcomingness.
         | 
         | Hopefully not, but I assume you have to be _so_ careful with
         | these sort of things when the model is entirely black-box and
         | you can 't actually validate what it's actually doing inside.
        
           | dataangel wrote:
           | Came here to say this. 100% is too good to be true and it's
           | almost certainly the AI has figured out a signal leak from
           | the camera, image format, room, etc.
        
             | Closi wrote:
             | Yes! I would also be surprised if the ground truth didn't
             | have some errors in it.
             | 
             | If a model was 100% accurate, considering the
             | nature/accuracy of manually diagnosing autism you would
             | probably expect the AI to either find new cases or identify
             | a few incorrect diagnosises.
        
           | shubb wrote:
           | It appears they also report good results for predicting
           | symptom severity. It's less obvious how the cameras etc would
           | leak into severity. Unless it actually works (it does seem a
           | bit too good to be true), I'm thinking the test set was in
           | the base model or something
        
             | Closi wrote:
             | Unsure, but there are lots of variables there and there
             | could be even more we don't know about not mentioned in the
             | paragraph! Maybe more severe cases involved longer periods
             | to help the patient calm down in the dark environment? I
             | dunno! Just something smells fishy. You are right, could
             | have also been training data leaking, just looks like there
             | are multiple leaky elements here potentially!
             | 
             | Also, the study checked ASD participants were autistic by
             | using structured interviews with psychologists against the
             | DSM-5, but the TD participants were never assessed by
             | psychologists, so if autism under-diagnosis is a thing,
             | there could theoretically be false-negatives.
        
           | jiggawatts wrote:
           | If they consistently captured the images in different
           | settings, then I guarantee you that that's what the AI
           | learned.
           | 
           | Just being in a dark room longer is sufficient to make
           | changes that an AI could pick up on.
        
           | ajb wrote:
           | Darn, was excited for a minute. This sort of experiment needs
           | double blinding.
           | 
           | Ideally, they should capture the images from children before
           | diagnosis, then see if they can predict the diagnosis.
        
         | bookofjoe wrote:
         | Also concussions according to the article, which is news to
         | this retired former neurosurgical anesthesiologist.(38 years in
         | practice; stopped 2015 at age 67 because I believed [still do])
         | it's better to retire [from my profession, at least] too early
         | than too late.
        
       | ortusdux wrote:
       | Similarly - https://ascopost.com/news/october-2023/ai-software-
       | demonstra...
       | 
       | In addition to demonstrating 100% (n = 59/59) sensitivity for
       | detecting melanoma, the AI software had a detection rate of 99.5%
       | (n = 189/190) for all skin cancers and 92.5% (n = 541/585) for
       | precancerous lesions.
        
         | eddiewithzato wrote:
         | Next we need to train them for the pregnancy stage. We already
         | screen for autism and Down syndrome, with AI it will be even
         | more accurate.
        
           | syspec wrote:
           | There's a screening for autism during pregnancy?
        
       | therobot24 wrote:
       | Anything with 100% accuracy is suspect, either via the model, the
       | dataset, or the means of measuring
        
       | etothepii wrote:
       | There's a famous story (probably apocryphal) about the military
       | of a powerful nation training an early AI to find pictures of
       | submarines beneath the sea.
       | 
       | There was great excitement as it was near 100%.
       | 
       | It later transpired the pictures with submarines in had a white
       | border.
        
         | morkalork wrote:
         | I've heard this one before but with soviet tanks back in the
         | 2000s!
        
           | erehweb wrote:
           | May be an urban legend, according to this site:
           | https://gwern.net/tank
        
           | sva_ wrote:
           | I think there was something about an ANN detecting skin
           | melanoma, assigning a high likelihood if there is a
           | clinic/doctors office in the background.
        
         | sterlind wrote:
         | haven't modern model architectures gotten better at avoiding
         | this kind of overfitting? like obviously data quality is still
         | very important, but my understanding is that dropout mitigates
         | this by randomly cutting out these unwanted feature channels.
         | the models learn to distinguish all differences, rather than
         | just one, or fixed combinations of several.
        
           | dragonwriter wrote:
           | > haven't modern model architectures gotten better at
           | avoiding this kind of overfitting?
           | 
           | Overfitting is, AIUI, a training method and data issue, not a
           | model issue alone. I doubt any model is resistant to
           | overfitting if you give it data where the answer is reliably
           | encoded some aspect it can use but outside of what you want
           | it to look at.
           | 
           | Now, you can notice suspicious results and investigate (or
           | you can just publish a 100% success rate and call it a day.)
        
           | daveguy wrote:
           | It really doesn't have to do with most ML architectures. It
           | has to do with experiment design. If some data used in
           | testing is part of the training process there will be over
           | fitting. That's why a final test set is required for unbiased
           | evaluation.
        
       | RecycledEle wrote:
       | I do not believe they achieved 100% accuracy because the original
       | diagnoses could not have been 100% accurate.
        
         | hereme888 wrote:
         | Good point. I wonder how severe the autism was to make sure the
         | reference subjects were 'certainly' within the ASD.
        
       | wrsh07 wrote:
       | This reminds me of the ml model that realized if an x-ray was
       | taken at the center for cancer research it was likely to be an
       | image of a cancer patient
        
       | bikerideronmoon wrote:
       | 100% accuracy? I strongly doubt it. I would bet anything over 10%
       | and they have got a billion dollar corporation.
        
       | kossTKR wrote:
       | I wonder if physiognomy will come back as a field, if AI scans
       | like these have any validity.
       | 
       | I remember stumbling upon multiple esoteric accounts on both
       | Twitter and Tiktok with communities seemingly obsessed with
       | characterising various psychological traits from purely looking
       | at facial features, importantly without racial undertones.
       | 
       | While this on the surface sounds ridiculous and has various
       | horrible historical echoes, i've always had a hunch there was
       | actually something to this science from a purely intuitive
       | perspective and knowing lots of people - again very importantly
       | disregarding anything about race - instead focusing on the myriad
       | of hormone linked features, neurotypicalism, alcohol,
       | environmental factors, whatever traits that seemingly somehow go
       | "across races".
       | 
       | Or maybe there's nothing there.
        
       | hereme888 wrote:
       | Does anyone know if the code can be found anywhere? I'd like to
       | check it out.
        
       | theferalrobot wrote:
       | Am I reading this wrong? They only had validation sets with no
       | final test set which makes the results kinda worthless because we
       | don't know how overfit they were to these validation sets (which
       | can easily happen with any sort of parameter tuning). There is a
       | reason why a proper study needs three splits train/validation
       | (and possible multiple of these if you use k-fold) and a final to
       | be used as sparingly as possible 'test' set.
       | 
       | See the paper, "On estimating model accuracy with repeated cross-
       | validation"
       | 
       | Even the sklearn docs for cross validation show this split:
       | https://scikit-learn.org/stable/_images/grid_search_cross_va...
        
       | robocat wrote:
       | I wonder if autism is a 100% binary diagnosis, versus a partial
       | measurement. It will be interesting to see how many adults might
       | get diagnosed - especially women since they have a lower rate of
       | autism.                 Autism is 4 times more common in boys
       | than girls, and women are diagnosed with autism later in life and
       | less frequently than men
        
       | samstave wrote:
       | So I had seen this study that showed that autistic kids really
       | like to spin objects... I didn't think anything of it aside from
       | storing it.
       | 
       | A few years later I met my wife's nephew, who was about 5 or so -
       | and he was constantly spinning things... and I asked if he was
       | autistic, and they said no.
       | 
       | A few month passed by, and he was officially diagnosed as
       | autistic.
       | 
       | I wonder if something in the retina, and the way that it signals
       | to the brain is soothing if there is a spinning image signal
       | coming through.
       | 
       | I wonder if one were able to apply a HUD either in a contact or
       | such, where there might be a slightly spinning halo/ring that one
       | might look through, if it is that spinning things sooth an
       | autistic signal processor. There are two different spin stimuli
       | it appears that autistic people find soothing, visual or physical
       | (spinning of themselves).
        
         | javajosh wrote:
         | An interesting application for a virtual reality headset. You
         | could at least do anecdotal testing with your friends who have
         | autistic children.
        
       ___________________________________________________________________
       (page generated 2023-12-22 23:02 UTC)