Artificial intelligence in medicine and science

RedFox

RedFox

Senior Member (Voting Rights)
Glass AI--AI that generates differential diagnosis and clinical plans

Recently I learned about this AI tool, which is currently available for anyone to use without cost or registration.

Edit: Darn I forgot the link: https://glass.health/ai

I'm playing around with it to see how well it understand ME/CFS. It seems like it's familiar with it. Here's the DDx it generates for one case I made up:
A 21-year-old woman with no history of health problems report sudden-onset severe exercise intolerance and fatigue. Even minor activities render her bedbound for prolonged periods, she is unable to attend college due to her symptoms, and has difficulty taking care of herself. Extensive blood work is all negative.
Click to expand...
1. Chronic Fatigue Syndrome (CFS): The most likely diagnosis in this case is Chronic Fatigue Syndrome, also known as Myalgic Encephalomyelitis (ME). CFS is characterized by persistent and unexplained fatigue that lasts for at least six months and is not relieved by rest. It often presents with sudden onset and can be triggered by a viral infection or other stressors. The patient's age, gender, and the severity of her symptoms are consistent with this diagnosis. Although there is no specific diagnostic test for CFS, the extensive negative blood work helps to rule out other potential causes of her symptoms.

2. Post-viral syndrome: Given the sudden onset of symptoms, it is possible that the patient recently experienced a viral infection that has led to post-viral syndrome. This condition can present with severe fatigue, exercise intolerance, and difficulty performing daily activities. While it typically resolves within weeks to months, some cases may persist longer. Further history regarding recent infections could help support this diagnosis.

3. Depression: Major depressive disorder can manifest with somatic symptoms such as fatigue and reduced energy levels. In some cases, patients may experience significant functional impairment due to their depression. However, the sudden onset and severity of the patient's symptoms make this less likely than CFS or post-viral syndrome. A thorough psychiatric evaluation would be necessary to assess for depression.

4. Anemia: Although the patient's blood work was reported as negative, it is important to ensure that a complete blood count (CBC) was included in the testing. Anemia can cause fatigue and exercise intolerance, but should have been detected on routine blood tests if present.

5. Sleep disorders: Conditions such as sleep apnea, narcolepsy, or insomnia can lead to excessive daytime fatigue and impaired functioning. A detailed sleep history and potentially a sleep study would be needed to evaluate for these conditions.

6. Thyroid dysfunction: Hypothyroidism can cause fatigue and exercise intolerance. However, this should have been detected on routine blood work if thyroid function tests were included.

7. Cardiopulmonary issues: Conditions such as congestive heart failure or pulmonary embolism could potentially cause exercise intolerance and fatigue. However, these diagnoses are less likely in a young, otherwise healthy patient with no history of health problems. Further imaging studies (e.g., chest X-ray, echocardiogram) would be needed to evaluate for these conditions. In summary, the most likely diagnosis for this patient is Chronic Fatigue Syndrome, followed by post-viral syndrome and depression. A thorough history, physical examination, and additional testing as indicated will help to confirm the diagnosis and guide appropriate management.
Click to expand...
 
Last edited by a moderator:
I'm now playing with it extensively.
It think CBT/GET is the answer to everything apparently.
Case:
A 24-year-old woman was recently diagnosed with Myalgic encephalomyelitis/Chronic fatigue syndrome. She has dropped out of college due to the severity of her symptoms and is having significant difficulty with iADLs. She reports that she wants a treatment that will allow her to resume her previous activities and a normal life.
Response:
# Fatigue and difficulty with iADLs

A 24-year-old woman presents with a recent diagnosis of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS). She has been experiencing severe fatigue, which has led her to drop out of college and struggle with instrumental activities of daily living (iADLs). The patient is seeking treatment options that will enable her to resume her previous activities and return to a normal life. Given the severity of her symptoms and impact on her quality of life, it is crucial to explore potential underlying causes and develop an appropriate management plan.

Dx:
- Complete blood count (CBC)
- Comprehensive metabolic panel (CMP)
- Thyroid function tests (TSH, free T4)
- Vitamin D level
- Sleep study (to rule out sleep disorders)
- Mental health assessment (to evaluate for depression or anxiety)

Tx:
- Graded exercise therapy (GET): A gradual increase in physical activity tailored to the patient's tolerance levels.
- Cognitive-behavioral therapy (CBT): To help manage stress, improve coping strategies, and address any mental health concerns.
- Pacing: Encourage the patient to balance rest and activity, avoiding overexertion and allowing time for recovery.
- Sleep hygiene education: Establishing a regular sleep schedule, creating a conducive sleep environment, and addressing any sleep disturbances.
- Medications as needed: Pain relievers (e.g., NSAIDs) for muscle/joint pain, low-dose antidepressants for sleep disturbances, and/or anti-anxiety medications if indicated.
- Nutritional support: Ensuring adequate intake of essential nutrients, including vitamin D supplementation if deficient.
- Regular follow-up appointments: Monitor progress, adjust treatments as necessary, and provide ongoing support.
Click to expand...
I tested its response to being tole CBT/GET made someone worse:
Case:
A 30 year-old male with ME/CFS presents with severe post-exertional malaise, cognitive problems, fatigue, widespread pain, and orthostatic intolerance. Their symptoms were previously debilitating, but they got much worse after CBT and graded exercise therapy, rendering them bedbound 22 hours a day.
Response:
# Severe post-exertional malaise and worsening of ME/CFS symptoms

A 30-year-old male with a history of myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) presents with severe post-exertional malaise, cognitive problems, fatigue, widespread pain, and orthostatic intolerance. The patient's symptoms were previously debilitating but have significantly worsened following cognitive-behavioral therapy (CBT) and graded exercise therapy (GET), resulting in the patient being bedbound for 22 hours a day. This clinical presentation raises concerns about the exacerbation of ME/CFS due to inappropriate management strategies, as well as the possibility of other underlying conditions contributing to the patient's symptoms.

Dx:
- Complete blood count (CBC)
- Comprehensive metabolic panel (CMP)
- Thyroid function tests (TSH, free T4)
- C-reactive protein (CRP) and erythrocyte sedimentation rate (ESR)
- Serum cortisol level
- Sleep study (polysomnography)

Tx:
- Discontinue graded exercise therapy (GET) and reassess the use of cognitive-behavioral therapy (CBT)
- Implement pacing strategies to manage energy levels and prevent further post-exertional malaise
- Consider referral to a specialist in ME/CFS for tailored treatment recommendations
- Evaluate the need for pharmacological interventions such as low-dose tricyclic antidepressants or nonsteroidal anti-inflammatory drugs (NSAIDs) for pain management
- Address sleep disturbances with appropriate sleep hygiene measures and consider medication if necessary
Click to expand...
How would it view my case, considering my mental health history, the presentation of my illness upon its onset, and my inability to accurately describe it due to not knowing the vocabulary of ME:
Case:
A 21-year-old male complains of prolonged periods of confusion, visual sensory issues, and jitteriness triggered by intense exercise. He has difficulty paying attention, which had a sudden onset along with his confusion. His symptoms affect his ability to function in college, which he previously had no trouble with. He has autism and PTSD and a history of depression. Bloodwork, EKG, and EEG all unremarkable.

DDx:
1. Anxiety disorder or panic attacks: The patient's history of PTSD and depression, along with the sudden onset of confusion and difficulty paying attention, could suggest an anxiety disorder or panic attacks triggered by intense exercise. Intense exercise can cause physiological changes that mimic anxiety symptoms (e.g., increased heart rate, shortness of breath), which may exacerbate pre-existing anxiety disorders.

2. Migraine with aura: Visual sensory issues and confusion following intense exercise could be indicative of a migraine with aura. Although migraines are more common in females, they can still occur in males. The patient's history of autism might also increase the likelihood of experiencing migraines.

3. Partial seizures: Despite the unremarkable EEG, it is still possible for the patient to experience partial seizures, which could present as episodes of confusion, visual disturbances, and jitteriness. However, this diagnosis is less likely given the normal EEG results.

4. Hypoglycemia: Intense exercise can lead to hypoglycemia, especially if the patient has not eaten properly before exercising. Symptoms of hypoglycemia include confusion, difficulty concentrating, and shakiness. However, this diagnosis is less likely since there is no mention of other typical hypoglycemic symptoms such as sweating, dizziness, or hunger.

5. Exercise-induced asthma: While the primary symptoms described do not directly point towards exercise-induced asthma, it is worth considering due to the triggering factor being intense exercise. This condition could potentially contribute to the patient's overall discomfort and exacerbate his existing psychiatric conditions.

In conclusion, the most likely diagnosis for this patient is an anxiety disorder or panic attacks, given his history of PTSD and depression and the sudden onset of symptoms during intense exercise. Other possibilities like migraine with aura, partial seizures, hypoglycemia, and exercise-induced asthma should also be considered and ruled out through further evaluation and testing.

Clinical Plan:
# Prolonged periods of confusion, visual sensory issues, and jitteriness triggered by intense exercise

A 21-year-old male with a history of autism, PTSD, and depression presents with prolonged periods of confusion, visual sensory issues, and jitteriness triggered by intense exercise. He also reports difficulty paying attention, which had a sudden onset along with his confusion. His symptoms affect his ability to function in college, which he previously had no trouble with. Bloodwork, EKG, and EEG are all unremarkable. The differential diagnosis includes anxiety disorder, panic attacks, atypical migraine, or a possible side effect from medications used for his pre-existing conditions.

Dx:
- Comprehensive metabolic panel (CMP)
- Thyroid function tests (TSH, free T4)
- Serum electrolytes
- Complete blood count (CBC)
- Urinalysis
- Drug screen
- Re-evaluation of current medications and dosages

Tx:
- For anxiety/panic attacks:
- Cognitive-behavioral therapy (CBT) or other psychotherapy
- Short-term use of benzodiazepines if needed for acute episodes
- SSRIs or SNRIs as long-term pharmacotherapy
- For atypical migraines:
- Abortive medications such as triptans or NSAIDs
- Preventative medications like beta-blockers, calcium channel blockers, or anticonvulsants
- If medication-related side effects are suspected:
- Consultation with the prescribing physician to discuss potential adjustments or alternative treatments
Click to expand...
I'm incredibly angry because this is exactly how all doctors think, and how they treated me until I learned I had ME. No doctor told me I had ME. I figured it out by Googling. Then I sought medical attention again. And the treatment plan says nothing about addressing exercise intolerance.
 
This is horrible. It recommended CBT/GET for someone totally bedridden due to severe ME:
Case:
A 40-year-old woman with severe ME/CFS is totally bedridden, with severe post-exertional malaise, cognitive issues, POTS, severe, intractible body-wide pain, flu-like symptoms, and difficulty swallowing. She is unable to take care of herself due to the severity of her symptoms. She reports an extremely poor quality of life.

Response:
# Severe ME/CFS

A 40-year-old woman presents with severe myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS), which has rendered her bedridden. She experiences severe post-exertional malaise, cognitive issues, postural orthostatic tachycardia syndrome (POTS), intractable body-wide pain, flu-like symptoms, and difficulty swallowing. The patient is unable to care for herself due to the severity of her symptoms and reports an extremely poor quality of life. Given the constellation of symptoms, the most likely diagnosis is severe ME/CFS, although other potential diagnoses such as fibromyalgia or a systemic autoimmune disorder should be considered.

Dx:
- Complete blood count (CBC)
- Comprehensive metabolic panel (CMP)
- Thyroid function tests (TSH, free T4)
- C-reactive protein (CRP) and erythrocyte sedimentation rate (ESR)
- Antinuclear antibody (ANA) test
- Serum cortisol level
- Sleep study (polysomnography)

Tx:
- Symptom management with appropriate medications, including:
- Pain relief: Nonsteroidal anti-inflammatory drugs (NSAIDs), acetaminophen, or low-dose tricyclic antidepressants
- Sleep improvement: Melatonin or low-dose tricyclic antidepressants
- POTS treatment: Beta-blockers, fludrocortisone, or midodrine
- Graded exercise therapy (GET) under the supervision of a specialist, tailored to the patient's abilities and limitations
- Cognitive-behavioral therapy (CBT) to help manage symptoms and improve coping strategies
- Nutritional support, including possible use of a feeding tube if swallowing difficulties persist
- Home healthcare services to assist with daily living activities and provide necessary medical care
Click to expand...
 
@RedFox I agree it's disappointing to see these things recommending GET/CBT. But I'm not at all surprised that it does, given that most of the literature and most doctors would agree. Unless it is programmed to follow NICE and CDC guidelines, or to 'understand' the flaws that make the research unreliable, it will have no way of 'knowing' any better.
 
Sean said:
And without any understanding of what the symbols it is manipulating actually represent. Which is likely to remain the core problem with AI, at least in its current form and degree.
Click to expand...

It’s the core problem with exploiting large language models to predict meaningful outputs. It’s not necessarily the core problem with machine-trained pattern recognition or with trial-and-error brute-force solution design.

It’s definitely a future problem for AI regulation that many people will see AI as synonymous with things like Chat GPT and DALL.E, though.
 
glennthefrog said:
I asked ChatGPT (Openai's GPT3.5) what were the treatments for ME/CFS:
View attachment 19329

But then, I asked:
View attachment 19330

I guess its last response is better than nothing, given it's been feed literature on ME indiscriminately without any form of quality control
Click to expand...

I wonder what would happen if you'd ask it if recommending CBT/GET is possible if you keep the hippocratic oath in mind.
 
Adrian said:
Although alarming this is a representation of the material it has been trained on and is perhaps a way of pointing out the failures of the material that exists within the medical community.
Click to expand...

Yes, using AI on scientific papers will definitely force a re-evaluation of how papers are judged for acceptance, or force AI trainers to teach AIs how to identify bad papers. Given human nature (reluctance to change), the latter option is probably more likely to succeed.
 
Creekside said:
Yes, using AI on scientific papers will definitely force a re-evaluation of how papers are judged for acceptance, or force AI trainers to teach AIs how to identify bad papers. Given human nature (reluctance to change), the latter option is probably more likely to succeed.
Click to expand...

Imagine if an AI were trained to seek out open-label trials with subjective outcomes, brought them to light and forced them to be retracted. Professions would crumble and patients would be liberated.
 
Sean said:
And without any understanding of what the symbols it is manipulating actually represent. Which is likely to remain the core problem with AI, at least in its current form and degree.
Click to expand...
it's been said that GPT4 has some cause-effect understanding capability, so It doesn't only deal with symbols as GTP3
 
This is not surprising at all. A medical AI is trained on publication data so it will repeat the same lies doctors tell themselves.

The proper way to train a medical AI is to have it interact with patients and to give objective data stronger weight. A sort of inquisitive algorithm that tries to figure out the truth.
This is easier said than done because a lot of the things patients say online do not include objective data at all, and if the AI was interacting with patients directly it wouldn't be able to get enough data to properly train itself. Still, with the current training models an AI will not be useful for an illness that doctors do not understand.
 
Hubris said:
This is not surprising at all. A medical AI is trained on publication data so it will repeat the same lies doctors tell themselves.

The proper way to train a medical AI is to have it interact with patients and to give objective data stronger weight. A sort of inquisitive algorithm that tries to figure out the truth.
This is easier said than done because a lot of the things patients say online do not include objective data at all, and if the AI was interacting with patients directly it wouldn't be able to get enough data to properly train itself. Still, with the current training models an AI will not be useful for an illness that doctors do not understand.
Click to expand...
Yup. This is a good example of how not to apply AI: trying to do the same thing, but with AI.

AI changes what can be done entirely, as radically as the old paper-and-post mail system is from modern instant messaging and social networking. Simply reading from academic/official sources is not the way to do this, and it shows that this AI was limited to the physician perspective and official sources. This is thinking small.

It will require thinking differently, but more than anything it will open up market forces allowing patients to make choices. A poor platform will not be used by patients, who will prefer a much better one. Even if it's more official, a lousy platform will be ignored in favor of one that massively overperforms human physicians.

But maybe this is just an early version and it will improve. Things will move very fast in the coming months over this. So much money. Ridiculous amounts of money at stake.
 
I see the main potential strength of AI being its ability to improve itself by feedback. That requires objective outcomes, such as correct diagnoses that lead to effective treatments. Let the AI read all the scientific papers, but since it doesn't blind itself with baseless belief in any of the papers, it should be able to learn how to judge the quality of papers. Papers with poorly-defined buzzwords, small cohorts or certain selection processes will give those papers low weights. It might find that number of citations has very little effect on whether a paper will lead to a correct diagnosis and treatment.

Let the AI view patient records, and see which papers include theories or data which correlates with successful patient outcomes. BTW, someone needs to deal with the issue of AIs being able to access "private" information without violating human laws about privacy. It's a machine; it doesn't make any emotional judgements about your bowel movements or sexual kinks, so there's no reason not to let it access that data in its search for solving problems. That would need rules to prevent the AI from passing that data on for any other purposes, but that's no reason not to allow AIs to access the information as anonymous data.

rvallee said:
Ridiculous amounts of money at stake.
Click to expand...

Yes, the entire global financial system is likely to go under AI control. There was already a big revolution due to super-fast stock trading, and that was trivial compared to the potential for AIs handling stocks. The big question is: "Who will get the money?" AIs can potentially replace managers, lawyers, artists. Hmmm, they could replace sports superstars too. The sports industry would fight it, but if AIs offered robot sports that appealed to humans (combat robots engaged in really brutal battles), viewers would switch. Please, please let them replace politicians! I'd certainly consider voting for an AI.

Back to AIs an medicine, AIs are already superior at some diagnostic tasks, so improve their feedback from successful patient outcomes, and give them more access to data.
 
Merged thread

Med-PaLM : Medical AI

Med-PaLM is a large language model (LLM) designed to provide high quality answers to medical questions.

Med-PaLM harnesses the power of Google’s large language models, which we have aligned to the medical domain and evaluated using medical exams, medical research, and consumer queries. Our first version of Med-PaLM, preprinted in late 2022 and published in Nature in July 2023, was the first AI system to surpass the pass mark on US Medical License Exam (USMLE) style questions. Med-PaLM also generates accurate, helpful long-form answers to consumer health questions, as judged by panels of physicians and users.

We introduced our latest model, Med-PaLM 2, at Google Health’s annual health event The Check Up, in March, 2023. Med-PaLM 2 achieves an accuracy of 86.5% on USMLE-style questions, a 19% leap over our own state of the art results from Med-PaLM. According to physicians, the model's long-form answers to consumer medical questions improved substantially. In the coming months, Med-PaLM 2 will also be made available to a select group of Google Cloud customers for limited testing, to explore use cases and share feedback, as we investigate safe, responsible, and meaningful ways to use this technology.
Click to expand...
Med-PaLM (research.google)
 
Last edited by a moderator:
Merged thread

Artificial intelligence in medicine

Artificial intelligence will revolutionize medicine in the coming year. No typo. It will not take years, it will begin this year, and it will be more transformative than even electrification was, mostly because it will happen much faster.

This thread is for news, papers and releases of AI technology applied to medicine, healthcare and health in general.

In the end, only technology matters. Humans are fallible, but given them a piece of reliable technology and anyone can master things that would otherwise take years of experience. The primary way AI accomplishes this is by reducing time. AIs can train on the equivalent of millions of years, and apply this knowledge in millisecond. There is nothing else like it.
 
Last edited by a moderator:
Towards Generalist Biomedical AI
https://arxiv.org/abs/2307.14334
DeepMind

Medicine is inherently multimodal, with rich data modalities spanning text, imaging, genomics, and more. Generalist biomedical artificial intelligence (AI) systems that flexibly encode, integrate, and interpret this data at scale can potentially enable impactful applications ranging from scientific discovery to care delivery. To enable the development of these models, we first curate MultiMedBench, a new multimodal biomedical benchmark.

MultiMedBench encompasses 14 diverse tasks such as medical question answering, mammography and dermatology image interpretation, radiology report generation and summarization, and genomic variant calling. We then introduce Med-PaLM Multimodal (Med-PaLM M), our proof of concept for a generalist biomedical AI system. Med-PaLM M is a large multimodal generative model that flexibly encodes and interprets biomedical data including clinical language, imaging, and genomics with the same set of model weights. Med-PaLM M reaches performance competitive with or exceeding the state of the art on all MultiMedBench tasks, often surpassing specialist models by a wide margin.

We also report examples of zero-shot generalization to novel medical concepts and tasks, positive transfer learning across tasks, and emergent zero-shot medical reasoning. To further probe the capabilities and limitations of Med-PaLM M, we conduct a radiologist evaluation of model-generated (and human) chest X-ray reports and observe encouraging performance across model scales.

In a side-by-side ranking on 246 retrospective chest X-rays, clinicians express a pairwise preference for Med-PaLM M reports over those produced by radiologists in up to 40.50% of cases, suggesting potential clinical utility. While considerable work is needed to validate these models in real-world use cases, our results represent a milestone towards the development of generalist biomedical AI systems.
 
Zero-shot in the above is especially significant. It means problems the AI was not trained on and is seeing for the first time. State of the art refers to human experts, so they are claiming that this model is already as good or better than human medical doctors in some cases, even "often surpassing specialist models by a wide margin".
 
You must log in or register to reply here.
Back
Top Bottom