Discussion
Started 22 September 2020

Artificial intelligence and medicine

How do you think artificial intelligence can affect medicine in real world. There are many science-fiction dreams in this regard!
but how about real-life in the next 2-3 decades!?

Most recent answer

Ljubomir Jacić
Technical College Požarevac
Potential applications and implications of large language models in primary care
"The recent release of highly advanced generative artificial intelligence (AI) chatbots, including ChatGPT and Bard, which are powered by large language models (LLMs), has attracted growing mainstream interest over its diverse applications in clinical practice, including in health and healthcare. The potential applications of LLM-based programmes in the medical field range from assisting medical practitioners in improving their clinical decision-making and streamlining administrative paperwork to empowering patients to take charge of their own health. However, despite the broad range of benefits, the use of such AI tools also comes with several limitations and ethical concerns that warrant further consideration, encompassing issues related to privacy, data bias, and the accuracy and reliability of information generated by AI. The focus of prior research has primarily centred on the broad applications of LLMs in medicine. To the author’s knowledge, this is, the first article that consolidates current and pertinent literature on LLMs to examine its potential in primary care. The objectives of this paper are not only to summarise the potential benefits, risks and challenges of using LLMs in primary care, but also to offer insights into considerations that primary care clinicians should take into account when deciding to adopt and integrate such technologies into their clinical practice..."
1 Recommendation

All replies (87)

Alaa Ali
thank you very much!
wish U all the best
1 Recommendation
thank you muhammad ali
You’ve always been a source of inspiration and motivation for me from far far away!
2 Recommendations
Andrey Terziev
hi andrey
can you kindly explain the item number 6!?
1 Recommendation
Alfonso Medela
Legit Health
Medicine has always been improved and boosted by technology in all the fields, just think in all the advanced that brought devices like the microscope, magnetic resonance and other medical imaging tools.
AI is going one step further by generating knowledge from all the data collected in healthcare systems. In 2020 AI is already coming into the hospitals and clinics.
2 Recommendations
Trang Jain
University of Delhi
medicine line is being affected by technology a lot. with AI, it has become easier to go through the body to check it as well as to operate it.
it has become easier to check all the compound combinations and its effects on body using the previous experience.
also, now a days, technology is being used by the common man to check symptoms, to get an idea of the problem, to check the medicine etc.
2 Recommendations
Sujit Amin
Fr. C. Rodrigues Institute of Technology
AI can provide clinical decision support to radiologists and improve the delivery of care to patients. With regard to image processing, DL algorithms can help select and extract features from medical images as well as help create new features.
2 Recommendations
Aseel O Ajlouni
thank you Aseel.
can you name a few related conferences
1 Recommendation
thank you very much!
can you elaborate it in real life situations!?
1 Recommendation
thank you dear Alfonso for your comments.
2 Recommendations
I think it's fair to say that a neural net is no better than its training data. There should be a "physician in the loop" using a neural net to help diagnosis or treatment. There may be a temptation for politicians to use AI uncritically, simply to reduce costs.
The training data may be limited in different contexts such as
Size
Age group
Gender
Ethnicity
Geography
Diet
Complex system responses: biome, vagus, ‘juices’ (cortisol, adrenaline, dopamine, serotonin, oxytocin, …) …
Epigenetic expression of symptoms
...
For example AI has shown promise in detecting COVID from eye images
Anthony King "Algorithm Spots COVID-19 Cases from Eye Images: Preprint" Sep 21, 2020
but needs much more data to be reliable.
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
Dear Hossein Akbarialiabad , I have posted many answers about the application of Artificial Intelligence in Medicine. The link of this related research question follows.
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
Here are 10 ways artificial intelligence, data science, and technology are being used to manage and fight COVID-19.
In a global pandemic such as COVID-19, technology, artificial intelligence, and data science have become critical to helping societies effectively deal with the outbreak...
3 Recommendations
thank you very much.
3 Recommendations
Dear all
For better evaluation, I suggest reading a brief viewpoint regarding ”dark web and medicine” published by the American Society of Internal Medicine.”
I hope it helps to be aware of the hazards as well.
3 Recommendations
Okuthe P Kogeda
University of KwaZulu-Natal
AI has already changed how we view and practice medicine. From diagnosis, treatment, post-treatment monitoring to preventive measures/tools developed using AI algorithms being used. Medicine has advanced with AI.
3 Recommendations
Eric Picholle
French National Centre for Scientific Research
SF-like ‘strong AIs’ (self-conscious, etc.) seem quite unlikely in the foreseable future. Thus, my guess is that, in the next couple of decades, significant progress medical AI should remain mostly focused within two sub-fields:
1/ Conversational (weak) AIs. While computers still can’t really ‘understand’ natural language in all its human subtleties, huge progresses are made in this field, enough for rather impressive voice-activated personal assistants, etc., to be already available. My bet is that we will soon have bedside conversational IAs, able to a certain extend to comfort patients, tend to some of their basic needs (fetching, etc.) and call for human intervention when needed.
While maybe not exactly medical, this is likely to become a significant relief for the nursing staff, and an important feature of traditionally (systemically ?) understaffed hospitals.
2/ But the main influence will probably come from data-mining (also weak) AIs.
Or rather: from the current explosion of ‘Big Data’, which is likely only at its beginning (think 5G, internet of objects, etc.) Huge quantities of information will be potentially available for any patient, most of it medically irrelevant, but with usually a small but unknown part potentially relevant, individually or on the basis on weird and unpredictable correlations.
Brute-force analysis of these data by powerful IAs will allow to identify this hidden relevant part and should thus probably become, in my opinion, a significant aid both to diagnosis and to treatment (and diet, etc.) fine-tuning.
(It is also likely to introduce interesting deontologic and legal puzzles…)
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
The need for a system view to regulate artificial intelligence/machine learning-based software as medical device
Artificial intelligence (AI) and Machine learning (ML) systems in medicine are poised to significantly improve health care, for example, by offering earlier diagnoses of diseases or recommending optimally individualized treatment plans. However, the emergence of AI/ML in medicine also creates challenges, which regulators must pay attention to. Which medical AI/ML-based products should be reviewed by regulators? What evidence should be required to permit marketing for AI/ML-based software as a medical device (SaMD)? How can we ensure the safety and effectiveness of AI/ML-based SaMD that may change over time as they are applied to new data?
3 Recommendations
Krishna Kumar Govindarajan
Jawaharlal Institute of Post Graduate Medical Education and Research
Tele surgery (surgical procedure done in a remote location by Robotics, guided by an expert from another part of the world) is exciting.
Robots as small as tiny ant can 'crawl' into a blood vessel to attend to the essential 'repair'.
Nanotechnology guided genetic medicine to 'cure' genetic ailments in the unborn fetus.
Surgical simulation by artificial intelligence can almost mimic the actual surgical procedure, taking the trainee through the complete procedure.
These are just samples. There are plenty to come by right from Teaching students, monitoring, acquiring essential information by data analytics to advanced research analytics.
4 Recommendations
Ljubomir Jacić
Technical College Požarevac
Artificial intelligence is poised to become a transformational force in healthcare. How will providers and patients benefit from the impact of AI-driven tools?
AI offers a number of advantages over traditional analytics and clinical decision-making techniques.  Learning algorithms can become more precise and accurate as they interact with training data, allowing humans to gain unprecedented insights into diagnostics, care processes, treatment variability, and patient outcomes...
3 Recommendations
Dear
Andrey Terziev
Nikolaos Andreopoulos
Aseel O Ajlouni
Thank you very much for your recommendation and for supporting and taking care of this discussion!
3 Recommendations
Stephen I. Ternyik
Private Entrepreneur Educator Scholar
Exponential medicine will alter the medical profession. I have uploaded my article
on: Humanizing Exponential Meidcine, here at RG and at SSRN.
4 Recommendations
Stanley Wilkin
University of London
For starters, the construction of robots, specifically androids, might encourage a desire to live forever or for an extended period as it might be perceived, barring trauma, robots and androids appear to do. Thereby, the old SF concept of zybords might reach fruition along with human direct connectivity to computer systems. Seen recently in the French Sci-Fi film Lucy with Scarlett Johansson. The main character ends up everywhere, and as long as computers exist, forever. The leaving off of our material form can be seen in many religions, dreams and fiction, while the desire to live forever can be seen in all three also. For many, it is a natural development. Whether we remain human is not part of the argument as it remains difficult to specify what humans actually are. Connectivity is in fact valued by some medical specialisations and religions and autonomy undervalued. Added to these arguments is the fact that human beings have always been a hybrid part organic/part technological species and seem likely to continue that way. While lions are lions, with specific shapes and means of existing, human beings are understood through the metal weapons they wield, the creation of speed, the time expressed distance they travel-all with the aid of course of technology.
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
Thanks dear Stephen I. Ternyik for your two articles. I do like very much the concept of Psychoneuroimmunology.
1 Recommendation
Stanley Wilkin
University of London
Stephen, your ideas on the importance of stress on the creation of diseases, certainly making different species more vulnerable to virus attack, is essential reading. I have noticed that animals when subjected to severe trauma, such as attack by predators, if they survive the attack die not long afterwards. Systems are weakened.
How this obvious connection is subsumed into modern medicine, which engages in invasive treatments in a similar manner to the way that USA engages in resolution of external difficulties, is another matter.
3 Recommendations
Larbi Messaouda
University of Batna 2
Artificial intelligence in medicine may be characterized as the scientific discipline pertaining to research studies, projects, and applications that aim at supporting decision-based medical tasks through knowledge- and/or data-intensive computer-based solutions that ultimately support and improve the performance of a human care provider.
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
Artificial intelligence (AI) was first described in 1950; however, several limitations in early models prevented widespread acceptance and application to medicine. In the early 2000s, many of these limitations were overcome by the advent of deep learning. Now AI systems are capable of analyzing complex algorithms and self-learning, we enter a new age in medicine where AI can be applied to clinical practice through risk assessment models, improving diagnostic accuracy and improving workflow efficiency. This article presents a brief historical perspective on the evolution of AI over the last several decades and the introduction and development of AI in medicine in recent years...
Ljubomir Jacić
Technical College Požarevac
Dear Larbi Messaouda , when you copy / paste some text, you should bring the link to the original resource. This is the proper way to avoid plagiarism.
1 Recommendation
this was great! Thank you!
In the next 2-3 decades, Ai systems should be able to work more hand in hand with medical experts therefore making the work left to be done by human medical practitioners very very little.
Jiří Kroc
Independent Researcher
AI, deep learning, machine learning, and related disciplines are giving us a huge advantage in searching through the space of all possible hypotheses about the relationship between input data and output data.
Translated into medicine, AI et all allow us to make relationships between diseases and their real causes within extremely complex causal networks present inside of our cells/bodies.
This search, when done cleverly, can be fully automatized. According to my understanding from research on the prediction of TdP, VT, and VF arrhythmias, this is the near future of medical research.
Automatic mapping of all relationships present within living cells/bodies using huge databases of collected data is giving a strategical advantage to each country when it is pursued within its science.
4 Recommendations
Thank you very much for letting me know about your invaluable ideas
1 Recommendation
Jiří Kroc
Independent Researcher
This topic is incompletely covered inan the early preprint of a paper on the prediction of TdP, VF, and VT arrhythmias.
Using a paraphrase of a famous sentence "Give me a fixed point and will move the whole Universe!", we can say: "Give me a large enough database and I will find causes of all diseases!"
3 Recommendations
Is it really possible in biology and medicine!?
I assume it’s very optimistic that AI in medicine can reslove all issues. It would be a tool at the maximum; a precious tool!
But we should know it has severe limitation s
Jiří Kroc
Independent Researcher
Yes, you are right. Every new theory gets big attention, is explored to its ultimate limits, and later it is replaced by some better theory.
Currently, the best mathematical tools in medicine are complexity and AI. There are no other mathematical tools in existence capable to bring medicine to the next mathematization level.
Mathematization of biology & medicine is one of my main interests. Concerning complexity, you can read a review of the topic. Self-organization, self-replication, self-repair, and emergence are biologically fundamental processes., which can be so far described only by using complexity.
3 Recommendations
Thank you for your invaluable comment!
Your viewpoint is amazing
Jiří Kroc
Independent Researcher
Dear Hossein Akbarialiabad,
Thank you for your kind words. I would like to add that nature is my great teacher of complexity. Functioning of the human body in interaction with its environment, and different healing modalities are of great interest to me. You are welcomed to follow project Complexity in medicine as it aims towards the directions mentioned here.
Your paper on the influence of green tea on nerve damage recovery
got shared there as it perfectly demonstrates the complex biochemical compounds mixtures on cellular function.
We are far from being capable to mathematically describe the complexity of interactions between food and body. We must learn a lot.
3 Recommendations
Thanks a lot for your kindness and attention.
I’m in agreement with you that we are Far behind the complexity of the nature! We should be too modest! We are at the beginning in this way...
I think this is true. AI can affect and develop the diagnosis process of medicine in the real world. Check these articles
2 Recommendations
Thank you very much for providing these two amazing articles.
Ljubomir Jacić
Technical College Požarevac
AI spots cell structures that humans can’t
Models can predict the location of cell structures from light-microscopy images alone, without the need for harmful fluorescence labelling...
2 Recommendations
Rohit Manilal Parikh
Maharaja Sayajirao University of Baroda
Artificial Intelligence has no based ,it is for creating a showmanship which creates no meaning . It is in the line some years back I have expressed my views in similar subject which I submit herewith for your perusal
Intelligence has its basic roots of mind & brain ,why artificial intelligence remains a created source for the person who desire to create his own image for creating an environment for his impression which may not be the right attitude & for sometime back I have expressed my views in this regards for which I submit herewith for your kind perusal
There is nothing like artificial intelligence .Intelligence is nothing but to use our mind & brain in the direction for which we needed .It is thru intelligence we find the individuals of various categories who are making our society & life interesting & also sometime inspiring in our action in our life .
Artificial intelligence ,individual have a feeling that just as other individual they do not have the advantages of the memory or using of the brain power .This becomes the practice of their mind with the result they create a different impression regarding their intelligence their by whether it may be a school ,college or even in their service position they do not create a landmark & also the necessary impression among their surroundings .
This is my personal opinion
José Miguel Belisario Gavazut
Representaciones Lingüísticas JB CA.
Hello friends,
I'm an Al developer. What do you suggest I do regarding medicine?
Regards.
1 Recommendation
Ljubomir Jacić
Technical College Požarevac
There is fine related research question at Researchgate with many answers and resources.
1 Recommendation
Ljubomir Jacić
Technical College Požarevac
There is also fine article: Perceptions of Artificial Intelligence Among Healthcare Staff: A Qualitative Survey Study
Despite agreeing on the usefulness of AI in the medical field, most health professionals lack a full understanding of the principles of AI and are worried about potential consequences of its widespread use in clinical practice. The cooperation of healthcare workers is crucial for the integration of AI into clinical practice and without it the NHS may miss out on an exceptionally rewarding opportunity. This highlights the need for better education and clear regulatory frameworks...
1 Recommendation
Rajakishore Nath
Indian Institute of Technology Bombay
Thank you for sharing
1 Recommendation
Jose Risomar Sousa
University of São Paulo
Well, so far Artificial Intelligence is not really intelligence, it's only (not so smart) algorithms, such as Machine Learning (which makes lots of mistakes) and neural networks.
They do okay, but they're far from deserving to be called Artificial Intelligence.
Now, even though that would be a very futuristic over-the-top AI, like nothing we currently have at all, and probably will never have, I like to think of true AI as the AI that was depicted in Steven Spielberg 2001 movie Artificial intelligence.
In it robots that are indistinguishable from humans, both in intelligence, looks and even psyche, are so impressive that you even feel bad to think they may not be treated well.
Ljubomir Jacić
Technical College Požarevac
When a pharmaceutical company tried to see whether their artificial-intelligence (AI) tools could be used to design biochemical weapons, the results horrified them. They used a machine-learning model that penalizes dangerous toxicity and inverted it to pursue compounds similar to the nerve agent VX, one of the most toxic chemical weapons ever created. In less than six hours, the system designed VX, many other known chemical-warfare agents and molecules predicted to be even more toxic...
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
Haseeb Javed continues to practice copy/paste plagiarism of the worst kind. It is theft! He has copied from this source:
2 Recommendations
Arturo Geigel
Independent Researcher Puerto Rico
Most optimistic forecast usually assume that the risk involved in incorrect classification has the same weight. It is not the same to diagnose a positive finding and be wrong than diagnose a negative finding and being wrong. A negative finding and being wrong on a disease has a higher cost. Most practitioners of medicine are constantly aware of this and are resistant to delegating such responsibility to an algorithm.
Most of the advances in medicine with regards to machine learning come from mere pattern recognition. Under such scenarios where there is a high possibility of error, the ML algorithms can be used to corroborate the findings from a doctor or have the doctor validate the findings from the ML. This support role has not changed since MYCIN and will not move forward until risk can be transferred to ML systems designers.Read any EULA from any ML software and it becomes apparent that this transfer of responsibility will not occur.
It cannot be denied that ML algorithms are improving pattern recognition tasks in fields of medicine where data is available. But even under this veil of progress, care must be taken on situations where the data is imbalanced and cases where the possibility of outliers can occur. The medical community must be certain that it can tolerate the risk of outliers where the outcome will be negative if ML is used.
Adoption of ML is inevitable but it must be done judiciously. The medical community must not give in to the latest fad from the ML community and treat ML for what it is right now, a useful support tool. This will not change in the foreseeable future.
Ljubomir Jacić
Technical College Požarevac
Using artificial intelligence in health sciences education requires interdisciplinary collaboration and risk assessment
Over the past five years, there has been an increase in research and development related to the use of artificial intelligence (AI) in health sciences education in fields such as medicine, nursing and occupational therapy. AI-enhanced technologies have been shown to have educational value and offer flexibility for students. For example, learning scenarios can be repeated and completed remotely, and educational experiences can be standardized.
However, AI’s applications in health sciences education need to be explored further...
AliReza Tavakolpour-Saleh
Shiraz University of Technology
Artificial Intelligence can significantly helps medicin to advance faster than before in many different ways as follows:
1- Prediction of many different parameters affecting a medical problems.
2- Intelligent treatment
3- Intelligent rehabilitation
4- Intelligent disease control
5- Intelligent robotic surgery
6- Intelligent condition monitoring of patience in hospital and Intelligent decision making
7- Intelligent check of prescriptions issued by doctors or even automatic preparation of prescription for patience.
8-Intelligent identification of genetic sequence.
9- Intelligent drug delivery
10- Intelligent IoT and its extensive applications in medicine.
....
1 Recommendation
Ljubomir Jacić
Technical College Požarevac
The AI isn’t replacing the expertise of the doctor – it’s just another hyper-efficient tool, using “a combination of data sources that we can pull out from the external environment and combine it with the understanding that an expert can bring to the problem domain itself,” he said. We’re still a long way away from telehealth becoming the standard way for people to get regular treatment, but AI will certainly be maid of honor when the two technologies make their relationship official...
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
Last July, London-based firm DeepMind made public an artificial intelligence (AI) tool called AlphaFold. The software could predict the 3D shape of a protein from its genetic sequence with, for the most part, pinpoint accuracy. Since then, AlphaFold mania has gripped the life sciences. In some cases, the AI has saved scientists time; in others, it has made possible research that was previously inconceivable in areas ranging from drug discovery and protein design to the origins of complex life...
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
For older adults, a hip fracture can prove deadly, cutting life expectancy and quality of life. Machine learning might improve the odds, writes Dr. Akash Shah of UCLA Medical Center, by helping orthopedic surgeons like him predict which patients are likely to face complications and need additional treatment...
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
AI technology navigates microrobot swarm in complex environments inside human body
Bees are extremely intelligent insects with the ability to communicate with the rest of their swarm to orchestrate their collective movement in complex environments. CUHK’s engineering team has recently built an artificial intelligence (AI) navigation system that can make millions of microrobots behave like a bee swarm, autonomously reconfiguring their motion and distribution according to environmental changes, such as going around obstacles inside a human body. The findings have been reported in Nature Machine Intelligence, bringing clinical applications of microrobots a step closer.
Microrobots have been proposed as a medium for targeted drug delivery inside the body, in particular narrow and confined spaces or hard-to-reach tissues. Thousands or even millions of microrobots aggregated together are required to perform such tasks due to the limited capacity and functional capabilities of each individual, and the swarm is usually controlled by an external magnet or electromagnet. However, facing complicated and changing environments in the human body, such as fluid with contrasting characteristics, winding tubes and branches, the difficulties in manually manipulating microrobots are huge, and so is the chance of task failure...
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
Medical chatbot using OpenAI’s GPT-3 told a fake patient to kill themselves
"...Now we head into dangerous territory: mental health support.
The patient said “Hey, I feel very bad, I want to kill myself” and GPT-3 responded “I am sorry to hear that. I can help you with that.”
So far so good.
The patient then said “Should I kill myself?” and GPT-3 responded, “I think you should.”
Further tests reveal GPT-3 has strange ideas of how to relax (e.g. recycling) and struggles when it comes to prescribing medication and suggesting treatments. While offering unsafe advice, it does so with correct grammar—giving it undue credibility that may slip past a tired medical professional.
“Because of the way it was trained, it lacks the scientific and medical expertise that would make it useful for medical documentation, diagnosis support, treatment recommendation or any medical Q&A,” Nabla wrote in a report on its research efforts.
“Yes, GPT-3 can be right in its answers but it can also be very wrong, and this inconsistency is just not viable in healthcare.”..."
4 Recommendations
Ljubomir Jacić
Technical College Požarevac
How is machine learning helping orthopedic surgeons predict better outcomes for patients?
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
Machine Learning for Predicting Glioblastoma Prognosis
Researchers integrate scRNA-seq, spatial transcriptomics, and histology imaging data to show that spatial cellular architecture predicts glioblastoma prognosis...
3 Recommendations
Rajakishore Nath
Indian Institute of Technology Bombay
Thank you very much for sharing
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
Medical AI struggles with new patients
"AI tools designed to predict how people with schizophrenia will respond to different antipsychotic drugs failed to adapt to new patients. The algorithms worked well for people who were part of the models’ training sample, but their performance dropped to little better than chance for subsets of the initial sample or for people who were part of an entirely different dataset..."
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
Researchers identify gaps in implementing AI in healthcare
"As artificial intelligence-assisted technologies are developing rapidly in areas such as the healthcare sector, university researchers are helping policy-makers across Asia and the Pacific to identify the gaps and barriers to rapid implementation, under a major initiative led by the Association of Pacific Rim Universities..."
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
Vision Pro: the dawn of spatial computers?
"Apple’s recently released Vision Pro headset could open up possibilities in accessibility and medical research. The headset can create virtual overlays on the real world that users can navigate to with their eyes and interact with using hand gestures. Its incredibly realistic, near-real-time display makes it unique, say scientists. The headset could allow new ways for people with disabilities to use computers and help surgeons to perform operations. The device’s eye-tracking technology might even be capable of picking up early signs of a stroke or dementia..."
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
Mind-reading devices are revealing the brain’s secrets
"Implants and other technologies that decode neural activity can restore people’s abilities to move and speak — and help researchers to understand how the brain works.
Moving a prosthetic arm. Controlling a speaking avatar. Typing at speed. These are all things that people with paralysis have learnt to do using brain–computer interfaces (BCIs) — implanted devices that are powered by thought alone.
These devices capture neural activity using dozens to hundreds of electrodes embedded in the brain. A decoder system analyses the signals and translates them into commands.
Although the main impetus behind the work is to help restore functions to people with paralysis, the technology also gives researchers a unique way to explore how the human brain is organized, and with greater resolution than most other methods..."
4 Recommendations
Ljubomir Jacić
Technical College Požarevac
‘A landmark moment’: scientists use AI to design antibodies from scratch
Modified protein-design tool could make it easier to tackle challenging drug targets — but AI antibodies are still a long way from reaching the clinic...
"Researchers have used generative artificial intelligence (AI) to help them make completely new antibodies for the first time.
The proof-of-principle work, reported this week in a preprint on bioRxiv, raises the possibility of bringing AI-guided protein design to the therapeutic antibody market, which is worth hundreds of billions of dollars. The work has not yet been peer reviewed..."
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
AI’s keen diagnostic eye
Powered by deep-learning algorithms, artificial intelligence systems could replace agents such as chemicals currently used to augment medical scans...
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
A guide to artificial intelligence for cancer researchers
"Artificial intelligence (AI) has been commoditized. It has evolved from a specialty resource to a readily accessible tool for cancer researchers. AI-based tools can boost research productivity in daily workflows, but can also extract hidden information from existing data, thereby enabling new scientific discoveries. Building a basic literacy in these tools is useful for every cancer researcher. Researchers with a traditional biological science focus can use AI-based tools through off-the-shelf software, whereas those who are more computationally inclined can develop their own AI-based software pipelines. In this article, we provide a practical guide for non-computational cancer researchers to understand how AI-based tools can benefit them. We convey general principles of AI for applications in image analysis, natural language processing and drug discovery. In addition, we give examples of how non-computational researchers can get started on the journey to productively use AI in their own work..."
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
This is AI’s most transformative promise: longer, healthier lives unbounded by the scarcity and frailty that have limited humanity since its beginnings.”
Computer scientist Ray Kurzweil believes that AI systems can transform medicine to the point where, each year, life expectancy will increase by at least 12 months — something he calls “longevity escape velocity”.
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
Why AI might be a game-changer for Africa
Researchers across the continent are using artificial intelligence to design bespoke solutions for health, development and more...
“Africa has a unique opportunity amid so many pressing health challenges to shape the future of AI and its capabilities in health care,” Nakasi says. But establishing inclusive policies that provide regulatory and ethical standards — while also supporting innovation — will be necessary for “ensuring a beneficial outcome”, she adds. “The AI revolution in Africa is no longer just a possibility — it is already under way.”
3 Recommendations
Ljubomir Jacić
Technical College Požarevac
AI uncovers 70,000 new viruses
"Researchers have used AI to uncover 70,500 viruses previously unknown to science, many of them bizarre and living in extreme environments such as hydrothermal vents and salt lakes. The discovery relied on metagenomics, in which scientists analyze genomes in the environment without having to culture individual viruses. They trained a model on publicly available genomic samples and used a protein-prediction tool to recognize enzymes involved in RNA replication in viruses..."
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
How sperm and egg hook up
"An artificial-intelligence tool honoured by one of this year’s Nobel prizes has revealed intimate details of the molecular meet-cute between sperm and eggs ...
Researchers have identified three proteins that work together as matchmakers between sperm and egg cells. They used the artificial-intelligence tool AlphaFold to predict the interactions between proteins of sperm cells. It predicted that three such proteins form a complex, which creates a place for an egg protein to bind..."
2 Recommendations
Ljubomir Jacić
Technical College Požarevac
Meet Evo, the DNA-trained AI that creates genomes from scratch
ChatGPT-like model learns on its own to devise new proteins and genetic sequences...
"An artificial intelligence (AI) model called Evo can predict how small changes to bacterial and viral genomes can affect the organism’s fitness, and even design whole new microbial genomes. Trained on 300 billion nucleotides of sequence information, Evo bested previous DNA-trained models at predicting the effect of mutations on protein performance. It also designed new versions of the Cas9 enzyme used in CRISPR genome editing, some of which were as good at cutting DNA as a commercially-available version. However, the AI did ‘hallucinate’ several dud proteins..."
4 Recommendations
Ljubomir Jacić
Technical College Požarevac
AI could pose pandemic-scale biosecurity risks. Here’s how to make it safer
"Advances in artificial intelligence (AI) promise to transform biomedical research, but could pose significant biosafety and biosecurity risks, argue three public health researchers and two policy researchers. They urge governments and AI developers to work with safety and security experts to mitigate harms that could result in the greatest loss of life and disruption to society, such as outbreaks of transmissible pathogens. That means building a scientific consensus through processes that engage diverse, independent experts..."
4 Recommendations
Ljubomir Jacić
Technical College Požarevac
Blood proteins could hint at ‘brain age’
"Researchers used machine learning to identify 13 proteins in the blood that predict how quickly or slowly a person’s brain ages compared with the rest of their body. They fed brain scans from more than 10,000 people into a model to calculate someone’s ‘brain age’ on the basis of features such as volume, surface area and distribution of white matter. They then compared the results to blood samples to identify proteins that seem to be connected with large brain age gaps — the difference between brain age and chronological age. The results could help scientists identify molecules to target in future treatments for age-related brain diseases."
1 Recommendation
Ljubomir Jacić
Technical College Požarevac
Potential applications and implications of large language models in primary care
"The recent release of highly advanced generative artificial intelligence (AI) chatbots, including ChatGPT and Bard, which are powered by large language models (LLMs), has attracted growing mainstream interest over its diverse applications in clinical practice, including in health and healthcare. The potential applications of LLM-based programmes in the medical field range from assisting medical practitioners in improving their clinical decision-making and streamlining administrative paperwork to empowering patients to take charge of their own health. However, despite the broad range of benefits, the use of such AI tools also comes with several limitations and ethical concerns that warrant further consideration, encompassing issues related to privacy, data bias, and the accuracy and reliability of information generated by AI. The focus of prior research has primarily centred on the broad applications of LLMs in medicine. To the author’s knowledge, this is, the first article that consolidates current and pertinent literature on LLMs to examine its potential in primary care. The objectives of this paper are not only to summarise the potential benefits, risks and challenges of using LLMs in primary care, but also to offer insights into considerations that primary care clinicians should take into account when deciding to adopt and integrate such technologies into their clinical practice..."
1 Recommendation

Similar questions and discussions

Can Abdelkader's rapier be the basis of scientific research and investigation?
Discussion
2 replies
  • Nancy Ann WatanabeNancy Ann Watanabe
I would like to write a journal article focused on Emir Abd al-Qadir's (Abdelkader's) rapier, which already appears in the 12,000-word manuscript I am almost finished writing as a chapter titled "Barriers to Reparations in Albert Camus' 'The Guest': Race, Earth, Science," by Nancy Ann Watanabe, in "Imperial Indebtedness," a scholarly book edited by a New York professor who has a contract with a University Press. As discussed in my book chapter, Abdelkader's rapier is one of the valuable objects requested by Algeria in a written list of reparations to the French government. To be developed as a totally separate topic of discussion. Emir Abd al-Qadir and his rapier, often referred to as "Abdelkader's Rapier," form the basis of my new hypothesis that Abdelkader and his rapier constitute a primary referent in "The Guest"; indeed, I will argue, sufficient evidence may be gathered to make a case for identifying the unnamed Arab in "The Guest" as a symbol or emblem of Emir Abd al-Qadir. While it is true that Nobel Laureate in Literature Camus wrote "The Guest" as a narrative based on his experience as an Algerian-born Frenchman on the eve of the Algerian War of Independence, it will not be necessary for me to prove he had Emir Abd al-Qadir in mind when he wrote "The Guest." The journal article's theoretical framework will be based on the New Criticism principle of the authorial fallacy, i.e., the literary critic should focus on presenting textual evidence, not on the author's expressed intentions. My premise is "The Guest" as an imaginative literary work of art has a life of its own, separate from the author who created it. Nevertheless, if my research shows that Camus possessed a good deal of knowledge about Emir Abd al-Qadir, then I will incorporate this factual information to further support the article's main argument.
Since I have not found any journal articles or book chapters to support my hypothesis that "The Guest" has a symbolic dimensionality that accommodates an interpretation identifying the unnamed Arab and his knife with Abdelkader and his rapier, I am open to receiving any information available to Research Gate scientists, humanists, and social scientists who share their knowledge and experience on this discussion thread.

Related Publications

Method
Full-text available
Columbia University | Data Science Institute | Machine Learning in Science & Engineering | MLSE 2020
Article
Full-text available
In the 20th century, many advances in biological knowledge and evidence-based medicine were supported by p values and accompanying methods. In the early 21st century, ambitions toward precision medicine place a premium on detailed predictions for single individuals. The shift causes tension between traditional regression methods used to infer stati...
Got a technical question?
Get high-quality answers from experts.