Multiplex immunofluorescence and immunohistochemistry benefit patients by allowing cancer pathologists to identify several proteins expressed on the surface of cells, enabling cell classification, better understanding of the tumour micro-environment, more accurate diagnoses, prognoses, and tailored immunotherapy based on the immune status of individual patients. However, they are expensive and time consuming processes which require complex staining and imaging techniques by expert technicians. Hoechst staining is much cheaper and easier to perform, but is not typically used in this case as it binds to DNA rather than to the proteins targeted by immunofluorescent techniques, and it was not previously thought possible to differentiate cells expressing these proteins based only on DNA morphology. In this work we show otherwise, training a deep convolutional neural network to identify cells expressing three proteins (T lymphocyte markers CD3 and CD8, and the B lymphocyte marker CD20) with greater than 90% precision and recall, from Hoechst 33342 stained tissue only. Our model learns previously unknown morphological features associated with expression of these proteins which can be used to accurately differentiate lymphocyte subtypes for use in key prognostic metrics such as assessment of immune cell infiltration,and thereby predict and improve patient outcomes without the need for costly multiplex immunofluorescence.

Massive deployment of Graph Neural Networks (GNNs) in high-stake applications generates a strong demand for explanations that are robust to noise and align well with human intuition. Most existing methods generate explanations by identifying a subgraph of an input graph that has a strong correlation with the prediction. These explanations are not robust to noise because independently optimizing the correlation for a single input can easily overfit noise. Moreover, they do not align well with human intuition because removing an identified subgraph from an input graph does not necessarily change the prediction result. In this paper, we propose a novel method to generate robust counterfactual explanations on GNNs by explicitly modelling the common decision logic of GNNs on similar input graphs. Our explanations are naturally robust to noise because they are produced from the common decision boundaries of a GNN that govern the predictions of many similar input graphs. The explanations also align well with human intuition because removing the set of edges identified by an explanation from the input graph changes the prediction significantly. Exhaustive experiments on many public datasets demonstrate the superior performance of our method.

At AWS, we love sharing our passion for technology and innovation, and AWS DeepComposer is no exception. This service is designed to help everyone learn about generative artificial intelligence (AI) through the language of music. You can use a sample melody, upload your own melody, or play a tune using the virtual or a real keyboard. Best of all, you don't have to write any code. But what exactly is generative AI, and why is it useful?

Deep learning is an advanced branch of machine learning that enables computers to solve complex problems from driving a car to successfully flying a helicopter without strictly learning from simulations. Deep learning is a combination of mathematics and Neurobiology, the artificial intelligence science aims to project the human learning process on computers so that computers could learn and improve from experience. As mentioned earlier artificial intelligence science is based on how we learn, deep learning is accomplished by imitating human brain architecture. When the child a signal is transmitted from the child's eyes, ears, and hands to the brain, that signals reach the brain and begin their journey in the nodes, after reaching the final node the brain concludes to identify this new object by its characteristics illuminating, heat, and voice. For simplicity we assumed that the child only learns the object characteristics after pain and this is not true in real life learning process is always on and each aspect of the object will be learned in the precise second of the encounter.

Artificial intelligence and machine learning (AI/ML) algorithms are increasingly developed in health care for diagnosis and treatment of a variety of medical conditions ([ 1 ][1]). However, despite the technical prowess of such systems, their adoption has been challenging, and whether and how much they will actually improve health care remains to be seen. A central reason for this is that the effectiveness of AI/ML-based medical devices depends largely on the behavioral characteristics of its users, who, for example, are often vulnerable to well-documented biases or algorithmic aversion ([ 2 ][2]). Many stakeholders increasingly identify the so-called black-box nature of predictive algorithms as the core source of users' skepticism, lack of trust, and slow uptake ([ 3 ][3], [ 4 ][4]). As a result, lawmakers have been moving in the direction of requiring the availability of explanations for black-box algorithmic decisions ([ 5 ][5]). Indeed, a near-consensus is emerging in favor of explainable AI/ML among academics, governments, and civil society groups. Many are drawn to this approach to harness the accuracy benefits of noninterpretable AI/ML such as deep learning or neural nets while also supporting transparency, trust, and adoption. We argue that this consensus, at least as applied to health care, both overstates the benefits and undercounts the drawbacks of requiring black-box algorithms to be explainable. It is important to first distinguish explainable from interpretable AI/ML. These are two very different types of algorithms with different ways of dealing with the problem of opacity—that AI predictions generated from a black box undermine trust, accountability, and uptake of AI. A typical AI/ML task requires constructing an algorithm that can take a vector of inputs (for example, pixel values of a medical image) and generate an output pertaining to, say, disease occurrence (for example, cancer diagnosis). The algorithm is trained on past data with known labels, which means that the parameters of a mathematical function that relate the inputs to the output are estimated from that data. When we refer to an algorithm as a “black box,” we mean that the estimated function relating inputs to outputs is not understandable at an ordinary human level (owing to, for example, the function relying on a large number of parameters, complex combinations of parameters, or nonlinear transformations of parameters). Interpretable AI/ML (which is not the subject of our main criticism) does roughly the following: Instead of using a black-box function, it uses a transparent (“white-box”) function that is in an easy-to-digest form, for example, a linear model whose parameters correspond to additive weights relating the input features and the output or a classification tree that creates an intuitive rule-based map of the decision space. Such algorithms have been described as intelligible ([ 6 ][6]) and decomposable ([ 7 ][7]). The interpretable algorithm may not be immediately understandable by everyone (even a regression requires a bit of background on linear relationships, for example, and can be misconstrued). However, the main selling point of interpretable AI/ML algorithms is that they are open, transparent, and capable of being understood with reasonable effort. Accordingly, some scholars argue that, under many conditions, only interpretable algorithms should be used, especially when they are used by governments for distributing burdens and benefits ([ 8 ][8]). However, requiring interpretability would create an important change to ML as it is being done today—essentially that we forgo deep learning altogether and whatever benefits it may entail. Explainable AI/ML is very different, even though both approaches are often grouped together. Explainable AI/ML, as the term is typically used, does roughly the following: Given a black-box model that is used to make predictions or diagnoses, a second explanatory algorithm finds an interpretable function that closely approximates the outputs of the black box. This second algorithm is trained by fitting the predictions of the black box and not the original data, and it is typically used to develop the post hoc explanations for the black-box outputs and not to make actual predictions because it is typically not as accurate as the black box. The explanation might, for instance, be given in terms of which attributes of the input data in the black-box algorithm matter most to a specific prediction, or it may offer an easy-to-understand linear model that gives similar outputs as the black-box algorithm for the same given inputs ([ 4 ][4]). Other models, such as so-called counterfactual explanations or heatmaps, are also possible ([ 9 ][9], [ 10 ][10]). In other words, explainable AI/ML ordinarily finds a white box that partially mimics the behavior of the black box, which is then used as an explanation of the black-box predictions. Three points are important to note: First, the opaque function of the black box remains the basis for the AI/ML decisions, because it is typically the most accurate one. Second, the white box approximation to the black box cannot be perfect, because if it were, there would be no difference between the two. It is also not focusing on accuracy but on fitting the black box, often only locally. Finally, the explanations provided are post hoc. This is unlike interpretable AI/ML, where the explanation is given using the exact same function that is responsible for generating the output and is known and fixed ex ante for all inputs. A substantial proportion of AI/ML-based medical devices that have so far been cleared or approved by the US Food and Drug Administration (FDA) use noninterpretable black-box models, such as deep learning ([ 1 ][1]). This may be because blackbox models are deemed to perform better in many health care applications, which are often of massively high dimensionality, such as image recognition or genetic prediction. Whatever the reason, to require an explanation of black-box AI/ML systems in health care at present entails using post hoc explainable AI/ML models, and this is what we caution against here. Explainable algorithms have been a relatively recent area of research, and much of the focus of tech companies and researchers has been on the development of the algorithms themselves—the engineering—and not on the human factors affecting the final outcomes. The prevailing argument for explainable AI/ML is that it facilitates user understanding, builds trust, and supports accountability ([ 3 ][3], [ 4 ][4]). Unfortunately, current explainable AI/ML algorithms are unlikely to achieve these goals—at least in health care—for several reasons. ### Ersatz understanding Explainable AI/ML (unlike interpretable AI/ML) offers post hoc algorithmically generated rationales of black-box predictions, which are not necessarily the actual reasons behind those predictions or related causally to them. Accordingly, the apparent advantage of explainability is a “fool's gold” because post hoc rationalizations of a black box are unlikely to contribute to our understanding of its inner workings. Instead, we are likely left with the false impression that we understand it better. We call the understanding that comes from post hoc rationalizations “ersatz understanding.” And unlike interpretable AI/ML where one can confirm the quality of explanations of the AI/ML outcomes ex ante, there is no such guarantee for explainable AI/ML. It is not possible to ensure ex ante that for any given input the explanations generated by explainable AI/ML algorithms will be understandable by the user of the associated output. By not providing understanding in the sense of opening up the black box, or revealing its inner workings, this approach does not guarantee to improve trust and allay any underlying moral, ethical, or legal concerns. There are some circumstances where the problem of ersatz understanding may not be an issue. For example, researchers may find it helpful to generate testable hypotheses through many different approximations to a black-box algorithm to advance research or improve an AI/ML system. But this is a very different situation from regulators requiring AI/ML-based medical devices to be explainable as a precondition of their marketing authorization. ### Lack of robustness For an explainable algorithm to be trusted, it needs to exhibit some robustness. By this, we mean that the explainability algorithm should ordinarily generate similar explanations for similar inputs. However, for a very small change in input (for example, in a few pixels of an image), an approximating explainable AI/ML algorithm might produce very different and possibly competing explanations, with such differences not being necessarily justifiable or understood even by experts. A doctor using such an AI/ML-based medical device would naturally question that algorithm. ### Tenuous connection to accountability It is often argued that explainable AI/ML supports algorithmic accountability. If the system makes a mistake, the thought goes, it will be easier to retrace our steps and delineate what led to the mistake and who is responsible. Although this is generally true of interpretable AI/ML systems, which are transparent by design, it is not true of explainable AI/ML systems because the explanations are post hoc rationales, which only imperfectly approximate the actual function that drove the decision. In this sense, explainable AI/ML systems can serve to obfuscate our investigation into a mistake rather than help us to understand its source. The relationship between explainability and accountability is further attenuated by the fact that modern AI/ML systems rely on multiple components, each of which may be a black box in and of itself, thereby requiring a fact finder or investigator to identify, and then combine, a sequence of partial post hoc explanations. Thus, linking explainability to accountability may prove to be a red herring. Explainable AI/ML systems not only are unlikely to produce the benefits usually touted of them but also come with additional costs (as compared with interpretable systems or with using black-box models alone without attempting to rationalize their outputs). ### Misleading in the hands of imperfect users Even when explanations seem credible, or nearly so, when combined with prior beliefs of imperfectly rational users, they may still drive the users further away from a real understanding of the model. For example, the average user is vulnerable to narrative fallacies, where users combine and reframe explanations in misleading ways. The long history of medical reversals—the discovery that a medical practice did not work all along, either failing to achieve its intended goal or carrying harms that outweighed the benefits—provides examples of the risks of narrative fallacy in health care. Relatedly, explanations in the form of deceptively simple post hoc rationales can engender a false sense of (over)confidence. This can be further exacerbated through users' inability to reason with probabilistic predictions, which AI/ML systems often provide ([ 11 ][11]), or the users' undue deference to automated processes ([ 2 ][2]). All of this is made more challenging because explanations have multiple audiences, and it would be difficult to generate explanations that are helpful for all of them. ### Underperforming in at least some tasks If regulators decide that the only algorithms that can be marketed are those whose predictions can be explained with reasonable fidelity, they thereby limit the system's developers to a certain subset of AI/ML algorithms. For example, highly nonlinear models that are harder to approximate in a sufficiently large region of the data space may thus be prohibited under such a regime. This will be fine in cases where complex models—like deep learning or ensemble methods—do not particularly outperform their simpler counterparts (characterized by fairly structured data and meaningful features, such as predictions based on relatively few patient medical records) ([ 8 ][8]). But in others, especially in cases with massively high dimensionality—such as image recognition or genetic sequence analysis—limiting oneself to algorithms that can be explained sufficiently well may unduly limit model complexity and undermine accuracy. If explainability should not be a strict requirement for AI/ML in health care, what then? Regulators like the FDA should focus on those aspects of the AI/ML system that directly bear on its safety and effectiveness—in particular, how does it perform in the hands of its intended users? To accomplish this, regulators should place more emphasis on well-designed clinical trials, at least for some higher-risk devices, and less on whether the AI/ML system can be explained ([ 12 ][12]). So far, most AI/ML-based medical devices have been cleared by the FDA through the 510(k) pathway, requiring only that substantial equivalence to a legally marketed (predicate) device be demonstrated, without usually requiring any clinical trials ([ 13 ][13]). Another approach is to provide individuals added flexibility when they interact with a model—for example, by allowing them to request AI/ML outputs for variations of inputs or with additional data. This encourages buy-in from the users and reinforces the model's robustness, which we think is more intimately tied to building trust. This is a different approach to providing insight into a model's inner workings. Such interactive processes are not new in health care, and their design may depend on the specific application. One example of such a process is the use of computer decision aids for shared decision-making for antenatal counseling at the limits of gestational viability. A neonatologist and the prospective parents might use the decision aid together in such a way to show how various uncertainties will affect the “risk:benefit ratios of resuscitating an infant at the limits of viability” ([ 14 ][14]). This reflects a phenomenon for which there is growing evidence—that allowing individuals to interact with an algorithm reduces “algorithmic aversion” and makes them more willing to accept the algorithm's predictions ([ 2 ][2]). ### From health care to other settings Our argument is targeted particularly to the case of health care. This is partly because health care applications tend to rely on massively high-dimensional predictive algorithms where loss of accuracy is particularly likely if one insists on the ability of good black-box approximations with simple enough explanations, and expertise levels vary. Moreover, the costs of misclassifications and potential harm to patients are relatively higher in health care compared with many other sectors. Finally, health care traditionally has multiple ways of demonstrating the reliability of a product or process, even in the absence of explanations. This is true of many FDA-approved drugs. We might think of medical AI/ML as more like a credence good, where the epistemic warrant for its use is trust in someone else rather than an understanding of how it works. For example, many physicians may be quite ignorant of the underlying clinical trial design or results that led the FDA to believe that a certain prescription drug was safe and effective, but their knowledge that it has been FDA-approved and that other experts further scrutinize it and use it supplies the necessary epistemic warrant for trusting the drug. But insofar as other domains share some of these features, our argument may apply more broadly and hold some lessons for regulators outside health care as well. ### When interpretable AI/ML is necessary Health care is a vast domain. Many AI/ML predictions are made to support diagnosis or treatment. For example, Biofourmis's RhythmAnalytics is a deep neural network architecture trained on electrocardiograms to predict more than 15 types of cardiac arrhythmias ([ 15 ][15]). In cases like this, accuracy matters a lot, and understanding is less important when a black box achieves higher accuracy than a white box. Other medical applications, however, are different. For example, imagine an AI/ML system that uses predictions about the extent of a patient's kidney damage to determine who will be eligible for a limited number of dialysis machines. In cases like this, when there are overarching concerns of justice— that is, concerns about how we should fairly allocate resources—ex ante transparency about how the decisions are made can be particularly important or required by regulators. In such cases, the best standard would be to simply use interpretable AI/ML from the outset, with clear predetermined procedures and reasons for how decisions are taken. In such contexts, even if interpretable AI/ML is less accurate, we may prefer to trade off some accuracy, the price we pay for procedural fairness. We argue that the current enthusiasm for explainability in health care is likely overstated: Its benefits are not what they appear, and its drawbacks are worth highlighting. For health AI/ML-based medical devices at least, it may be preferable not to treat explainability as a hard and fast requirement but to focus on their safety and effectiveness. Health care professionals should be wary of explanations that are provided to them for black-box AI/ML models. Health care professionals should strive to better understand AI/ML systems to the extent possible and educate themselves about how AI/ML is transforming the health care landscape, but requiring explainable AI/ML seldom contributes to that end. 1. [↵][16]1. S. Benjamens, 2. P. Dhunnoo, 3. B. Meskó , NPJ Digit. Med. 3, 118 (2020). [OpenUrl][17][PubMed][18] 2. [↵][19]1. B. J. Dietvorst, 2. J. P. Simmons, 3. C. Massey , Manage. Sci. 64, 1155 (2018). [OpenUrl][20] 3. [↵][21]1. A. F. Markus, 2. J. A. Kors, 3. P. R. Rijnbeek , J. Biomed. Inform. 113, 103655 (2021). [OpenUrl][22][PubMed][18] 4. [↵][23]1. M. T. Ribeiro, 2. S. Singh, 3. C. Guestrin , in KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM, 2016), pp. 1135–1144. 5. [↵][24]1. A. Bohr, 2. K. Memarzadeh 1. S. Gerke, 2. T. Minssen, 3. I. G. Cohen , in Artificial Intelligence in Healthcare, A. Bohr, K. Memarzadeh, Eds. (Elsevier, 2020), pp. 295–336. 6. [↵][25]1. Y. Lou, 2. R. Caruana, 3. J. Gehrke , in KDD '12: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM, 2012), pp. 150–158. 7. [↵][26]1. Z. C. Lipton , ACM Queue 16, 1 (2018). [OpenUrl][27] 8. [↵][28]1. C. Rudin , Nat. Mach. Intell. 1, 206 (2019). [OpenUrl][29] 9. [↵][30]1. D. Martens, 2. F. Provost , Manage. Inf. Syst. Q. 38, 73 (2014). [OpenUrl][31] 10. [↵][32]1. S. Wachter, 2. B. Mittelstadt, 3. C. Russell , Harv. J. Law Technol. 31, 841 (2018). [OpenUrl][33] 11. [↵][34]1. R. M. Hamm, 2. S. L. Smith , J. Fam. Pract. 47, 44 (1998). [OpenUrl][35][PubMed][36] 12. [↵][37]1. S. Gerke, 2. B. Babic, 3. T. Evgeniou, 4. I. G. Cohen , NPJ Digit. Med. 3, 53 (2020). [OpenUrl][38] 13. [↵][39]1. U. J. Muehlematter, 2. P. Daniore, 3. K. N. Vokinger , Lancet Digit. Health 3, e195 (2021). [OpenUrl][40] 14. [↵][41]1. U. Guillen, 2. H. Kirpalani , Semin. Fetal Neonatal Med. 23, 25 (2018). [OpenUrl][42][PubMed][18] 15. [↵][43]Biofourmis, RhythmAnalytics (2020); [www.biofourmis.com/solutions/][44]. Acknowledgments: We thank S. Wachter for feedback on an earlier version of this manuscript. All authors contributed equally to the analysis and drafting of the paper. Funding: S.G. and I.G.C. were supported by a grant from the Collaborative Research Program for Biomedical Innovation Law, a scientifically independent collaborative research program supported by a Novo Nordisk Foundation grant (NNF17SA0027784). I.G.C. was also supported by Diagnosing in the Home: The Ethical, Legal, and Regulatory Challenges and Opportunities of Digital Home Health, a grant from the Gordon and Betty Moore Foundation (grant agreement number 9974). Competing interests: S.G. is a member of the Advisory Group–Academic of the American Board of Artificial Intelligence in Medicine. I.G.C. serves as a bioethics consultant for Otsuka on their Abilify MyCite product. I.G.C. is a member of the Illumina ethics advisory board. I.G.C. serves as an ethics consultant for Dawnlight. The authors declare no other competing interests. [1]: #ref-1 [2]: #ref-2 [3]: #ref-3 [4]: #ref-4 [5]: #ref-5 [6]: #ref-6 [7]: #ref-7 [8]: #ref-8 [9]: #ref-9 [10]: #ref-10 [11]: #ref-11 [12]: #ref-12 [13]: #ref-13 [14]: #ref-14 [15]: #ref-15 [16]: #xref-ref-1-1 "View reference 1 in text" [17]: {openurl}?query=rft.jtitle%253DNPJ%2BDigit.%2BMed.%26rft.volume%253D3%26rft.spage%253D118%26rft_id%253Dinfo%253Apmid%252Fhttp%253A%252F%252Fwww.n%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [18]: /lookup/external-ref?access_num=http://www.n&link_type=MED&atom=%2Fsci%2F373%2F6552%2F284.atom [19]: #xref-ref-2-1 "View reference 2 in text" [20]: {openurl}?query=rft.jtitle%253DManage.%2BSci.%26rft.volume%253D64%26rft.spage%253D1155%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [21]: #xref-ref-3-1 "View reference 3 in text" [22]: {openurl}?query=rft.jtitle%253DJ.%2BBiomed.%2BInform.%26rft.volume%253D113%26rft.spage%253D103655%26rft_id%253Dinfo%253Apmid%252Fhttp%253A%252F%252Fwww.n%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [23]: #xref-ref-4-1 "View reference 4 in text" [24]: #xref-ref-5-1 "View reference 5 in text" [25]: #xref-ref-6-1 "View reference 6 in text" [26]: #xref-ref-7-1 "View reference 7 in text" [27]: {openurl}?query=rft.jtitle%253DACM%2BQueue%26rft.volume%253D16%26rft.spage%253D1%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [28]: #xref-ref-8-1 "View reference 8 in text" [29]: {openurl}?query=rft.jtitle%253DNat.%2BMach.%2BIntell.%26rft.volume%253D1%26rft.spage%253D206%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [30]: #xref-ref-9-1 "View reference 9 in text" [31]: {openurl}?query=rft.jtitle%253DManage.%2BInf.%2BSyst.%2BQ.%26rft.volume%253D38%26rft.spage%253D73%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [32]: #xref-ref-10-1 "View reference 10 in text" [33]: {openurl}?query=rft.jtitle%253DHarv.%2BJ.%2BLaw%2BTechnol.%26rft.volume%253D31%26rft.spage%253D841%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [34]: #xref-ref-11-1 "View reference 11 in text" [35]: {openurl}?query=rft.jtitle%253DThe%2BJournal%2Bof%2Bfamily%2Bpractice%26rft.stitle%253DJ%2BFam%2BPract%26rft.aulast%253DHamm%26rft.auinit1%253DR.%2BM.%26rft.volume%253D47%26rft.issue%253D1%26rft.spage%253D44%26rft.epage%253D52%26rft.atitle%253DThe%2Baccuracy%2Bof%2Bpatients%2527%2Bjudgments%2Bof%2Bdisease%2Bprobability%2Band%2Btest%2Bsensitivity%2Band%2Bspecificity.%26rft_id%253Dinfo%253Apmid%252F9673608%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [36]: /lookup/external-ref?access_num=9673608&link_type=MED&atom=%2Fsci%2F373%2F6552%2F284.atom [37]: #xref-ref-12-1 "View reference 12 in text" [38]: {openurl}?query=rft.jtitle%253DNPJ%2BDigit.%2BMed.%26rft.volume%253D3%26rft.spage%253D53%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [39]: #xref-ref-13-1 "View reference 13 in text" [40]: {openurl}?query=rft.jtitle%253DLancet%2BDigit.%2BHealth%26rft.volume%253D3%26rft.spage%253D195e%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [41]: #xref-ref-14-1 "View reference 14 in text" [42]: {openurl}?query=rft.jtitle%253DSemin.%2BFetal%2BNeonatal%2BMed.%26rft.volume%253D23%26rft.spage%253D25%26rft_id%253Dinfo%253Apmid%252Fhttp%253A%252F%252Fwww.n%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [43]: #xref-ref-15-1 "View reference 15 in text" [44]: http://www.biofourmis.com/solutions/

A man unable to speak after a stroke has produced sentences through a system that reads electrical signals from speech production areas of his brain, researchers report this week. The approach has previously been used in nondisabled volunteers to reconstruct spoken or imagined sentences. But this first demonstration in a person who is paralyzed “tackles really the main issue that was left to be tackled—bringing this to the patients that really need it,” says Christian Herff, a computer scientist at Maastricht University who was not involved in the new work. The participant had a stroke more than a decade ago that left him with anarthria—an inability to control the muscles involved in speech. Because his limbs are also paralyzed, he communicates by selecting letters on a screen using small movements of his head, producing roughly five words per minute. To enable faster, more natural communication, neurosurgeon Edward Chang of the University of California, San Francisco, tested an approach that uses a computational model known as a deep-learning algorithm to interpret patterns of brain activity in the sensorimotor cortex, a brain region involved in producing speech ( Science , 4 January 2019, p. [14][1]). The approach has so far been tested in volunteers who have electrodes surgically implanted for nonresearch reasons such as to monitor epileptic seizures. In the new study, Chang's team temporarily removed a portion of the participant's skull and laid a thin sheet of electrodes smaller than a credit card directly over his sensorimotor cortex. To “train” a computer algorithm to associate brain activity patterns with the onset of speech and with particular words, the team needed reliable information about what the man intended to say and when. So the researchers repeatedly presented one of 50 words on a screen and asked the man to attempt to say it on cue. Once the algorithm was trained with data from the individual word task, the man tried to read sentences built from the same set of 50 words, such as “Bring my glasses, please.” To improve the algorithm's guesses, the researchers added a processing component called a natural language model, which uses common word sequences to predict the likely next word in a sentence. With that approach, the system only got about 25% of the words in a sentence wrong, they report this week in The New England Journal of Medicine . That's “pretty impressive,” says Stephanie Riès-Cornou, a neuroscientist at San Diego State University. (The error rate for chance performance would be 92%.) Because the brain reorganizes over time, it wasn't clear that speech production areas would give interpretable signals after more than 10 years of anarthria, notes Anne-Lise Giraud, a neuroscientist at the University of Geneva. The signals' preservation “is surprising,” she says. And Herff says the team made a “gigantic” step by generating sentences as the man was attempting to speak rather than from previously recorded brain data, as most studies have done. With the new approach, the man could produce sentences at a rate of up to 18 words per minute, Chang says. That's roughly comparable to the speed achieved with another brain-computer interface, described in Nature in May. That system decoded individual letters from activity in a brain area responsible for planning hand movements while a person who was paralyzed imagined handwriting. These speeds are still far from the 120 to 180 words per minute typical of conversational English, Riès-Cornou notes, but they far exceed what the participant can achieve with his head-controlled device. The system isn't ready for use in everyday life, Chang notes. Future improvements will include expanding its repertoire of words and making it wireless, so the user isn't tethered to a computer roughly the size of a minifridge. [1]: http://www.sciencemag.org/content/363/6422/14

Proteins are the minions of life, working alone or together to build, manage, fuel, protect, and eventually destroy cells. To function, these long chains of amino acids twist and fold and intertwine into complex shapes that can be slow, even impossible, to decipher. Scientists have dreamed of simply predicting a protein's shape from its amino acid sequence—an ability that would open a world of insights into the workings of life. “This problem has been around for 50 years; lots of people have broken their head on it,” says John Moult, a structural biologist at the University of Maryland, Shady Grove. But a practical solution is in their grasp. Several months ago, in a result hailed as a turning point, computational biologists showed that artificial intelligence (AI) could accurately predict protein shapes. Now, David Baker and Minkyung Baek at the University of Washington, Seattle, and their colleagues have made AI-based structure prediction more powerful and accessible. Their method, described online in Science this week, works on not just simple proteins, but also complexes of proteins, and its creators have made their computer code freely available. Since the method was posted online last month, the team has used it to model more than 4500 protein sequences submitted by other researchers. Savvas Savvides, a structural biologist at Ghent University, had tried six times to model a problematic protein. He says Baker's and Baek's program, called RoseTTAFold, “paved the way to a structure solution.” In fall of 2020, DeepMind, a U.K.-based AI company owned by Google, wowed the field with its structure predictions in a biennial competition ( Science , 4 December 2020, p. [1144][1]). Called Critical Assessment of Protein Structure Prediction (CASP), the competition uses structures newly determined using laborious lab techniques such as x-ray crystallography as benchmarks. DeepMind's program, AlphaFold2, did “really extraordinary things [predicting] protein structures with atomic accuracy,” says Moult, who organizes CASP. But for many structural biologists, AlphaFold2 was a tease: “Incredibly exciting but also very frustrating,” says David Agard, a structural biophysicist at the University of California, San Francisco. DeepMind has yet to publish its method and computer code for others to take advantage of. In mid-June, 3 days after the Baker lab posted its RoseTTAFold preprint, Demis Hassabis, DeepMind's CEO, tweeted that AlphaFold2's details were under review at a publication and the company would provide “broad free access to AlphaFold for the scientific community.” DeepMind's 30-minute presentation at CASP was enough to inspire Baek to develop her own approach. Like AlphaFold2, it uses AI's ability to discern patterns in vast databases of examples, generating ever more informed and accurate iterations as it learns. When given a new protein to model, RoseTTAFold proceeds along multiple “tracks.” One compares the protein's amino acid sequence with all similar sequences in protein databases. Another predicts pairwise interactions between amino acids within the protein, and a third compiles the putative 3D structure. The program bounces among the tracks to refine the model, using the output of each one to update the others. DeepMind's approach, although still under wraps, involves just two tracks, Baek and others believe. Gira Bhabha, a cell and structural biologist at New York University School of Medicine, says both methods work well. “Both the DeepMind and Baker lab advances are phenomenal and will change how we can use protein structure predictions to advance biology,” she says. A DeepMind spokesperson wrote in an email, “It's great to see examples such as this where the protein folding community is building on AlphaFold to work towards our shared goal of increasing our understanding of structural biology.” But AlphaFold2 solved the structures of only single proteins, whereas RoseTTAFold has also predicted complexes, such as the structure of the immune molecule interleukin-12 latched onto its receptor. Many biological functions depend on protein-protein interactions, says Torsten Schwede, a computational structural biologist at the University of Basel. “The ability to handle protein-protein complexes directly from sequence information makes it extremely attractive for many questions in biomedical research.” Baker concedes that, in general, AlphaFold2's structures are more accurate. But Savvides says the Baker lab's approach better captures “the essence and particularities of protein structure,” such as identifying strings of atoms sticking out of the sides of the protein—features key to interactions between proteins. Agard adds that Baker's and Baek's approach is faster and requires less computing power than DeepMind's, which relied on Google's massive servers. However, the DeepMind spokesperson wrote that its latest algorithm is more than 16 times as fast as the one it used at CASP in 2020. As a result, she wrote, “It's not clear to us that the system being described is an advance in speed.” Beginning on 1 June, Baker and Baek began to challenge their method by asking researchers to send in their most baffling protein sequences. Fifty-six head scratchers arrived in the first month, all of which have now predicted structures. Agard's group sent in an amino acid sequence with no known similar proteins. Within hours, his group got a protein model back “that probably saved us a year of work,” Agard says. Now, he and his team know where to mutate the protein to test ideas about how it functions. Because Baek's and Baker's group has released its computer code on the web, others can improve on it; the code has been downloaded 250 times since 1 July. “Many researchers will build their own structure prediction methods upon Baker's work,” says Jinbo Xu, a computational structural biologist at the Toyota Technological Institute at Chicago. Moult agrees: “When there's a breakthrough like this, 2 years later, everyone is doing it as well if not better than before.” [1]: http://www.sciencemag.org/content/370/6521/1144

Deep learning models keep getting bigger, and AI-powered devices keep getting smaller, which means there is plenty of room for innovation in the chips that make such applications possible. The race to make faster, more efficient AI chips has many contestants, and they range from the world's largest providers of cloud computing to small startups making chips for edge devices. Nvidia may hold the crown in the AI chip market right now, but many of these companies are hoping to outgun the GPU juggernaut with new, unique processor architectures. What follows are the 10 coolest AI chips of 2021 so far.

In this article, you will learn about a real-world example of the use of artificial intelligence in medical imaging. Read on to learn the details of how various deep learning models are combined to analyze images taken with a microscope. You may have read use cases where AI is used in medical diagnosis to differentiate between images showing pathological and non-pathological features (e.g. Capillaroscopy consists of observing the blood capillaries at the base of the patient's nails (nail bed) using a microscope called a capillaroscope and helps to determine the state of the patient's vascular system in a simple, fast and non-invasive way. Capillaroscopy is frequently used for the diagnosis and follow-up of some autoimmune diseases such as scleroderma, dermatomyositis or mixed connective tissue disease.

Artificial intelligence (AI) is the simulation of human actions and intelligence by computers. It is a combination of many technologies such as Machine Learning, Natural Language Processing and Applied Intelligence. Reactive machines don't have the ability to learn and adapt, hence they are not used for memory based scenarios and can be used for automatic responses to a limited set of inputs. Limited memory machines are capable of learning from historical data and make decisions. They use deep learning techniques for training and storing memory for these machines.