Tag Archives: Health

Using AI to identify the aggressiveness of prostate cancer

Prostate cancer diagnoses are common, with 1 in 9 men developing prostate cancer in their lifetime. A cancer diagnosis relies on specialized doctors, called pathologists, looking at biological tissue samples under the microscope for signs of abnormality in the cells. The difficulty and subjectivity of pathology diagnoses led us to develop an artificial intelligence (AI) system that can identify the aggressiveness of prostate cancer.

Since many prostate tumors are non-aggressive, doctors first obtain small samples (biopsies) to better understand the tumor for the initial cancer diagnosis. If signs of tumor aggressiveness are found, radiation or invasive surgery to remove the whole prostate may be recommended. Because these treatments can have painful side effects, understanding tumor aggressiveness is important to avoid unnecessary treatment.

Grading the biopsies

One of the most crucial factors in this process is to “grade” any cancer in the sample for how abnormal it looks, through a process called Gleason grading. Gleason grading involves first matching each cancerous region to one of three Gleason patterns, followed by assigning an overall “grade group” based on the relative amounts of each Gleason pattern in the whole sample. Gleason grading is a challenging task that relies on subjective visual inspection and estimation, resulting in pathologists disagreeing on the right grade for a tumor as much as 50 percent of the time. To explore whether AI could assist in this grading, we previously developed an algorithm that Gleason grades large samples (i.e. surgically-removed prostates) with high accuracy, a step that confirms the original diagnosis and informs patient prognosis.

Our research

In our recent work, “Development and Validation of a Deep Learning Algorithm for Gleason Grading of Prostate Cancer from Biopsy Specimens”, published in JAMA Oncology, we explored whether an AI system could accurately Gleason grade smaller prostate samples (biopsies). Biopsies are done during the initial part of prostate cancer care to get the initial cancer diagnosis and determine patient treatment, and so are more commonly performed than surgeries. However, biopsies can be more difficult to grade than surgical samples due to the smaller amount of tissue and unintended changes to the sample from tissue extraction and preparation process. The AI system we developed first “grades” each region of biopsy, and then summarizes the region-level classifications into an overall biopsy-level score.

Gleason grading

The first stage of the deep learning system Gleason grades every region in a biopsy. In this biopsy, green indicates Gleason pattern 3 while yellow indicates Gleason pattern 4.

Our results 

Given the complexity of Gleason grading, we worked with six experienced expert pathologists to evaluate the AI system. These experts, who have specialized training in prostate cancer and an average of 25 years of experience, determined the Gleason grades of 498 tumor samples. Highlighting how difficult Gleason grading is, a cohort of 19 “general” pathologists (without specialist training in prostate cancer) achieved an average accuracy of 58 percent on these samples. By contrast, our AI system’s accuracy was substantially higher at 72 percent. Finally, some prostate cancers have ambiguous appearances, resulting in disagreements even amongst experts. Taking this uncertainty into account, the deep learning system’s agreement rate with experts was comparable to the agreement rate between the experts themselves.

Cancer pathology workflow

Potential cancer pathology workflow augmented with AI-based assistive tools: a tumor sample is first collected and digitized using a high-magnification scanner. Next, the AI system provides a grade group for each sample.

These promising results indicate that the deep learning system has the potential to support expert-level diagnoses and expand access to high-quality cancer care. To evaluate if it could improve the accuracy and consistency of prostate cancer diagnoses, this technology needs to be validated as an assistive tool in further clinical studies and on larger and more diverse patient groups. However, we believe that AI-based tools could help pathologists in their work, particularly in situations where specialist expertise is limited.

Our research advancements in both prostate and breast cancer were the result of collaborations with the Naval Medical Center San Diego and support from Verily. Our appreciation also goes to several institutions that provided access to de-identified data, and many pathologists who provided advice or reviewed prostate cancer samples. We look forward to future research and investigation into how our technology can be best validated, designed and used to improve patient care and cancer outcomes.

Exploring Faster Screening with Fewer Tests via Bayesian Group Testing

Posted by Marco Cuturi and Jean-Philippe Vert, Research Scientists, Google Research, Brain Team

How does one find a needle in a haystack? At the turn of World War II, that question took on a very concrete form when doctors wondered how to efficiently detect diseases among those who had been drafted into the war effort. Inspired by this challenge, Robert Dorfman, a young statistician at that time (later to become Harvard professor of economics), proposed in a seminal paper a 2-stage approach to detect infected individuals, whereby individual blood samples first are pooled in groups of four before being tested for the presence or absence of a pathogen. If a group is negative, then it is safe to assume that everyone in the group is free of the pathogen. In that case, the reduction in the number of required tests is substantial: an entire group of four people has been cleared with a single test. On the other hand, if a group tests positive, which is expected to happen rarely if the pathogen’s prevalence is small, at least one or more people within that group must be positive; therefore, a few more tests to determine the infected individuals are needed.
Left: Sixteen individual tests are required to screen 16 people — only one person’s test is positive, while 15 return negative. Right: Following Dorfman’s procedure, samples are pooled into four groups of four individuals, and tests are executed on the pooled samples. Because only the second group tests positive, 12 individuals are cleared and only those four belonging to the positive group need to be retested. This approach requires only eight tests, instead of the 16 needed for an exhaustive testing campaign.
Dorfman’s proposal triggered many follow-up works with connections to several areas in computer science, such as information theory, combinatorics or compressive sensing, and several variants of his approach have been proposed, notably those leveraging binary splitting or side knowledge on individual infection probability rates. The field has grown to the extent that several sub-problems are recognized and deserving of an entire literature on their own. Some algorithms are tailored for the noiseless case in which tests are perfectly reliable, whereas some consider instead the more realistic case where tests are noisy and may produce false negatives or positives. Finally, some strategies are adaptive, proposing groups based on test results already observed (including Dorfman’s, since it proposes to re-test individuals that appeared in positive groups), whereas others stick to a non-adaptive setting in which groups are known beforehand or drawn at random.

In “Noisy Adaptive Group Testing using Bayesian Sequential Experimental Design”, we present an approach to group testing that can operate in a noisy setting (i.e., where tests can be mistaken) to decide adaptively by looking at past results which groups to test next, with the goal to converge on a reliable detection as quickly, and with as few tests, as possible. Large scale simulations suggest that this approach may result in significant improvements over both adaptive and non-adaptive baselines, and are far more efficient than individual tests when disease prevalence is low. As such, this approach is particularly well suited for situations that require large numbers of tests to be conducted with limited resources, as may be the case for pandemics, such as that corresponding to the spread of COVID-19. We have open-sourced the code to the community through our GitHub repo.

Noisy and Adaptive Group Testing in a Non-Asymptotic Regime
A group testing strategy is an algorithm that is tasked with guessing who, among a list of n people, carries a particular pathogen. To do so, the strategy provides instructions for pooling individuals into groups. Assuming a laboratory can execute k tests at a time, the strategy will form a k ⨉ n pooling matrix that defines these groups. Once the tests are carried out, the results are used to decide whether sufficient information has been gathered to determine who is or is not infected, and if not, how to form new groups for another round of testing.

We designed a group testing approach for the realistic setting where the testing strategy can be adaptive and where tests are noisy — the probability that the test of an infected sample is positive (sensitivity) is less than 100%, as is the specificity, the probability that a non-infected sample returns negative.

Screening More People with Fewer Tests Using Bayesian Optimal Experimental Design
The strategy we propose proceeds the way a detective would investigate a case. They first form several hypotheses about who may or may not be infected, using evidence from all tests (if any) that have been carried out so far and prior information on the infection rate (a). Using these hypotheses, our detectives produce an actionable item to continue the investigation, namely a next wave of groups that may help in validating or invalidating as many hypotheses as possible (b), and then loop back to (a) until the set of plausible hypotheses is small enough to unambiguously identify the target of the search. More precisely,
  1. Given a population of n people, an infection state is a binary vector of length n that describes who is infected (marked with a 1), and who is not (marked with a 0). At a certain time, a population is in a given state (most likely a few 1’s and mostly 0’s). The goal of group testing is to identify that state using as few tests as possible. Given a prior belief on the infection rate (the disease is rare) and test results observed so far (if any), we expect that only a small share of those infection states will be plausible. Rather than evaluating the plausibility of all 2n possible states (an extremely large number even for small n), we resort to a more efficient method to sample plausible hypotheses using a sequential Monte Carlo (SMC) sampler. Although quite costly by common standards (a few minutes using a GPU in our experimental setup), we show in this work that SMC samplers remain tractable even for large n, opening new possibilities for group testing. In short, in return for a few minutes of computations, our detectives get an extensive list of thousands of relevant hypotheses that may explain tests observed so far.

  2. Equipped with a relevant list of hypotheses, our strategy proceeds, as detectives would, by selectively gathering additional evidence. If k tests can be carried out at the next iteration, our strategy will propose to test k new groups, which are computed using the framework of Bayesian optimal experimental design. Intuitively, if k=1 and one can only propose a single new group to test, there would be clear advantage in building that group such that its test outcome is as uncertain as possible, i.e., with a probability that it returns positive as close to 50% as possible, given the current set of hypotheses. Indeed, to progress in an investigation, it is best to maximize the surprise factor (or information gain) provided by new test results, as opposed to using them to confirm further what we already hold to be very likely. To generalize that idea to a set of k>1 new groups, we score this surprise factor by computing the mutual information of these “virtual” group tests vs. the distribution of hypotheses. We also consider a more involved approach that computes the expected area under the ROC curve (AUC) one would obtain from testing these new groups using the distribution of hypotheses. The maximization of these two criteria is carried out using a greedy approach, resulting in two group selectors, GMIMAX and GAUCMAX (greedy maximization of mutual information or AUC, respectively).
The interaction between a laboratory (wet_lab) carrying out testing, and our strategy, composed of a sampler and a group selector, is summarized in the following drawing, which uses names of classes implemented in our open source package.
Our group testing framework describes an interaction between a testing environment, the wet_lab, whose pooled test results are used by the sampler to draw thousands of plausible hypotheses on the infection status of all individuals. These hypotheses are then used by an optimization procedure, group_selector, that figures out what groups may be the most relevant to test in order to narrow down on the true infection status. Once formed, these new groups are then tested again, closing the loop. At any point in the procedure, the hypotheses formed by the sampler can be averaged to obtain the average probability of infection for each patient. From these probabilities, a decision on whether a patient is infected or not can be done by thresholding these probabilities at a certain confidence level.
Benchmarking
We benchmarked our two strategies GMIMAX and GAUCMAX against various baselines in a wide variety of settings (infection rates, test noise levels), reporting performance as the number of tests increases. In addition to simple Dorfman strategies, the baselines we considered included a mix of non-adaptive strategies (origami assays, random designs) complemented at later stages with the so-called informative Dorfman approach. Our approaches significantly outperform the others in all settings.
We executed 5000 simulations on a sample population of 70 individuals with an infection rate of 2%. We have assumed sensitivity/specificity values of 85% / 97% for tests with groups of maximal size 10, which are representative of current PCR machines. This figure demonstrates that our approach outperforms the other baselines with as few as 24 tests (up to 8 tests used in 3 cycles), including both adaptive and non-adaptive varieties, and performs significantly better than individual tests (plotted in the sensitivity/specificity plane as a hexagon, requiring 70 tests), highlighting the savings potential offered by group testing. See preprint for other setups.
Conclusion
Screening a population for a pathogen is a fundamental problem, one that we currently face during the current COVID-19 epidemic. Seventy years ago, Dorfman proposed a simple approach currently adopted by various institutions. Here, we have proposed a method to extend the basic group testing approach in several ways. Our first contribution is to adopt a probabilistic perspective, and form thousands of plausible hypotheses of infection distributions given test outcomes, rather than trust test results to be 100% reliable as Dorfman did. This perspective allows us to seamlessly incorporate additional prior knowledge on infection, such as when we suspect some individuals to be more likely than others to carry the pathogen, based for instance on contact tracing data or answers to a questionnaire. This provides our algorithms, which can be compared to detectives investigating a case, the advantage of knowing what are the most likely infection hypotheses that agree with prior beliefs and tests carried out so far. Our second contribution is to propose algorithms that can take advantage of these hypotheses to form new groups, and therefore direct the gathering of new evidence, to narrow down as quickly as possible to the "true" infection hypothesis, and close the case with as little testing effort as possible.

Acknowledgements
We would like to thank our collaborators on this work, Olivier Teboul, in particular, for his help preparing figures, as well as Arnaud Doucet and Quentin Berthet. We also thank Kevin Murphy and Olivier Bousquet (Google) for their suggestions at the earliest stages of this project, as well as Dan Popovici for his unwavering support pushing this forward; Ignacio Anegon, Jeremie Poschmann and Laurent Tesson (INSERM) for providing us background information on RT-PCR tests and Nicolas Chopin (CREST) for giving guidance on his work to define SMCs for binary spaces.

Source: Google AI Blog


Unlocking the "Chemome" with DNA-Encoded Chemistry and Machine Learning

Posted by Patrick Riley, Principal Engineer, Accelerated Science Team, Google Research

Much of the development of therapeutics for human disease is built around understanding and modulating the function of proteins, which are the main workhorses of many biological activities. Small molecule drugs such as ibuprofen often work by inhibiting or promoting the function of proteins or their interactions with other biomolecules. Developing useful “virtual screening” methods where potential small molecules can be evaluated computationally rather than in a lab, has long been an area of research. However, the persistent challenge is to build a method that works well enough across a wide range of chemical space to be useful for finding small molecules with physically verified useful interaction with a protein of interest, i.e., “hits”.

In “Machine learning on DNA-encoded libraries: A new paradigm for hit-finding”, recently published in the Journal of Medicinal Chemistry, we worked in collaboration with X-Chem Pharmaceuticals to demonstrate an effective new method for finding biologically active molecules using a combination of physical screening with DNA-encoded small molecule libraries and virtual screening using a graph convolutional neural network (GCNN). This research has led to the creation of the Chemome initiative, a cooperative project between our Accelerated Science team and ZebiAI that will enable the discovery of many more small molecule chemical probes for biological research.

Background on Chemical Probes
Making sense of the biological networks that support life and produce disease is an immensely complex task. One approach to study these processes is using chemical probes, small molecules that aren’t necessarily useful as drugs, but that selectively inhibit or promote the function of specific proteins. When you have a biological system to study (such as cancer cells growing in a dish), you can add the chemical probe at a specific time and observe how the biological system responds differently when the targeted protein has increased or decreased activity. But, despite how useful chemical probes are for this kind of basic biomedical research, only 4% of human proteins have a known chemical probe available.

The process of finding chemical probes begins similarly to the earliest stages of small molecule drug discovery. Given a protein target of interest, the space of small molecules is scanned to find “hit” molecules that can be further tested. Robotic assisted high throughput screening where up to hundred of thousands or millions of molecules are physically tested is a cornerstone of modern drug research. However, the number of small molecules you can easily purchase (1.2x109) is much larger than that, which in turn is much smaller than the number of small drug like molecules (estimates from 1020 to 1060). “Virtual screening” could possibly quickly and efficiently search this vast space of potentially synthesizable molecules and greatly speed up the discovery of therapeutic compounds.

DNA-Encoded Small Molecule Library Screening
The physical part of the screening process uses DNA-encoded small molecule libraries (DELs), which contain many distinct small molecules in one pool, each of which is attached to a fragment of DNA serving as a unique barcode for that molecule. While this basic technique has been around for several decades, the quality of the library and screening process is key to producing meaningful results.

DELs are a very clever idea to solve a biochemical challenge, which is how to collect small molecules into one place with an easy way to identify each. The key is to use DNA as a barcode to identify each molecule, similar to Nobel Prize winning phage display technology. First, one generates many chemical fragments, each with a unique DNA barcode attached, along with a common chemical handle (the NH2 in this case). The results are then pooled and split into separate reactions where a set of distinct chemical fragments with another common chemical handle (e.g., OH) are added. The chemical fragments from the two steps react and fuse together at the common chemical handles. The DNA fragments are also connected to build one continuous barcode for each molecule. The net result is that by performing 2N operations, one gets N2 unique molecules, each of which is identified by its own unique DNA barcode. By using more fragments or more cycles, it’s relatively easy to make libraries with millions or even billions of distinct molecules.
An overview of the process of creating a DNA encoded small molecule library. First, DNA “barcodes” (represented here with numbered helices) are attached to small chemical fragments (the blue shapes) which expose a common chemical “handle” (e.g. the NH2 shown here). When mixed with other chemical fragments (the orange shapes) each of which has another exposed chemical “handle” (the OH) with attached DNA fragments, reactions merge the sets of chemical and DNA fragments, resulting in a voluminous library of small molecules of interest, each with a unique DNA “barcode”.
Once the library has been generated, it can be used to find the small molecules that bind to the protein of interest by mixing the DEL together with the protein and washing away the small molecules that do not attach. Sequencing the remaining DNA barcodes produces millions of individual reads of DNA fragments, which can then be carefully processed to estimate which of the billions of molecules in the original DEL interact with the protein.

Machine Learning on DEL Data
Given the physical screening data returned for a particular protein, we build an ML model to predict whether an arbitrarily chosen small molecule will bind to that protein. The physical screening with the DEL provides positive and negative examples for an ML classifier. To simplify slightly, the small molecules that remain at the end of the screening process are positive examples and everything else are negative examples. We use a graph convolutional neural network, which is a type of neural network specially designed for small graph-like inputs, such as the small molecules in which we are interested.

Results
We physically screened three diverse proteins using DEL libraries: sEH (a hydrolase), ERα (a nuclear receptor), and c-KIT (a kinase). Using the DEL-trained models, we virtually screened large make-on-demand libraries from Mcule and an internal molecule library at X-Chem to identify a diverse set of molecules predicted to show affinity with each target. We compared the results of the GCNN models to a random forest (RF) model, a common method for virtual screening that uses standard chemical fingerprints, which we use as baseline. We find that the GCNN model significantly outperforms the RF model in discovering more potent candidates.
Fraction of molecules (“hit rates”) from those tested showing various levels of activity, comparing predictions from two different machine learned models (a GCNN and random forests, RF) on three distinct protein targets. The color scale on the right uses a common metric IC50 for representing the potency of a molecule. nM means “nanomolar” and µM means “micromolar”. Smaller values / darker colors are generally better molecules. Note that typical virtual screening approaches not built with DEL data normally only reach a few percent on this scale.
Importantly, unlike many other uses of virtual screening, the process to select the molecules to test was automated or easily automatable given the results of the model, and we did not rely on review and selection of the most promising molecules by a trained chemist. In addition, we tested almost 2000 molecules across the three targets, the largest published prospective study of virtual screening of which we are aware. While providing high confidence on the hit rates above, this also allows one to carefully examine the diversity of hits and the usefulness of the model for molecules near and far from the training set.

The Chemome Initiative
ZebiAI Therapeutics was founded based on the results of this research and has partnered with our team and X-Chem Pharmaceuticals to apply these techniques to efficiently deliver new chemical probes to the research community for human proteins of interest, an effort called the Chemome Initiative.

As part of the Chemome Initiative, ZebiAI will work with researchers to identify proteins of interest and source screening data, which our team will use to build machine learning models and make predictions on commercially available libraries of small molecules. ZebiAI will provide the predicted molecules to researchers for activity testing and will collaborate with researchers to advance some programs through discovery. Participation in the program requires that the validated hits be published within a reasonable time frame so that the whole community can benefit. While more validation must be done to make the hit molecules useful as chemical probes, especially for specifically targeting the protein of interest and the ability to function correctly in common assays, having potent hits is a big step forward in the process.

We’re excited to be a part of the Chemome Initiative enabled by the effective ML techniques described here and look forward to its discovery of many new chemical probes. We expect the Chemome will spur significant new biological discoveries and ultimately accelerate new therapeutic discovery for the world.

Acknowledgements
This work represents a multi-year effort between the Accelerated Science Team and X-Chem Pharmaceuticals with many people involved. This project would not have worked without the combined diverse skills of biologists, chemists, and ML researchers. We should especially acknowledge Eric Sigel (of X-Chem, now at ZebiAI) and Kevin McCloskey (of Google), the first authors on the paper and Steve Kearnes (of Google) for core modelling ideas and technical work.

Source: Google AI Blog


Learn more about anxiety with a self-assessment on Search

Editor’s note: This post is authored by Daniel H. Gillison, Jr., CEO of The National Alliance on Mental Illness.

Anxiety disorders affect 48 million adults in the U.S. Anxiety presents itself as a wide range of symptoms, and can be a result of biological factors or triggered by a change in environment or exposure to a stressful event. With COVID-19 introducing new points of stress, communities are seeing a rise in mental health issues and needs. New Census Bureau data released last week shows that a third of Americans are now showing signs of clinical anxiety or depression.

The National Alliance on Mental Illness (NAMI) is the nation’s largest grassroots mental health organization and we’re partnering with Google to provide access to mental health resources. Starting today when people in the U.S. search on Google for information about anxiety, we’ll provide access to a clinically-validated questionnaire called the GAD-7 (Generalized Anxiety Disorder-7). The GAD-7 will show up in the knowledge panel—the box of information that displays key facts when you search for something—and also has medically-validated information about anxiety, including symptoms and common treatments.

Anxiety self-assessment

This seven-question survey covers many of the same questions a health professional may ask, and your answers are private and secure (Google does not collect or share answers or results from the questionnaire). The GAD-7 helps people understand how their self-reported anxiety symptoms map to anxiety levels of people who completed the same questionnaire. The tool also provides access to resources developed by NAMI so people can learn more and seek help when needed. 

Anxiety self-assessment results

The GAD-7 is the third mental health screener available on Google Search. We’ve previously partnered with Google so that people who search for information on depression and PTSD can access relevant clinically-validated questionnaires that provide more information and links to resources about those conditions. The self-assessments are currently available in the U.S., and Google hopes to make them available in additional countries over time.

Anxiety can show up as a wide range of physical and emotional symptoms, and it can take decades for people who first experience symptoms to get treatment. By providing access to authoritative information, and the resources and tools to learn more about anxiety, we hope to empower more people to take action and seek help.

Source: Search


Learn more about anxiety with a self-assessment on Search

Editor’s note: This post is authored by Daniel H. Gillison, Jr., CEO of The National Alliance on Mental Illness.

Anxiety disorders affect 48 million adults in the U.S. Anxiety presents itself as a wide range of symptoms, and can be a result of biological factors or triggered by a change in environment or exposure to a stressful event. With COVID-19 introducing new points of stress, communities are seeing a rise in mental health issues and needs. New Census Bureau data released last week shows that a third of Americans are now showing signs of clinical anxiety or depression.

The National Alliance on Mental Illness (NAMI) is the nation’s largest grassroots mental health organization and we’re partnering with Google to provide access to mental health resources. Starting today when people in the U.S. search on Google for information about anxiety, we’ll provide access to a clinically-validated questionnaire called the GAD-7 (Generalized Anxiety Disorder-7). The GAD-7 will show up in the knowledge panel—the box of information that displays key facts when you search for something—and also has medically-validated information about anxiety, including symptoms and common treatments.

Anxiety self-assessment

This seven-question survey covers many of the same questions a health professional may ask, and your answers are private and secure (Google does not collect or share answers or results from the questionnaire). The GAD-7 helps people understand how their self-reported anxiety symptoms map to anxiety levels of people who completed the same questionnaire. The tool also provides access to resources developed by NAMI so people can learn more and seek help when needed. 

Anxiety self-assessment results

The GAD-7 is the third mental health screener available on Google Search. We’ve previously partnered with Google so that people who search for information on depression and PTSD can access relevant clinically-validated questionnaires that provide more information and links to resources about those conditions. The self-assessments are currently available in the U.S., and Google hopes to make them available in additional countries over time.

Anxiety can show up as a wide range of physical and emotional symptoms, and it can take decades for people who first experience symptoms to get treatment. By providing access to authoritative information, and the resources and tools to learn more about anxiety, we hope to empower more people to take action and seek help.

Source: Search


Exposure Notification API launches to support public health agencies

Note: The following is a joint statement from Apple and Google.

One of the most effective techniques that public health officials have used during outbreaks is called contact tracing. Through this approach, public health officials contact, test, treat and advise people who may have been exposed to an affected person. One new element of contact tracing is Exposure Notifications: using privacy-preserving digital technology to tell someone they may have been exposed to the virus. Exposure Notification has the specific goal of rapid notification, which is especially important to slowing the spread of the disease with a virus that can be spread asymptomatically.   

To help, Apple and Google cooperated to build Exposure Notifications technology that will enable apps created by public health agencies to work more accurately, reliably and effectively across both Android phones and iPhones. Over the last several weeks, our two companies have worked together, reaching out to public health officials, scientists, privacy groups and government leaders all over the world to get their input and guidance. 

Starting today, our Exposure Notifications technology is available to public health agencies on both iOS and Android. What we’ve built is not an app—rather public health agencies will incorporate the API into their own apps that people install. Our technology is designed to make these apps work better. Each user gets to decide whether or not to opt-in to Exposure Notifications; the system does not collect or use location from the device; and if a person is diagnosed with COVID-19, it is up to them whether or not to report that in the public health app. User adoption is key to success and we believe that these strong privacy protections are also the best way to encourage use of these apps.  

Today, this technology is in the hands of public health agencies across the world who will take the lead and we will continue to support their efforts. 

Exposure Notification API launches to support public health agencies

Note: The following is a joint statement from Apple and Google.

One of the most effective techniques that public health officials have used during outbreaks is called contact tracing. Through this approach, public health officials contact, test, treat and advise people who may have been exposed to an affected person. One new element of contact tracing is Exposure Notifications: using privacy-preserving digital technology to tell someone they may have been exposed to the virus. Exposure Notification has the specific goal of rapid notification, which is especially important to slowing the spread of the disease with a virus that can be spread asymptomatically.   

To help, Apple and Google cooperated to build Exposure Notifications technology that will enable apps created by public health agencies to work more accurately, reliably and effectively across both Android phones and iPhones. Over the last several weeks, our two companies have worked together, reaching out to public health officials, scientists, privacy groups and government leaders all over the world to get their input and guidance. 

Starting today, our Exposure Notifications technology is available to public health agencies on both iOS and Android. What we’ve built is not an app—rather public health agencies will incorporate the API into their own apps that people install. Our technology is designed to make these apps work better. Each user gets to decide whether or not to opt-in to Exposure Notifications; the system does not collect or use location from the device; and if a person is diagnosed with COVID-19, it is up to them whether or not to report that in the public health app. User adoption is key to success and we believe that these strong privacy protections are also the best way to encourage use of these apps.  

Today, this technology is in the hands of public health agencies across the world who will take the lead and we will continue to support their efforts. 

Source: Android


How AI could predict sight-threatening eye conditions

Age-related macular degeneration (AMD) is the biggest cause of sight loss in the UK and USA and is the third largest cause of blindness across the globe. The latest research collaboration between Google Health, DeepMind and Moorfields Eye Hospital is published in Nature Medicine today. It shows that artificial intelligence (AI) has the potential to not only spot the presence of AMD in scans, but also predict the disease’s progression. 

Vision loss and wet AMD

Around 75 percent of patients with AMD have an early form called “dry” AMD that usually has relatively mild impact on vision. A minority of patients, however, develop the more sight-threatening form of AMD called exudative, or “wet” AMD. This condition affects around 15 percent of patients, and occurs when abnormal blood vessels develop underneath the retina. These vessels can leak fluid, which can cause permanent loss of central vision if not treated early enough.

Macular degeneration mainly affects central vision, causing "blind spots" directly ahead

Macular degeneration mainly affects central vision, causing "blind spots" directly ahead (Macular Society).

Wet AMD often affects one eye first, so patients become heavily reliant upon their unaffected eye to maintain their normal day-to-day living. Unfortunately, 20 percent of these patientswill go on to develop wet AMD in their other eye within two years. The condition often develops suddenly but further vision loss can be slowed with treatments if wet AMD is recognized early enough. Ophthalmologists regularly monitor their patients for signs of wet AMD using 3D optical coherence tomography (OCT) images of the retina.

The period before wet AMD develops is a critical window for preventive treatment, which is why we set out to build a system that could predict whether a patient with wet AMD in one eye will go on to develop the condition in their second eye. This is a novel clinical challenge, since it’s not a task that is routinely performed.

How AI could predict the development of wet AMD

In collaboration with colleagues at DeepMind and Moorfields Eye Hospital NHS Foundation Trust, we’ve developed an artificial intelligence (AI) model that has the potential to predict whether a patient will develop wet AMD within six months. In the future, this system could potentially help doctors plan studies of earlier intervention, as well as contribute more broadly to clinical understanding of the disease and disease progression. 

We trained and tested our model using a retrospective, anonymized dataset of 2,795 patients. These patients had been diagnosed with wet AMD in one of their eyes, and were attending one of seven clinical sites for regular OCT imaging and treatment. For each patient, our researchers worked with retinal experts to review all prior scans for each eye and determine the scan when wet AMD was first evident. In collaboration with our colleagues at DeepMind we developed an AI system composed of two deep convolutional neural networks, one taking the raw 3D scan as input and the other, built on our previous work, taking a segmentation map outlining the types of tissue present in the retina. Our prediction system used the raw scan and tissue segmentations to estimate a patient’s risk of progressing to wet AMD within the next six months. 

To test the system, we presented the model with a single, de-identified scan and asked it to predict whether there were any signs that indicated the patient would develop wet AMD in the following six months. We also asked six clinical experts—three retinal specialists and three optometrists, each with at least ten years’ experience—to do the same. Predicting the possibility of a patient developing wet AMD is not a task that is usually performed in clinical practice so this is the first time, to our knowledge, that experts have been assessed on this ability. 

While clinical experts performed better than chance alone, there was substantial variability between their assessments. Our system performed as well as, and in certain cases better than, these clinicians in predicting wet AMD progression. This highlights its potential use for informing studies in the future to assess or help develop treatments to prevent wet AMD progression.

Future work could address several limitations of our research. The sample was representative of practice at multiple sites of the world’s largest eye hospital, but more work is needed to understand the model performance in different demographics and clinical settings. Such work should also understand the impact of unstudied factors—such as additional imaging tests—that might be important for prediction, but were beyond the scope of this work.

What’s next 

These findings demonstrate the potential for AI to help improve understanding of disease progression and predict the future risk of patients developing sight-threatening conditions. This, in turn, could help doctors study preventive treatments.

This is the latest stage in our partnership with Moorfields Eye Hospital NHS Foundation Trust, a long-standing relationship that transitioned from DeepMind to Google Health in September 2019. Our previous collaborations include using AI to quickly detect eye conditions, and showing how Google Cloud AutoML might eventually help clinicians without prior technical experience to accurately detect common diseases from medical images. 

This is early research, rather than a product that could be implemented in routine clinical practice. Any future product would need to go through rigorous prospective clinical trials and regulatory approvals before it could be used as a tool for doctors. This work joins a growing body of research in the area of developing predictive models that could inform clinical research and trials. In line with this, Moorfields will be making the dataset available through the Ryan Initiative for Macular Research. We hope that models like ours will be able to support this area of work to improve patient outcomes. 


How AI could predict sight-threatening eye conditions

Age-related macular degeneration (AMD) is the biggest cause of sight loss in the UK and USA and is the third largest cause of blindness across the globe. The latest research collaboration between Google Health, DeepMind and Moorfields Eye Hospital is published in Nature Medicine today. It shows that artificial intelligence (AI) has the potential to not only spot the presence of AMD in scans, but also predict the disease’s progression. 

Vision loss and wet AMD

Around 75 percent of patients with AMD have an early form called “dry” AMD that usually has relatively mild impact on vision. A minority of patients, however, develop the more sight-threatening form of AMD called exudative, or “wet” AMD. This condition affects around 15 percent of patients, and occurs when abnormal blood vessels develop underneath the retina. These vessels can leak fluid, which can cause permanent loss of central vision if not treated early enough.

Macular degeneration mainly affects central vision, causing "blind spots" directly ahead

Macular degeneration mainly affects central vision, causing "blind spots" directly ahead (Macular Society).

Wet AMD often affects one eye first, so patients become heavily reliant upon their unaffected eye to maintain their normal day-to-day living. Unfortunately, 20 percent of these patientswill go on to develop wet AMD in their other eye within two years. The condition often develops suddenly but further vision loss can be slowed with treatments if wet AMD is recognized early enough. Ophthalmologists regularly monitor their patients for signs of wet AMD using 3D optical coherence tomography (OCT) images of the retina.

The period before wet AMD develops is a critical window for preventive treatment, which is why we set out to build a system that could predict whether a patient with wet AMD in one eye will go on to develop the condition in their second eye. This is a novel clinical challenge, since this it’s not a task that is routinely performed.

How AI could predict the development of wet AMD

In collaboration with colleagues at DeepMind and Moorfields Eye Hospital NHS Foundation Trust, we’ve developed an artificial intelligence (AI) model that has the potential to predict whether a patient will develop wet AMD within six months. In the future, this system could potentially help doctors plan studies of earlier intervention, as well as contribute more broadly to clinical understanding of the disease and disease progression. 

We trained and tested our model using a retrospective, anonymized dataset of 2,795 patients. These patients had been diagnosed with wet AMD in one of their eyes, and were attending one of seven clinical sites for regular OCT imaging and treatment. For each patient, our researchers worked with retinal experts to review all prior scans for each eye and determine the scan when wet AMD was first evident. In collaboration with our colleagues at DeepMind we developed an AI system composed of two deep convolutional neural networks, one taking the raw 3D scan as input and the other, built on our previous work, taking a segmentation map outlining the types of tissue present in the retina. Our prediction system used the raw scan and tissue segmentations to estimate a patient’s risk of progressing to wet AMD within the next six months. 

To test the system, we presented the model with a single, de-identified scan and asked it to predict whether there were any signs that indicated the patient would develop wet AMD in the following six months. We also asked six clinical experts—three retinal specialists and three optometrists, each with at least ten years’ experience—to do the same. Predicting the possibility of a patient developing wet AMD is not a task that is usually performed in clinical practice so this is the first time, to our knowledge, that experts have been assessed on this ability. 

While clinical experts performed better than chance alone, there was substantial variability between their assessments. Our system performed as well as, and in certain cases better than, these clinicians in predicting wet AMD progression. This highlights its potential use for informing studies in the future to assess or help develop treatments to prevent wet AMD progression.

Future work could address several limitations of our research. The sample was representative of practice at multiple sites of the world’s largest eye hospital, but more work is needed to understand the model performance in different demographics and clinical settings. Such work should also understand the impact of unstudied factors—such as additional imaging tests—that might be important for prediction, but were beyond the scope of this work.

What’s next 

These findings demonstrate the potential for AI to help improve understanding of disease progression and predict the future risk of patients developing sight-threatening conditions. This, in turn, could help doctors study preventive treatments.

This is the latest stage in our partnership with Moorfields Eye Hospital NHS Foundation Trust, a long-standing relationship that transitioned from DeepMind to Google Health in September 2019. Our previous collaborations include using AI to quickly detect eye conditions, and showing how Google Cloud AutoML might eventually help clinicians without prior technical experience to accurately detect common diseases from medical images. 

This is early research, rather than a product that could be implemented in routine clinical practice. Any future product would need to go through rigorous prospective clinical trials and regulatory approvals before it could be used as a tool for doctors. This work joins a growing body of research in the area of developing predictive models that could inform clinical research and trials. In line with this, Moorfields will be making the dataset available through the Ryan Initiative for Macular Research. We hope that models like ours will be able to support this area of work to improve patient outcomes. 


Dr. Karen DeSalvo on “putting information first” during COVID-19

Dr. Karen DeSalvo knows how to deal with a crisis. She was New Orleans Health Commissioner following Hurricane Katrina and a senior official at the Department of Health and Human Services when Ebola broke out. And now, as Google’s Chief Health Officer, she’s become the company’s go-to medical expert, advising our leaders on how to react to the coronavirus. Dr. DeSalvo has been a voice of reassurance for Googlers, but her expertise is helpful outside of Google, too. I recently spoke to Dr. DeSalvo about how we’ll get through the crisis, what Google is doing to help and what makes her optimistic despite the challenges we face. 


How is the coronavirus different from other public health crises you’ve dealt with? 
In my work in New Orleans, whether it was a hurricane, a fire or a power outage, we drew resources from other parts of the country if we needed help. In this case, the entire world has been impacted. Everyone is living with uncertainty, disrupted supply chains, impacts on travel and social infrastructure. While this creates a sense of community that I hope will continue beyond the pandemic, the downside is that we have less opportunity to send assistance to other places. Where there is opportunity, we’ve seen people paying it forward, like when California deployed ventilators to the East Coast. The sense of community that grows out of any disaster is the bright spot, for me.


How are industries sharing ideas and research in this global crisis?
Physicians are using technology to talk to each other constantly about what they’re seeing and doing, and in prior outbreaks this real-time communication wasn’t possible. It makes a huge difference in clinical care. In the medical community, you sometimes have to pay for a journal article. But now if you want to read about COVID-19, it’s free for any researcher, scientist, clinician or layperson. That’s putting information first, putting knowledge and science above proprietary interest. 

It’s happening in science, too. For instance, there’s a collaboration between competitors in the private sector on designing trials and assessing the outcome of drugs and vaccines. At Google, our Deepmind colleagues were able to use quantum computing to show protein folding, helping advance the thinking about therapeutics and vaccines. I don’t think we’ve seen this spirit of collaboration in the history of science, and it’s one of the reasons I’m so optimistic. 


What is Google doing to help curb misinformation?
In this historic moment, access to the right information at the right time will save lives. Period. This is why our Search teams design our ranking systems to promote the most relevant and reliable information available. We build these protections in advance so they’re ready when a crisis hits, and this approach serves as a strong defense against misinformation.  


When COVID-19 began to escalate, we built features on top of those fundamental protections to help people find information from local health authorities. We initially launched an SOS alert with the World Health Organization to make resources about COVID-19 easily discoverable. This has evolved into an expanded Search experience, providing easy access to more authoritative information, alongside new data and visualizations. 


We’re surfacing content that’s accessible to a whole range of communities, and there’s constant vigilance to remove misinformation on platforms like YouTube—this includes videos or other information that could be harmful to people.

Search COVID GIF

COVID-19 information on Search. 

What does it mean to be Google’s Chief Health Officer?
My role is to bring a holistic view of emotional, physical and social health and well-being to Google’s products and services, particularly under Google Health. During this pandemic, my team has also thought about how Google can assist public health efforts. This has meant anything from the Community Mobility Reports, a tool to help measure the impact of social distancing, to building playlists in partnership with YouTube geared towards clinicians, and showing testing sites for COVID-19 all over the world.


In the general public, what behaviors or mentalities have arisen that should continue in the future?
First, there are fundamental ways to reduce the transmission of communicable diseases like the flu or, in some communities, measles or tuberculosis. If you’re able to, it’s important to stay home if you’re sick, wash your hands, cough into your elbow—I call these the “Grandma rules.” Second, there are a lot of components to health: social health, emotional well-being, financial stability. Health is driven by more than just medical care, and this is a moment for us to remember that a holistic approach matters. 


What should business owners consider for when restrictions begin to lift?
They need to prepare for a world in which employees can work remotely as much as possible. Policies will still recommend social distancing, but we also need to create an environment where people who are sick feel comfortable staying home. That’s not realistic for every small business, so paying attention to the basic hygiene stuff—Do the Five—is also important. 


After Katrina, there was this time when the world was paying attention and trying to help, but the emotional and social impact on our community lasted for months. There will be some of that after this pandemic, because you can’t just flip a switch and have people go back to work. That’s the important thing—being patient as people put themselves back into a normal routine. 

Health is driven by more than just medical care, and this is a moment for us to remember that a holistic approach matters.

Taking off your Chief Health Officer hat, how do you reassure friends and family when they’re worried about this situation?
Medically, we need to be patient and let the scientists do their thing. It’s probably going to take until summer or early fall in the northern hemisphere to get clarity on what therapeutics work. The end game is to develop a vaccine so we can make sure everybody is protected. This is going to be a long journey with many months ahead, so we need to pace ourselves. 

Statistically, more people will have anxiety and depression from COVID-19 than will actually get COVID-19. To share tips on mental well-being, we recently launched the “Be Kind To Your Mind” PSA on Google Search.

Lastly, I remind those who are privileged to have a safe space to stay home when other people can’t. I think about my previous work with low income patients, and how this crisis impacts them as well as communities of color, non-native English speakers, and individuals with disabilities. Staying home is not safe, comfortable and financially feasible for everybody. We should all be doing what we can for our neighbors and our friends and the people who aren’t always seen.