Tag Archives: UK

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. 


Meet Kwara, a startup in the new Africa Immersion program

At Google for Startups, we look for ways to support promising new companies around the world. But those companies usually stay put in their home regions, which can be limiting—it means a smaller network of expertise to draw on, and a restricted pool of venture capital investors. We wanted to see what might happen if we expanded the geographical horizon, and connected up-and-coming businesses in one region with well-honed resources from a different region.


So in September, Google for Startups UK launched our first-ever Africa Immersion cohort, a 12-week program to bring expertise from Google and London startups to tech startups from Africa. We chose ten startups from our Launchpad Africa program, a network of tech startups around the world, who can share learnings, support and do business with each other. We wrapped up last week in Lagos, where we brought key investors from the UK to meet with the founders. 


To get a behind-the-scenes view of the Africa Immersion cohort, we chatted with Cynthia Wandia, co-founder and CEO of Kwara, an online and mobile banking platform for financial cooperatives (also known as credit unions and community banks).

First, what does Kwara do?


We provide secure, simple and affordable online and mobile banking for cooperative financial institutions and their members, who are often excluded by traditional banks. Starting in Kenya, our mission is to make sure that these institutions can meet their members’ financial needs instantly, helping them avoid expensive predatory alternatives.

Two Kwara team members smiling

Team Kwara: Austin Kabiru, Software Engineer, and Cynthia Wandia, Cofounder & CEO

How did you get started—where did the idea come from?

The idea started from the view that small-scale cash crop farmers should be able to command more value for their produce. As most farmers rely on the cooperative for their primary financial needs, we decided to strengthen the cooperatives by making them more secure, transparent and investible.

Who are your customers? What does your company do for them?

Our first sector is financial cooperatives, also known as credit unions and community banks. Our technology helps them acquire and retain more members, secure their members’ funds, and increase their own revenues. Members in turn benefit from increased convenience, transparency, peace of mind and more complete credit profiles. And since we link our banking platform to the formal financial sector, the members can also access shared channels such as ATM networks and widespread agent infrastructure.

Why did you decide to participate in the Africa Immersion program?

We were first connected to Google through Launchpad, a three-month accelerator program that provides early-stage startups with access to Google technology, mentorship and workshops on growing their businesses. Before Launchpad, we had acquired some customers who were willing to try out our product while it was still in an early testing stage, and we were making sure that we really could solve all the problems we wanted to address. Launchpad helped us focus on a single product and user, and define our tech team responsibilities. And the Google brand gave us added credibility with potential customers. We also benefited immensely from the lessons and experiences that other startups shared with us. So we were keen to participate in another Google program, specifically one that sought to open up new investor networks to us, as well as continue to introduce us to a peer group of admirable startups from all over the continent. 

Is there a moment or event from the program that particularly stands out to you?

Access to the Google for Startups UK team who have an extensive network and are very open to share has been the highlight. We have been linked with experts in product, fundraising and marketing, both from within Google and from leading startups in the UK.

What do you hope will come out of the program?

We hope to align with a few like-minded investors to start conversations about our next funding round. We also hope to continue our mentorship with the Google for Startups team, and hopefully speed up our marketing efforts.

Why newsrooms should pay attention to AI

Artificial intelligence is helping transform many businesses, and journalism is no exception. Newsrooms are already using AI to help organize and find videos and images, transcribe interviews in multiple languages and much more. But the industry  is still trying to understand the full impact AI can have.  

Today, we are releasing a report which highlights how AI offers new powers to journalists across the reporting process, from news gathering to distribution. It also underlines how news organizations that want to explore this potential must be ready to consider and carefully monitor the ethical and editorial implications of these new technologies.

This research is the result of Journalism AI, a year-long collaboration between Polis, the international journalism think tank at the London School of Economics and Political Science, and the Google News Initiative, to educate newsrooms about the potential offered by AI-powered technologies through research, training and networking.

Newsrooms around the world are experimenting with AI, and responses to the Journalism AI survey came from 71 media organizations in 32 countries. Publishers, editors and reporters shared their detailed thoughts on the potential of AI for the news industry, how it is impacting their organizations and the risks and challenges involved with this new wave of technological innovation. 

The findings make it clear that journalism should pay attention to AI, which has the potential for wide-ranging and profound influence on how journalism is made and consumed. 

On one side, AI technologies promise to free up time for journalists to work on the more creative aspects of the news production, leaving tedious and repetitive tasks to machines. At a time when the news industry is fighting for economic sustainability and for the public’s trust, it’s easy to see why this promise is highly attractive.

On the other side, via personalization and smart recommendations, AI can help the public cope with news overload, connecting them in a convenient way to credible content that is relevant, useful, and stimulating for their lives.

Newsrooms vary in their AI strategies and implementations, the challenges they’ve experienced and the way it’s changing the way they work and how they approach their business structure. 

Overall, respondents are optimistic about the positive impact that AI can bring, as long as journalists retain their ethical and editorial values and adapt to the new challenges—such as algorithmic bias and the rise of so-called “deepfakes,” in which AI is used to create fake images or videos and pass them as real. 

The report also warns against the risk of perceiving AI simply as a way to cut costs, and that it should instead be used to benefit the people who produce the journalism we consume. There are also significant concerns about a growing divide between large organizations with the resources to take advantage of the potential offered by AI, and smaller ones that risk being left behind.

With AI, the news industry has an opportunity to continue to reinvent itself for the information needs and behavior of people in our data-driven era. But with these new powers come responsibilities to maintain quality, increase editorial diversity and promote transparency of the systems they create. 

Take a read through the Journalism AI report to see the full findings of how media organizations view AI, and what’s next for the industry.