Vanessa Colimorio (left) and Sharon Kochlany (right) at a farm with their four-year-old twin daughters and one-year-old son. The kids share the same sperm donor.
Sharon Kochlany and Vanessa Colimorio's four-year-old twin girls had a classic school assignment recently: make a family tree. They drew themselves and their one-year-old brother branching off from their moms, with aunts, uncles, and grandparents forking off to the sides.
The recently-gained sovereignty of queer families stands to be lost if a consumer DNA test brings a stranger's identity out of the woodwork.
What you don't see in the invisible space between Kochlany and Colimorio, however, is the sperm donor they used to conceive all three children.
To look at a family tree like this is to see in its purest form that kinship can supersede biology—the boundaries of where this family starts and stops are clear to everyone in it, in spite of a third party's genetic involvement. This kind of self-definition has always been synonymous with LGBTQ families, especially those that rely on donor gametes (sperm or eggs) to exist.
But the world around them has changed quite suddenly: The recent consumer DNA testing boom has made it more complicated than ever for families built through reproductive technology—openly, not secretively—to maintain the strong sense of autonomy and privacy that can be crucial for their emotional security. Prospective parents and cryobanks are now mulling how best to bring a new generation of donor-conceived people into this world in a way that leaves open the choice to know more about their ancestry without obliterating an equally important choice: the right not to know about biological relatives.
For queer parents who have long fought for social acceptance, having a biological relationship to their children has been revolutionary, and using an unknown donor as a means to this end especially so. Getting help from a friend often comes with the expectation that the friend will also have social involvement in the family, which some people are comfortable with, but being able to access sperm from an unknown donor—which queer parents have only been able to openly do since the early 1980s—grants them the reproductive autonomy to create families seemingly on their own. That recently-gained sovereignty stands to be lost if a consumer DNA test brings a stranger's identity out of the woodwork.
At the same time, it's natural for donor-conceived people to want to know more about where they come from ethnically, even if they don't want to know the identity of their donor. As a donor-conceived person myself, I know my donor's self-reported ethnicity, but have often wondered how accurate it is.
Opening the Pandora's box of a consumer DNA test as a way to find out has always felt profoundly unappealing to me, however. Many people have accidentally learned they're donor-conceived by unwittingly using these tools, but I already know that about myself going in, and subsequently know I'll be connected to a large web of people whose existence I'm not interested in learning about. In addition to possibly identifying my anonymous donor, his family could also show up, along with any donor-siblings—other people with whom I share a donor. My single lesbian mom is enough for me, and the trade off to learn more about my ethnic ancestry has never seemed worth it.
In 1992, when I was born, no one was planning for how consumer DNA tests might upend or illuminate one's sense of self. But the donor community has always had to stay nimble with balancing privacy concerns and psychological well-being, so it should come as no surprise that figuring out how to do so in 2020 includes finding a way to offer ancestry insight while circumventing consumer DNA tests.
A New Paradigm
This is the rationale behind unprecedented industry news that LeapsMag can exclusively break: Within the next few weeks, California Cryobank, the largest cryobank in the country, will begin offering genetically-verified ancestry information on the free public part of every donor's anonymous profile in its database, something no other cryobanks yet offer (an exact launch date was not available at the time of publication). Currently, California Cryobank's donor profiles include a short self-reported list that might merely say, "Ancestry: German, Lebanese, Scottish."
The new information will be a report in pie chart form that details exactly what percentages of a donor's DNA come from up to 26 ethnicities—it's analogous to, but on a smaller scale than, the format offered by consumer DNA testing companies, and uses the same base technology that looks for single nucleotide polymorphisms in DNA that are associated with specific ethnicities. But crucially, because the donor takes the DNA test through California Cryobank, not a consumer-facing service, the information is not connected in a network to anyone else's DNA test. It's also taken before any offspring exist so there's no chance of revealing a donor-conceived person's identity this way.
Later, when a donor-conceived person is born, grows up, and wants information about their ethnicity from the donor side, all they need is their donor's anonymous ID number to look it up. The donor-conceived person never takes a genetic test, and therefore also can't accidentally find donor siblings this way. People who want to be connected to donor siblings can use a sibling registry where other people who want to be found share donor ID numbers and look for matches (this is something that's been available for decades, and remains so).
"With genetic testing, you have no control over who reaches out to you, and at what point in your life."
California Cryobank will require all new donors to consent to this extra level of genetic testing, setting a new standard for what information prospective parents and donor-conceived people can expect to have. In the immediate, this information will be most useful for prospective parents looking for donors with specific backgrounds, possibly ones similar to their own.
It's a solution that was actually hiding in plain sight. Two years ago, California Cryobank's partner Sema4, the company handling the genetic carrier testing that's used to screen for heritable diseases, started analyzing ethnic data in its samples. That extra information was being collected because it can help calculate a more accurate assessment of genetic risks that run in certain populations—like Ashkenazi Jews and Tay Sachs disease—than relying on oral family histories. Shortly after a plan to start collecting these extra data, Jamie Shamonki, chief medical officer of California Cryobank, realized the companies would be sitting on a goldmine for a different reason.
"I didn't want to use one of these genetic testing companies like Ancestry to accomplish this," says Shamonki. "The whole thing we're trying to accomplish is also privacy."
Consumer-facing DNA testing companies are not HIPAA compliant (whereas Sema4, which isn't direct-to-consumer, is HIPAA compliant), which means there are no legal privacy protections covering people who add their DNA to these databases. Although some companies, like 23andMe, allow users to opt-out of being connected with genetic relatives, the language can be confusing to navigate, requires a high level of knowledge and self-advocacy on the user's part, and, as an opt-out system, is not set up to protect the user from unwanted information by default; many unwittingly walk right into such information as a result.
Additionally, because consumer-facing DNA testing companies operate outside the legal purview that applies to other health care entities, like hospitals, even a person who does opt-out of being linked to genetic relatives is not protected in perpetuity from being re-identified in the future by a change in company policy. The safest option for people with privacy concerns is to stay out of these databases altogether.
For California Cryobank, the new information about donor heritage won't retroactively be added to older profiles in the system, so donor-conceived people who already exist won't benefit from the ancestry tool, but it'll be the new standard going forward. The company has about 500 available donors right now, many of which have been in their registry for a while; about 100 of those donors, all new, will have this ancestry data on their profiles.
Shamonki says it has taken about two years to get to the point of publicly including ancestry information on a donor's profile because it takes about nine months of medical and psychological screening for a donor to go from walking through the door to being added to their registry. The company wanted to wait to launch until it could offer this information for a significant number of donors. As more new donors come online under the new protocol, the number with ancestry information on their profiles will go up.
For Parents: An Unexpected Complication
While this change will no doubt be welcome progress for LGBTQ families contemplating parenthood, it'll never be possible to put this entire new order back in the box. What are such families who already have donor-conceived children losing in today's world of widespread consumer genetic testing?
Kochlany and Colimorio's twins aren't themselves much older than the moment at-home DNA testing really started to take off. They were born in 2015, and two years later the industry saw its most significant spike. By now, more than 26 million people's DNA is in databases like 23andMe and Ancestry; as a result, it's estimated that within a year, 90 percent of Americans of European descent will be identifiable through these consumer databases, by way of genetic third cousins, even if they didn't want to be found and never took the test themselves. This was the principle behind solving the Golden State Killer cold case.
The waning of privacy through consumer DNA testing fundamentally clashes with the priorities of the cyrobank industry, which has long sought to protect the privacy of donor-conceived people, even as open identification became standard. Since the 1980s, donors have been able to allow their identity to be released to any offspring who is at least 18 and wants the information. Lesbian moms pushed for this option early on so their children—who would obviously know they couldn't possibly be the biological product of both parents—would never feel cut off from the chance to know more about themselves. But importantly, the openness is not a two-way street: the donors can't ever ask for the identities of their offspring. It's the latter that consumer DNA testing really puts at stake.
"23andMe basically created the possibility that there will be donors who will have contact with their donor-conceived children, and that's not something that I think the donor community is comfortable with," says I. Glenn Cohen, director of Harvard Law School's Center for Health Law Policy, Biotechnology & Bioethics. "That's about the donor's autonomy, not the rearing parents' autonomy, or the donor-conceived child's autonomy."
Kochlany and Colimorio have an open identification donor and fully support their children reaching out to California Cryobank to get more information about him if they want to when they're 18, but having a singular name revealed isn't the same thing as having contact, nor is it the same thing as revealing a web of dozens of extended genetic relations. Their concern now is that if their kids participate in genetic testing, a stranger—someone they're careful to refer to as only "the donor" and never "dad"—will reach out to the children to begin some kind of relationship. They know other people who are contemplating giving their children DNA tests, and feel staunchly that it wouldn't be right for their family.
"With genetic testing, you have no control over who reaches out to you, and at what point in your life," Kochlany says. "[People] reaching out and trying to say, 'Hey I know who your dad is' throws a curveball. It's like, 'Wait, I never thought I had a dad.' It might put insecurities in their minds."
"We want them to have the opportunity to choose whether or not they want to reach out," Colimorio adds.
Kochlany says that when their twins are old enough to start asking questions, she and Colimorio plan to frame it like this: "The donor was kind of like a technology that helped us make you a person, and make sure that you exist," she says, role playing a conversation with their kids. "But it's not necessarily that you're looking to this person [for] support or love, or because you're missing a piece."
It's a line in the sand that's present even for couples still far off from conceiving. When Mallory Schwartz, a film and TV producer in Los Angeles, and Lauren Pietra, a marriage and family therapy associate (and Shamonki's step-daughter), talk about getting married someday, it's a package deal with talking about how they'll approach having kids. They feel there are too many variables and choices to make around family planning as a same-sex couple these days to not have those conversations simultaneously. Consumer DNA databases are already on their minds.
"It frustrates me that the DNA databases are just totally unregulated," says Schwartz. "I hope they are by the time we do this. I think everyone deserves a right to privacy when making your family [using a sperm donor]."
"I wouldn't want to create a world where people who are donor-conceived feel like they can't participate in this technology because they're trying to shut out [other] information."
On the prospect of having a donor relation pop up non-consensually for a future child, Pietra says, "I don't like it. It would be really disappointing if the child didn't want [contact], and unfortunately they're on the receiving end."
You can see how important preserving the right to keep this door closed is when you look at what's going on at The Sperm Bank of California. This pioneering cryobank was the first in the world to openly serve LGBTQ people and single women, and also the first to offer the open identification option when it opened in 1982, but not as many people are asking for their donor's identity as expected.
"We're finding a third of young people are coming forward for their donor's identity," says Alice Ruby, executive director. "We thought it would be a higher number." Viewed the other way, two-thirds of the donor-conceived people who could ethically get their donor's identity through The Sperm Bank of California are not asking the cryobank for it.
Ruby says that part of what historically made an open identification program appealing, rather than invasive or nerve-wracking, is how rigidly it's always been formatted around mutual consent, and protects against surprises for all parties. Those [donor-conceived people] who wanted more information were never barred from it, while those who wanted to remain in the dark could. No one group's wish eclipsed the other's. The potential breakdown of a system built around consent, expectations, and respect for privacy is why unregulated consumer DNA testing is most concerning to her as a path for connecting with genetic relatives.
For the last few decades in cryobanks around the world, the largest cohort of people seeking out donor sperm has been lesbian couples, followed by single women. For infertile heterosexual couples, the smallest client demographic, Ruby says donor sperm offers a solution to a medical problem, but in contrast, it historically "provided the ability for [lesbian] couples and single moms to have some reproductive autonomy." Yes, it was still a solution to a biological problem, but it was also a solution to a social one.
The Sperm Bank of California updated its registration forms to include language urging parents, donor-conceived people, and donors not to use consumer DNA tests, and to go through the cryobank if they, understandably, want to learn more about who they're connected to. But truthfully, there's not much else cryobanks can do to protect clients on any side of the donor transaction from surprise contact right now—especially not from relatives of the donor who may not even know someone in their family has donated sperm.
A Tricky Position
Personally, I've known I was donor-conceived from day one. It has never been a source of confusion, angst, or curiosity, and in fact has never loomed particularly large for me in any way. I see it merely as a type of reproductive technology—on par with in vitro fertilization—that enabled me to exist, and, now that I do exist, is irrelevant. Being confronted with my donor's identity or any donor siblings would make this fact of my conception bigger than I need it to be, as an adult with a full-blown identity derived from all of my other life experiences. But I still wonder about the minutiae of my ethnicity in much the same way as anyone else who wonders, and feel there's no safe way for me to find out without relinquishing some of my existential independence.
"People obviously want to participate in 23andMe and Ancestry because they're interested in knowing more about themselves," says Shamonki. "I wouldn't want to create a world where people who are donor-conceived feel like they can't participate in this technology because they're trying to shut out [other] information."
After all, it was the allure of that exact conceit—knowing more about oneself—that seemed to magnetically draw in millions of people to these tools in the first place. It's an experience that clearly taps into a population-wide psychic need, even—perhaps especially—if one's origins are a mystery.
Basecamp Research is using portable labs like this one to gather samples from ecosystems around the world.
Clark works for Basecamp Research, a biotech company headquartered in London, and his job is to collect samples from ecosystems around the world. By extracting DNA from soil, water, plants, microbes and other organisms, Basecamp is building an extensive database of the Earth’s proteins. While DNA itself isn’t a protein, the information stored in DNA is used to create proteins, so extracting, sequencing, and annotating DNA allows for the discovery of unique protein sequences.
Using what they’re finding in the middle of the Atlantic and beyond, Basecamp’s detailed database is constantly growing. The outputs could be essential for cleaning up the damage done by toxic chemicals and finding alternatives to these chemicals.
Catalysts for change
Proteins provide structure and function in all living organisms. Some of these functional proteins are enzymes, which quite literally make things happen.
“Industrial chemistry is heavily polluting, especially the chemistry done in pharmaceutical drug development. Biocatalysis is providing advantages, both to make more complex drugs and to be more sustainable, reducing the pollution and toxicity of conventional chemistry," says Ahir Pushpanath, who heads partnerships for Basecamp.
“Enzymes are perfectly evolved catalysts,” says Ahir Pushpanath, a partnerships lead at Basecamp. ”Enzymes are essentially just a polymer, and polymers are made up of amino acids, which are nature’s building blocks.” He suggests thinking about it like Legos — if you have a bunch of Lego pieces and use them to build a structure that performs a function, “that’s basically how an enzyme works. In nature, these monuments have evolved to do life’s chemistry. If we didn’t have enzymes, we wouldn’t be alive.”
In our own bodies, enzymes catalyze everything from vision to digesting food to regrowing muscles, and these same types of enzymes are necessary in the pharmaceutical, agrochemical and fine chemical industries. But industrial conditions differ from those inside our bodies. So, when scientists need certain chemical reactions to create a particular product or substance, they make their own catalysts in their labs — generally through the use of petroleum and heavy metals.
These petrochemicals are effective and cost-efficient, but they’re wasteful and often hazardous. With growing concerns around sustainability and long-term public health, it's essential to find alternative solutions to toxic chemicals. “Industrial chemistry is heavily polluting, especially the chemistry done in pharmaceutical drug development,” Pushpanath says.
Basecamp is trying to replace lab-created catalysts with enzymes found in the wild. This concept is called biocatalysis, and in theory, all scientists have to do is find the right enzymes for their specific need. Yet, historically, researchers have struggled to find enzymes to replace petrochemicals. When they can’t identify a suitable match, they turn to what Pushpanath describes as “long, iterative, resource-intensive, directed evolution” in the laboratory to coax a protein into industrial adaptation. But the latest scientific advances have enabled these discoveries in nature instead.
Marlon Clark, a research scientist at Basecamp Research, looks for novel biochemistries in the Azores.
Glen Gowers
Enzyme hunters
Whether it’s Clark and a colleague setting off on an expedition, or a local, on-the-ground partner gathering and processing samples, there’s a lot to be learned from each collection. “Microbial genomes contain complete sets of information that define an organism — much like how letters are a code allowing us to form words, sentences, pages, and books that contain complex but digestible knowledge,” Clark says. He thinks of the environmental samples as biological libraries, filled with thousands of species, strains, and sequence variants. “It’s our job to glean genetic information from these samples.”
“We can actually dream up new proteins using generative AI," Pushpanath says.
Basecamp researchers manage this feat by sequencing the DNA and then assembling the information into a comprehensible structure. “We’re building the ‘stories’ of the biota,” Clark says. The more varied the samples, the more valuable insights his team gains into the characteristics of different organisms and their interactions with the environment. Sequencing allows scientists to examine the order of nucleotides — the organic molecules that form DNA — to identify genetic makeups and find changes within genomes. The process used to be too expensive, but the cost of sequencing has dropped from $10,000 a decade ago to as low as $100. Notably, biocatalysis isn’t a new concept — there have been waves of interest in using natural enzymes in catalysis for over a century, Pushpanath says. “But the technology just wasn’t there to make it cost effective,” he explains. “Sequencing has been the biggest boon.”
AI is probably the second biggest boon.
“We can actually dream up new proteins using generative AI,” Pushpanath says, which means that biocataylsis now has real potential to scale.
Glen Gowers, the co-founder of Basecamp, compares the company’s AI approach to that of social networks and streaming services. Consider how these platforms suggest connecting with the friends of your friends, or how watching one comedy film from the 1990s leads to a suggestion of three more.
“They’re thinking about data as networks of relationships as opposed to lists of items,” says Gowers. “By doing the same, we’re able to link the metadata of the proteins — by their relationships to each other, the environments in which they’re found, the way those proteins might look similar in sequence and structure, their surrounding genome context — really, this just comes down to creating a searchable network of proteins.”
On an Azores island, this volcanic opening may harbor organisms that can help scientists identify enzymes for biocatalysis to replace toxic chemicals.
Emma Bolton
Uwe Bornscheuer, professor at the Institute of Biochemistry at the University of Greifswald, and co-founder of Enzymicals, another biocatalysis company, says that the development of machine learning is a critical component of this work. “It’s a very hot topic, because the challenge in protein engineering is to predict which mutation at which position in the protein will make an enzyme suitable for certain applications,” Bornscheuer explains. These predictions are difficult for humans to make at all, let alone quickly. “It is clear that machine learning is a key technology.”
Benefiting from nature’s bounty
Biodiversity commonly refers to plants and animals, but the term extends to all life, including microbial life, and some regions of the world are more biodiverse than others. Building relationships with global partners is another key element to Basecamp’s success. Doing so in accordance with the access and benefit sharing principles set forth by the Nagoya Protocol — an international agreement that seeks to ensure the benefits of using genetic resources are distributed in a fair and equitable way — is part of the company's ethos. “There's a lot of potential for us, and there’s a lot of potential for our partners to have exactly the same impact in building and discovering commercially relevant proteins and biochemistries from nature,” Clark says.
Bornscheuer points out that Basecamp is not the first company of its kind. A former San Diego company called Diversa went public in 2000 with similar work. “At that time, the Nagoya Protocol was not around, but Diversa also wanted to ensure that if a certain enzyme or microorganism from Costa Rica, for example, were used in an industrial process, then people in Costa Rica would somehow profit from this.”
An eventual merger turned Diversa into Verenium Corporation, which is now a part of the chemical producer BASF, but it laid important groundwork for modern companies like Basecamp to continue to scale with today’s technologies.
“To collect natural diversity is the key to identifying new catalysts for use in new applications,” Bornscheuer says. “Natural diversity is immense, and over the past 20 years we have gained the advantages that sequencing is no longer a cost or time factor.”
This has allowed Basecamp to rapidly grow its database, outperforming Universal Protein Resource or UniProt, which is the public repository of protein sequences most commonly used by researchers. Basecamp’s database is three times larger, totaling about 900 million sequences. (UniProt isn’t compliant with the Nagoya Protocol, because, as a public database, it doesn’t provide traceability of protein sequences. Some scientists, however, argue that Nagoya compliance hinders progress.)
“Eventually, this work will reduce chemical processes. We’ll have cleaner processes, more sustainable processes," says Uwe Bornscheuer, a professor at the University of Greifswald.
With so much information available, Basecamp’s AI has been trained on “the true dictionary of protein sequence life,” Pushpanath says, which makes it possible to design sequences for particular applications. “Through deep learning approaches, we’re able to find protein sequences directly from our database, without the need for further laboratory-directed evolution.”
Recently, a major chemical company was searching for a specific transaminase — an enzyme that catalyzes a transfer of amino groups. “They had already spent a year-and-a-half and nearly two million dollars to evolve a public-database enzyme, and still had not reached their goal,” Pushpanath says. “We used our AI approaches on our novel database to yield 10 candidates within a week, which, when validated by the client, achieved the desired target even better than their best-evolved candidate.”
Basecamp’s other huge potential is in bioremediation, where natural enzymes can help to undo the damage caused by toxic chemicals. “Biocatalysis impacts both sides,” says Gowers. “It reduces the usage of chemicals to make products, and at the same time, where contamination sites do exist from chemical spills, enzymes are also there to kind of mop those up.”
So far, Basecamp's round-the-world sampling has covered 50 percent of the 14 major biomes, or regions of the planet that can be distinguished by their flora, fauna, and climate, as defined by the World Wildlife Fund. The other half remains to be catalogued — a key milestone for understanding our planet’s protein diversity, Pushpanath notes.
There’s still a long road ahead to fully replace petrochemicals with natural enzymes, but biocatalysis is on an upward trajectory. "Eventually, this work will reduce chemical processes,” Bornscheuer says. “We’ll have cleaner processes, more sustainable processes.”
In an initial study, Canary analyzed speech recordings with AI and identified early stage Alzheimer’s with 96 percent accuracy.
Arnold was diagnosed sooner than many others. It's important to find out early, when interventions can make the most difference. One promising avenue is looking at how people talk. Research has shown that Alzheimer’s affects a part of the brain that controls speech, resulting in small changes before people show other signs of the disease.
Now, Canary Speech, a company based in Utah, is using AI to examine elements like the pitch of a person’s voice and their pauses. In an initial study, Canary analyzed speech recordings with AI and identified early stage Alzheimer’s with 96 percent accuracy.
Developing the AI model
Canary Speech’s CEO, Henry O’Connell, met cofounder Jeff Adams about 40 years before they started the company. Back when they first crossed paths, they were both living in Bethesda, Maryland; O’Connell was a research fellow at the National Institutes of Health studying rare neurological diseases, while Adams was working to decode spy messages. Later on, Adams would specialize in building mathematical models to analyze speech and sound as a team leader in developing Amazon's Alexa.
It wasn't until 2015 that they decided to make use of the fit between their backgrounds. ““We established Canary Speech in 2017 to build a product that could be used in multiple languages in clinical environments,” O'Connell says.
The need is growing. About 55 million people worldwide currently live with Alzheimer’s, a number that is expected to double by 2050. Some scientists think the disease results from a buildup of plaque in the brain. It causes mild memory loss at first and, over time, this issue get worse while other symptoms, such as disorientation and hallucinations, can develop. Treatment to manage the disease is more effective in the earlier stages, but detection is difficult since mild symptoms are often attributed to the normal aging process.
O’Connell and Adams specialize in the complex ways that Alzheimer’s effects how people speak. Using AI, their mathematical model analyzes 15 million data points every minute, focusing on certain features of speech such as pitch, pauses and elongation of words. It also pays attention to how the vibrations of vocal cords change in different stages of the disease.
To create their model, the team used a type of machine learning called deep neural nets, which looks at multiple layers of data - in this case, the multiple features of a person’s speech patterns.
“Deep neural nets allow us to look at much, much larger data sets built out of millions of elements,” O’Connell explained. “Through machine learning and AI, we’ve identified features that are very sensitive to an Alzheimer’s patient versus [people without the disease] and also very sensitive to mild cognitive impairment, early stage and moderate Alzheimer's.” Based on their learnings, Canary is able to classify the disease stage very quickly, O’Connell said.
“When we’re listening to sublanguage elements, we’re really analyzing the direct result of changes in the brain in the physical body,” O’Connell said. “The brain controls your vocal cords: how fast they vibrate, the expansion of them, the contraction.” These factors, along with where people put their tongues when talking, function subconsciously and result in subtle changes in the sounds of speech.
Further testing is needed
In an initial trial, Canary analyzed speech recordings from phone calls to a large U.S. health insurer. They looked at the audio recordings of 651 policyholders who had early stage Alzheimer’s and 1018 who did not have the condition, aiming for a representative sample of age, gender and race. They used this data to create their first diagnostic model and found that it was 96 percent accurate in identifying Alzheimer’s.
Christian Herff, an assistant professor of neuroscience at Maastricht University in the Netherlands, praised this approach while adding that further testing is needed to assess its effectiveness.
“I think the general idea of identifying increased risk for cognitive impairment based on speech characteristics is very feasible, particularly when change in a user’s voice is monitored, for example, by recording speech every year,” Herff said. He noted that this can only be a first indication, not a full diagnosis. The accuracy still needs to be validated in studies that follows individuals over a period of time, he said.
Toby Walsh, a professor of artificial intelligence at the University of New South Wales, also thinks Canary’s tool has potential but highlights that Canary could diagnose some people who don’t really have the disease. “This is an interesting and promising application of AI,” he said, “but these tools need to be used carefully. Imagine the anxiety of being misdiagnosed with Alzheimer’s.”
As with many other AI tools, privacy and bias are additional issues to monitor closely, Walsh said.
Other languages
A related issue is that not everyone is fluent in English. Mahnaz Arvaneh, a senior lecturer in automatic control and systems engineering at the University of Sheffield, said this could be a blind spot.
“The system may not be very accurate for those who have English as their second language as their speaking patterns would be different, and any issue might be because of language deficiency rather than cognitive issues,” Arvaneh said.
The team is expanding to multiple languages starting with Japanese and Spanish. The elements of the model that make up the algorithm are very similar, but they need to be validated and retrained in a different language, which will require access to more data.
Recently, Canary analyzed the phone calls of 233 Japanese patients who had mild cognitive impairment and 704 healthy people. Using an English model they were able to identify the Japanese patients who had mild cognitive impairment with 78 percent accuracy. They also developed a model in Japanese that was 45 percent accurate, and they’re continuing to train it with more data.
The future
Canary is using their model to look at other diseases like Huntington’s and Parkinson’s. They’re also collaborating with pharmaceuticals to validate potential therapies for Alzheimer’s. By looking at speech patterns over time, Canary can get an indication of how well these drugs are working.
Dave Arnold and his wife dance at his nephew’s wedding in Rochester, New York, ten years ago, before his Alzheimer's diagnosis.
Dave Arnold
Ultimately, they want to integrate their tool into everyday life. “We want it to be used in a smartphone, or a teleconference call so that individuals could be examined in their home,” O’Connell said. “We could follow them over time and work with clinical teams and hospitals to improve the evaluation of patients and contribute towards an accurate diagnosis.”
Arnold, the patient with early stage Alzheimer’s, sees great promise. “The process of getting a diagnosis is already filled with so much anxiety,” he said. “Anything that can be done to make it easier and less stressful would be a good thing, as long as it’s proven accurate.”