×

We use cookies to help make LingQ better. By visiting the site, you agree to our cookie policy.


image

TED, Max Little: A test for Parkinson's with a phone call

Max Little: A test for Parkinson's with a phone call

00:11So, well, I do applied math, and this is a peculiar problem for anyone who does applied math, is that we are like management consultants. No one knows what the hell we do. So I am going to give you some -- attempt today to try and explain to you what I do.

00:25So, dancing is one of the most human of activities. We delight at ballet virtuosos and tap dancers you will see later on. Now, ballet requires an extraordinary level of expertise and a high level of skill, and probably a level of initial suitability that may well have a genetic component to it. Now, sadly, neurological disorders such as Parkinson's disease gradually destroy this extraordinary ability, as it is doing to my friend Jan Stripling, who was a virtuoso ballet dancer in his time. So great progress and treatment has been made over the years. However, there are 6.3 million people worldwide who have the disease, and they have to live with incurable weakness, tremor, rigidity and the other symptoms that go along with the disease, so what we need are objective tools to detect the disease before it's too late. We need to be able to measure progression objectively, and ultimately, the only way we're going to know when we actually have a cure is when we have an objective measure that can answer that for sure. 01:25But frustratingly, with Parkinson's disease and other movement disorders, there are no biomarkers, so there's no simple blood test that you can do, and the best that we have is like this 20-minute neurologist test. You have to go to the clinic to do it. It's very, very costly, and that means that, outside the clinical trials, it's just never done. It's never done. 01:44But what if patients could do this test at home? Now, that would actually save on a difficult trip to the clinic, and what if patients could do that test themselves, right? No expensive staff time required. Takes about $300, by the way, in the neurologist's clinic to do it. 01:59So what I want to propose to you as an unconventional way in which we can try to achieve this, because, you see, in one sense, at least, we are all virtuosos like my friend Jan Stripling.

02:08So here we have a video of the vibrating vocal folds. Now, this is healthy and this is somebody making speech sounds, and we can think of ourselves as vocal ballet dancers, because we have to coordinate all of these vocal organs when we make sounds, and we all actually have the genes for it. FoxP2, for example. And like ballet, it takes an extraordinary level of training. I mean, just think how long it takes a child to learn to speak. From the sound, we can actually track the vocal fold position as it vibrates, and just as the limbs are affected in Parkinson's, so too are the vocal organs. So on the bottom trace, you can see an example of irregular vocal fold tremor. We see all the same symptoms. We see vocal tremor, weakness and rigidity. The speech actually becomes quieter and more breathy after a while, and that's one of the example symptoms of it. 02:53So these vocal effects can actually be quite subtle, in some cases, but with any digital microphone, and using precision voice analysis software in combination with the latest in machine learning, which is very advanced by now, we can now quantify exactly where somebody lies on a continuum between health and disease using voice signals alone.

03:14So these voice-based tests, how do they stack up against expert clinical tests? We'll, they're both non-invasive. The neurologist's test is non-invasive. They both use existing infrastructure. You don't have to design a whole new set of hospitals to do it. And they're both accurate. Okay, but in addition, voice-based tests are non-expert. That means they can be self-administered. They're high-speed, take about 30 seconds at most. They're ultra-low cost, and we all know what happens. When something becomes ultra-low cost, it becomes massively scalable. So here are some amazing goals that I think we can deal with now. We can reduce logistical difficulties with patients. No need to go to the clinic for a routine checkup. We can do high-frequency monitoring to get objective data. We can perform low-cost mass recruitment for clinical trials, and we can make population-scale screening feasible for the first time. We have the opportunity to start to search for the early biomarkers of the disease before it's too late. 04:07So, taking the first steps towards this today, we're launching the Parkinson's Voice Initiative. With Aculab and Patients Like Me, we're aiming to record a very large number of voices worldwide to collect enough data to start to tackle these four goals. We have local numbers accessible to three quarters of a billion people on the planet. Anyone healthy or with Parkinson's can call in, cheaply, and leave recordings, a few cents each, and I'm really happy to announce that we've already hit six percent of our target just in eight hours. Thank you. (Applause) (Applause)

04:43Tom Rielly: So Max, by taking all these samples of,

04:47let's say, 10,000 people, you'll be able to tell who's healthy and who's not? What are you going to get out of those samples?

04:54Max Little: Yeah. Yeah. So what will happen is that, during the call you have to indicate whether or not you have the disease or not, you see. TR: Right. ML: You see, some people may not do it. They may not get through it. But we'll get a very large sample of data that is collected from all different circumstances, and it's getting it in different circumstances that matter because then we are looking at ironing out the confounding factors, and looking for the actual markers of the disease. 05:15TR: So you're 86 percent accurate right now? 05:18ML: It's much better than that. Actually, my student Thanasis, I have to plug him, because he's done some fantastic work, and now he has proved that it works over the mobile telephone network as well, which enables this project, and we're getting 99 percent accuracy. 05:30TR: Ninety-nine. Well, that's an improvement. So what that means is that people will be able to — ML: (Laughs) TR: People will be able to call in from their mobile phones and do this test, and people with Parkinson's could call in, record their voice, and then their doctor can check up on their progress, see where they're doing in this course of the disease. 05:46ML: Absolutely.

05:47TR: Thanks so much. Max Little, everybody.

05:48ML: Thanks, Tom. (Applause)


Max Little: A test for Parkinson's with a phone call Max Little: Ein Test für Parkinson mit einem Telefonanruf Max Little: Una prueba de Parkinson con una llamada telefónica Max Little : Un appel téléphonique pour tester la maladie de Parkinson Max Little: Un test per il Parkinson con una telefonata マックス・リトル電話でのパーキンソン病検査 Max Little: Test na Parkinsona za pomocą telefonu Max Little: Um teste para a doença de Parkinson com um telefonema Макс Литтл: Тест на болезнь Паркинсона с помощью телефонного звонка Макс Літтл: Тест на хворобу Паркінсона за допомогою телефонного дзвінка Max Little:通过电话测试帕金森病 Max Little:通過電話測試帕金森病

00:11So, well, I do applied math, and this is a peculiar problem for anyone who does applied math, is that we are like management consultants. 00:11Donc, je fais des mathématiques appliquées, et c'est un problème particulier pour tous ceux qui font des mathématiques appliquées, c'est que nous sommes comme des consultants en gestion. 00:11 Итак, я занимаюсь прикладной математикой, и это особая проблема для всех, кто занимается прикладной математикой, в том, что мы как консультанты по управлению. 00:11 Peki, ben uygulamalı matematik yapıyorum ve bu uygulamalı matematik yapan herkes için tuhaf bir sorun, biz yönetim danışmanları gibiyiz. No one knows what the hell we do. Personne ne sait ce que nous faisons. So I am going to give you some -- attempt today to try and explain to you what I do. Итак, я собираюсь дать вам кое-что... сегодня попытаться объяснить вам, что я делаю.

00:25So, dancing is one of the most human of activities. We delight at ballet virtuosos and tap dancers you will see later on. Now, ballet requires an extraordinary level of expertise and a high level of skill, and probably a level of initial suitability that may well have a genetic component to it. Le ballet exige un niveau extraordinaire d'expertise et de compétence, et probablement un niveau d'aptitude initiale qui pourrait bien avoir une composante génétique. Так вот, балет требует экстраординарного уровня знаний и высокого уровня мастерства, а также, вероятно, уровня начальной пригодности, которая вполне может иметь генетический компонент. Now, sadly, neurological disorders such as Parkinson's disease gradually destroy this extraordinary ability, as it is doing to my friend Jan Stripling, who was a virtuoso ballet dancer in his time. So great progress and treatment has been made over the years. Так что большой прогресс и лечение были достигнуты за эти годы. However, there are 6.3 million people worldwide who have the disease, and they have to live with incurable weakness, tremor, rigidity and the other symptoms that go along with the disease, so what we need are objective tools to detect the disease before it's too late. Однако во всем мире насчитывается 6,3 миллиона человек, страдающих этим заболеванием, и им приходится жить с неизлечимой слабостью, тремором, ригидностью и другими симптомами, сопровождающими болезнь, поэтому нам нужны объективные инструменты для выявления болезни до того, как она станет слишком серьезной. поздно. We need to be able to measure progression objectively, and ultimately, the only way we're going to know when we actually have a cure is when we have an objective measure that can answer that for sure. Nous devons être en mesure de mesurer la progression de manière objective et, en fin de compte, la seule manière de savoir si nous avons un remède, c'est de disposer d'une mesure objective qui nous permette de répondre à cette question avec certitude. Нам нужно иметь возможность объективно измерять прогрессирование, и, в конечном счете, единственный способ узнать, когда у нас действительно есть лекарство, — это когда у нас есть объективная мера, которая может точно ответить на этот вопрос. 01:25But frustratingly, with Parkinson's disease and other movement disorders, there are no biomarkers, so there's no simple blood test that you can do, and the best that we have is like this 20-minute neurologist test. You have to go to the clinic to do it. It's very, very costly, and that means that, outside the clinical trials, it's just never done. C'est très, très coûteux, et cela signifie qu'en dehors des essais cliniques, cela n'est jamais fait. Это очень, очень дорого, и это означает, что помимо клинических испытаний, это просто никогда не делается. It's never done. 01:44But what if patients could do this test at home? Now, that would actually save on a difficult trip to the clinic, and what if patients could do that test themselves, right? Cela permettrait d'éviter un déplacement difficile à la clinique, et si les patients pouvaient faire ce test eux-mêmes, n'est-ce pas ? No expensive staff time required. Takes about $300, by the way, in the neurologist's clinic to do it. 01:59So what I want to propose to you as an unconventional way in which we can try to achieve this, because, you see, in one sense, at least, we are all virtuosos like my friend Jan Stripling.

02:08So here we have a video of the vibrating vocal folds. 02:08Voici une vidéo de la vibration des cordes vocales. 02:08 Итак, у нас есть видео с вибрацией голосовых связок. Now, this is healthy and this is somebody making speech sounds, and we can think of ourselves as vocal ballet dancers, because we have to coordinate all of these vocal organs when we make sounds, and we all actually have the genes for it. FoxP2, for example. And like ballet, it takes an extraordinary level of training. I mean, just think how long it takes a child to learn to speak. From the sound, we can actually track the vocal fold position as it vibrates, and just as the limbs are affected in Parkinson's, so too are the vocal organs. À partir du son, nous pouvons suivre la position du pli vocal lorsqu'il vibre, et tout comme les membres sont affectés dans la maladie de Parkinson, les organes vocaux le sont également. По звуку мы можем отслеживать положение голосовых связок по мере их вибрации, и так же, как при болезни Паркинсона поражаются конечности, так же поражаются и голосовые органы. So on the bottom trace, you can see an example of irregular vocal fold tremor. Итак, на нижней кривой вы можете увидеть пример нерегулярного тремора голосовых связок. We see all the same symptoms. We see vocal tremor, weakness and rigidity. On observe des tremblements vocaux, une faiblesse et une rigidité. Мы видим вокальный тремор, слабость и ригидность. The speech actually becomes quieter and more breathy after a while, and that's one of the example symptoms of it. Au bout d'un certain temps, l'élocution devient plus silencieuse et plus haletante, et c'est l'un des exemples de symptômes de la maladie. 02:53So these vocal effects can actually be quite subtle, in some cases, but with any digital microphone, and using precision voice analysis software in combination with the latest in machine learning, which is very advanced by now, we can now quantify exactly where somebody lies on a continuum between health and disease using voice signals alone. 02:53Dans certains cas, ces effets vocaux peuvent être très subtils, mais avec n'importe quel microphone numérique, et en utilisant un logiciel d'analyse vocale de précision associé aux dernières avancées en matière d'apprentissage automatique, nous pouvons désormais quantifier exactement la position d'une personne sur un continuum entre santé et maladie en utilisant uniquement les signaux vocaux. 02:53Таким образом, в некоторых случаях эти вокальные эффекты могут быть довольно тонкими, но с любым цифровым микрофоном и с помощью программного обеспечения для точного анализа голоса в сочетании с последними достижениями в области машинного обучения, которое сейчас очень продвинуто, мы теперь можем количественно определить, где именно кто-то находится на континууме между здоровьем и болезнью, используя только голосовые сигналы.

03:14So these voice-based tests, how do they stack up against expert clinical tests? 03:14 Итак, как эти голосовые тесты соотносятся с экспертными клиническими тестами? We'll, they're both non-invasive. The neurologist's test is non-invasive. They both use existing infrastructure. You don't have to design a whole new set of hospitals to do it. And they're both accurate. Et ils sont tous deux exacts. Okay, but in addition, voice-based tests are non-expert. D'accord, mais en plus, les tests basés sur la voix ne sont pas des tests d'experts. That means they can be self-administered. Cela signifie qu'ils peuvent être auto-administrés. They're high-speed, take about 30 seconds at most. They're ultra-low cost, and we all know what happens. When something becomes ultra-low cost, it becomes massively scalable. Quand quelque chose devient ultra-économique, il devient massivement évolutif. So here are some amazing goals that I think we can deal with now. Voici donc quelques objectifs étonnants qui, je pense, peuvent être atteints maintenant. We can reduce logistical difficulties with patients. No need to go to the clinic for a routine checkup. We can do high-frequency monitoring to get objective data. We can perform low-cost mass recruitment for clinical trials, and we can make population-scale screening feasible for the first time. Nous pouvons procéder à un recrutement massif et peu coûteux pour les essais cliniques, et nous pouvons rendre le dépistage à l'échelle de la population réalisable pour la première fois. Мы можем провести недорогой массовый набор для клинических испытаний, и мы можем впервые сделать возможным скрининг в масштабе всего населения. We have the opportunity to start to search for the early biomarkers of the disease before it's too late. 04:07So, taking the first steps towards this today, we're launching the Parkinson's Voice Initiative. 04:07 Итак, делая первые шаги к этому сегодня, мы запускаем инициативу «Голос Паркинсона». With Aculab and Patients Like Me, we're aiming to record a very large number of voices worldwide to collect enough data to start to tackle these four goals. Avec Aculab et Patients Like Me, nous visons à enregistrer un très grand nombre de voix dans le monde pour collecter suffisamment de données pour commencer à atteindre ces quatre objectifs. С Aculab и пациентами, как я, мы стремимся записать очень большое количество голосов по всему миру, чтобы собрать достаточно данных, чтобы начать решать эти четыре цели. We have local numbers accessible to three quarters of a billion people on the planet. Anyone healthy or with Parkinson's can call in, cheaply, and leave recordings, a few cents each, and I'm really happy to announce that we've already hit six percent of our target just in eight hours. Thank you. (Applause) (Applause)

04:43Tom Rielly: So Max, by taking all these samples of,

04:47let's say, 10,000 people, you'll be able to tell who's healthy and who's not? What are you going to get out of those samples?

04:54Max Little: Yeah. Yeah. So what will happen is that, during the call you have to indicate whether or not you have the disease or not, you see. TR: Right. ML: You see, some people may not do it. They may not get through it. But we'll get a very large sample of data that is collected from all different circumstances, and it's getting it in different circumstances that matter because then we are looking at ironing out the confounding factors, and looking for the actual markers of the disease. Но мы получим очень большую выборку данных, собранных из самых разных обстоятельств, и получение их в разных обстоятельствах имеет значение, потому что тогда мы смотрим на сглаживание смешанных факторов и ищем фактические маркеры болезни. 05:15TR: So you're 86 percent accurate right now? 05:15TR : Vous avez donc une précision de 86 % à l'heure actuelle ? 05:18ML: It's much better than that. Actually, my student Thanasis, I have to plug him, because he's done some fantastic work, and now he has proved that it works over the mobile telephone network as well, which enables this project, and we're getting 99 percent accuracy. 05:30TR: Ninety-nine. Well, that's an improvement. So what that means is that people will be able to — ML: (Laughs) TR: People will be able to call in from their mobile phones and do this test, and people with Parkinson's could call in, record their voice, and then their doctor can check up on their progress, see where they're doing in this course of the disease. 05:46ML: Absolutely.

05:47TR: Thanks so much. 05:47TR : Merci beaucoup. Max Little, everybody.

05:48ML: Thanks, Tom. (Applause)