So, 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.
Dakle, bavim se primenjenom matematikom i svojstven problem za svakoga ko se bavi primenjenom matematikom, je taj da smo mi kao konsultanti u oblasti menedžmenta. Niko ne zna šta dovraga radimo. Dakle, pokušaću danas da vam objasnim šta radim.
So, 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.
Dakle, ples je jedna od najljudskijih aktivnosti. Uživamo u virtuozima baleta i plesačima stepa koje ćete videti kasnije. E sad, balet zahteva izvanredan nivo stručnosti i visok nivo umeća, i verovatno određeni nivo predodređenosti koji je vrlo verovatno sakriven u genima. Nažalost, poremećaji nervnog sistema kao što je Parkinsonova bolest postepeno uništavaju ovu izvanrednu sposobnost, kao što to čini mom prijatelju Janu Striplingu, koji je bio virtuoz baleta u svoje vreme. Važan napredak u lečenju je napravljen tokom godina. I pored toga, 6,3 miliona ljudi širom sveta ima ovu bolest i mora da živi sa neizlečivom slabošću, drhtavicom, ukočenošću i ostalim simptomima koji prate ovu bolest, pa ono što nam je potrebno jesu objektivni alati da prepoznamo bolest pre nego što je kasno. Moramo biti sposobni da objektivno odredimo napredovanje, i na kraju krajeva, jedini način da znamo da zapravo imamo lek je da posedujemo objektivne mere koje mogu sigurno odgovoriti na to.
But 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.
Ali frustrirajuće je to što kod Parkinsonove bolesti i ostalih poremećaja kretanja, ne postoje nikakvi biomarkeri, ne postoji običan test krvi koji možete uraditi, i najbolje što imamo je ovaj test nervnog sistema od 20 minuta. Morate uraditi taj test u klinici. Veoma, veoma je skup, i to znači da, van kliničkih ispitivanja nikad se ne sprovodi. Nikad.
But 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.
Ali šta ako bi pacijenti mogli da urade test kod kuće? Tako bi ih zapravo poštedeli teškog puta do klinike, i šta kad bi sami mogli da urade test, zar ne? Ne zahteva vreme skupog osoblja. Košta, uzgred, 300 dolara, na neurološkoj klinici, da se uradi.
So 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.
Ono što želim da vam predložim kao nekonvencionalan način putem kojeg želimo ovo da postignemo, jer, vidite, na neki način barem, svi smo mi virtuozi kao moj prijatelj Jan Stripling.
So 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.
Ovde imamo video vibrirajućih glasnih žica. Ovo je zdravo i ovo je neko ko stvara govorne zvukove i možemo zamisliti sebe kao vokalne baletane, jer moramo da koordiniramo svim ovim vokalnim organima kad stvaramo zvukove, i svi mi zapravo posedujemo gene za to. Na primer, "FoxP2" . I kao i balet, to zahteva izuzetan nivo treninga. Mislim, zamislite samo koliko treba detetu da nauči da priča. Pomoću zvuka, možemo pratiti poziciju glasne žice kako vibrira, i kao što su udovi pogođeni kod Parkinsona, tako su i vokalni organi. Na donjoj crti, možete videti primer nepravilnog drhtanja glasne žice. Vidimo sve iste simptome. Vidimo vokalno podrhtavanje, slabost i ukočenost. Govor zapravo postaje tiši i zadihaniji posle nekog vremena, i ovo jedan primer simptoma.
So 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.
Ovi vokalni efekti mogu biti zaista poprilično suptilni, u nekim slučajevima, ali sa bilo kojim digitalnim mikrofonom, i koristeći precizne softvere za analizu glasa u kombinaciji sa najnovijim mogućnostima mašinskog učenja, koje je mnogo unapređeno danas, možemo tačno odrediti gde se neko nalazi na kontinuumu između zdravlja i bolesti koristeći jedino glasovne signale.
So 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.
Kako ovi testovi na osnovu glasa stoje naspram ekspertskih kliničkih testova? Pa, oba su neinvazivna. Neurološki test je neinvazivan. Oba koriste postojeću infrastrukturu. Ne morate dizajnirati potpuno nove bolnice da bi ga uradili. I oba su tačna. Dobro, ali osim toga, testovi na bazi glasa ne zahtevaju stručnjaka. To znači da se mogu samostalno koristiti. Brzi su, potrebno je najviše 30 sekundi. Veoma su jeftini i svi znamo šta se dešava. Kad nešto postane jako jeftino, postaje masovno upotrebljavano. Evo nekoliko neverovatnih ciljeva koje mislim da možemo rešiti sad. Možemo smanjiti logističke poteškoće sa pacijentima. Nema potreba da se ide u bolnicu na rutinsku kontrolu. Možemo uraditi kontrolu visoke frekvencije da bismo dobili objektivne podatke. Možemo izvršti jeftine masovne regrutacije za klinička ispitivanja, i možemo po prvi put uraditi testiranja na nivou populacije. Imamo mogućnost da započnemo potragu za ranim biomarkerima bolesti pre nego što bude kasno.
So, taking the first steps towards this today, we're launching the Parkinson's Voice Initiative. With Aculab and PatientsLikeMe, 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)
I tako, čineći prve korake ka ovome danas, pokrećemo Parkinsonovu Glasnu Inicijativu. Sa "Aculab" i "PatientsLikeMe", ciljamo da snimimo veliki broj širom sveta da bismo sakupili dovoljno podata i započeli ostvarivanje ova četiri cilja. Imamo lokalne brojeve dostupne za tri-četrvrtine milijarde ljudi na planeti. Svako ko je zdrav ili sa Parkinsonom može nazvati, jeftino, i ostaviti snimke, nekoliko centi za svaki, i zaista sam srećan da objavim da smo već dostigli 6% naše ciljne grupe u roku od samo 8 sati. Hvala vam. (Aplauz) (Aplauz)
Tom Rielly: So Max, by taking all these samples of,
Tom Rajli: Znači Maks, uzimajući sve ove uzorke od,
let'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?
recimo, 10.000 ljudi, vi ćete moći da kažete ko je zdrav, a ko nije? Šta ćete dobiti iz svih tih uzoraka?
Max 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.
Maks Litl: Da. Da. Ono što će se desiti je, za vreme poziva morate naznačiti da li imate bolest ili ne, znate. TR: U redu. ML: Neki ljudi neće to uraditi. Oni možda neće proći kroz to. Ali mi ćemo dobiti veliki broj uzoraka koji su prikupljeni pod različitim okolnostima, i uzimati ih u različitim okolnostima je važno jer zatim nastojimo da izdvojimo zbunjujuće faktore
TR: So you're 86 percent accurate right now?
i tražimo stvarne markere bolesti.
ML: 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.
TR: Znači vi ste sad 86% tačni? ML: Mnogo je bolje od toga. Zapravo, moj student Tanasis, moram ga spomenuti, jer je uradio fantastičan posao, i dokazao je da to funkcioniše i preko mobilne telefonske mreže
TR: 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.
što omogućava ovaj projekat, i postajemo 99% tačni. TR: Devedeset devet. Pa, to je zaista napredak. Dakle, to znači da će ljudi biti u mogućnosti - ML: (Smeh) TR: Ljudi će moći da nazovu sa svojih mobilnih telefona i urade ovaj test, i ljudi sa Parkinsonom mogu nazvati, snimiti svoj glas i zatim njihov doktor može proveriti njihov napredak,
ML: Absolutely.
videti u kojoj fazi je bolest.
TR: Thanks so much. Max Little, everybody.
ML: Apsolutno.
ML: Thanks, Tom. (Applause)
TR: Hvala ti puno. Maks Litl.