Press "Enter" to skip to content

How Big Data is Helping Build Safer Hospitals? | Dr. Tav Pritesh Sethi | TEDxAIIMS


[Applause]

[Applause] some doctors are amazing computer

some doctors are amazing computer

some doctors are amazing computer scientists I would say with the kind of

scientists I would say with the kind of

scientists I would say with the kind of tinkering that you can do with human

tinkering that you can do with human

tinkering that you can do with human physiology which is the most complicated

physiology which is the most complicated

physiology which is the most complicated machine we are really amazing hackers do

machine we are really amazing hackers do

machine we are really amazing hackers do you know that it took about eighty four

you know that it took about eighty four

you know that it took about eighty four thousand processors put together into

thousand processors put together into

thousand processors put together into the Japanese supercomputer K the steam

the Japanese supercomputer K the steam

the Japanese supercomputer K the steam so to simulate just one second of human

so to simulate just one second of human

so to simulate just one second of human brain activity and I’m not talking of

brain activity and I’m not talking of

brain activity and I’m not talking of the brains that are sitting here I’m

the brains that are sitting here I’m

the brains that are sitting here I’m talking of regular vanilla brains so so

talking of regular vanilla brains so so

talking of regular vanilla brains so so if you are really worried about robots

if you are really worried about robots

if you are really worried about robots taking over the world or even taking

taking over the world or even taking

taking over the world or even taking over this event the humans are in safe

over this event the humans are in safe

over this event the humans are in safe space but seriously ten years back when

space but seriously ten years back when

space but seriously ten years back when I was finishing medical school I didn’t

I was finishing medical school I didn’t

I was finishing medical school I didn’t feel like I was a hacker of physiology I

feel like I was a hacker of physiology I

feel like I was a hacker of physiology I didn’t feel like that I could hack

didn’t feel like that I could hack

didn’t feel like that I could hack precisely disease back to health and I

precisely disease back to health and I

precisely disease back to health and I was at a loss so I took to science and I

was at a loss so I took to science and I

was at a loss so I took to science and I was happy that I do it I did it and it

was happy that I do it I did it and it

was happy that I do it I did it and it was the era of big day right the big

was the era of big day right the big

was the era of big day right the big data was just beginning genomics

data was just beginning genomics

data was just beginning genomics revolution had begun with big data

revolution had begun with big data

revolution had begun with big data permeating into medicine but there was a

permeating into medicine but there was a

permeating into medicine but there was a problem

problem

problem very few people here would know that I

very few people here would know that I

very few people here would know that I am also an expert musician just watch me

I’m not sure if you could hear that but

I’m not sure if you could hear that but that was the problem of the Big Data

that was the problem of the Big Data

that was the problem of the Big Data revolution we thought that our

revolution we thought that our

revolution we thought that our physiologies and our health is a meetly

physiologies and our health is a meetly

physiologies and our health is a meetly laid out organized system and if we had

laid out organized system and if we had

laid out organized system and if we had the data we could actually create the

the data we could actually create the

the data we could actually create the music but now we know that is not the

music but now we know that is not the

music but now we know that is not the case so traditional data which look like

case so traditional data which look like

case so traditional data which look like the one of left was neatly organized

the one of left was neatly organized

the one of left was neatly organized medical research was neatly organized

medical research was neatly organized

medical research was neatly organized whereas now we know for sure that

whereas now we know for sure that

whereas now we know for sure that neither our physiologies nor the big

neither our physiologies nor the big

neither our physiologies nor the big data is neatly organized it’s like it’s

data is neatly organized it’s like it’s

data is neatly organized it’s like it’s messy actually we are a mess it’s like

messy actually we are a mess it’s like

messy actually we are a mess it’s like the Einsteins messy desk

the Einsteins messy desk

the Einsteins messy desk nobody knows where are the connections

nobody knows where are the connections

nobody knows where are the connections how to make those connections and that’s

how to make those connections and that’s

how to make those connections and that’s why I would say that doctors biologists

why I would say that doctors biologists

why I would say that doctors biologists engineers bio physicists and biochemists

engineers bio physicists and biochemists

engineers bio physicists and biochemists really need to take up the science of

really need to take up the science of

really need to take up the science of data because after all we have the

data because after all we have the

data because after all we have the connections made up in the right side of

connections made up in the right side of

connections made up in the right side of our brain and from there it’s just one

our brain and from there it’s just one

our brain and from there it’s just one leap onto the left side of the brain

leap onto the left side of the brain

leap onto the left side of the brain which is quantitative thinking so what

which is quantitative thinking so what

which is quantitative thinking so what I’m gonna do today is break up that

I’m gonna do today is break up that

I’m gonna do today is break up that quantitative thinking it into three

quantitative thinking it into three

quantitative thinking it into three smaller steps that we can understand and

smaller steps that we can understand and

smaller steps that we can understand and take these are phenotype deeply approach

take these are phenotype deeply approach

take these are phenotype deeply approach systemically and enable decisions so if

systemically and enable decisions so if

systemically and enable decisions so if I were to ask you that the beating of

I were to ask you that the beating of

I were to ask you that the beating of our hearts resembles which of the images

our hearts resembles which of the images

our hearts resembles which of the images on the top the left of the right you

on the top the left of the right you

on the top the left of the right you might be surprised to know that a heart

might be surprised to know that a heart

might be surprised to know that a heart rate intubate intervals do not resemble

rate intubate intervals do not resemble

rate intubate intervals do not resemble the periodic pattern on the left they

the periodic pattern on the left they

the periodic pattern on the left they actually resemble the complex multi-tier

actually resemble the complex multi-tier

actually resemble the complex multi-tier of fractal patterns that are found all

of fractal patterns that are found all

of fractal patterns that are found all over the nature on the right like the

over the nature on the right like the

over the nature on the right like the broccoli here so diversity and

broccoli here so diversity and

broccoli here so diversity and complexity are actually a measure of

complexity are actually a measure of

complexity are actually a measure of healthiness of health

healthiness of health

healthiness of health I enjoyed doing my PhD and viola was

I enjoyed doing my PhD and viola was

I enjoyed doing my PhD and viola was having fun with looking at these signals

having fun with looking at these signals

having fun with looking at these signals we really found a use for it the

we really found a use for it the

we really found a use for it the phenotype the signals deeply and we

phenotype the signals deeply and we

phenotype the signals deeply and we found that these signals really held

found that these signals really held

found that these signals really held meaning for small airway disease which

meaning for small airway disease which

meaning for small airway disease which is notoriously difficult to detect so we

is notoriously difficult to detect so we

is notoriously difficult to detect so we could design a non-invasive marker of

could design a non-invasive marker of

could design a non-invasive marker of small early small airway disease without

small early small airway disease without

small early small airway disease without doing biopsies and this was based on the

doing biopsies and this was based on the

doing biopsies and this was based on the mathematics of the how our respiratory

mathematics of the how our respiratory

mathematics of the how our respiratory trees behave and we were able to show

trees behave and we were able to show

trees behave and we were able to show that this achieved unprecedented

that this achieved unprecedented

that this achieved unprecedented sensitivity the resolution that you see

sensitivity the resolution that you see

sensitivity the resolution that you see on the right versus the standard

on the right versus the standard

on the right versus the standard techniques that you see on the left so

techniques that you see on the left so

techniques that you see on the left so this is just one example of phenotyping

this is just one example of phenotyping

this is just one example of phenotyping deeply but I would warn you that

deeply but I would warn you that

deeply but I would warn you that phenotyping deeply sometimes can get

phenotyping deeply sometimes can get

phenotyping deeply sometimes can get immersive we can get lost in the

immersive we can get lost in the

immersive we can get lost in the patterns because the mathematics is

patterns because the mathematics is

patterns because the mathematics is beautiful so here I come to the second

beautiful so here I come to the second

beautiful so here I come to the second principle that I use continuously in my

principle that I use continuously in my

principle that I use continuously in my data science which is approach

data science which is approach

data science which is approach systemically look at the forest first

systemically look at the forest first

systemically look at the forest first whether it makes sense whether the

whether it makes sense whether the

whether it makes sense whether the bigger picture makes sense and this I’m

bigger picture makes sense and this I’m

bigger picture makes sense and this I’m going to illustrate by our work on

going to illustrate by our work on

going to illustrate by our work on 200,000 patients data collected on a

200,000 patients data collected on a

200,000 patients data collected on a single day all across India by Chess

single day all across India by Chess

single day all across India by Chess Research Foundation Pune

Research Foundation Pune

Research Foundation Pune we were skeptical because this was

we were skeptical because this was

we were skeptical because this was questionnaire based data so I decided to

questionnaire based data so I decided to

questionnaire based data so I decided to do the checks by doing the big picture

do the checks by doing the big picture

do the checks by doing the big picture first by doing network analysis and

first by doing network analysis and

first by doing network analysis and that’s what we found

that’s what we found

that’s what we found each node here is a symptom or a disease

each node here is a symptom or a disease

each node here is a symptom or a disease and you could see that in the bigger

and you could see that in the bigger

and you could see that in the bigger picture diseases have friends they form

picture diseases have friends they form

picture diseases have friends they form communities and they are in key

communities and they are in key

communities and they are in key influencers in this network in this

influencers in this network in this

influencers in this network in this disease makeup which you call the

disease makeup which you call the

disease makeup which you call the symptom this symptom is the symptom of

symptom this symptom is the symptom of

symptom this symptom is the symptom of the pediatric age group of the Indian

the pediatric age group of the Indian

the pediatric age group of the Indian population we imagined how would these

population we imagined how would these

population we imagined how would these networks change across age group how

networks change across age group how

networks change across age group how would they flow we did just that by

would they flow we did just that by

would they flow we did just that by using computational techniques and he

using computational techniques and he

using computational techniques and he found that on the x axis here is the age

found that on the x axis here is the age

found that on the x axis here is the age groups 0 to 10 and more than 16 you

groups 0 to 10 and more than 16 you

groups 0 to 10 and more than 16 you could see that these networks far

could see that these networks far

could see that these networks far formed loaded streamlines the most

formed loaded streamlines the most

formed loaded streamlines the most loaded streamline is the respiratory

loaded streamline is the respiratory

loaded streamline is the respiratory streamline hair it’s being the most

streamline hair it’s being the most

streamline hair it’s being the most prevalent but look at circulatory in the

prevalent but look at circulatory in the

prevalent but look at circulatory in the red

red

red it becomes more loaded as we age and it

it becomes more loaded as we age and it

it becomes more loaded as we age and it merges with endocrine which is diabetes

merges with endocrine which is diabetes

merges with endocrine which is diabetes most predominantly that top streamline

most predominantly that top streamline

most predominantly that top streamline thin stream lining on the top is female

thin stream lining on the top is female

thin stream lining on the top is female genitalia it gets loaded it comes down

genitalia it gets loaded it comes down

genitalia it gets loaded it comes down it merges with anemia they stay together

it merges with anemia they stay together

it merges with anemia they stay together in the reproductive age group and then

in the reproductive age group and then

in the reproductive age group and then they separate out any me of menstrual

they separate out any me of menstrual

they separate out any me of menstrual disorders is so hugely prevalent in

disorders is so hugely prevalent in

disorders is so hugely prevalent in India and this big data was actually

India and this big data was actually

India and this big data was actually telling us some stories but we didn’t

telling us some stories but we didn’t

telling us some stories but we didn’t stop at stories we decided to take it

stop at stories we decided to take it

stop at stories we decided to take it further to do machine learning and

further to do machine learning and

further to do machine learning and artificial intelligence models to really

artificial intelligence models to really

artificial intelligence models to really make predictions here is a Bayesian

make predictions here is a Bayesian

make predictions here is a Bayesian network analysis which is an artificial

network analysis which is an artificial

network analysis which is an artificial intelligence model upon the same data

intelligence model upon the same data

intelligence model upon the same data but what we did here was we combined

but what we did here was we combined

but what we did here was we combined that 2 lakh patient data together with

that 2 lakh patient data together with

that 2 lakh patient data together with the data available on LPG penetration

the data available on LPG penetration

the data available on LPG penetration into the country clean cooking fuel and

into the country clean cooking fuel and

into the country clean cooking fuel and we found that we did the Bayesian

we found that we did the Bayesian

we found that we did the Bayesian networks analysis LPG penetration which

networks analysis LPG penetration which

networks analysis LPG penetration which is in green the Novo comes out to be

is in green the Novo comes out to be

is in green the Novo comes out to be linked with obstructive airway disease

linked with obstructive airway disease

linked with obstructive airway disease these are separate sources of data

these are separate sources of data

these are separate sources of data remember there’s no crosstalk between

remember there’s no crosstalk between

remember there’s no crosstalk between them before the analysis so what if this

them before the analysis so what if this

them before the analysis so what if this was just an incidental finding the same

was just an incidental finding the same

was just an incidental finding the same techniques that allowed us to track

techniques that allowed us to track

techniques that allowed us to track dynamically the change in networks we

dynamically the change in networks we

dynamically the change in networks we used here to track the stability of

used here to track the stability of

used here to track the stability of models and that’s what you see on the

models and that’s what you see on the

models and that’s what you see on the top by using bootstraps upon the same

top by using bootstraps upon the same

top by using bootstraps upon the same data each seeing a different angle of

data each seeing a different angle of

data each seeing a different angle of the data critical conditions like sepsis

the data critical conditions like sepsis

the data critical conditions like sepsis and bad outcomes by using big data and

and bad outcomes by using big data and

and bad outcomes by using big data and the patterns that I just kind of showed

the patterns that I just kind of showed

the patterns that I just kind of showed you so we will be using phenotyping

you so we will be using phenotyping

you so we will be using phenotyping deeply approaching systemically and

deeply approaching systemically and

deeply approaching systemically and enabling decisions to create alerts for

enabling decisions to create alerts for

enabling decisions to create alerts for the doctors

so where are we now since it is a full

so where are we now since it is a full spectrum project we have started in the

spectrum project we have started in the

spectrum project we have started in the data science right from the scratch we

data science right from the scratch we

data science right from the scratch we are building up these resources we are

are building up these resources we are

are building up these resources we are building up technologies we are build we

building up technologies we are build we

building up technologies we are build we have built up 4,000 hours 40,000 hours

have built up 4,000 hours 40,000 hours

have built up 4,000 hours 40,000 hours of continuously monitored data at the

of continuously monitored data at the

of continuously monitored data at the Department of Pediatrics over the last

Department of Pediatrics over the last

Department of Pediatrics over the last five months but are we big yet I would

five months but are we big yet I would

five months but are we big yet I would not say yes my collaborator at Stanford

not say yes my collaborator at Stanford

not say yes my collaborator at Stanford School of Medicine has access to about

School of Medicine has access to about

School of Medicine has access to about 3.5 million hours of in continuous

3.5 million hours of in continuous

3.5 million hours of in continuous recording but we are starting right from

recording but we are starting right from

recording but we are starting right from the scratch and we are injecting our

the scratch and we are injecting our

the scratch and we are injecting our domain expertise into the building up of

domain expertise into the building up of

domain expertise into the building up of the systems and also in building up of

the systems and also in building up of

the systems and also in building up of the models so we’ll be there soon those

the models so we’ll be there soon those

the models so we’ll be there soon those brocolli patterns that I showed earlier

brocolli patterns that I showed earlier

brocolli patterns that I showed earlier they are actually enabling us to detect

they are actually enabling us to detect

they are actually enabling us to detect stability of these patients in the ICUs

stability of these patients in the ICUs

stability of these patients in the ICUs how stable they are how wondering are

how stable they are how wondering are

how stable they are how wondering are these signatures do they relate to

these signatures do they relate to

these signatures do they relate to outcomes for the real results on this

outcomes for the real results on this

outcomes for the real results on this we’ll have to wait a bit just like any

we’ll have to wait a bit just like any

we’ll have to wait a bit just like any full-spectrum project we have a great

full-spectrum project we have a great

full-spectrum project we have a great team and an amazing set of mentors and

team and an amazing set of mentors and

team and an amazing set of mentors and I’m really proud of the team of doctors

I’m really proud of the team of doctors

I’m really proud of the team of doctors and engineers that is actually backing

and engineers that is actually backing

and engineers that is actually backing us so what is the new pulse of Medicine

us so what is the new pulse of Medicine

us so what is the new pulse of Medicine is it big data or is it get a science or

is it big data or is it get a science or

is it big data or is it get a science or is it machine learning I would say that

is it machine learning I would say that

is it machine learning I would say that the new pulse of medicine is you all

the new pulse of medicine is you all

the new pulse of medicine is you all those who venture out into the

those who venture out into the

those who venture out into the next-generation medicine and will create

next-generation medicine and will create

next-generation medicine and will create a difference let’s make every bit count

a difference let’s make every bit count

a difference let’s make every bit count thanks very much

thanks very much

thanks very much [Applause]

”

Be First to Comment

Leave a Reply

Your email address will not be published. Required fields are marked *