Fast Charged #16. Beyond the Scalpel: AI, Surgery, and the Future of Personalized Care

Introduction to EndoBattery Fast Charged

Alanna
0:01

Welcome

to

Endo

Battery

Fast

Charged
,

a

series

dedicated

to

keeping

you

informed

and

empowered

in

the

realm

of

endometriosis
.

Teaming

up

with

board-certified

patient

advocates
,

we

bring

you

the

latest

articles
,

research

and

insights

to

equip

you

with

accurate

information

and

a

deeper

understanding
.

Whether

you're

expanding

your

knowledge
,

staying

updated

or

seeking

clarity
,

you're

in

the

right

place
.

I'm

your

host
,

alana
,

and

this

is

Endo

Battery

Fast

Charged

charging

and

empowering

your

life

with

knowledge
.

Welcome

back

to

Endo

Battery

Fast

Charged
,

where

we

power

through

the

latest

research

shaping

endometriosis

and

women's

health
.

I

couldn't

be

more

excited

to

have

our

very

first

guest

on

this

series
,

Dr
.
Canio

Martinelli
,

an

OBGYN

specialist

and

the

head

of

clinical

program

at

Sbarro

Health

Research

Organization

at

Temple

University
.

Dr

Martinelli
,

recently

named

FDA

AACR

Oncology

Educational

Fellow
,

is

at

the

forefront

of

translating

cutting-edge

science

into

real-world

impact
.

His

work

connects

emerging

research
,

clinical

care

and

the

future

treatment

for

people

with

endometriosis
,

helping

us

better

understand

where

innovation

can

truly

change

lives
.

And

just

as

a

friendly

reminder
,

correlation

does

not

equal

causation
.

So

let's

keep

our

curiosity

fully

charged
,

but

stay

grounded

as

we

dig

in
.

Alanna
1:27

You

know

how

I

always

say

grab

a

cup

of

coffee

or

a

cup

of

tea

and

join

me

at

the

table

before

we

get

started
.

Well
,

what

if

that

cup

could

do

more

than

just

taste

good
?

Meet

Strong

Coffee

Company
,

my

little

secret

weapon
.

It's

premium

instant

coffee

loaded

with

protein
,

mcts

and

adaptogens

so

you

get

smooth
,

energy
,

sharp

focus

and

none

of

that

jittery

crash
.

Basically
,

it's

coffee

that

actually

shows

up

for

you
.

Use

my

promo

code

endobattery

for

an

exclusive

20%

discount

and

yes
,

when

you

do
,

you're

helping

me

keep

these

expert

conversations

brewing

here

at

IndoBattery
.

So

go

on
,

grab

your

cup
,

power

up

by

going

to

strongcoffeecompanycom

and

using

the

code

Endo
Battery
,

and

let's

make

this

episode

even

better
.

Let's

get

into

this
.

Thank

you

so

much

for

joining

me

and

sitting

down

and

going

over

this

research
.

Let's

start

with

how

we

do

research
.

Canio
2:24

First

of

all
,

thank

you

for

having

me

here
.

You

already

know

how

much

I

appreciate

you
.

I

mean
,

whatever

you

do

is

incredible

for

patients
,

for

people

and

for

us

also
,

scientists

and

physicians
,

because

research
,

as

we

already

said
,

is

about

trying

to

find

the

right

answer

to

people
.

So

we

need

to

resonate

together
,

to

talk

together
,

to

be

much

more

connected

when

it

comes

to

research
.

We're

talking

about

one

of

my

greatest

passion
,

because

research

is

a

way

to

find

solution

to

problems
.

So

every

research

starts

with

what

we

call

research

question
.

So

what

is

the

question

we

are

trying

to

address
?

And

after

we

get

that

question
,

then

we

start

to

develop

different

hypotheses

and

then

the

goal

here

is

trying

to

have

the

right

methodology

to

confirm

or

not

our

hypothesis
.

So

it's

everything

extremely

serious

and

rigid
,

because

at

the

end
,

the

conclusion

that

we

get

from

that
,

out

of

this
,

has

to

be

applicable

to

people

in

a

specific

way
.

It

means

that

we

need

to

not

just

give

an

information
,

just

give

this

study

showed

this
.

We

need

to

be

able

also

to

tell

them

these

are

the

data
,

this

is

the

way

you

have

to

apply

that
.

So

it's

then

after

we've

published

the

study
.

That's

what

we

call

the

critical

appraisal
.

So

how

can

I

really

use

that

data
?

Is

it

going

to

use

the

data

in

the

same

way

in

the

world
?

Is

it

applied

only

to

specific

population
,

especially

right

now

that

we

are

going

in

personalized

and

precision

medicine
?

We

will

talk

about

that
,

but

so

I

think

that

it's

much

easier

to

talk

about

specific

articles
.

I

can

tell

you

all

the

process
.

Canio
4:11

One

of

the

most

interesting

for

people

study

that

we

published

was

the

one

on

AI

applied

to

improve

the

clinical

metrics

for

physician
.

Because

everybody

had

this

experience
,

like

me

as

a

physician
.

Also
,

explore

CHATGPT

to

explore

rather

than

Claude,

Gemini
,

and
,

since

access

to

healthcare

is

very
,

very

hard

today
,

as

well

as

education

for

medical

students
,

everybody
,

somehow

we

relate

with

this

new

technology
,

how

we

relate

with

this

new

technology
.

So

our

idea

is

let's

do

this

scientific

study

in

order

to

try

to

understand

not

just

whether

this

new

machine
,

these

new

tools
,

are

better

than

physician
,

but

I

want

to

try

to

understand

if

the

reasoning

of

this

machine

is

actually

different

than

physician
,

because

if

I

understand

that
,

I

know

how

to

find

a

way

to

match

them
,

to

merge

them
,

how

to

really

improve

the

ability

for

physician
.

But

if

I'm

even

able

to

understand

how
,

the

reason
,

I

can

give

practical

tips

to

people

and

say
,

okay
,

if

you

really

want

to

have

a

suggestion
,

a

tip

from

Chachi

PT

or

Clodagh

Gemini

or

Meta
,

you

can

ask

it
,

but

you

need

to

be

aware

and

to

be

able

how

to

handle

that

information
.

That's

the

key
,

because

as

you

go

to

different

doctors
,

they

can

give

you

different

information
.

Which

one

is

the

right

one
?

You

can

pick

up

the

right

one

in

front

of

a

doctor

because

he

or

she

is

nice

or

because

you

can

resonate

with

it

when

you

do

with

what

we

call

large

language

models
.

So

it's

like

very

disconnected

stuff
.

You

don't

have

any
,

not

just

you

as

a

patient

or

people
,

but

you

even

as

a

doctor
.

Right

now
.

You

don't

have

any

tips
,

any

guidelines

to

say
,

ok
,

what

he's

saying

is

100%

sure
,

because

you

don't

know

where

the

data

comes

from
.

Canio
5:59

So

what

we

did
?

We

actually

use

different

LLMs

different

like

ChatGPT
,

clove
,

gemini
,

Meta
,

the

different

version

and

we

choose

24

residents

in

a

gynecology

and

we

develop

60

different

clinical

scenarios
.

So

we

ask

to

the

resident

and

we

ask

to

LLMs

to

try

to

approach

the

clinical

scenario
,

to

give

us

an

answer
.

We

did

this

in

a

different

situation

because

the

idea

is

trying

to

see

how

can

I

use

that

technology

and

even

to

test

the

technology

in

different

situations
.

So

we

decided

to

split

the

question

following

language
.

So

we

test

the

scenarios

in

English

and

in

Italian
,

and

then

we

test

the

scenarios

even

with

time

constraints
.

It

means

that

for

some

question
,

people

were

completely

free

to

answer
,

with

all

the

calm

of

the

world
,

the

question
.

In

other

scenarios

they

needed

to

give

the

same

question
,

the

same

answer

in

10

seconds
.

Canio
7:00

And

then

the

resident
,

the

gynecological

resident
.

They

were

actually

grouped

in

different

years

of

expertise
,

so

they

were

the

fresh

one

and

the

senior

one
.

That

was

a

study

that

was

conducted

last

year
,

so

during

2024,
.

That's

important

to

see

because

the

technology
,

especially

in

AI
,

is

speeding

up

so

much
.

So

maybe

right

now

the

duration

could

be

different
.

But

I

actually

did

another

test

where

I

saw

that

the

metrics

are

pretty

much

the

same
.

So

let's

start

from

the

first

outcome
,

so

the

first

results

from

the

study
.

If

we

took

overall
,

the

all

LLM

versus

the

all

resident

across

all

the

different

ages

of

expertise
,

we

are

basically

seeing

that

they

match

as

a

result
.

So

right

now
,

specifically

to

that
,

60

scenarios
,

ai

is

able

to

give

you

almost

the

same

answer

of

residents
,

not

senior

physicians
.

Canio
7:58

But

then

we

did

what

we

call

sub-analysis
,

so

within

the

data

we

try

to

explore

correlation

in

order

to

get

practical

information
.

So

we

understood
,

for

example
,

that

if

you

compare

the

senior

physician

at

a

resident

in

gynecology

to

the

average

of

LLMs
,

the

senior

are

much
,

much

better

than

the

average

LLM
.

But

if

you

take

the

best

LLM
,

there

was

one

that

you

need

to

pay
.

That

one

is

almost

same

accuracy

of

the

senior

residents
.

But

the

other

sub-analysis

was

during

time

constraints
,

because

when

you

put

pressure

on

people

and

residents

you

see

that

their

performance

metrics

gonna

really

reduce

a

lot
,

while

the

LLM

metrics

are

staying

stable
.

And

then

we

also

saw

the

pattern
,

what

we

call

the

pattern

of

mistake

of

humans

compared

to

machines
,

and

we

saw

that

the

pattern

of

mistakes

is

actually

different
.

So

that's

important

because

what

you

do

as

a

physician

or

a

people

like
,

whenever

you

inquire

those

machines
,

they

come

to

a

conclusion

the

different

one

you

take
.

So

who

is

the

one

that

is

right
,

me

or

the

machine
?

Alanna
9:10

Right
.

Canio
9:11

The

problem

is

that

being

able

to

predict

whether

a

machine

is

wrong

is

as

much

as

hard

than

being

able

to

predict

whether

a

physician

is

wrong
.

So

the

real

take

from

the

study

is

maybe

for

people

right

now

are

able

to

give

you

general

advices

in

the

right

way
,

but

if

you

really

want

to

have

the

answer

from

yourself
,

it's

still

not

well

performed
.

Because

if

you

want

to

know

something

about

anything

issue
,

any

field
,

you

want

to

have

a

kind

of

recommendation
,

it

could

be

okay

using

the

stuff
.

But

if

you

have

a

problem

and

you

want

to

have

a

solution

that

is

really

perfect

for

yourself

in

your

specific

time
,

your

specific

situation
,

well

that's

not

the

right

tool
.

And

when

it

comes

for

physician
,

it

depends

the

way

you

use

LLM
,

because

basically

this

stuff

is

just

an

advanced

researcher
.

It

depends

the

way

you

use

LLM
,

because

you

basically

this

stuff

is

just

an

advanced

researcher
.

It

depends

the

way

you

write

the

prompt
.

So

in

the

way

you

give

them

the

data

to

analyze

the

case
,

the

more

option

the

machine

has
,

it's

easier

for

them
,

for

the

machine

to

make

a

mistake
.

And

that's

where

it

comes
.

Canio
10:31

Expert

physician
,

expert

physician
,

the

one

that's

not

just

you

know
,

mastering

one

technique

and

offering

only

one

technique

to

patient

or

one

treatment
.

The

great

physician

is

one

that

knows

a

lot

of

different

kind

of

management

and

is

able

to

apply

that

specific

management

or

treatment

to

your

specific

condition

of

life
.

So

in

this

matching

course
,

you

know
,

senior

physicians

are

so

much

better

than

LLM
.

But

here

again
,

we

don't

need

LL

to

substitute

humans
.

We

need

LLM

in

maybe
,

for

example
,

when

you

have

pressure
,

when

you

have

a

high

workload
,

you

need

to

take

a

decision
.

It

can

help

you

to

give

the

data

that

you

need

to

take

the

decision
.

So

it's

much

more

like

a

co-piloting

and

when

it

comes

to

people
,

it

can

be

an

assistant

to

check

on

it
,

like
,

okay
,

did

you

check

this
,

did

you
?

But

not

just

for

giving

medical

advices
,

but

in

order

to

get

the

data

that

then

will

be

incorporated

by

the

system

and

the

physician

is

able

to

track

the

data

in

a

more

clear

way
.

Here

is

all

about

having

the

chance

to

see

the

pattern
.

The

pattern

of

the

data

coming

from

a

patient

is

critical

for

the

physician

to

act

in

the

best

way
.

Canio
11:50

So

this

first

study

basically
,

is

showing

that

if

we

need

to

train

a

system
,

we

know

that

the

way

AI

and

doctors

so

humans

reason

is

different
.

We

need

to

be

aware

of

these

differences

and

then
,

when

we

want

to

implement

a

system

that

is

AI

powered

with

human

in

the

loop
,

it

means

that

there

is

a

system

that

is

taking

care

about

you

you

need

AI

that

is

called

supervised
.

So

it

means

that

I

need

to

teach

the

AI

whatever

I

know

and

I

need

to

set

boundaries
,

because

these

LLM

in

the

studies

were

like

commercial

LLM
,

so

everybody

can

get

access

to

that
.

The

next

step

is

going

to

be

being

able

to

use

that

technology

but
,

more

importantly
,

being

able

to

teach

and

set

boundaries
.

So

it

says

you

cannot

go

too

far

away

from

that
.

If

the

patient

really

want

to

have

that

kind

of

answer
,

you're

not

able

to

give

it
.

Canio
12:43

So

just

says

you

cannot

go

too

far

away

from

that
.

If

the

patient

really

want

to

have

that

kind

of

answer
,

you're

not

able

to

give

it
.

So

just

say

refer

to

the

doctors

and

we

need

them

to

train

time

after

time
,

year

after

year

and

in

a

way

that

it

can

take

care

of

the

most

annoying

stuff

and

humans

can

be

much

more

oriented
.

They

can

be

used

in

very

complex

scenarios
,

but

overall

that's

even

a

challenge

for

humans
,

actually
,

because

you

are

understanding

here

that

as

a

human
,

you

need

to

go

faster

here
.

As

a

physician
,

you

need

to

be

extremely

trained

to

think
.

You

need

to

be

extremely

trained

not

to

analyze

the

data
,

but

to

talk

with

people
,

because

they

are

getting

to

us
.

I'm

not

saying

that

I

will

make

a

diagnosis
.

I'm

saying

that

if

we

do

not

evolve

as

humans
,

ai

will

get

better

than

us
.

Canio
13:31

That's

for

sure
,

because

it's

all

around

the

data

and

this

study

is

showing

that

Average

AI

is

basically

average

resident

in

a

gynecology
.

It's

kind

of

you

know
,

push

even

for

next

generation
,

young

generation
.

You

need

to

do

better

than

me

because

I'm

going

to

build

a

system

that

better

than

me
.

If

you're

not

better

than

me
,

my

system

is

going

to

be

better

than

you

as

a

physician
,

and

so

it's

kind

of

a

research
.

It's

kind

of

scary

because

if

you

look

at

the

data
,

basically

what

we're

showing

is

that

actual

LMM

can

be

even

useful

in

learning

for

physicians
.

Canio
14:07

But

I

want

to

give

hope
.

You

know

that

if

you

read

the

discussion

of

the

paper
,

it's

all

about

how

can

I

get

this

data

to

tailor

the

new

AI

model

to

help

physicians
.

And

with

those

data

now

we're

going

to

the

next

step
.

That

is

the

ongoing

paper

that

we

are

basically

writing

right

now
.

I

can't

say

the

name

of

the

study

because

actually

it's

going

to

be

published

very

soon
.

It's

called

Pulsar

Study
.

It's

a

study

where

we

are

right

now

building

the

architecture
,

the

digital

human

architecture
,

of

the

system

that

we

will

develop

in

the

future
.

And

that's

very

cool

because

it

comes

from

my

heart
.

My

passion

is

I

don't

know

if

you

have

any

question

for

the

other

study
,

otherwise

I

jump

in

this

new
.

Alanna
14:56

Well
,

I

think

I

want

something

to

point

out

in

this

study

and

maybe

you

touch

on

this

more
.

This

isn't

necessarily

a

replacement

for

doctors
.

It's

a

tool

to

be

helpful

for

providers

and

for

patients
,

not

a

replacement

for

those

that

might

be

a

little

bit

scary
.

You're

saying

that

this

study

is

emphasizing

that

it's

not

taking

over
,

it's

making

them

better
.

Canio
15:16

Yes
,

absolutely
.

You

know
,

I

know

education

medical

in

healthcare

is

crazy
,

but

that's

a

cool

thing
.

We

need

to

keep

pushing
,

because

whenever

we

understand
,

whenever

actually

we

explore

this

system
,

we

are

basically

exploring

a

way

to

understand

how

people

reason

even

more
,

because

whatever

we

are

doing

in

the

computer

science

applied

to

healthcare

is

actually

just

transpose

what

humans

already

do

in

their

brain

and

build

a

artificial

system

that

is

able

to

do

basically

the

same

stuff

and

the

same

way
.

While

we

are

exploring

this

new

technology
,

what's

happening

is

that

we

are

even

exploring

ourselves

much

better
.

So

it's

a

way

that

is

kind

of

a

challenge
,

because

the

more

you

develop

it
,

the

more

you

have

new

connection

in

your

mind
,

and

AI

right

now

is

not

able

to

find

something

that

is

not

possible
,

to

find

Everything

new

that

it

finds

is

not

necessarily

true
.

Same

things

in

the

research

right
,

whatever

we

find
,

it's

not

necessarily

true
.

As

same

things

in

the

research

right
,

whatever

we

find
,

it's

not

necessarily

true
.

We

need

them

to

validate

and
,

in

real

people
,

to

see

it
,

to

show

that

it's

really
,

really

good
.

So

in

doing

this
,

ai

is

extremely

brilliant
.

When

we

tell

them

exactly

a

very

limited

system
,

we

say

that's

how

we

work
,

we

give

you

rules

and

that's

where

you

have

to

act

Unlikely
.

Right

now

we're

not

talking

about

ChatGPD

or

anything

commercial

available
.

It's

a

system

that

uses

their

technology
,

but

they're

a

system

underdeveloped
,

so

it's

still

not

reality
.

Canio
16:58

There

are

also

lots

of

studies

that

are

showing

that

most

of

the

AI

tools

that

have

been

developing

in

healthcare
,

in

the

first

stages

phases

they

are

brilliant
.

Then
,

when

they

apply

the

tools

to

real

situation
,

real

hospital
,

they

really

do

not

perform

well
.

Yes
,

that's

because

we

need

to

understand
,

we

need

to

validate

those

stuff
,

so

it's

not

necessarily

right
.

So

the

science

is

cool

because

it's

kind

of

remember

that

you

need

to

be

humble
,

you

know
,

still

need

to

consider

that

you've

wrong
.

Your

research

question

may

be

wrong
.

If

it's

wrong
,

it

doesn't

mean

that

is

bad
.

It

means

that

that

is

not

the

right

way
.

You

need

to

find

another

one
.

And

from

that

perspective
,

we

are

getting

to

like

by

make

failure

and

mistake
.

We

are

getting

to

like

buying

make

failure

and

mistake
.

We

are

getting

to

something

much
,

much

better

and

it's

going

to

happen
.

It's

happening

very
,

very
,

very

fast
.

Alanna
17:50

Interesting
.

So

did

this

research

then

translate

into

what

your

next

paper

that's

going

to

be

published

Did

it
?

Was

that

the

catalyst

to

this

next

paper
,

Exactly
?

Canio
18:03

Absolutely

the

way

we
,

you

know
,

whenever

we

do

research
,

let's

say
,

even

needs

to

resonate

with

the

money

and

the

funding

that

we

have
.

So

we

need

to

be

strategic

in

what

we

do

because

we

need

to

worth

every

penny
,

every

dollar

we

have
.

So

we

need

to

move

in

that

direction

and

every

evidence

that

whenever

you

publish

a

paper
,

you
,

whatever

people

read
,

there

are

data
.

But

behind

that

paper

there

is

a

team

of

people

that

recently

talk
,

so

they

make

briefing

and

meeting
,

they

analyze

data
,

contextualize

data

within

the

actual

medical

knowledge

and

the

future

and

the

different

other

science
.

How

can

I

do

that
?

So

it's

everything

you

experience

coming

from

the

paper
.

So

that's

why

whenever

scientists

publish

paper
,

they're

excited
.

Canio
18:49

Maybe

nobody's

going

to

read

the

paper

when

it

comes

to

people

like
,

not

the

medical

community
,

but

for

us

it's

amazing

because

behind

that

paper

there

are

ideas
,

confirmed
,

dismissed
.

People

get

gut

hungry
,

you

know
.

And

then

there

is

all

the

all

of

this

stuff
.

So

there

are

humans
,

life
,

working

for

something

and

challenging

each

other

to

do

something

different

and

change

the

actual

like

management
.

So

it

helped

us

to

jump

to

the

other

program

that

actually

is

not

just

this

paper
,

but

it

is

our

history
,

other

papers
,

like

they

merged

together

and

they

jumped

in

this

new

paper
,

that

is
,

a

theoretical

paper

with

some

computational

predictions

or

some

preliminary

data
.

That

is

called

PULSAR
.

That's

basically

meaning

probabilistic

and

user-centered

learning

for

surgical

adaptive

recommendation
.

Alanna
19:46

That's

a

long

word

for

a

lot

of

us
,

oh

my

gosh
,

alan
.

Canio
19:50

I

think

I

could

speak

about

that

for

hours
,

because

it's

really

what

really

drives

me
.

So

please

stop

me

if

I

keep

going

like

without

any

direction
.

But

it's

really

something

that

I
,

you

know
,

whenever

I

go

to

sleep
.

Alanna
20:12

I

think

about

that
,

believe

me
.

So

the

research

is

like
.

The

words

in

the

title

itself

are

more

manpower

than

I

want

to

put

in

half

the

time

just

to

think

of

what

it

is
.

What

is

this

paper
,

though
?

What

does

it

entail
?

Because

I'm

sure

that

it's

like

a

new

pathway

to

what

the

future

holds

for

patient-centered

care
.

Canio
20:27

Okay
,

Maybe

we

can

talk

about

that

by

having

a

conversation
.

I

want

to

try

to

introduce

the

things

by

using

metaphor
.

Alanna
20:36

Okay
.

Canio
20:38

So

let's

say

that
,

do

you

like

cooking
,

love

it
.

So

whenever

you

cook
,

do

you

follow

a

specific

recipe
,

the

specific

steps
,

or

you

go

by

your

mind
?

A

little

bit

of

both
.

Okay
,

exactly
,

exactly
.

I

love

this

answer
.

So

sometimes

you

change

the

recipe
,

you

change

ingredients
.

The

question

here

is

how

and

what

is

the

things

that

you

follow

to

change

your

mind

about

some

step
.

You

know

what

I

mean
.

Like
,

how

do

you
?

We're

talking

about

your

decision-making

process

in

your

mind
.

So

whenever

you

decide

to

change

something

in

your

like
,

let's

say
,

management

of

the

dish
,

what

is

the

things

that

really

drive

you
?

Alanna
21:21

If

I

like

the

flavor

of

something

or

if

I

don't

have

the

right

ingredient
,

but

something

can

substitute

it
,

so

like

knowing

what

I

have

available

to

me

versus

what

I

want
,

if

that

makes

sense
.

Canio
21:33

Okay
,

it

makes

sense
.

But

you

know
,

maybe

you

can

open

your

kitchen

and

you

find

a

hundred

ingredients
.

How

do

you

pick

especially

specifically

that

one

instead

of

another

one
?

Alanna
21:43

What

might

work

better

in

my

mind
,

like

what

I

feel

like

would

make

it

better
.

Canio
21:49

That's

based

on

what

your

feeling

is

based

on

what
?

Alanna
21:52

Yeah
?

Canio
21:52

And

what's

your

opinion

is

based

on
?

Alanna
21:54

The

way

I

feel

or

the

way

I

prefer

things
.

Exactly

yeah
.

Canio
21:59

Now

we

are

entering

what

we

call

in

this

paper

the

gray

] Gray Area Dilemma in Surgical Decisions

Canio
22:03

area

dilemma
.

So

there

is

a

gray

area

in

our

mind

of

decision-making

process
,

especially

in

surgery
,

where

actually

we

do

something
.

Most

of

the

process

is

evidence-based
,

but

sometimes

during

this

process

there

are

little

choices

in

every

surgery
.

Every

surgery

is

completely

different

than

anyone

else

and

from

anyone

else
,

because

every

patient

is

completely

different

than

each

other
.

So

then
,

surgery

is

a

specific

field

of

medicine

because

it's

the

same

time

diagnosis

and

treatment
,

because

you

don't

have

all

the

data

that

you

really

need

before

the

surgery
.

Most

of

the

time

you

discover

something

when

you

open

the

patient

and

when

you're

there

you're

making

diagnosis

and

you

have

to

change
,

sometimes
,

your

mind
.

That's

why
,

when

we

share

informed

consent
,

there

is

a

huge

list

of

something

that

can

happen
,

like

we

are

doing
.

A

surgeon

that

maybe

you

know

for

endometriosis

they

say

I

can

resect

the

bowel
,

you

can

come

up

with

a

stoma
,

we

can

resect

ureter
,

it

may

be

possible

that

we

have

a

urinary

stoma
,

you

know
,

but

there

is

even

a

risk

of

fatality
.

That's

because

we

don't

have

a

clear

idea

what's

happening

100%

before

opening

the

patient
.

When

you

are

there
,

you

really

have

the
.

You

know

the

reality
,

so

you

need

to

adapt

your

decision-making

process

as

a

surgeon

between

evidence

coming

from

science

and

then

something

that

you

have

in

your

mind

that's

based

on

your

experience
,

your

intuition
,

something

we're

still

not

able

to

identify
.

That's

the

gray

area

dilemma
,

and

the

best

surgeon

is

the

one

that

somehow

has

that

gray

area

that

is

much

more

efficient

and

effective

when
,

at

the

end
,

it

takes

the

choice

for

the

patient

during

surgery
.

It

doesn't

mean

that

it's

necessarily

the

one

that

is

the

oldest

one
,

but

it's

the

one

that

the

sum

of

his

option

is

actually

the

result

as

a

result
,

as

the

best

outcome

for

the

patient

is

actually

the

result

as

a

result
,

as

the

best

outcome

for

the

patient
.

And

that's

why

surgery

is

extremely

hard

to

teach
,

rather

than

compared

to

any

other

field

of

medicine
,

because

it's

hard

to

explain
,

objectify

and

structure

the

gray

area

of

the

decision

making

of

the

surgeon
.

Canio
24:16

Now
,

where

this

study
,

you

know
,

fit
,

this

study

fit

in
,

uh

in

in

all

of

this
.

So

the

thing

here

is

I

need

someone
,

since
,

starting

from

the

previous

study

where

we

wanted

to

try

to

codify

the

uh

decision-making

pattern

of

the

machine
,

here

is

trying

to

codify

the

decision-making

process

of

the

human

by

using

AI
.

The

goal

is

using

AI

technology

Uh
,

I'm

not

going

to

go

into

the

details

in

this

but

the

human

by

using

AI
.

The

goal

is

using

AI

technology
.

I'm

not

going

to

go

into

details

in

this
,

but

the

goal

is

using

AI

in

order

to

detect

and

to

study

how

the

surgeon

behaves

in

all

the

different

scenarios
,

all

the

different

surgeries
.

But

the

most

important

thing

is

then

to

anchor

and

to

attach

to

this

reasoning

and

evaluation

what's

happening

to

the

patient
,

because

we

need

to

anchor

the

algorithm

to

the

outcome

for

the

patient
,

because

the

matrix

here

is

I

can

judge

whether

the

action

of

a

surgeon

was

better

than

the

other

one

by

relating

his

action

or

her

action

to

the

outcome

of

the

patient
.

And

it's

not

just

that
,

because

then

any

patient

is

different
.

Someone

could

say

exactly

the

goal

is

try

to

destroy

them
.

Canio
25:33

Let

me

say

that

the

patient

in

all

little

pieces
.

Those

are

data

before

the

surgery
,

with

all

the

imaging
,

objective

evaluation
,

clinical

examination
,

and

so

we

get

some

of

the

data
.

Then
,

during

the

surgery
,

we

have

a

video
,

so

we

get

information

coming

from

the

video

getting

during

the

surgery
,

and

that's

another

package

of

data
.

The

other

thing

that's

very

interesting

is

that

whenever

you

do

surgery
,

you

are

modifying

the

anatomy
.

You

are

modifying

the

biology

of

the

body
,

so

what's

happening

is

that

we

need

to

be

able

to

relate

our

action

to

the

modification

in

that

specific

patient
.

Canio
26:10

Science

is

always

working

on

understanding

the

differences
,

so

all

of

this

little

action

will

generate

differences

between

the

patient
,

and

so

at

the

end

you

have

to

like

try

to

picture

that

at

one

patient

during

all

the

process
,

so

assessed

in

a

dynamic

way
,

so

pre
,

during

surgery
,

after

surgery
,

will

be

actually

represented

by

billions

of

data
.

And

these

data

are

actually

belonging

they're

not

like

random

they

are

belonging

to

specific

compartments

and

that's

a

called

layer
,

and

that's

where

actually

multi-army

comes

in
.

So

we

don't

just

need

to

get

the

data
,

but

we

need

to

organize

in

their

own

compartment

and

then

we

need

to

be

able

to

relate

them

in

a

structured

way
.

Each

of

them

needs

to

be

like

part

of

a

compartment

and

then

we

need

to

in

this

billion

of

data
.

We

need

that

to

understand

what

was

the

strategy

that

actually
,

in

that

specific

case
,

helped

the

surgeon

to

get

to

the

best

result

for

the

patient
.

And

then

in

the

next

case
,

the

machine

would

be
.

Canio
27:15

After

doing

that
,

with

different

physicians

and

different

people
,

the

machine

would

be

able

to

guide

us

and

also

the

patient
,

by

little

by

little
,

say

okay
,

if

you

do

this
,

be

careful
,

because

last

time

you

did

that
,

you

did

the

same

stuff
.

Canio
27:30

Although

it's

anatomically

and

technically

correct
,

let

me

say

that

was

not

good

extremely

good

for

the

patient
.

Because

whatever

we

need

to

do

is

to

anchor

this

to

the

patient

outcomes
.

Most

of

the

time

if

you

talk

to

physicians
,

to

surgeons
,

they

say

I

did

this

and

it

was

perfect
.

The

other

one

did

another

stuff

that

was

indeed

perfect
.

So

here

is

not

about

doing

what

physician

or

surgeon

says

is

perfect
,

but

is

to

anchor

any
,

every

single

step

to

the

patient

outcomes
.

And

that

is

going

to

improve

even

understanding

of

how

a

surgeon

thinks
.

In

that

gray

area

is

even

medical

education

and

also

in

the

shared

decision

making
,

because

at

this

way
,

after

some

times
,

before

the

patient

comes

to

me
,

you

know
,

before

the

surgery

I

can
,

by

looking

at

the

data
,

say

okay
,

that's

the

best

choice

for

you

among

the

all

possible

ones

and

it's

going

to

give

you

that

specific

risk

and

that

specific

benefit
.

Alanna
28:28

Interesting
.

So

it's

like

a
,

it's

a

guide

for

the

doctor

to

give

the

patient

the

best

outcome

while

also

giving
,

like

the

patient
,

a

voice

in

the

long-term

outcome
.

Exactly
,

exactly
.

That's

great

and

that's

like

something
,

because

I

think

we

always

say

it's

not

a

one-size-fits-all
,

especially

with

endometriosis

surgery
,

and

so

just

tailoring

the

approach

to

the

actual

patient

prior

to

surgery

for

better

outcomes

long-term
,

is

that

kind

of

Wow
,

I

was

so

confused

when

I

explained

all

of

this

and

you

got

everything

very

clearly
.

Canio
29:05

I

don't

know

how

you

did

it
.

I

was

so
.

It

was

a

mess

when

I

said

that
,

because

I

follow

Meeting Dr. Cano Martinelli

Canio
29:11

my

inner

flow
,

you

know

what

I

mean
.

Alanna
29:12

No
,

I

picked

it

up
.

I

just

am

like

fascinated

by

the

fact

that

you

know
,

as

patients
,

we

are

constantly

looking

at

okay
,

like
,

is

this

bowel

resection

right

for

me
,

or

is

this

whatever

resection

right

for

me
,

or

is

this

whatever

Is

it

right

for

me
?

And

this

is

just

a

good
,

more

educated

way

of

approaching

a

surgery

and

making

it

truly

multidisciplinary

from
,

like
,

the

AI

standpoint
,

mixed

with

the

provider
,

mixed

with

the

patient
,

the

outcome

being

better
.

This

is

crazy

to

me
.

Canio
29:41

What

you

said
.

See
,

this

conversation

is

beautiful

for

this

reason
,

because

it's

I'm

learning

something

from

you

and

I

or

treatment
,

we

take

our

decision

by

looking

at

data

coming

from
.

We

say
,

population

study
,

so

all

the

data

we

have
.

We

say
,

ok
,

you

have

to

do

that

because

the

chance

of

success

is

this

or

because

it's

best

for

you
.

But

OK
,

the

question

is

how
,

as

a

patient
,

how

am

I

similar

to

the

population

that

was

using

in

the

study

that

generate

the

evidence
?

And

that's

where

medicine

is

not

precise
,

because

the

evidence

are

coming

from

a

set

of

data

that

not

necessarily

are

the

same

of

the

very

next

patient

that

is

in

front

of

me
.

And

when

it

comes

to

surgery
,

it's

even

more

difficult
,

because

I

don't

give

the

same

pills

to

everybody
,

but

actually

I'm

tailoring

the

surgical

procedure

to

the

specific

patient

and

that's

unique

in

any

patient
.

So
,

whatever

you

introduce

a

decision

and

the

differences
,

you

are

making

the

decision-making

process

much

more

complicated
.

Alanna
31:02

Yeah
.

Canio
31:03

And

very

hard

to

understand
.

Alanna
31:04

Is

this

what
?

When

you

did

this

paper
,

were

they

seeing

video

or

AI

like

virtual

reality

ways

of

doing

the

surgery
,

or

was

it

just

words

Like

was

it

just

feedback
?

Canio
31:16

through
.

That's

a

very
,

very

interesting

question

because

it's

like

it's

actually

a

very

detailed

question

and

so

I

need

to

jump

necessarily

to

details
.

So

in

order

to

design
,

first

of

all
,

you

start

by

designing

the

algorithm

that

is

more

efficient
,

Because

in

order

to

do

something
,

you

can

do

it

in

different

ways
.

Then

you

have

to

find

the

one

that

really

is

tuned

in

the

right

way
.

So

this

starts

as

a

theoretical

study

coming

from

observation

that

I

had

personally

in

my

life

experience

as

a

physician

and

scientist
,

Because

one

of

the

fantastic

things

you

know
,

if

you

really

want

to

judge

I

don't

want

to

say

judge
,

but

if

you

really

want

to

have

the

real

feeling

of

a

surgeon
,

I

think

it's

based

on

how

really

he

traveled

in

his

life
.

So

because

as

much

she

has

or

she

has

been

exposed

to

something

different
,

then

he

can

understand

really

what's

the

best

things
.

Because

whenever

you

are

in

the

best

center

in

the

world
,

they're

going

to

teach

you

that's

the

right

method

and

that's

okay

because

it

comes

from

a

school
.

But

you

need

to

get

to

that

conclusion

after

you

see

different

methods

and

you

start

to

believe

actually
,

that

is

to

see

that

there

are

surgeons

that

are

doing

different

kind

of

techniques

and

they

still

have

treating

in

the

best

way

possible

and

patients

are

happy

about

that
.

So

the

thing

is

coming

from

two

problems
.

So

evidence
,

real

problem
,

where

you

see

all

of

these
,

a

surgeon

in

school

says

that

they

are

doing

the

best

things

for

the

patient
.

Canio
32:55

And

then

methodological

problem
.

That's

coming

from

my

research

field
,

where

actually

you

have

to

question

everything

you

do
.

And

how

do

you

stop

questioning

what

you

do

when

you

have

no

more

grade

zones
?

How

do

you

not

have

grade

zones
?

You

start

to

get

the

data

and

start

to
,

mathematically

speaking
,

give

a

system

for

each

of

the

data

you

come

in

game
.

So

the

question

is

what

kind

of

data

are

there
?

The

kind

of

data
,

every

kind

of

data
.

So

they

comes

from

imaging
,

they

come

from

talking
,

so

word

they

come

from
.

It's

called

finite

element

analysis
.

So

what

this

conceptualization

thinks

about

is

that

we

get

the

data

from

ultrasound

or

RMI

and

we

translate

those

data

that

are

basically

pixel

in

a

system
,

a

computer

that

is

able

to

simulate

the

real

functioning

of

the

anatomy
,

but

in

a

functional

way
,

so

you

can

simulate

what's

happening
.

You

say
,

okay
,

I

want

to

do

this

procedure
.

You

simulate

the

procedure

and

you

see

that

something

else

is

happening

and

that's

why

you

can

tailor

the

surgery

before

doing

the

surgery
,

and

then

it's

going

to

tell

you

that

the

things

you're

doing

is

good
.

Canio
34:08

Well
,

this

is

easy

when

it

comes

to

cancer
.

So

oncological

surgery
,

because

the

goal

is

overall

survival
.

But

when

it

comes

to

function
,

it's

a

completely

different

stuff
,

Because

how

do

you

really

assess

functionality

in

women

today
?

By

some

questionnaire

what

is

functionality
?

It's

actually

really
.

It's

different

for

every

woman
.

So
,

for

example
,

I

can

say

that

for

a

young

athlete

woman
,

functionality

is

being

able

to

have

no

pain

and

to

be

as

much

as

she

can

and

give

the

best

performance
.

For

an

old

lady
,

maybe

the

functionality

is

able

to

hold

the

hands

of

her

grandson
.

So

even

if

she's

pained
,

it's

not

a

problem
.

So

is

everything

based

on

this

question
?

How

can

I

represent

mathematically

people's

problem

and

human's

problem
?

Because

whatever

you

are

searching
,

you're

human

acting

and

not

human
.

And

so

when

the

study

will

be

published
,

the

cool

things

are

going

to

be

the

architecture

of

all

of

this
,

because

it's

going

to

be

extremely

detailed

and

every

step

is

connected

to

another

one
.

Alanna
35:22

And

then

there

are

loops

that

reinforce

and

retune

all

the

system

again

connect

it

to

another

one
,

and

then

there

are

loops

that

reinforce

and

retune

all

the

system

again
.

It's

like

taking

both

the

visual

of

the

scans

and

then

you're

taking

the

patient
.

Does

it

account

for
,

like

patient

symptoms
?

Does

it

account

for
,

like

all

of

the

functional

things

that

are

at

that

point

failing

them

for

lack

of

a

better

word

and

taking

that

into

consideration

and

giving

you

or

the

provider

the

approach

that's

going

to

best

suit

them

long

term

in

a

visual

manner
?

Or

is

it

just

like

spelling

it

out
,

it's

like

a

checklist
,

or

is

it

like

a

visual

aid

for

them
?

Canio
35:59

And

that's

where

it

comes
.

Another

project
,

right
,

and

that

makes

me

feel

that

we

are

going

in

the

right

direction
.

This

is

something

very
,

very
,

you

know
,

exclusive
,

preliminary
,

because

here

comes

the

second

point

communication
.

And

do

you

really

understand

whether

what

you're

telling

people

patient

you're

really

able

to

explain

in

a

clear

way
?

Are

you

able
,

really

you

know
,

whenever

you

say

the

chance

of

success

is

80%

and

the

failure

20%
?

Okay
,

and

the

patient

said

that

every

patient

will

believe

they're

going

to

be

in

the

20%
.

Canio
36:40

So

there

is

a

problem

here
,

even

in

communication
,

and

that's

another

part

of

the

problem

that

is

not

focused

in

this

paper
,

but

it's

another

project

we

are

leading
,

that's

translational

communication

in

the

medicine
,

and

we

are

working

together

with

visual

artists
,

so

they

are

helping

us

in

trying

to

understand

how

to

translate

complicated

medical

stuff

in

something

that

people

can

really

understand
,

but

not

logically

understand
,

even

emotionally

understand
.

Canio
37:11

They

need

to

understand

that
,

because

when

you

say

80
,

20%

are

very
,

you

know
,

great

data
,

but

the

80%

is

not

just

the

80%
,

it's

also

what's

happening

if

you

don't

do

that

kind

of

procedure
.

So

if

you

don't

do

that

kind

of

procedure
,

so

if

you

don't

choose

that

procedure
,

something

else

is

going

to

happen
.

So

it's

giving

the

right

let's

say

even

emotional

way

to

pure

great

data
?

The

answer

for

me

I

don't

know
.

I'm

working

together

with

the

visual

artists
,

so

people

that

work

with

that

are

inspired

by

emotion

much

more

than

me
,

that

have

been

exposed

in

life

to

something

different

than

me
.

So

in

science

and

that's

the

beauty

of

the

United

States
,

I

have

to

tell

this

Whenever

you

work

in

university
,

you

have

all

of

these

academic

people

working

together

and

give

their

point

of

view

and

really
,

at

the

end
,

try

to

do

something

that

is

really

effective
,

not

just

beautiful

chrome
.

It

needs

to

work

out
.

Alanna
38:10

Right
,

I'm

excited

to

see

where

that

one

goes
,

because

I

feel

like

that

could

change

the

narrative

of

outcomes
.

Canio
38:17

Yes
,

which
?

Alanna
38:17

is

exciting

] Episode Closing

Alanna
38:18

.

That's

a

wrap

for

EndoBattery's

Fast

Charge

this

week
.

I

hope

this

episode

left

you

inspired

and

empowered

to

continue

advocating

for

your

care

and

encourage

that

research

is

happening

and

change

can

happen

in

our

lifetime
.

Make

sure

to

join

us

next

time

as

Kanyo

sits

down

with

us

to

explore

more

research

that's

being

done
.

Until

then
,

continue

advocating

for

you

and

for

others
.