ABOUT THE SPEAKER
Pratik Shah - Medical technologist
Dr. Pratik Shah creates novel intersections between engineering, medical imaging, machine learning and medicine.

Why you should listen

Dr. Shah's research program at the MIT Media Lab develops scalable and low-cost diagnostics and therapeutics. His ongoing research areas at MIT include: 1) artificial intelligence and machine learning methods for detection of cancer biomarkers using standard photographs vs. expensive medical images; 2) unorthodox artificial intelligence and machine learning algorithms to design optimal and faster clinical trials and to reduce adverse effects on patients; and 3) low-cost and open source imaging devices, paper diagnostics, algorithms and mobile phones to improve public health and generate real-world data.

Clinical studies with Pratik's medical technologies have revealed "missing sick" patients, who otherwise remain undiagnosed in conventional healthcare settings. Dr. Shah's graduate and postdoctoral research contributed to the discovery of a vaccine component to prevent pneumococcal (Streptococcus pneumoniae) diseases; the identification of new pathways, technologies and metabolites as antimicrobials to target gastrointestinal infections; and a nonprofit to deploy a low-cost water quality test for the developing world.

Past recognition for Dr. Shah includes the American Society for Microbiology's Raymond W. Sarber national award, the Harvard Medical School and Massachusetts General Hospitals ECOR Fund for Medical Discovery postdoctoral fellowship, the AAAS-Lemelson Invention Ambassador Award and a TED Fellowship. Pratik has been an invited discussion leader at Gordon Research Seminars; a speaker at Cold Spring Harbor Laboratories, Gordon Research Conferences and IEEE bioengineering conferences; and a peer reviewer for leading scientific publications and funding agencies. Pratik has a BS, MS, and a PhD in Microbiology and completed fellowship training at The Broad Institute of MIT and Harvard, Massachusetts General Hospital and Harvard Medical School.

More profile about the speaker
Pratik Shah | Speaker | TED.com
TEDGlobal 2017

Pratik Shah: How AI is making it easier to diagnose disease

Filmed:
1,571,835 views

Today's AI algorithms require tens of thousands of expensive medical images to detect a patient's disease. What if we could drastically reduce the amount of data needed to train an AI, making diagnoses low-cost and more effective? TED Fellow Pratik Shah is working on a clever system to do just that. Using an unorthodox AI approach, Shah has developed a technology that requires as few as 50 images to develop a working algorithm -- and can even use photos taken on doctors' cell phones to provide a diagnosis. Learn more about how this new way to analyze medical information could lead to earlier detection of life-threatening illnesses and bring AI-assisted diagnosis to more health care settings worldwide.
- Medical technologist
Dr. Pratik Shah creates novel intersections between engineering, medical imaging, machine learning and medicine. Full bio

Double-click the English transcript below to play the video.

00:13
Computer algorithms today
are performing incredible tasks
0
1280
3856
00:17
with high accuracies, at a massive scale,
using human-like intelligence.
1
5160
4736
00:21
And this intelligence of computers
is often referred to as AI
2
9920
3936
00:25
or artificial intelligence.
3
13880
1856
00:27
AI is poised to make an incredible impact
on our lives in the future.
4
15760
4200
00:32
Today, however,
we still face massive challenges
5
20880
3936
00:36
in detecting and diagnosing
several life-threatening illnesses,
6
24840
3496
00:40
such as infectious diseases and cancer.
7
28360
2360
00:44
Thousands of patients every year
8
32000
2296
00:46
lose their lives
due to liver and oral cancer.
9
34320
2800
00:49
Our best way to help these patients
10
37880
2696
00:52
is to perform early detection
and diagnoses of these diseases.
11
40600
4320
00:57
So how do we detect these diseases today,
and can artificial intelligence help?
12
45880
4160
01:03
In patients who, unfortunately,
are suspected of these diseases,
13
51920
3656
01:07
an expert physician first orders
14
55600
2656
01:10
very expensive
medical imaging technologies
15
58280
2616
01:12
such as fluorescent imaging,
CTs, MRIs, to be performed.
16
60920
4096
01:17
Once those images are collected,
17
65040
2296
01:19
another expert physician then diagnoses
those images and talks to the patient.
18
67360
4520
01:24
As you can see, this is
a very resource-intensive process,
19
72520
3456
01:28
requiring both expert physicians,
expensive medical imaging technologies,
20
76000
4416
01:32
and is not considered practical
for the developing world.
21
80440
3096
01:35
And in fact, in many
industrialized nations, as well.
22
83560
3360
01:39
So, can we solve this problem
using artificial intelligence?
23
87760
2880
01:43
Today, if I were to use traditional
artificial intelligence architectures
24
91840
4056
01:47
to solve this problem,
25
95920
1216
01:49
I would require 10,000 --
26
97160
1456
01:50
I repeat, on an order of 10,000
of these very expensive medical images
27
98640
4016
01:54
first to be generated.
28
102680
1376
01:56
After that, I would then go
to an expert physician,
29
104080
2896
01:59
who would then analyze
those images for me.
30
107000
2496
02:01
And using those two pieces of information,
31
109520
2096
02:03
I can train a standard deep neural network
or a deep learning network
32
111640
3656
02:07
to provide patient's diagnosis.
33
115320
2136
02:09
Similar to the first approach,
34
117480
1736
02:11
traditional artificial
intelligence approaches
35
119240
2143
02:13
suffer from the same problem.
36
121407
1449
02:14
Large amounts of data, expert physicians
and expert medical imaging technologies.
37
122880
4560
02:20
So, can we invent more scalable, effective
38
128320
4296
02:24
and more valuable artificial
intelligence architectures
39
132640
3296
02:27
to solve these very important
problems facing us today?
40
135960
3056
02:31
And this is exactly
what my group at MIT Media Lab does.
41
139040
3296
02:34
We have invented a variety
of unorthodox AI architectures
42
142360
3856
02:38
to solve some of the most important
challenges facing us today
43
146240
3176
02:41
in medical imaging and clinical trials.
44
149440
2200
02:44
In the example I shared
with you today, we had two goals.
45
152480
3056
02:47
Our first goal was to reduce
the number of images
46
155560
2976
02:50
required to train
artificial intelligence algorithms.
47
158560
3256
02:53
Our second goal -- we were more ambitious,
48
161840
2096
02:55
we wanted to reduce the use
of expensive medical imaging technologies
49
163960
3736
02:59
to screen patients.
50
167720
1216
03:00
So how did we do it?
51
168960
1200
03:02
For our first goal,
52
170920
1216
03:04
instead of starting
with tens and thousands
53
172160
2056
03:06
of these very expensive medical images,
like traditional AI,
54
174240
3016
03:09
we started with a single medical image.
55
177280
2056
03:11
From this image, my team and I
figured out a very clever way
56
179360
3776
03:15
to extract billions
of information packets.
57
183160
2736
03:17
These information packets
included colors, pixels, geometry
58
185920
3696
03:21
and rendering of the disease
on the medical image.
59
189640
2536
03:24
In a sense, we converted one image
into billions of training data points,
60
192200
4336
03:28
massively reducing the amount of data
needed for training.
61
196560
3536
03:32
For our second goal,
62
200120
1216
03:33
to reduce the use of expensive medical
imaging technologies to screen patients,
63
201360
3856
03:37
we started with a standard,
white light photograph,
64
205240
2856
03:40
acquired either from a DSLR camera
or a mobile phone, for the patient.
65
208120
4336
03:44
Then remember those
billions of information packets?
66
212480
2456
03:46
We overlaid those from
the medical image onto this image,
67
214960
3536
03:50
creating something
that we call a composite image.
68
218520
2520
03:53
Much to our surprise,
we only required 50 --
69
221480
3296
03:56
I repeat, only 50 --
70
224800
1336
03:58
of these composite images to train
our algorithms to high efficiencies.
71
226160
3840
04:02
To summarize our approach,
72
230680
1336
04:04
instead of using 10,000
very expensive medical images,
73
232040
3176
04:07
we can now train the AI algorithms
in an unorthodox way,
74
235240
3016
04:10
using only 50 of these high-resolution,
but standard photographs,
75
238280
4256
04:14
acquired from DSLR cameras
and mobile phones,
76
242560
2496
04:17
and provide diagnosis.
77
245080
1536
04:18
More importantly,
78
246640
1216
04:19
our algorithms can accept,
in the future and even right now,
79
247880
3136
04:23
some very simple, white light
photographs from the patient,
80
251040
2816
04:25
instead of expensive
medical imaging technologies.
81
253880
2440
04:29
I believe that we are poised
to enter an era
82
257120
3096
04:32
where artificial intelligence
83
260240
1936
04:34
is going to make an incredible
impact on our future.
84
262200
2536
04:36
And I think that thinking
about traditional AI,
85
264760
2456
04:39
which is data-rich but application-poor,
86
267240
2776
04:42
we should also continue thinking
87
270040
1536
04:43
about unorthodox artificial
intelligence architectures,
88
271600
3016
04:46
which can accept small amounts of data
89
274640
1936
04:48
and solve some of the most important
problems facing us today,
90
276600
2936
04:51
especially in health care.
91
279560
1256
04:52
Thank you very much.
92
280840
1216
04:54
(Applause)
93
282080
3840

▲Back to top

ABOUT THE SPEAKER
Pratik Shah - Medical technologist
Dr. Pratik Shah creates novel intersections between engineering, medical imaging, machine learning and medicine.

Why you should listen

Dr. Shah's research program at the MIT Media Lab develops scalable and low-cost diagnostics and therapeutics. His ongoing research areas at MIT include: 1) artificial intelligence and machine learning methods for detection of cancer biomarkers using standard photographs vs. expensive medical images; 2) unorthodox artificial intelligence and machine learning algorithms to design optimal and faster clinical trials and to reduce adverse effects on patients; and 3) low-cost and open source imaging devices, paper diagnostics, algorithms and mobile phones to improve public health and generate real-world data.

Clinical studies with Pratik's medical technologies have revealed "missing sick" patients, who otherwise remain undiagnosed in conventional healthcare settings. Dr. Shah's graduate and postdoctoral research contributed to the discovery of a vaccine component to prevent pneumococcal (Streptococcus pneumoniae) diseases; the identification of new pathways, technologies and metabolites as antimicrobials to target gastrointestinal infections; and a nonprofit to deploy a low-cost water quality test for the developing world.

Past recognition for Dr. Shah includes the American Society for Microbiology's Raymond W. Sarber national award, the Harvard Medical School and Massachusetts General Hospitals ECOR Fund for Medical Discovery postdoctoral fellowship, the AAAS-Lemelson Invention Ambassador Award and a TED Fellowship. Pratik has been an invited discussion leader at Gordon Research Seminars; a speaker at Cold Spring Harbor Laboratories, Gordon Research Conferences and IEEE bioengineering conferences; and a peer reviewer for leading scientific publications and funding agencies. Pratik has a BS, MS, and a PhD in Microbiology and completed fellowship training at The Broad Institute of MIT and Harvard, Massachusetts General Hospital and Harvard Medical School.

More profile about the speaker
Pratik Shah | Speaker | TED.com