北部智慧醫療專班開學典禮 日期: 2019/08/31 09:00 - 12:30 (六) 地點: 林口長庚醫院 研究大樓一樓綜合會議廳 (桃園市龜山區文化一路15號 Google Map) 主辦單位: 台灣人工智慧學校、林口長庚醫院 協辦單位: 台大醫院、三軍總醫院

3. 3

4. 4

5. 5

6. /
(Polanyi's Paradox)
6
1964

8. 1950-1960 1980-1990 2010-Present

9. /
Keyword in AI Research
9

10. 10

11. / AI - 11
Training a prediction machine by
showing examples instead of
programming it.
-Yann LeCun
(prediction machine: )

12. / AI - 12
Find the common patterns
from the left waveforms
It seems impossible to write
a program for speech
recognition
You quickly get lost in the
exceptions and special cases.
(Slide Credit: Hung-Yi Lee)

13. / AI -
You said
“ ”
(Slide Credit: Hung-Yi Lee)

14. / AI - 14

15. 15

16. / 16

17. / 17

18. / 18

19. / 19

20. / 20

21. 21

22. /
AI
22

23. / 23

24. /
-
24

25. /
-
25

26. /
-
26

27. /
-
27

28. /
Deep Learning, Machine Learning, and AI
28

29. Healthy Diseased
Hemorrhages
No DR Mild DR Moderate DR Severe DR Proliferative DR
1 2 3 4 5

30. / 30
Classical Machine Learning
Deep Learning
Rule-based System
Rule extraction
LessDomainExperts,
MoreEngineers&MoreAccuracy

31. 31

32. 32
Using
Deep Learning

33. /
There is no free lunch
33
Classical
Machine Learning
Deep Learning

34. / 34https://www.kaggle.com/c/two-sigma-financial-news/leaderboard

35. 35(Slide Credit: McKinsey&Company)

36. AI
IN MEDICINE
36

37. / 37

38. 0.95
F-score
Algorithm Ophthalmologist
(median)
0.91
“The study by Gulshan and colleagues
truly represents the brave new world in
medicine.”
“Google just published this paper in JAMA
(impact factor 44.405) [...] It actually lives
up to the hype.”
Dr. Andrew Beam, Dr. Isaac
Kohane Harvard Medical School
Dr. Luke Oakden-Rayner
University of Adelaide

39. /
Deep Learning for Detection of Diabetic Eye Disease
39
Algorithm’s F1-score: 0.95
Median F1-score of 8 ophthalmologists : 0.91

40. / 40

41. /
AI
75 during 2008 – 2013 in NewYork City
, , , etc.
AI , 63% , 5%
AI vs. Judges
, (!)
,
( , 1000 )
41

42. / 42
https://www.youtube.com/watch?v=ljBOzdKuX7A

43. 43

44. 44

45. 45OCT: Optical CoherenceTomography ( )

46. 46

47. arxiv.org/abs/1703.02442
Tumor localization score (FROC):
model: 0.89
pathologist: 0.73
(Slide Credit: Google Brain)

48. / 48
Deep Learning for Kidney Function Classification and
Prediction using Ultrasound-based Imaging
Chin-Chi Kuo1, Chun-Min Chang2, Kuan-Ting Liu2,Wei-Kai Lin2,
Chih-Wei Chung1, and Kuan-Ta Chen2
1Big Data Center, China Medical University Hospital, China Medical University,Taichung,Taiwan
2Institute of Information Science,Academia Sinica,Taiwan
eGFR
( )

49. / 49

50. /
10 XGBoost Models Ensemble
Accuracy 0.851
Precision 0.870
Recall 0.667
F1 score 0.757
AUC 0.91

51. Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
51
Goal: diagnose irregular heart rhythms, also known as
arrhythmias, from single-lead ECG signals better than a
cardiologist

52. /
Input and Output
Input: a time-series of raw ECG signal
The 30 second long ECG signal is sampled at 200 Hz
From 29,163 patients
Output: a sequence of rhythm classes
The model outputs a new prediction once every second
Total 14 rhythm classes are identified
52

53. / 53

54. /
Model
34 layers NN
16 residual blocks
2 conv layers per block
Filter length = 16 samples
# filter = 64*k, k start from 1 and is
incremented every 4-th residual block
Every residual block subsamples
its input by a factor of 2
54

55. /
Results – F1 score
55

56. / 56

57. 57

58. 58
* 28 out of 142 patients were labeled as depressed.https://www.csail.mit.edu/news/model-can-more-naturally-detect-depression-conversations

59. /
Synthetic Speech Generated from Brain Recordings
59https://www.ucsf.edu/news/2019/04/414296/synthetic-speech-generated-brain-recordings

60. /
Synthetic Speech Generated from Brain Recordings
60
https://www.sciencemag.org/news/2019/01/artificial-intelligence-turns-brain-activity-speech

61. /
Google Healthcare Focuses
61

62. Predictive tasks for healthcare
Given a large corpus of training data of de-identified medical records, can we
predict interesting aspects of the future for a patient not in the training set?
! will patient be readmitted to hospital in next N days?
! what is the likely length of hospital stay for patient checking in?
! what are the most likely diagnoses for the patient right now? and
why?
! what medications should a doctor consider prescribing?
! what tests should be considered for this patient?
! which patients are at highest risk for X in next month?
Collaborating with several healthcare organizations, including UCSF,
Stanford, and Univ. of Chicago. Have early promising results.

63. / 63

64. /
DeepVariant: Creating a universal SNP and small indel variant caller with deep neural networks
64

65. / 65

66. /
DeepVariant vs. GATK
66

67. / 67
DeepVariant vs. GATK

68. / 68https://www.hbrtaiwan.com/article_content_AR0008072.html

69. / 69
Rajkomar,Alvin, Jeffrey Dean, and Isaac Kohane. "Machine learning in
medicine." New England Journal of Medicine380.14 (2019): 1347-1358.

70. /
The 2014 HSBC Expat Explorer survey rates healthcare
70
https://expathealth.org/healthcare/top-5-health-care-expats/

71. /
LIMITATIONS OF AI
71

72. /
(Moravec’s Paradox)
High cognitive processes
Conscious processes
Chesses, math, problem solving
Difficult for humans
Easy for computers
Low Cognitive processes
Perception, action, fight/flight
responses, social interactions
Easy for humans
Difficult for computers
72

73. / 73

74. / 74

75. /
https://ifaketextmessage.com/

76. / 76

77. /
Strong AI Weak AI
Can think
Own conscious
Act as it can think
Consciousless
(1980)

78. /
What we can and cannot today
What we can have
Safer car, autonomous car
Better medical image analysis
Personalized medicine
Adequate language translation
Useful but stupid chatbots
Information search, retrieval,
filtering
Numerous applications in energy,
finance, manufacturing, commerce,
law, …
What we cannot have (yet)
Machine with common sense
Intelligent personal assistants
“Smart” chatbots
Household robots
Agile and dexterous robots
Artificial General Intelligence (AGI)
78
(Credit:Yann LeCun)

79. 79
2015 207
31,000 3,700
90% Markram

80. / 80

81. / 81

82. /
Generating adversarial patches againstYOLOv2
82
https://www.youtube.com/watch?
feature=youtu.be&v=MIbFvK2S9g8&app=desktop

83. /
AI Don’t Know What They are Talking About
83
https://www.facebook.com/playgroundenglish/videos/629372370729430/?
hc_ref=ARQHCaS2GZ9jUgZermEupF5yerADq2X9F9P40OR3n70poUiCy7R0X3oHrGxyL
SrWVdI

84. Change is the only constant.
- Heraclitus (535 BC - 475 BC)
(Slide Credit:Albert Chen)

85. / 85
https://www.israel21c.org/food-expiration-dates-are-about-to-undergo-a-revolution/

86. 86

87. /
Precision Medicine
87

88. /
Rainforest Connection
88

89. /
Rainforest Connection
89

90. / 90
https://www.youtube.com/watch?v=ljBOzdKuX7A

91. / 91
https://www.youtube.com/watch?v=ljBOzdKuX7A

92. /
AI …
92
2000 2018