의료 빅데이터와 인공지능의 현재와 미래

서울대 최형진

Contents

1. What is Healthcare Big Data? 2. Healthcare Big Data

① Genetic Data② Electrical Health Records③ National Healthcare Data④ Medical Images⑤ Sensor/Mobile Data⑥ Data Integration

3. Healthcare Big Data + Artificial Intelligence

Contents

$215MPrecision Medicine Initiative

2015/1/30

Integration of Multi-Big-Data

미국 내분비 학회

미국 골대사 학회

Big Data Dimensions

New Analysis Tool (R, Python, Matlab)New Approach

( 중환자실 심전도 )

Data Variety

Tipping Point for Big Data Healthcare

2013 McKinsey The big data revolution in healthcare

Hypothesis Driven Science Data Driven Science

Hypothesis

Collect Data

GenerateHypothesis

Analyze

Candidate GeneApproach

Genome-wideApproach

Choose a Gene from Prior Knowledge

Analyze the Gene

Analyze ALL Genes

Discover Novel Findings

GWAS (Genome wide association study)

SNP chipWhole Genome SNP Profiling (500K~1M SNPs)

Common Variant

Choi HJ, Doctoral Thesis

Estrada et al., Nature Genetics, 2012

+ novel targets for bone biology

Recent largest GWASGEFOS consortium

2010 An Environment-Wide Associ-ation Study (EWAS) on Type 2 Dia-betes Mellitus

Environment-Wide Association Study (EWAS)

다양한 환경인자들

GWAS PheWAS Phenotype-wide Association Study

1000 개의 질병들Bioinformatics. 2010 PheWAS: demonstrating the feasibility of a phenome-wide scan to discover gene-disease associations.

Phenotype-wide Association Study

Genome-Envirome-Phenome-wideAssociation Study

Proposal (Choi)

Genome-wide

Environment-wide(Life style, diet, exercise, pollution)

Anatome-Phenome-wideAssociation Study

2015.2.19. Nature. Genetic and epigenetic fine mapping of causal autoimmune disease variants

Phenome

의료 빅데이터의 새로운 역할전통적인 관점 연구

Large scale(unstructured)data

Summary(Modify)

Classical hypothesis driven study

새로운 관점 연구

Hypothesis Generating Study

Contents

저의 유전자 분석 결과를

반영하여 진료해주세

요 !!헠 ?

Protein

Metabolite

Epigenetics

Genetics Information and OMICs

Genomics

Epigenomics

Transcriptomics

Proteomics

Metabolomics

WBC Liver CancerGermline mutation Somatic mutation

Epigenomics

Proteomics

Metabolomics

Epigenomics

Proteomics

Metabolomics

Epigenomics

Proteomics

Metabolomics

GermlineGenomics

CancerGenomics

Transcriptomics Transcriptomics Transcriptomics

Proteomics

Promise of Human Genome Project

Tissue Specific Expression

Comprehensive Catalogues of Genomic DataVariation in the human genome

Mendelian (monogenic) diseases (N=22,432)

Whole genome sequencing (N=1,000)

Four ethnic groups (CEU, YRI, JPT, CHB, N=270)

GWAS catalogComplex (multigenic) traits(1926 publications and 13410 SNPs)

Disease-related variations

Functional elements

2014-06-29

All Major Tissues/OrgansAll Proteins + All RNAs

2015 Science Tissue-based map of the human proteome

1. Immunohistochemistry (IHC)24,028 antibodies (16,975 proteins) >13 million IHC images

2. RNA-sequencing

(N=44)

111 Reference Human Epigenomes

2015.2.19. Nature. Integrative analysis of 111 reference human epigenomes

Data Dimensions

2015.2.19. Nature. Integrative analysis of 111 reference human epigenomes

Building the Interactome

2015 Science Uncovering disease-disease relationships through the incomplete interactome

Network-based Model of Disease-disease Relationship

2015 Science Uncovering disease-disease relationships through the incomplete interactome

Disease genetic susceptibility Cancer driver somatic mutation

Pharmacogenomics

Targeted Cancer Treatment

(EGFR)

Causal Variant

Targeted Drug(MODY-SU)

Drug Efficacy/Side Effect Related Genotype

(CYP, HLA)

Genetic Diagnosis(Mendelian,

Cystic fibrosis)Molecular

Classification- Prognosis(Leukemia)

Hereditary Cancer(BRCA)

Microbiome(Bacteria,

Virus)

Genomic Medicine

Risk prediction(Complex disease,

Diabetes)

Germline Variants

Fetal DNA

1) Cancer Genome

Cancer Targeted Therapy

Targeted TherapyGenetic TestCancer

Cancer Rebiopsy

2013 JCO Genomics-Driven Oncology- Framework for an Emerging Paradigm

Liquid Biopsy

2) Common Complex Disease Susceptibility

Influence of Genetics on Human Disease

For any condition the overall balance of genetic and environmental determinants

can be represented by a point some-where within the triangle.

Single Locus /

Mendelian

Multiple Loci or multi-chromosomal

Environmental

Cystic FibrosisHemophilia A

Examples:Alzheimer’s Disease

Type II Diabetes

Cardiovascular Disease

DietCarcinogensInfectionsStressRadiationLifestyle

Gene = F8Gene= CFTR

F8 = Coagulation Factor VIIICFTR = Cystic Fibrosis Conductance Transmembrane Regulator

Lung Cancer

49 2008 HMG Genome-based prediction of common diseases- advances and prospects

50 2008 HMG Genome-based prediction of common diseases- advances and prospects

Diabetes ≠ Genetic Disease? • Familial aggregation

– Genetic influences?– Epigenetic influences

• Intrauterine environment– Shared family environment?

• Socioeconomic status• Dietary preferences• Food availability• Gut microbiome content

• Overestimated heritability– Phantom heritability

2012. Drong AW, Lindgren CM, McCarthy MI. Clin Pharmacol Ther. The genetic and epigenetic basis of type 2 diabetes and obesity.2012. PNAS The mystery of missing heritability- Genetic interactions create phantom heritability

Genetics of eating behavior

2011 Genetics of eating behavior

Gene-Environment Interaction

Gene Environment

Disease

Genetic Predisposition Score Sugar-Sweetened Beverages

Soda School

No-Soda School

Obese Family Lean Family

3) Rare Mendelian Disease Susceptibility

Mendelian (single-gene) genetic disorderKnown single-gene candi-

dates testingWhole Genome or Whole Ex-

ome Sequencing

Laboratory Director강현석

4) Pharmacogenomics

65 2012 European Heart Journal. Personalized medicine: hope or hype?

Herceptin

Glivec

Pharmacogenomic Biomarkers in Drug Labeling (N=166)2015.9.14.Atorvastatin, Azathioprine, Car-bamazepine, Carvediolol, Clopidogrel, Codein, Di-azepam…..

Large Effect Size Variant?

Disease susceptibility variant Pharmacogenetic variant

EnvironmentalExposure

DrugExposure

5) Other GenomeFetal DNA

Microbiome (Bacteria, Virus DNA)

30 만원 -200 만원

73 ( 출처 : 금창원 대표님 블로그)

Pharmacogenetic Tests: 최형진

No Drug(N= 10)

Gene(6 genes=8

biomarkers)

Target SNPs (N=12)

#5(HJC) Genotype Interpretation Clinical Interpretation

1 Clopidogrel CYP2C19rs4244285 (G>A) GG

*1/*1(EM) Use standard dosers4986893 (G>A) GG

rs12248560 (C>T) CC

2 WarfarinVKORC1 rs9923231 (C>T) TT

Low dose(higher risk of bleeding) Warfarin dose=0.5~2 mg/dayCYP2C9 rs1799853 (C>T) CC

rs1057910 (A>C) AC3 Simvastatin SLCO1B1 rs4149056 (T>C) TT Normal

4 Azathioprine (AP), MP, or TG TPMT rs1142345 (A>G) AA Normal

5 Carbamazepine or Phenytoin HLA-B*1502 rs2844682 (C>T) CT Normalrs3909184 (C>G) CC

6 Abacavir HLA-B*5701 rs2395029 (T>G) TT Normal7 Allopurinol HLA-B*5801 rs9263726 (G>A) GG NormalClopidogrel1): UM/EM=standard dose, IM/PM= consider alternative antiplatelet agent (eg. prasugrel/ticagrelor)Warfarin2): high dose=5~7 mg/day, medium dose=3~4 mg/day, low dose=0.5~2 mg/day

=0최형진+1,000,000?

2014 NEJM Genotype–Phenotype Correlation — Promiscuity in the Era of Next-Generation Sequencing

Future of Genomic Medicine?

Test when neededWithout information Know your type

Bloodtype

Genotype

Here is my sequence

Contents

Electronic Health Records

2012 NRG Mining electronic health records- towards better research applications and clinical care

Common EHR Data

Joshua C. Denny Chapter 13: Mining Electronic Health Records in the Genomics Era. PLoS Comput Biol. 2012 December; 8(12):

International Classification of Diseases (ICD)Current Procedural Terminology (CPT)

Medication Data

Lab Data

Big Data Analysis

1.8 1/Creatinine

한 환자의 10 년간 신장기능의 변화전체 환자의 당 조절 정도 분포

PCA Analysis혈당

신장기능

Machine Learning

2014 Big data bioinformatics

Clinical Notes

밤동안 저혈당수면 Lt.foot rolling Keep 떨림 , 식은땀 , 현기증 , 공복감 , 두통 , 피로감등의 저혈당 에 저혈당 이 있을 즉알려주도록 밤사이 특이호소 수면유지상처와 통증 상처부위 출혈 oozing, severe pain 알리도록 고혈당 처방된 당뇨식이의 중요성과 간식을 자제하도록 . 고혈당 ,, 관리 방법 . 당뇨약 이해 잘 하고 수술부위 oozing Rt.foot rolling keep 드레싱 상태를 고혈당 고혈당 의식변화 BST 387 checked. 고혈당으로 인한 구강 내 감염 위해 식후 양치 , gargle 등 구강 위생 격려 . 당뇨환자의 발관리 방법에 . 목표 혈당 , 목표 당화혈색소에 . 식사를 거르거나 지연하지 않도록 . 식사요법 , 운동요법 , 약물요법을 정확히 지키는 것이 중요을 .처방된 당뇨식이의 중요성과 간식을 자제하도록 . 고혈당 ,, 관리 방법 . 혈당 정상 범위임 rt foot rolling 중으로 pain 호소 밤사이 수면양호걱정신경 예민감정변화 중임감정을 표현하도록 지지하고 경청기분상태 condition 조금 나은 듯 하다고 혈당 조절과 관련하여 신경쓰는 모습 보이며 혈당 self 로 측정하는 모습 보임혈당 조절에 안내하고 불편감 지속알리도록고혈당 고혈당 의식변화 고혈당 허약감 지남력 혈당조절 안됨고혈당으로 인한 구강 내 감염 위해 식후 양치 , gargle 등 구강 위생 격려 . 당뇨환자의 정기점검 내용과 빈도에 .BST 140 으로 저혈당 호소 밤동안 저혈당수면 Lt.foot rolling Keep 떨림 , 식은땀 , 현기증 , 공복감 , 두통 , 피로감등의 저혈당 에 저혈당 이 있을 즉알려주도록 pain 및 불편감 호소 WA 잘고혈당 고혈당 의식변화 고혈당 허약감 지남력 혈당조절 안됨식사요법 , 운동요법 , 약물요법을 정확히 지키는 것이 중요을 . 저혈당 / 고혈당 과 대처법에 . 혈당정상화 , 표준체중의 유지 , 정상 혈중지질의 유지에 . 고혈당 ,, 관리 방법 . 혈당측정법 , 인슐린 자가 투여법 , 경구투약 ,수분 섭취량 , 대체 탄수화물 , 의료진의 도움이 필요한 사항에 교혈당 정상 범위임수술부위 oozing Rt.foot rolling keep 수술 부위 ( 출혈 , 통증 , 부종 ) 수술부위 출혈 상처부위 oozing Wound 당겨지지 않도록 적절한 체위 취하기 설명감염 발생 위험 요인 수술부위 출혈 밤동안 저혈당 호소 수면 양상 양호 rt foot rolling유지하며 감염이나 심한 통증등 침상안정중임BST 420 checkd. R1 알림 obs 하자 Rt DM foot site pain oozing 없는 상태로 저혈당 은 낮동안에는 . BST BST 347 mg /dl checked. R1notify 후 apidra 10U sc 주사 . 안전간호 시행안전간호 시행

간호기록지 Word Cloud

Natural Language Processing (NLP)

Contents

Number of patients with medical treatments related to os-teoporosis in each calendar year

2005 2006 2007 20080

1500MaleFemale

Calendar year

2011 JBMM Burden of osteoporosis in adults in Korea- a national health insurance database study

Korean Society for Bone and Mineral Research

Anti-hypertensive prescrip-tions

(2008-2011)N = 8,315,709

New usersN = 2,357,908

Age ≥ 50 yrsMonotherapy

Compliant user (MPR≥80%)No previous fracture

N = 528,522

Prevalent usersN = 5,957,801

Excluded

Age <50Combination therapy

Inadequate compliancePrevious fracture

N = 1,829,386

Final study population

심평원 빅데이터 연구고혈압약과 골절

Choi et al., 2015 International Journal of Cardiology

Compare Fracture Risk Comparator?Hypertension

CCB HighBlood Pressure

FractureRisk

Non-user

Healthy

Non-user

Cohort study (Health Insurance Review & Assessment Service)New-user design (drug-related toxicity)Non-user comparator (hypertension without medication)

2007 20112008Choi et al., 2015 International Journal of Cardiology

Distribution of ARB MPR(Histogram)

ARB Non-user

ARB user

80 120

Medication Possession Ratio (MPR)Total prescription days

Observation days

350 days (Prescription)

365 days (Observation)MPR96%

MPR (%)Choi et al., 2015 International Journal of Cardiology

Data Variety

Overview of secondary data in public health by data source

보험청구자료 건강검진

NHIS (National Health Insurance Corporation): 국민건강보험공단 ( 보험공단 )HIRA (Health Insurance Review and Assessment Service) : 건강보험심사평가원 ( 심평원 )

통계청 암센터

J Korean Med Assoc 2014 May; 근거중심 보건의료의 시행을 위한 빅데이터 활용

Big data platform model by Korea Institute of Drug Safety and Risk Management

Contents

SIMENS: CT Cardio-Vascular Engine

2013 Science Structural and Functional Brain Networks- From Connections to Cognition

fMRI analysis

2013 Science Functional interactions as big data in the human brain

1132013 Science Functional interactions as big data in the human brain

2012 Decoding subject-driven cognitive states with whole-brain connectivity patterns

Obesity fMRI ResearchPreliminary Pilot Results

p<0.005 uncorrected

Activation of visual, motor and prefrontal brain area in response to visual food cue

Food presentation max 4sec

Feedback 1sec

Fixation1~10sec

Choi et al., on going

Resting state fMRI analysisComplex network approach

Parcellation 116 brain regions by AAL map

Adjacency matrix Network properties

node degree, clustering coefficient

Choi et al., on going

Genome Big Data + Brain Big Data

Connectome-wide GWAS

2014 Nature Neuroscience. Whole-genome analyses of whole-brain data- working within an expanded search space

118 2015 Nature. Common genetic variants influence human subcortical brain structures

Published online 21 January 2015

119 2015 Nature. Common genetic variants influence human subcortical brain structures

Radiomics

2014 Nature Communications. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach

Quantitative nuclear morphometry

2015 Laboratory Investigation. Novel genotype-phenotype associations in human cancers enabled by advanced molecular platforms and computational analysis of whole slide images

딥러닝으로 폐암 진단을 돕는다 , 의사를 위한 인공 지능 ‘뷰노 메드 (Vuno-Med)’

Artificial Intelligence for Doctors and Patients

Contents

1282015 Sci Transl Med. The emerging field of mobile health

131 삼성서울병원 ( 홍승봉 신경과 교수 , 전홍진 정신건강의학과 부교수 ) 협업

피부 사진 원격 진단 / 처방

심전도 원격 진단 / 처방

NFC 혈당측정기

데이터베이스 기반 혈당관리

혈당 변화 실시간 모니터링

저녁 식사전 고혈당

Date Time name foodType calories unit amount2014-08-

09 0 미역국 0 23 1 국그릇 (300ml) 105 g2014-08-

09 0 잡곡밥 0 80 1/4 공기 (52.5g) 52 g2014-08-

09 0 열무김치 0 3 1/4 소접시 (8.75g) 9 g2014-08-

09 0 파프리카 0 6 1/2 개 (33.25g) 35 g2014-08-

09 0 토란대무침 0 28 1/2 소접시 (46.5g) 46 g2014-08-

09 1 복숭아 0 91 1 개 (269g) 268 g2014-08-

09 2 마른오징어 2 88 1/4 마리 (25g) 25 g2014-08-

09 2 파프리카 0 6 1/2 개 (33.25g) 35 g2014-08-

09 2 저지방우유 1 72 1 컵 (200ml) 180 g2014-08-

09 2 복숭아 0 183 2 개 (538g) 538 g2014-08-

09 3 복숭아 0 91 1 개 (269g) 268 g2014-08-

09 3 파프리카 0 6 1/2 개 (33.25g) 35 g2014-08-

09 4 파프리카 0 6 1/2 개 (33.25g) 35 g2014-08-

09 4 식빵 1 92 1 장 (33g) 33 g2014-08-

09 4 삶은옥수수 1 197 1 개 반 (150g) 150 g2014-08-

09 4 복숭아 0 91 1 개 (269g) 268 g2014-08-

09 4 저지방우유 1 72 1 컵 (200ml) 180 g2014-08-

10 0 복숭아 0 91 1 개 (269g) 268 g2014-08-

10 0 저지방우유 1 36 1/2 컵 (100ml) 90 g2014-08-

10 0 두부 0 20 1/4 인분 (25g) 25 g2014-08-

10 0 견과류 2 190 1/4 컵 (50g) 31 g2014-08-

10 0 파프리카 0 11 1 개 (66.5g) 65 g2014-08-

10 2 방울토마토 0 8 4 개 (60g) 60 g2014-08-

10 2 김밥 1 318 1 줄 (200g) 200 g2014-08-

10 3 복숭아 0 91 1 개 (269g) 268 g2014-08-

10 4 잡곡밥 0 161 1/2 공기 (105g) 105 g2014-08-

10 4 복숭아 0 91 1 개 (269g) 268 g2014-08-

10 4 김치 0 3 1/4 소접시 (10g) 12 g2014-08-

10 4 장조림 1 66 1/2 소접시 (45g) 45 g2014-08-

10 4 콩나물국 0 14 3/4 국그릇 (187.5ml) 83 g2014-08-

10 5 포도 0 45 3/4 대접시 (75g) 75 g

식사량 실시간 모니터링아

침아

침간

식점

심점

심간

식저

녁저

녁간

식아

침아

침간

식점

심점

심간

식저

녁저

녁간

식아

침아

침간

식점

심점

심간

식저

녁저

녁간

식아

침아

침간

식점

심점

심간

식저

녁저

녁간

식아

침아

침간

식점

심점

심간

식저

녁저

녁간

식아

침아

침간

식점

심점

심간

식저

녁저

녁간

식아

침아

침간

식점

심점

심간

식저

녁저

녁간

2014-08-09 2014-08-10 2014-08-11 2014-08-12 2014-08-13 2014-08-14 2014-08-15

600점심 과식

저녁 금식

운동량 실시간 모니터링

8/9/20

8/10/2

8/11/2

8/12/2

8/13/2

8/14/2

8/15/2

걸음 수

운동 X

운동

식사

스마트폰 활용 당뇨병 통합관리

의사

상담 교육

조회 /분석

교육간호사

매주 / 필요시

진료 처방

2-3 달 간격

평가 회의매주 / 필요시

식사 /운동

스마트폰

데이터베이스 서버

자가관리

전송

분석

혈당측정

혈당측정기

Social Network and Obesity Prevalence

2013 PLOS One. Assessing the Online Social Environment for Surveillance of Obesity Prevalence

2013 PLOS CB Reassessing Google Flu Trends Data for Detection of Seasonal and Pandemic Influenza

Google Flu Trends

151http://startupbank.co.kr/board/board_view.html?ps_boid=75&ps_db=report_s

152 2015 Cell Metabolism. A Smartphone App Reveals Erratic Diurnal Eating Patterns in Humans that Can Be Modulated for Health Benefits

November 3, 2015

153 2015 Cell Metabolism. A Smartphone App Reveals Erratic Diurnal Eating Patterns in Humans that Can Be Modulated for Health Benefits

Personalized Nutrition by Prediction of Glycemic Responses

2015 Cell. Personalized Nutrition by Prediction of Glycemic Responses

Received: October 5, 2015; Received in revised form: October 29, 2015;

Accepted: October 30, 2015;

Contents

2014 JAMA Finding the Missing Link for Big Biomedical Data

electronic medical records (EMRs) and genotype data from 11,210 indi-viduals

2015 STM Identification of type 2 diabetes subgroups through topological analysis of patient similarity

2015 Sci Rep. Repurpose terbu-taline sulfate for amyotrophic lateral sclerosis using electronic medical records

2015 Sci Rep. Repurpose terbutaline sulfate for amyotrophic lateral sclerosis using electronic medical records

Apple Health App

2015 Nature Immunology. A vision and a prescription for big data–enabled medicine

http://hineca.tistory.com/entry/Vol11-3%EC%9B%94%ED%98%B8-%EB%B3%B4%EA%B1%B4%EC%9D%98%EB%A3%8C%EC%9D%B4%EC%8A%88-%EA%B7%BC%EC%8B%9C%EA%B5%90%EC%A0%95%EC%88%A0

2014.3.

국가기관

의료기관

연구기관

개인

개인식별정보통합

정보저장 통계인공지능

건강관리

정보공개

수집 분석 활용

개인집단

Overview of Healthcare Data

Contents

Healthcare Big Data + Artificial Intelligence

Healthcare Big Data Machine Learning

Novel Insights and Applications

In a scan of 3,000 images, IBM technology was able to spot melanoma with an accuracy of about 95 percent, much better than the 75 percent to 84 percent average of today's largely manual methods.IBM Research will continue to work with Sloan Kettering to develop additional measure-ments and approaches to fur-ther refine diagnosis, as well as refine their approach through larger sets of data.

Dec 17, 2014

Aug. 11, 2015

IBM is betting that the same technology that recog-nizes cats can identify tumors and other signs of dis-eases. In the long run, IBM and others in the field hope such systems can become reliable advisers to radiolo-gists, dermatologists and other practitioners who analyze images—especially in parts of the world where health-care providers are scarce.While IBM hopes Watson will learn to interpret Merge’s images, it also expects the combination of imagery, medical records and other data to reveal patterns relevant to diagnosis and treatment that a human physician may miss, ushering in an era of computer-assisted care. Two other recent IBM ac-quisitions, Phytel Inc. and Explorys Inc., yielded 50 million electronic medical records.

Dec. 10, 2015

Novo Nordisk A/S is teaming up with IBM Watson Health, a divi-sion of International Business Machines Corp., to create a “vir-tual doctor” for diabetes patients that could dis-pense treatment advice such as insulin dosage.

Environment

Exercise

Metabolism

GlucoseDM

Blood PressureHTN

CardiovascularDisease

Cognitive

Hormone

Behavior

Psychotherapy

Behavior Therapy

Policy Making

Genetic TestingNeuroimaging

Neuromodulation

Survey

Sensor

DrugDiagnosis

Government

DataMining

Environment Survey

NeuroimagingGenetics Lab/Hormone Hospital

Cognitive

Personalize

Psychotherapy

DietaryIntervention

ExerciseIntervention

Exercise

Glucose

Mobile

Neuromodulation

Monitoring

Multidimensional ArchitectureGene

Hormone

Psychology

Behavior

Phenotype

Outcome

MetabolicDisease Vascular

Disease

The FUTURE MEDICINEis already

at PRESENT

의료 빅데이터와 인공지능의 현재와 미래

Health & Medicine

빅데이터와 저널리즘의 만남, 빅데이터...

올챙이 현재와 미래

2016 W3C Conference #1 : 웹 개발의 현재와 미래

Apt 공격의 현재와 미래 그리고 대응 방안

Apt(advanced persistent threat) 공격의 현재와 대응.....

FT직군의 현재와 미래 - 홍윤표

모바일 웹 UI/UX의 현재와 미래 - Agenda

(최종) 빅데이터와 교통정책의 연계...

20회 오픈업 발표자료 - 01 오픈트레이드...

빅데이터와 AI를 활용한 신용평가의 변화...

[법무법인 민후 l 김경환 변호사] 빅데이터와....

아홉단어 현재와 권위사이 20140709

[Issue Monitor] 스마트 헬스케어의 현재와...

빅데이터와 교육데이터마이닝 (고려대학교...

빅데이터와 타겟 마케팅 Ver 1 0

데브옵스(DevOps)의 현재와 미래 - ChatOps &...