Upload
hyung-jin-choi
View
1.327
Download
5
Embed Size (px)
DESCRIPTION
2014 대한의료정보학회 추계학술대회 임상의사 관점의 의료빅데이터 연구와 임상적용 From Clinic To Data, From Data To Clinic
Citation preview
Contents
1. What is Healthcare Big Data?
2. Healthcare Big Data
① Electrical Health Records (EHR) Structured/Unstructured Data
② Medical Images
③ National Healthcare Data
④ Behavior/Sensor Data
⑤ Genetic Data
3. Clinical and Research Applications
Hypothesis Driven Science Data Driven Science
Hypothesis
Collect
Data
Data
Generate
Hypothesis
Analyze
Analyze
Candidate Gene
Approach
Genome-wide
Approach
Choose a Gene
from Prior Knowledge
Analyze the Gene
Analyze ALL Genes
Discover Novel Findings
GWAS
(Genome wide association study)
SNP chip
Whole Genome
SNP Profiling (500K~1M SNPs)
Common Variant
Estrada et al., Nature Genetics, 2012
+ novel targets
for bone biology
Recent largest GWAS
GEFOS consortium
2010 An Environment-Wide
Association Study (EWAS) on Type
2 Diabetes Mellitus
Environment-Wide Association Study (EWAS)
다양한 환경인자들
1000 개의 질병들 Bioinformatics. 2010 PheWAS: demonstrating the feasibility of a phenome-wide scan to discover gene-disease associations.
Marylyn D. Ritchie
Contents
1. What is Healthcare Big Data?
2. Healthcare Big Data
① Electrical Health Records (EHR) Structured/Unstructured Data
② Medical Images
③ National Healthcare Data
④ Behavior/Sensor Data
⑤ Genetic Data
3. Clinical and Research Applications
Genomics
Wearable/
Smart Device
Medical Informatics
Genome Medicine
Quantified Self
Health Avatar
Electronic Medical Records (EMR)
Medical Images (MRI, CT)
National Healthcare data (Insurance)
Contents
1. What is Healthcare Big Data?
2. Healthcare Big Data
① Electrical Health Records (EHR) Structured/Unstructured Data
② Medical Images
③ National Healthcare Data
④ Behavior/Sensor Data
⑤ Genetic Data
3. Clinical and Research Applications
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)
Big Data Analysis
0
0.2
0.4
0.6
0.8
1
1.2
1.4
1.6
1.81/Creatinine
한 환자의 10년간 신장기능의 변화 전체 환자의 당 조절 정도 분포
충북대 정보통계학과
허태영 교수
밤동안 저혈당수면 Lt.foot rolling Keep떨림,
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 keep드레싱 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 범위임rt foot rolling
중으로 pain호소 밤사이 수면양호걱정신경 예민감정변화 중임감정을 표현하도록 지지하고
경청기분상태 condition 조금 나은 듯 하다고 혈당 조절과 관련하여 신경쓰는 모습 보이며 혈당
self로 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 Keep떨림, 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 keep수술 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 양호rt foot rolling유지하며 감염이나 심한 통증등 침상안정중임BST
420 checkd. R1 알림 obs 하자Rt 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
1. What is Healthcare Big Data?
2. Healthcare Big Data
① Electrical Health Records (EHR) Structured/Unstructured Data
② Medical Images
③ National Healthcare Data
④ Behavior/Sensor Data
⑤ Genetic Data
3. Clinical and Research Applications
ER Multiple Rule-Out Scan of a
Patient With Disturbance of
Consciousness and Without Breath-
Hold.
SOMATOM Definition Flash
Scanning
Author: Junichiro Nakagawa, MD,*
Isao Ukai, MD*, Osamu Tasaki, MD,
PhD*, Tomoko Fujihara**
and Katharina Otani, PhD ***
Date: Dec 13, 2010
* Trauma and Acute Critical Care
Center, Osaka University Hospital,
Osaka, Japan
**CT Marketing Department,
Healthcare, Siemens Japan K.K.,
Tokyo, Japan
***Research & Collaboration
Development Department,
Healthcare, Siemens Japan K.K.,
Tokyo, Japan
Brain Vasculature
Color =
Vessel Diameters 2011 Optimization of MicroCT Imaging and Blood Vessel Diameter Quantitation of Preclinical Specimen Vasculature with Radiopaque Polymer Injection Medium
Functional Connectivity
2013 Sciencce Functional interactions as big data in the human brain
N=50,000 voxels
N(N – 1)/2 = 1,249,975,000 Pairs
Seed Region Based Analysis
Obesity fMRI Research
Preliminary Pilot Results
p<0.005 uncorrected
Activation of visual, motor and prefrontal brain area in response to visual food cue
3
+
Food presentation
max 4sec
Feedback
1sec
Fixation
1~10sec
Choi et al., on going
Resting state fMRI analysis
Complex network approach
Parcellation
116 brain regions
by AAL map
Adjacency matrix Network properties
node degree, clustering coefficient
Choi et al., on going
Clinical Implication of TBS
2014 Endocrine. Utility of the trabecular bone score (TBS) in secondary osteoporosis
Contents
1. What is Healthcare Big Data?
2. Healthcare Big Data
① Electrical Health Records (EHR) Structured/Unstructured Data
② Medical Images
③ National Healthcare Data
④ Behavior/Sensor Data
⑤ Genetic Data
3. Clinical and Research Applications
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
Number of patients with medical treatments related to
osteoporosis in each calendar year
2005 2006 2007 20080
500
1000
1500Male
Female
Calendar year
Nu
mb
er (
thou
san
d)
2011 JBMM Burden of osteoporosis in adults in Korea- a national health insurance database study
Korean Society for
Bone and Mineral
Research
Anti-hypertensive
prescriptions
(2008-2011)
N = 8,315,709
New users
N = 2,357,908
Age ≥ 50 yrs
Monotherapy
Compliant user (MPR≥80%)
No previous fracture
N = 528,522
Prevalent users
N = 5,957,801
Excluded
Age <50
Combination therapy
Inadequate compliance
Previous fracture
N = 1,829,386
Final study population
심평원 빅데이터 연구
고혈압약과 골절
Choi et al., in submission
Compare Fracture Risk
Comparator? Hypertension
CCB High
Blood Pressure
Fracture
Risk
BB
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 2011 2008
Distribution of ARB MPR
(Histogram)
ARB Non-user
20
Fre
qu
en
cy D
en
sity
ARB user
80 120
Medication Possession Ratio (MPR)
Total prescription days
Observation days
350 days (Prescription)
365 days (Observation)
MPR
96%
MPR (%)
Contents
1. What is Healthcare Big Data?
2. Healthcare Big Data
① Electrical Health Records (EHR) Structured/Unstructured Data
② Medical Images
③ National Healthcare Data
④ Behavior/Sensor Data
⑤ Genetic Data
3. Clinical and Research Applications
Date Time name foodType calories unit amount 2014-08-09 0 미역국 0 23 1국그릇 (300ml) 105 g 2014-08-09 0 잡곡밥 0 80 1/4공기 (52.5g) 52 g 2014-08-09 0 열무김치 0 3 1/4소접시 (8.75g) 9 g 2014-08-09 0 파프리카 0 6 1/2개 (33.25g) 35 g 2014-08-09 0 토란대무침 0 28 1/2소접시(46.5g) 46 g 2014-08-09 1 복숭아 0 91 1개 (269g) 268 g 2014-08-09 2 마른오징어 2 88 1/4마리 (25g) 25 g 2014-08-09 2 파프리카 0 6 1/2개 (33.25g) 35 g 2014-08-09 2 저지방우유 1 72 1컵 (200ml) 180 g 2014-08-09 2 복숭아 0 183 2개 (538g) 538 g 2014-08-09 3 복숭아 0 91 1개 (269g) 268 g 2014-08-09 3 파프리카 0 6 1/2개 (33.25g) 35 g 2014-08-09 4 파프리카 0 6 1/2개 (33.25g) 35 g 2014-08-09 4 식빵 1 92 1장 (33g) 33 g 2014-08-09 4 삶은옥수수 1 197 1개 반 (150g) 150 g 2014-08-09 4 복숭아 0 91 1개 (269g) 268 g 2014-08-09 4 저지방우유 1 72 1컵 (200ml) 180 g 2014-08-10 0 복숭아 0 91 1개 (269g) 268 g 2014-08-10 0 저지방우유 1 36 1/2컵 (100ml) 90 g 2014-08-10 0 두부 0 20 1/4인분 (25g) 25 g 2014-08-10 0 견과류 2 190 1/4 컵 (50g) 31 g 2014-08-10 0 파프리카 0 11 1개 (66.5g) 65 g 2014-08-10 2 방울토마토 0 8 4개 (60g) 60 g 2014-08-10 2 방울토마토 0 8 4개 (60g) 60 g 2014-08-10 2 방울토마토 0 8 4개 (60g) 60 g 2014-08-10 2 김밥 1 318 1줄 (200g) 200 g 2014-08-10 3 복숭아 0 91 1개 (269g) 268 g 2014-08-10 4 잡곡밥 0 161 1/2공기 (105g) 105 g 2014-08-10 4 복숭아 0 91 1개 (269g) 268 g 2014-08-10 4 김치 0 3 1/4소접시 (10g) 12 g 2014-08-10 4 장조림 1 66 1/2소접시 (45g) 45 g 2014-08-10 4 콩나물국 0 14 3/4국그릇 (187.5ml) 83 g 2014-08-10 5 포도 0 45 3/4대접시 (75g) 75 g
식사량 실시간 모니터링
0
100
200
300
400
500
600
아침
아침
간식
점심
점심
간식
저녁
저녁
간식
아침
아침
간식
점심
점심
간식
저녁
저녁
간식
아침
아침
간식
점심
점심
간식
저녁
저녁
간식
아침
아침
간식
점심
점심
간식
저녁
저녁
간식
아침
아침
간식
점심
점심
간식
저녁
저녁
간식
아침
아침
간식
점심
점심
간식
저녁
저녁
간식
아침
아침
간식
점심
점심
간식
저녁
저녁
간식
2014-08-09 2014-08-10 2014-08-11 2014-08-12 2014-08-13 2014-08-14 2014-08-15
점심 과식
저녁 금식
스마트폰 활용 당뇨병 통합관리
의사
상담 교육
조회/
분석
교육간호사
매주/필요시
진료 처방
2-3달 간격
평가 회의 매주/필요시
식사/
운동 스마트폰
데이터베이스 서버
자가관리
전송
분석
혈당
측정 혈당측정기
Contents
1. What is Healthcare Big Data?
2. Healthcare Big Data
① Electrical Health Records (EHR) Structured/Unstructured Data
② Medical Images
③ National Healthcare Data
④ Behavior/Sensor Data
⑤ Genetic Data
3. Clinical and Research Applications
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
Predicting Complex Diseases
2013 NG Predicting the influence of common variants
“For most diseases, it should be possible to identify the individuals with the highest
genetic risk. However, if the aim is to identify individuals with just twice the mean
population risk, we cannot currently do that with SNPs”
Mean population risk
Highest genetic risk
x2
Dis
ease R
isk
Rare Variant?
Variants and Disease Susceptibility
2008 NRG Genome-wide association studies for complex traits- consensus, uncertainty and challenges
Genotype Based Diabetes Therapy
Diabetes due to KATP channel mutations sulphonylurea
2007 American Journal of Physiology - Endocrinology and Metabolism. ATP-sensitive K+ channels and disease- from molecule to malady
Influence of Genetics on Human Disease
For any condition the overall balance of g
enetic and environmental determinants ca
n be represented by a point somewhere w
ithin the triangle.
105
Single
Locus /
Mendelian
Multiple
Loci or multi-
chromosomal
Environmental
Cystic Fibrosis
Hemophilia A
Examples:
Alzheimer’s Disease
Type II Diabetes
Cardiovascular Disease
Diet
Carcinogens
Infections
Stress
Radiation
Lifestyle
Gene = F8
Gene= CFTR
F8 = Coagulation Factor VIII
CFTR = Cystic Fibrosis Conductance Transmembrane Regulator
Lung Cancer
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
Influence of Genetics on Human Disease
For any condition the overall balance of g
enetic and environmental determinants ca
n be represented by a point somewhere w
ithin the triangle.
113
Single
Locus /
Mendelian
Multiple
Loci or multi-
chromosomal
Environmental
Cystic Fibrosis
Hemophilia A
Examples:
Alzheimer’s Disease
Type II Diabetes
Cardiovascular Disease
Diet
Carcinogens
Infections
Stress
Radiation
Lifestyle
Gene = F8
Gene= CFTR
F8 = Coagulation Factor VIII
CFTR = Cystic Fibrosis Conductance Transmembrane Regulator
Lung Cancer
Mendelian (single-gene) genetic
disorder
Known single-gene
candidates testing
Whole Genome or Whole
Exome Sequencing
2013.11.14.
141 drugs
158 labels
60 indications/contraindications Atorvastatin, Azathioprine, Carbamazepine, Carvediolol, Clopidogrel, Codein, Diazepam…..
CPIC Pharmacogenetic Tests: 최형진
No Drug
(N= 10)
Gene
(6 genes=8 bioma
rkers)
Target SNPs
(N=12)
#5
(HJC) Genotype Interpretation Clinical Interpretation
1 Clopidogrel CYP2C19
rs4244285 (G>A) GG *1/*1
(EM) Use standard dose rs4986893 (G>A) GG
rs12248560 (C>T) CC
2 Warfarin
VKORC1 rs9923231 (C>T) TT Low dose
(higher risk of bleeding) Warfarin dose=0.5~2 mg/day
CYP2C9 rs1799853 (C>T) CC
rs1057910 (A>C) AC
3 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 Normal
rs3909184 (C>G) CC
6 Abacavir HLA-B*5701 rs2395029 (T>G) TT Normal
7 Allopurinol HLA-B*5801 rs9263726 (G>A) GG Normal
Clopidogrel1): 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
$99
N>400,000
Future of Genomic Medicine?
Test when needed Without information Know your type
Blood
type
Geno
type
Here is my
sequence
Voxel-wise GWAS
2014 Nature Neuroscience. Whole-genome analyses of whole-brain data- working within an expanded search space
Connectome-wide GWAS
2014 Nature Neuroscience. Whole-genome analyses of whole-brain data- working within an expanded search space
Disease GWAS vs. Whole-brain GWAS
2014 Nature Neuroscience. Whole-genome analyses of whole-brain data- working within an expanded search space
2014 PLOS GENT. Global genetic variations predict brain response to faces
Connectivity of face network
Contents
1. What is Healthcare Big Data?
2. Healthcare Big Data
① Electrical Health Records (EHR) Structured/Unstructured Data
② Medical Images
③ Government Data
④ Behavior/Sensor Data
⑤ Genetic Data
3. Clinical and Research Applications
Clinical and Research Applications
1. Clinical Decision Support
2. Public Health Surveillance
3. Personal Health Record
4. Healthcare Data Integration
Clinical and Research Applications
1. Clinical Decision Support
2. Public Health Surveillance
3. Personal Health Record
4. Healthcare Data Integration
Clinical and Research Applications
1. Clinical Decision Support
2. Public Health Surveillance
3. Personal Health Record
4. Healthcare Data Integration
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
Clinical and Research Applications
1. Clinical Decision Support
2. Public Health Surveillance
3. Personal Health Record
4. Healthcare Data Integration
Clinical and Research Applications
1. Clinical Decision Support
2. Public Health Surveillance
3. Personal Health Record
4. Healthcare Data Integration
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
Clinical and Research Applications
1. Clinical Decision Support
2. Public Health Surveillance
3. Personal Health Record
4. Healthcare Data Integration
5. How to Prepare for Big Data Driven
Healthcare
빅데이터 연구 적용
전통적인 관점 연구
Large scale
(unstructured)
data
Summary
(Modify)
Classical hypothesis driven study
새로운 관점 연구
Hypothesis Generating Study