Genomics Big Data Wearable/ Smart Device Medical Informatics Genome Sequencing Data Science Quantified Self Health Avatar
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Genomics
Big Data Wearable/ Smart Device
Medical Informatics
Genome Sequencing
Data Science
Quantified Self
Health Avatar
Wearable and Medicine
Emergency!!
Heart Monitor of AliveCor
SAMSUNG Gear
Evolution of Diabetes Control
Insulin
Glucose
Insulin Injection
Episodic Glucose
Monitoring
Continuous Insulin
Injection
Continuous Glucose
Monitoring
Artificial Pancreas
Google’s
Smart Contact Lenses
Glucose Monitoring
Smart/Mobile Healthcare
KDNP 당뇨병수첩 – NFC 기반 혈당 결과 무선 전송 기능 포함
Date Calorie Budget Calories Logged Breakfast Cals Lunch Cals Dinner Cals. % Red % Yellow % Green
2014-05-23 1,400 1,325 386 463 476 29.00% 70.00% 0.00%
2014-05-22 1,400 1,672 238 566 868 28.00% 71.00% 0.00%
2014-05-19 1,400 196 196 0 0 0.00% 100.00% 0.00%
2014-05-17 1,400 695 283 412 0 0.00% 100.00% 0.00%
2014-04-05 1,400 477 477 0 0 0.00% 0.00% 100.00%
2014-03-22 1,400 576 208 368 0 36.00% 0.00% 63.00%
2013-12-15 1,400 800 300 200 300 37.00% 62.00% 0.00%
2013-08-14 1,400 665 0 0 665 0.00% 54.00% 45.00%
2013-08-10 1,400 150 0 150 0 0.00% 100.00% 0.00%
2013-08-09 1,400 440 440 0 0 54.00% 0.00% 45.00%
2013-07-05 1,400 200 200 0 0 0.00% 100.00% 0.00%
애니팡 성공 – SNS 경쟁
Apple Healthbook
Genomics/ Biomarker
Big Data/ Medical Informatics
Smart Device/ Wearable
Genome Sequencing
Data Science
Quantified Self
Health Avatar
Mobile Health
Machine Learning
Diabetic patients (n = 12,074; 35,545 fundus examinations) The time from onset of retinopathy to clinical diagnosis of diabetes was calculated as a point estimate by extrapolating the intercept of the best-fitting regression line with the horizontal axis.
2014 DC Estimating the Delay Between Onset and Diagnosis of Type 2 Diabetes From the Time Course of Retinopathy Prevalence
2014 DC Estimating the Delay Between Onset and Diagnosis of Type 2 Diabetes From the Time Course of Retinopathy Prevalence
의료 정보학 Medical Informatics
• 처방전달 시스템(OCS)
• 영상정보 저장전달 시스템(PACS)
• 전자의무기록(EMR)
• 의료 빅데이터
• 인공지능
빅 데이터 분석
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
AFTER • Dialysis pts, Hb <11 g/dL • Non-dialytic CKD eGFR <30 mL/min/1.73m2
Hb <10 g/dL
BEFORE • Dialysis pts, Hb <11
g/dL
- 6m 0m 6m 12m
Reimbursement
change
(pin
t/pe
rson
-year
)
Transfusion requirement
…………………….
Medical Big Data
Big data platform model by Korea Institute of Drug Safety and Risk Management
Future drug safety monitoring system based on the big data
Overview of secondary data in public health by data source
Medical Big Data
Medical Big Data
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 revision
Fracture rates per 10,000 person-years (95% CI)
819
Fracture Rates (per 10,000 Person-Years)
Total
Male
Female
AB: alpha-adrenergic blocker ACEI: angiotensin converting enzyme inhibitor DIUR: diuretics CCB: calcium channel blocker BB: beta-adrenergic blocker ARB: angiotesin-receptor blocker
2008-2011 Prescriptions N = 2,886,555
New Users N = 718,293
Monotherapy+Combination (MPR>80%) Age > 50 yrs
No previous fracture N = 208,648
심평원 빅데이터 연구 당뇨병약과 골절
Total
0 200 400 600
Metformin+DPP4i
SU+TZD
Metformin+TZD
Metformin+SU
AGI
SU
Metformin
Non-user
Fracture Rates per 10,000 Person-Years
Female
0 200 400 600
Metformin+DPP4i
SU+TZD
Metformin+TZD
Metformin+SU
AGI
SU
Metformin
Non-user
Fracture Rates per 10,000 Person-Years
Male
0 200 400 600
Metformin+DPP4i
SU+TZD
Metformin+TZD
Metformin+SU
AGI
SU
Metformin
Non-user
Fracture Rates per 10,000 Person-Years
Fracture Rates (per 10,000 Person-Years)
Total
0 200 400 600
Metformin+DPP4i
SU+TZD
Metformin+TZD
Metformin+SU
AGI
SU
Metformin
Non-user
Fracture Rates per 10,000 Person-Years
Female
0 200 400 600
Metformin+DPP4i
SU+TZD
Metformin+TZD
Metformin+SU
AGI
SU
Metformin
Non-user
Fracture Rates per 10,000 Person-Years
Male
0 200 400 600
Metformin+DPP4i
SU+TZD
Metformin+TZD
Metformin+SU
AGI
SU
Metformin
Non-user
Fracture Rates per 10,000 Person-Years
Total Male
Female
Medical Big Data Artificial Intelligence
Jeopardy!
2011년 인간 챔피언 두 명 과 퀴즈 대결을 벌여서 압도적인 우승을 차지
Medical Big Data Artificial Intelligence
2013 PLOS CB Reassessing Google Flu Trends Data for Detection of Seasonal and Pandemic Influenza
Google Flu Trends
Social Network and Obesity Prevalence
2013 PLOS One. Assessing the Online Social Environment for Surveillance of Obesity Prevalence
2014 JAMA Finding the Missing Link for Big Biomedical Data
Genomics
Big Data Wearable/ Smart Device
Medical Informatics
Genome Sequencing
Data Science
Quantified Self
Health Avatar
Any Questions?
• 최형진
• Hyung Jin Choi
• www.facebook.com/hyungjin.choi.75
Related Documents
