Big Data and Smart Healthcare
Download as PPTX, PDF•1 like•2,655 views
The document discusses the transformation in healthcare driven by big data and smart technologies, emphasizing the challenges posed by the vast amounts of unstructured data generated from patient records and social media. It highlights the importance of automating data processing and improving machine understanding, particularly through natural language processing and the semantic web, to enhance decision-making in healthcare. Additionally, it addresses the need for experts to interpret complex data sets to ensure trustworthiness and privacy while adapting to new federal healthcare rules and quality measures.
Big Data and Smart Healthcare
- 1. 1 Sujan Perera Kno.e.sis Center, Wright State University Big Data and Smart Healthcare Wright State Honors Institute Symposium
- 2. Healthcare is Changing • Introduction of new federal rules and incentive programs • Hospitals are forced to change the process (30-day readmission, ICD10 adaptation, quality measures) • Free and Open health information • Rise of discussions/forums/social media • 70-75% Americans online have used internet to find health information1 • Rapid growth of health related devices • Variety of cheap sensors for health status/activity monitoring • IBM Watson • Adaptation of Watson technology to Healthcare 1 http://www.additiveanalytics.com/blog/infographic-healthcare-social-media
- 3. Challenges on the way • Huge amount of data being generated • Scientific knowledge, social forums, patient records • Variety of data formats (text, images, videos) • Find the signal from noise (actionable information) • Expert can’t keep up with the new information • Need expert knowledge to interpret data (esp. combination of observations) • Trustworthiness • Especially on social forums • Privacy
- 4. It is clear that we need mechanisms to automate some parts of data processing and help humans in decision making. This talk will concentrate on how to improve the machine understanding of unstructured data
- 5. Structured vs Unstructured Data Patient Disorders ICD-9 Code Patient1 Hypertension 401 Patient2 Atrial fibrillation 427.31 Patient1 Pulmonary hypertension 416 Patient3 Edema 782.3 Patient4 hyperthyroidism 242.9 Coronary artery disease, status post four-vessel coronary artery bypass graft surgery on , by Dr. X with a left internal mammary artery to the left anterior descending artery, sequential vein graft to the ramus and first diagonal, and a vein graft to the posterior descending artery. He had normal left ventricular function. He is having some symptoms that are unclear if they are angina or not. I am therefore going to get him scheduled for an exercise Cardiolite stress test. VS
- 6. • Structured data is incomplete and not accurate2,3 • 80% of patient data is unstructured1 • Stake holders interested in unstructured data • Medical professionals • Scientists • Insurance Companies • Policy makers • Interesting Applications • Search • Prediction • Applications like CAC and CDI • Data and knowledge mining • Decision Support Unstructured Data 1 http://www.zdnet.com/within-two-years-80-percent-of-medical-data-will-be-unstructured-7000013707 2Strengths and Limitations of CMS Administrative Data in Research 3Comparison of clinical and administrative data sources for hospital coronary artery bypass graft surgery report cards
- 7. Patient Data Distribution Structured data Unstructured data Lab results HbA1C, BP, ECG
- 8. • Key indicators for readmission prediction reside in unstructured patient notes • facilities • “Holter monitor was ordered by Lisa. She failed to get this because she did not have transportation” • non-compliance • “Atrial fibrillation with poorly controlled ventricular rate due to noncompliance.” • financial status • “The patient mentioned that Bystolic is expensive and cannot afford it now.” How Important is Unstructured Data
- 9. • ICD10 adaptation – need to understand the relationships E08 - Diabetes mellitus due to underlying condition E08.0 - Diabetes mellitus due to underlying condition with hyperosmolarity E08.00 - without nonketotic hyperglycemic-hyperosmolar coma (NKHHC) E08.01 - with coma E08.1 - Diabetes mellitus due to underlying condition with ketoacidosis E08.10 - without coma E08.11 – with coma • The underlying condition can be congenital rubella, Cushing's syndrome, cystic fibrosis, malignant neoplasm, malnutrition, pancreatitis How Important is Unstructured Data
- 10. Search Mining Decision Support Knowledge Discovery Prediction NLP + Semantics The Solution
- 11. • Semantic Web – Provides a common framework that allows data to be shared and reused across application, enterprise, and community boundaries – Offers mechanisms to query data and reason over them • Natural Language Processing – Enable computers to understand natural language input The Solution
- 12. An Example He is off both Diovan and Lotrel. I am unsure if it is due to underlying renal insufficiency. He has actually been on atenolol alone for his hypertension. Raw Text Concepts Knowledge Inference diovan lotrel renal insufficiency atenolol hypertension diovanvaltuna valsartan antihypertensive agent atenolol tenominatenix kidney failure renal insufficiency kidney disease disorder blood pressure disorder hypertension systoloc hypertension pulmonary hypertension Patient taking diovan for hypertension Patient has kidney disease Patient is on antihypertensive drugs is used to treat is a drug disorder
- 13. cTAKES ezNLP ezKB <problem value="Asthma" cui="C0004096"/> <med value="Losartan" code="52175:RXNORM" /> <med value="Spiriva" code="274535:RXNORM" /> <procedure value="EKG" cui="C1623258" /> ezFIND ezMeasure ezCDIezCAC www.ezdi.us ezHealth Platform
- 15. Thank You Visit us: www.knoesis.org
Editor's Notes
- #3: Healthcare is changing by socially, economically, by law and technologically