EHRs & CDS (March 29, 2021)
0 likes190 views
This document discusses electronic health records (EHRs) and clinical decision support systems (CDS). It provides examples of different types of CDS, such as alerts and reminders, reference information, order sets, and diagnostic/treatment expert systems. The goal of health IT and CDS is to improve the quality of healthcare by making it safer, more timely, effective, efficient, patient-centered and equitable. However, human decisions are still necessary, so health IT should be designed to support, not replace, clinicians.
EHRs & CDS (March 29, 2021)
- 1. 1 1 Electronic Health Records (EHRs) & Clinical Decision Support Systems (CDS) Nawanan Theera-Ampornpunt, M.D., Ph.D. March 29, 2021 www.SlideShare.net/Nawanan
- 2. 2 2 2003 M.D. (First-Class Honors) 2011 Ph.D. (Health Informatics), Univ. of Minnesota Deputy Dean for Operations Lecturer, Department of Clinical Epidemiology & Biostatistics Faculty of Medicine Ramathibodi Hospital Mahidol University Interests: Health IT for Quality of Care, Social Media IT Management, Security & Privacy [email protected] SlideShare.net/Nawanan นพ.นวนรรน ธีระอัมพรพันธุ์ Dr.Nawanan Theera-Ampornpunt Introduction
- 3. 3 3 ▪ An Informatics Doctor ▪ Digital Health Transformation ▪ Health IT, Smart Hospital & CDS Outline
- 4. 4 An Informatics Doctor: A Real-Life Personal Story
- 6. 6 Class Discussion What ideas come to mind? Digital Health Transformation When you think of
- 9. 9 9 englishmoviez.com Rise of the Machines?
- 11. 11 “Big data is like teenage sex: everyone talks about it, nobody really knows how to do it, everyone thinks everyone else is doing it, so everyone claims they are doing it...” -- Dan Ariely @danariely (2013) Substitute “Big data” with “AI”, “Blockchain”, “IoT” of your choice. -- Nawanan Theera-Ampornpunt (2018)
- 13. 13 Let’s take a look at these pictures...
- 14. 14 14 Image Source: https://en.wikipedia.org/wiki/Industrial_robot (KUKA Roboter GmbH) “Smart” Manufacturing
- 16. 16 16 ER - Image Source: nj.com Healthcare (On TV)
- 17. 17 17 (At an undisclosed hospital) Healthcare (Reality)
- 18. 18 18 • Life-or-Death • Difficult to automate human decisions – Nature of business – Many & varied stakeholders – Evolving standards of care • Fragmented, poorly-coordinated systems • Large, ever-growing & changing body of knowledge • High volume, low resources, little time Why Healthcare Isn’t (Yet) “Smart”?
- 20. 20 https://www.youtube.com/watch?v=gxz9ZVvduGc Connecting People to a Healthy Future With Personalized Care – Kaiser Permanente
- 22. 22 22 To treat & to care for their patients to their best abilities, given limited time & resources Image Source: http://en.wikipedia.org/wiki/File:Newborn_Examination_1967.jpg (Nevit Dilmen) What Clinicians Want?
- 23. 23 Why Aren’t We Talk About These Words? http://hcca-act.blogspot.com/2011/07/reflections-on-patient-centred-care.html
- 24. 24 The Goal of Health Care The answer is already obvious... “Health” “Care”
- 25. 25 25 • Safe • Timely • Effective • Patient-Centered • Efficient • Equitable Institute of Medicine, Committee on Quality of Health Care in America. Crossing the quality chasm: a new health system for the 21st century. Washington, DC: National Academy Press; 2001. 337 p. High Quality Care
- 26. 26 26 Information Is Everywhere in Healthcare
- 27. 27 27 27 WHO (2009) Components of Health Systems
- 29. 29 29 Hospital Information System (HIS) Computerized Physician Order Entry (CPOE) Electronic Health Records (EHRs) Picture Archiving and Communication System (PACS) Various Forms of Health IT
- 30. 30 30 m-Health Health Information Exchange (HIE) Biosurveillance Telemedicine & Telehealth Images from Apple Inc., Geekzone.co.nz, Google, PubMed.gov, and American Telecare, Inc. Personal Health Records (PHRs) Health IT Beyond Hospitals
- 31. 31 31 Ordering Transcription Dispensing Administration Computerized Physician Order Entry (CPOE) Automatic Medication Dispensing Electronic Medication Administration Records (e-MAR) Barcoded Medication Administration Barcoded Medication Dispensing Health IT for Medication Safety
- 32. 32 32 Hospital A Hospital B Clinic D Policymakers Patient at Home Hospital C HIE Platform Health Information Exchange (HIE)
- 33. 33 33 • Safe –Drug allergies –Medication Reconciliation • Timely –Complete information at point of care • Effective –Better clinical decision-making Being Smart in Healthcare
- 34. 34 34 • Efficient –Faster care –Time & cost savings –Reducing unnecessary tests • Equitable –Access to providers & knowledge • Patient-Centered –Empowerment & better self-care Being Smart in Healthcare
- 35. 35 35 (IOM, 2001) (IOM, 2000) (IOM, 2011) Landmark Institute of Medicine Reports
- 36. 36 36 • Humans are not perfect and are bound to make errors • Highlight problems in U.S. health care system that systematically contributes to medical errors and poor quality • Recommends reform • Health IT plays a role in improving patient safety Summary of These Reports
- 37. 37 37 Image Source: (Left) http://docwhisperer.wordpress.com/2007/05/31/sleepy-heads/ (Right) http://graphics8.nytimes.com/images/2008/12/05/health/chen_600.jpg To Err is Human 1: Attention
- 38. 38 38 Image Source: Suthan Srisangkaew, Department of Pathology, Facutly of Medicine Ramathibodi Hospital To Err is Human 2: Memory
- 39. 39 39 External Memory Knowledge Data Long Term Memory Knowledge Data Inference DECISION PATIENT Perception Attention Working Memory CLINICIAN Elson, Faughnan & Connelly (1997) Clinical Decision Making
- 40. 40 40 • The real place where most of the values of health IT can be achieved – Expert systems • Based on artificial intelligence, machine learning, rules, or statistics • Examples: differential diagnoses, treatment options (Shortliffe, 1976) Clinical Decision Support Systems (CDS)
- 41. 41 41 – Alerts & reminders • Based on specified logical conditions • Examples: –Drug-allergy checks –Drug-drug interaction checks –Reminders for preventive services –Clinical practice guideline integration Clinical Decision Support Systems (CDS)
- 42. 42 42 Example of “Alerts & Reminders” Reducing Errors through Alerts & Reminders
- 43. 43 43 • Reference information or evidence- based knowledge sources –Drug reference databases –Textbooks & journals –Online literature (e.g. PubMed) –Tools that help users easily access references (e.g. Infobuttons) More CDS Examples
- 45. 45 45 • Pre-defined documents –Order sets, personalized “favorites” –Templates for clinical notes –Checklists –Forms Other CDS Examples
- 47. 47 47 • Simple UI designed to help clinical decision making –Abnormal lab highlights –Graphs/visualizations for lab results –Filters & sorting functions Other CDS Examples
- 48. 48 48 Image Source: http://geekdoctor.blogspot.com/2008/04/designing-ideal-electronic-health.html Abnormal Lab Highlights
- 49. 49 49 External Memory Knowledge Data Long Term Memory Knowledge Data Inference DECISION PATIENT Perception Attention Working Memory CLINICIAN Elson, Faughnan & Connelly (1997) Clinical Decision Making Abnormal lab highlights
- 50. 50 50 External Memory Knowledge Data Long Term Memory Knowledge Data Inference DECISION PATIENT Perception Attention Working Memory CLINICIAN Elson, Faughnan & Connelly (1997) Clinical Decision Making Drug-Drug Interaction Checks
- 51. 51 51 External Memory Knowledge Data Long Term Memory Knowledge Data Inference DECISION PATIENT Perception Attention Working Memory CLINICIAN Elson, Faughnan & Connelly (1997) Clinical Decision Making Diagnostic/Treatment Expert Systems (e.g. AI)
- 52. 52 52 • CDS as a replacement or supplement of clinicians? – The demise of the “Greek Oracle” model (Miller & Masarie, 1990) The “Greek Oracle” Model The “Fundamental Theorem” Model Friedman (2009) Wrong Assumption Correct Assumption Clinical Decision Support Systems (CDS)
- 53. 53 53 ▪ An informatics doctor thinks like a doctor but designs IT applications to help other doctors ▪ Digital Health Transformation is, first and foremost, about Health Care, not digital technologies ▪ EHRs & CDS are examples of useful Health IT ▪ Human decisions are still necessary in healthcare, so many health IT should work to support human decisions as CDS Summary