Decision Support System EBMeDS. Timo Haikonen

Transcription

1 Decision Support System EBMeDS Timo Haikonen

2 Disclosure: Timo Haikonen I certify that, to the best of my knowledge, no aspect of my current personal or professional roles might reasonably be expected to affect my views on the subject we are presenting other than the following: Director, international Duodecin Medical Publications Ltd, Helsinki, Finland

3 Summary Largest medical publisher in the Nordics Finnish Medical Society DUODECIM owns 100 % Provides both medical content and clinical decision support systems

4 Digital challenge By 2025 more data-driven, automated healthcare will displace up to 80% of physicians diagnostic and prescription work. - Vinod Khosla, cofounder of Sun Microsystems

5 The problem In 1950 it took 50 years to double medical knowledge In 1980, it took 7 years In 2010, it took 3.5 years In 2020 the projection is that it will take 73 days The solution: The solution: AI & CDS Trans Am Clin Climatol Assoc. 2011

6 Why CDS System? Increased quality of care Enchanced health outcomes Error reduction Less adverse events Improved efficiency Reduced costs Improved service satisfaction FDA, FASIA Health IT Report, Proposed Strategy and Reciommendations for a Risk-Based Framework, 2014

7 Update Log Files Conversions EBMeDS Basics Columna Database Data Filter Demographics Problems and Risks Investigations Interventions Health Services Documents EHR and End-User Data Net Patient and System Data (XML) Client Component Web Server EBMeDS Service Decision Support (XML/(X)HTML) Work Station Guideline Links Clinical Advice, Alerts Quality Indicators Smart Links Guidelines Smart Forms Background information Feedback External Web Resources EBMeDS Engine Content Tools

8 Update Log Files Conversions EBMeDS Basics Columna Database Data Filter Demographics Problems and Risks Investigations Interventions Health Services Documents EHR and End-User Data Net Patient and System Data (XML) Client Component Web Server EBMeDS Service Decision Support (XML/(X)HTML) Work Station Guideline Links Clinical Advice, Alerts Quality Indicators Smart Links Guidelines Smart Forms Background information Feedback External Web Resources EBMeDS Engine Content Tools

9 Individual, per-organization installations EHR/HIS 1 EHR/HIS 2 EHR/HIS EBMeDS EHR/HIS EBMeDS EHR/HIS 3 EHR/HIS 4 EHR/HIS EBMeDS EHR/HIS EBMeDS

10 Cloud-based Clinical Decision Support service EHR/ HIS EHR/ HIS National CDSS cloud service EHR/ HIS

11 External drivers in 2018 EMRAM stage 6 and 7 are becoming standard EHR requirements, CDS must be included! In the US Meaningfull Use stage criteria will require at leat 5 CDS interventions in EHR to qualify for federal funding. Mandatory in 2018!

12 NICE accreditation Evidence-based medicine methodology

13 Some of our partners

14

15 Table 1. Four domains of Big Data in Researchers at the Cold Spring Harbor Laboratory in the U.S. discovered that the field of genomics is the fastest-growing data generator in the world today. Moreover, the quantity of genetic data being produced on a daily basis is doubling every seven months at the current rate Stephens ZD, Lee SY, Faghri F, Campbell RH, Zhai C, et al. (2015) Big Data: Astronomical or Genomical?. PLoS Biol 13(7): e doi: /journal.pbio

16 Starren et al., JAMA 2013;309:1237

17 The Opportunity Population health management is going to have to be the answer to the question of how to curb the drivers of health care spending. Neal L. Patterson Chairman, CEO Cerner DUODECIM: Health Benefit Analysis Prediction Prevention Intervention

18 Health Benefit Analysis 1. Using EBMeDS identify patients, who would benefit from intervention (caregap). 2. Estimate & quantify the health benefit to each patient. 3. List the interventions in priority order by largest benefit. HEALTH BENEFIT Health benefit = Benefits - Harms

19

20

21 Intelligence Quotient and Intelligence Grade of Artificial Intelligence Feng Liu, Yong Shi, Ying Liu (Submitted on 29 Sep 2017) Although artificial intelligence is currently one of the most interesting areas in scientific research, the potential threats posed by emerging AI systems remain a source of persistent controversy. To address the issue of AI threat, this study proposes a standard intelligence model that unifies AI and human characteristics in terms of four aspects of knowledge, i.e., input, output, mastery, and creation. Using this model, we observe three challenges, namely, expanding of the von Neumann architecture; testing and ranking the intelligence quotient of naturally and artificially intelligent systems, including humans, Google, Bing, Baidu, and Siri; and finally, the dividing of artificially intelligent systems into seven grades from robots to Google Brain. Based on this, we conclude that AlphaGo belongs to the third grade. Subjects: Artificial Intelligence (cs.ai) Journal reference: Annals of Data Science, June 2017, Volume 4, Issue 2, pp

22 Google's A.I. has nearly twice the IQ of Siri, study says but a six-year-old child is smarter than both Google's AI had an IQ score of 47.28, while Siri's score was 23.94, in a review conducted in 2016, new research shows. Google's 2016 AI IQ score was considerably higher than it was in Jordan Novet Subjects: Artificial Intelligence (cs.ai) Journal reference: Annals of Data Science, June 2017, Volume 4, Issue 2, pp

23 Thank You