Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Advanced Analytics - The Power of data in healt...

Tulenkantajat2015
March 12, 2015
74

Advanced Analytics - The Power of data in healthcare - Stefan Ohlsson

Tulenkantajat2015

March 12, 2015
Tweet

Transcript

  1. $95 Billion on medical research every year Only 6% completed

    on time 170,000 clinical trials ongoing worldwide A new scientific paper is published every 30 second © 2015 International Business Machines Corporation
  2. Be  More  Right,  More  O4en   What action should I

    take? Decision management Why did it happen? Reporting, analysis, content analytics What could happen? Predictive analytics and modeling What is happening? Discovery and exploration © 2014 International Business Machines Corporation Kognitivt beslutsstöd © 2015 International Business Machines Corporation
  3. Be  More  Right,  More  O4en   What did I learn,

    what’s best? Cognitive What action should I take? Decision management Why did it happen? Reporting, analysis, content analytics What could happen? Predictive analytics and modeling What is happening? Discovery and exploration © 2014 International Business Machines Corporation Kognitivt beslutsstöd © 2015 International Business Machines Corporation
  4.   What  Really  Caused  Readmissions  at  Seton   The Data

    We Thought Would Be Useful … Wasn’t •  113 candidate predictors from structured and unstructured data sources •  Structured data was less reliable then unstructured data – increased the reliance on unstructured data 1. Jugular Venous Distention Indicator 2. Paid by Medicaid Indicator 3. Immunity Disorder Disease Indicator 4. Cardiac Rehab Admit Diagnosis with CHF Indicator 5. Lack of Emotion Support Indicator 6. Self COPD Moderate Limit Health History Indicator 7. With Genitourinary System and Endocrine Disorders 8. Heart Failure History 9. High BNP Indicator 10. Low Hemoglobin Indicator 11. Low Sodium Level Indicator 12. Assisted Living (from ICA Extract) 13. High Cholesterol History 14. Presence of Blood Diseases in Diagnosis History 15. High Blood Pressure Health History 16. Self Alcohol / Drug Use Indicator (Cerner + ICA) 17. Heart Attack History 18. Heart Disease History Top 18 Indicators Predictor Analysis % Encounters Structured Data % Encounters Unstructured Data Ejection Fraction (LVEF) 2% 74% Smoking Indicator 35% (65% Accurate) 81% (95% Accurate) Living Arrangements <1% 73% (100% Accurate) Drug and Alcohol Abuse 16% 81% Assisted Living 0% 13% ©
  5. Advanced Analytics and Decision Support Regional Cancer Center, Stockholm Cogni=ve

     Compu=ng   Data  readiness   Similarity  Analy=cs   Predic=ve  Analy=cs   §  Collabora=on  project  between  IBM  and  RCC   §  Develop  a  tool  for  tracking  treatment  outcomes  and  how  they  are   influenced  by:       –  Combina=ons  of  drugs   –  Correla=ons  with  other  diseases     –  Varia=ons  in  treatment  plans   §  Differences  in  geography  and  socio-­‐economics   ©
  6. © 2014 International Business Machines Corporation © 2014 International Business

    Machines Corporation 19 Next frontier – man and machine working side by side © 2015 International Business Machines Corporation
  7. The IBM Institute for Businesses Value •  Series of papers

    written by IBM experts, informed by client experiences •  Assessment of trends, risks and opportunities •  Providing a headlight into the future Collaborating Beyond Traditional Boundaries – What convergence means for our health care systems Analytics Across the Ecosystem – A prescription for optimising healthcare outcomes http://www-935.ibm.com/services/us/gbs/thoughtleadership/