SlideShare a Scribd company logo

Big Data Expo 2015 - Care IQ

•
•
B
BigDataExpo

De kritische zorgsector genereert 24/7 astronomische hoeveelheden data, die onze zoektocht naar informatie, kennis, en 'wijsheid' kunnen compliceren. De opeenhoping van klinische data overtreft dikwijls de capaciteit voor effectieve aggregatie en analyse. Bijgevolg wordt het doel de klinische kwaliteit, patiëntveiligheid en geïntegreerde patiëntenzorg onvolledig bereikt. Sven Van Poucke geeft een presentatie over de inzet van een Big Data Research Platform ter ondersteuning van de integratie van een grote klinische database ( MIMIC-II ) in een computer cluster (Hadoop / Hive) met RapidMiner (Radoop) data mining –technologie. Het doel van dit project is om de ontwikkeling van de klinische besluitvorming en closed loop systemen te vereenvoudigen. Bovendien biedt dit een toegankelijk en aantrekkelijk platform voor klinisch onderzoek

Related slideshows

LDI Research Seminar- Targeted Testing & Treatment for Breast Cancer 11_18_11
LDI Research Seminar- Targeted Testing & Treatment for Breast Cancer 11_18_11LDI Research Seminar- Targeted Testing & Treatment for Breast Cancer 11_18_11
LDI Research Seminar- Targeted Testing & Treatment for Breast Cancer 11_18_11
 
Whole body ct adult versus ped centers (iep)
Whole body ct adult versus ped centers (iep)Whole body ct adult versus ped centers (iep)
Whole body ct adult versus ped centers (iep)
 
Jco 2010-rizzo-jco.2010.29.2201
Jco 2010-rizzo-jco.2010.29.2201Jco 2010-rizzo-jco.2010.29.2201
Jco 2010-rizzo-jco.2010.29.2201
 
1 of 23
Data Mining and Clinical Decision Support in Critical Care Units: Bridging the 2 Solitudes? Sven Van Poucke, MD Dept. Anesthesiology, Intensive Care, Emergency Medicine, Pain Therapy, ZOL, Genk, Belgium Zhongheng Zhang, MD Dept. of Critical Care Medicine, Jinhua Municipal Central Hospital, Jinhua Hospital of Zhejiang University, Zhejiang, P.R. China.
2
3
Bridging the 2 Solitudes? “crazy” “nerd” “sexy” “normal”
Big Data Expo 2015 - Care IQ
ICU environment
2015, big data in healthcare: for whom the bell tolls?  data stream 24/7 ->information, knowledge, wisdom?  + extra information:  optimization of treatments  reduce adverse events  reduce admission rates  identification of populations  - in its infancy: -> Google baseline study
Big Data Expo 2015 - Care IQ
2015, big data in healthcare: for whom the bell tolls  ICU:  10% inpatients beds  >10% mortality  >400% cost  Preprocessed data:  highly heterogenous, multi-source, multi-scale  big data (volume, veracity,variety, velocity)  time-stamped, variable granularity and tenability  context sensitive feature extraction by fusion of domain knowledge and data driven methods
MIMIC-II
Methods DUA: NIH training course “Protecting Human Research Participants” Z.Z. and S.V.P (certification number: 1132877 and 1712927) Data extraction: Querybuilder interfase database by SQL with pgADmin PostgreSQL tools (version 1.12.3) Virtual Machine Radoop/Hive 38 tables: LABEVENTS, D_PATIENTS, COMORBIDITY_SCORES, ICUSTAY_DETAIL.
Querybuilder https://mimic2app.csail.mit.edu/querybuilder/
VM VirtualBox
Data Patients (n=11944), older than 15 years Age on ICU admission, sex, Elixhauser comorbidity score, Type of ICU setting, Day 1 sequential organ failure assessment (SOFA), Simplified Acute Physiology Score (SAPS-1), Time of ICU admission and discharge, date of death, All measurements of platelet count during ICU stay, Comorbidities: hypertension, paralysis, chronic pulmonary disease, diabetes, renal failure, acquired immunodeficiency syndrome (AIDS), coagulopathy, obesity and liver disease
https://www.youtube.com/watch?v=zToFij3SW8k RapidMiner-Radoop-Hive
Results
Results ICU mortality: 11.5% (n=1378) Survivors: significantly younger (63.9±18.4 years vs 70.3±16.2 years; p<0.001) significantly more male patients (57.0% vs 50.7%; p<0.0001) Mortality was higher for patients admitted on MICU and SICU, not for patients admitted on CCU and CSRU. SAPS-1 and SOFA scores: significantly higher in the non-survivors (13.9± 4.7 vs 19.3±5.6 and 5.4±3.4 vs 9.6±4.5) In the non-survivor group, significantly more renal failure, complicated diabetes, coagulopathy and liver disease The prevalence of normal platelet count on ICU admission was 73.8%. Low platelet count in 12.5%, 2.3%, 1.2%, 0.6% of the cases, respectively for grade 1, 2, 3 and 4 thrombocytopenia High platelet count in 9.0%, 0.3%, 0.0%, 0.3% of the cases for low, mild, severe and extreme thrombocythemia Attribute weights and forward selection by NB classification and SVM selected 10 attributes for mortality prediction Performance of predictive analysis (NB) resulted in an accuracy of 81.30%±3.58% and an AUC of 0.91±0.02 Performance of predictive analysis(SVM) resulted in an accuracy of 50.71%±0.18% and an AUC of 0.86±0.01
Results
Results
Conclusions -MIMIC-II is a valuable public database for intensive care research -We have successfully developed an integration in RapidMiner facilitating the access to MIMIC-II -This is a major step forward in the analysis of clinical databases using data mining technology -Essential is the will to communicate between medical professionals and data scientists. -Is an essential step in the development of clinical decision support and closed loop systems. -Extensive analysis before change in medical practice and inclusion in clinical guidelines.
Big Data Expo 2015 - Care IQ
RapidMiner4Health
23 We bring Analytics and Bio-Medical Expertise to your Data! www.carelics.nl

More Related Content

Big Data Expo 2015 - Care IQ

  • 1. Data Mining and Clinical Decision Support in Critical Care Units: Bridging the 2 Solitudes? Sven Van Poucke, MD Dept. Anesthesiology, Intensive Care, Emergency Medicine, Pain Therapy, ZOL, Genk, Belgium Zhongheng Zhang, MD Dept. of Critical Care Medicine, Jinhua Municipal Central Hospital, Jinhua Hospital of Zhejiang University, Zhejiang, P.R. China.
  • 2. 2
  • 3. 3
  • 4. Bridging the 2 Solitudes? “crazy” “nerd” “sexy” “normal”
  • 7. 2015, big data in healthcare: for whom the bell tolls?  data stream 24/7 ->information, knowledge, wisdom?  + extra information:  optimization of treatments  reduce adverse events  reduce admission rates  identification of populations  - in its infancy: -> Google baseline study
  • 9. 2015, big data in healthcare: for whom the bell tolls  ICU:  10% inpatients beds  >10% mortality  >400% cost  Preprocessed data:  highly heterogenous, multi-source, multi-scale  big data (volume, veracity,variety, velocity)  time-stamped, variable granularity and tenability  context sensitive feature extraction by fusion of domain knowledge and data driven methods
  • 11. Methods DUA: NIH training course “Protecting Human Research Participants” Z.Z. and S.V.P (certification number: 1132877 and 1712927) Data extraction: Querybuilder interfase database by SQL with pgADmin PostgreSQL tools (version 1.12.3) Virtual Machine Radoop/Hive 38 tables: LABEVENTS, D_PATIENTS, COMORBIDITY_SCORES, ICUSTAY_DETAIL.
  • 14. Data Patients (n=11944), older than 15 years Age on ICU admission, sex, Elixhauser comorbidity score, Type of ICU setting, Day 1 sequential organ failure assessment (SOFA), Simplified Acute Physiology Score (SAPS-1), Time of ICU admission and discharge, date of death, All measurements of platelet count during ICU stay, Comorbidities: hypertension, paralysis, chronic pulmonary disease, diabetes, renal failure, acquired immunodeficiency syndrome (AIDS), coagulopathy, obesity and liver disease
  • 17. Results ICU mortality: 11.5% (n=1378) Survivors: significantly younger (63.9±18.4 years vs 70.3±16.2 years; p<0.001) significantly more male patients (57.0% vs 50.7%; p<0.0001) Mortality was higher for patients admitted on MICU and SICU, not for patients admitted on CCU and CSRU. SAPS-1 and SOFA scores: significantly higher in the non-survivors (13.9± 4.7 vs 19.3±5.6 and 5.4±3.4 vs 9.6±4.5) In the non-survivor group, significantly more renal failure, complicated diabetes, coagulopathy and liver disease The prevalence of normal platelet count on ICU admission was 73.8%. Low platelet count in 12.5%, 2.3%, 1.2%, 0.6% of the cases, respectively for grade 1, 2, 3 and 4 thrombocytopenia High platelet count in 9.0%, 0.3%, 0.0%, 0.3% of the cases for low, mild, severe and extreme thrombocythemia Attribute weights and forward selection by NB classification and SVM selected 10 attributes for mortality prediction Performance of predictive analysis (NB) resulted in an accuracy of 81.30%±3.58% and an AUC of 0.91±0.02 Performance of predictive analysis(SVM) resulted in an accuracy of 50.71%±0.18% and an AUC of 0.86±0.01
  • 20. Conclusions -MIMIC-II is a valuable public database for intensive care research -We have successfully developed an integration in RapidMiner facilitating the access to MIMIC-II -This is a major step forward in the analysis of clinical databases using data mining technology -Essential is the will to communicate between medical professionals and data scientists. -Is an essential step in the development of clinical decision support and closed loop systems. -Extensive analysis before change in medical practice and inclusion in clinical guidelines.
  • 23. 23 We bring Analytics and Bio-Medical Expertise to your Data! www.carelics.nl