iCare4U – Decision support system for personalized medicine in ICUs

5th February 2018 - Decision support systems


This project proposes a decision support system based on intelligent modelling and patient sub-group analysis, to provide personalized therapy for critically ill patients. It is hypothesized that the “Collective Experience” from large clinical databases, where clinical decisions are linked with patient outcomes, can be used to identify specific patient sub-groups and build personalized therapy models towards a new era of personalized medicine, allowing the improvement of patient outcomes in the ICU. The validity of the proposed systems will be tested using two case studies where generalized severity scoring systems have consistently performed poorly: patients admitted to the ICU who then develop acute kidney injury, where two-thirds of these patients require renal support therapy; and severe sepsis a typical heterogeneous disease among critically ill patients, in which the immune response is highly dynamic and variable, and likely to need complex therapies to improve patient outcomes.

This project will use data from the MIMIC III database, that gather information of ICU patients admitted to the Beth Israel Deaconess Medical Center from 2001 to 2014. It will also use data from a Philips Healthcare database that gathers data from 333 different hospitals, 1,799,500 patients from 835 ICUs.  Further, it will also use a database collected from a Portuguese Hospital, Hospital Beatriz Angelo, which will allow the comparison of cross-country results in two different environments.



  1. National Academy of Engineering and Institute of Medicine, “Building a Better Delivery System: A New Engineering/Health Care Partnership”. National Academies Press, pp. 1-26, (2005). http://www.nationalacademies.org/onpi/030909643X.pdf
  2. Murugan, Raghavan.  Movement towards personalised medicine in the ICU. The Lancet Respiratory Medicine , Volume 3 , Issue 1 , 10 – 12, January 2015. http://dx.doi.org/10.1016/S2213-2600(14)70310-8
  3. Sen, A and Yende, S. Towards personalized medicine in sepsis: quest for Shangri-La?. Crit Care. 2013; 17: 303 http://ccforum.com/content/17/1/303
  4. Abrahams, E and Silver, M. The history of personalized medicine. in: E Gordon, S Koslow (Eds.) Integrative neuroscience and personalized medicine. Oxford University Press, New York; 2010: 3–16 http://oxfordindex.oup.com/view/10.1093/acprof:oso/9780195393804.001.0001
  5. Kravitz, RL, Duan, N, and Braslow, J. Evidence-based medicine, heterogeneity of treatment effects, and the trouble with averages. Milbank Q. 2004; 82: 661–687 http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2690188/
  6. Strand K, Flaaten H. Severity Scoring in the ICU: A Review. Acta Anaesthesioogical Scandinavica. 2008;52(4):467–478. http://www.ncbi.nlm.nih.gov/pubmed/18339152
  7. Celi LAG, Tang RJ, Villarroel MC, Davidzon GA, Lester WT, Chueh HC. A Clinical Database-Driven Approach to Decision Support: Predicting Mortality Among Patients with Acute Kidney Injury. Journal of healthcare engineering 2011;2(1):97-110. http://dx.doi.org/10.1260/2040-2295.2.1.97
  8. Uchino S, Kellum J, Bellomo R, Doig GS, Morimatsu H, Morgera S, Schetz M, Tan I, Bouman C, Macedo E, Gibney N, Tolwani A, Ronco C. Acute Renal Failure in Critically Ill Patients: A Multinational, Multicenter Study. JAMA. 2005;294(7):813–818. http://jama.jamanetwork.com/article.aspx?articleid=201386
  9. Celi, Leo Anthony, Andrew J Zimolzak, and David J Stone. “Dynamic Clinical Data Mining: Search Engine-Based Decision Support.” Ed. Gunther Eysenbach. JMIR Medical Informatics 2.1 (2014): e13. PMC. Web. 23 Jan. 2015. http://medinform.jmir.org/2014/1/e13/
  10. Fialho, A. S., Cismondi, F., Vieira, S.M., Sousa, J.M.C., Reti, S., Howell, M. and Finkelstein, S.N.  Disease-based modeling to predict fluid response in intensive care units. Methods of Information in Medicine, Vol. 52, Issue 6,  2013, pp. 494-502. http://dx.doi.org/10.3414/ME12-01-0093
  11. M. Fernandes, C.Silva,, S. M. Vieira, and J. M. C. Sousa, “Multimodeling for the Prediction of Patient Readmissions in Intensive Care Units,” In 2014 IEEE International Conference on Fuzzy Systems, Beijing, China, 2014. http://dx.doi.org/10.1109/FUZZ-IEEE.2014.6891779
  12. R Henriques, SC Madeira, BicSPAM: flexible biclustering using sequential patterns.BMC bioinformatics 15 (1), 130, 2014. http://www.biomedcentral.com/1471-2105/15/130
  13. I. Guyon, S. Gunn, M. Nikravesh, and L. A. Zadeh, editors. Feature Extraction: Foundations and Applications (Studies in Fuzziness and Soft Computing). Springer, August 2006. http://clopinet.com/isabelle/Projects/NIPS2003/call-for-papers.html
  14. I. Babaoglu, O. Findik and E. Ülker. A comparison of feature selection models utilizing binary particle swarm optimization and genetic algorithm in determining coronary artery disease using support vector machine. Expert Systems with Applications, 37(4):3177 – 3183, 2010. http://www.sciencedirect.com/science/article/pii/S0957417409008458
  15. S. Haykin. Neural Networks and Learning Machines (Third Edition), Prentice Hall Pub. November 2008. http://www.pearsonhighered.com/educator/product/Neural-Networks-and-Learning-Machines-3E/9780131471399.page
  16. S.M. Vieira, A. Silva, J.M.C. Sousa, J. de Brito, P.L. Gaspar. Modelling the service life of rendered facades using fuzzy systems. Automation in Construction, Volume 51, pp. 1-7, March 2015. http://www.sciencedirect.com/science/article/pii/S0926580514002556
  17. Cismondi, F., L.H., Abigail, Fialho, A.S., Vieira, S.M, Reti, S., Sousa, J.M.C and Finkelstein, S.N. Multi-stage modeling using fuzzy multi-criteria feature selection to improve survival prediction of ICU septic shock patients. Expert Systems with Applications, Vol. 39 (16), pp. 12332–12339, 2012. http://www.sciencedirect.com/science/article/pii/S0957417412006240
  18. L. F. Mendonça, J.M.C. Sousa and J.M.G. Sá da Costa. An architecture for fault detection and isolation based on fuzzy models. Expert Systems With Applications, Volume 36, Issue 2, 1092-1104, March 2009. http://dx.doi.org/10.1016/j.eswa.2007.11.009
  19. Lavrenko, V. et al, Mining of Concurrent Text and Time Series, Proceedings of the 6 th ACM SIGKDD Int’l Conference on Knowledge Discovery and Data Mining Workshop on Text Mining, 2000 http://homepages.inf.ed.ac.uk/vlavrenk/doc/kdd2k.pdf
  20. Bosma, R., Berg, J. van den, Berg, J. van den, Kaymak, U., Udo, H. & Verreth, J. (2012). A generic methodology for developing fuzzy decision models. Expert Systems with Applications, 39(1), 1200-1210. http://www.sciencedirect.com/science/article/pii/S0957417411010888
  21. Nuno Homem and Joao P. Carvalho, Authorship Identification and Author Fuzzy Fingerprints, NAFIPS2011 – 30th Annual Conference of the North American Fuzzy Information Processing Society, Mar. 2011 , pp. G401-G406, IEEE Xplorer http://www.l2f.inesc-id.pt/~fmmb/wiki/uploads/Work/misnis.ref05.pdf
  22. Nuno Homem and Joao P. Carvalho, Mobile Phone User Identification with Fuzzy Fingerprints, EUSFLAT-LFA 2011, Jul. 2011 , pp. 860-867 , Atlantis Press http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&ved=0CCAQFjAA&url=http%3A%2F%2Fwww.atlantis-press.com%2Fphp%2Fdownload_paper.php%3Fid%3D2338&ei=nmPJVIr3Ha_isASDsIHwCw&usg=AFQjCNEmMi08PxP-uKU42wkJKxGl6VsKWg&sig2=HnvFndFM0KulLBomQSPvXA&bvm=bv.84607526,d.cWc
  23. Nuno Homem and Joao P. Carvalho, Web User Identification with Fuzzy Fingerprints , FUZZ-IEEE 2011 – 2011 IEEE International Conference on Fuzzy Systems, Jun. 2011 , pp. 2622-2629 http://www.l2f.inesc-id.pt/~fmmb/wiki/uploads/Work/misnis.ref0c.pdf
  24. J. P. Shim, M. Warkentin, J. F. Courtney, D. J. Power, R. Sharda and Christer Carlsson. Past, present, and future of decision support technology. Decision Support Systems, 33(2):111 – 126, 2002. http://users.dcc.uchile.cl/~nbaloian/DSS-DCC/PastPresentAndFutureDSS.pdf
  25. R.F. DeBusk, N. Houston-Miller and L. Raby. Technical Feasibility of an Online Decision Support Systemfor Acute Coronary Syndromes. Circulation: Cardiovascular Quality and Outcomes, 3:694-700, 2010. http://circoutcomes.ahajournals.org/content/3/6/694.long
  26. M.M. Dierks and K. Nouri. Modeling risk in complex medical domains: understanding ‘hidden’ interactions and variations across different phases of care. Proceedings of Probabilistic Safety Assessment and Management (PSAM8) Annual Symposium, 2006. ASME Press. http://ebooks.asmedigitalcollection.asme.org/content.aspx?bookid=260&sectionid=38775920
  27. Johnson AEW, Pollard TJ, Shen L, Lehman L, Feng M, Ghassemi M, Moody B, Szolovits P, Celi LA, Mark RG. MIMIC-III, a freely accessible critical care database. Scientific Data (2016) https://www.nature.com/articles/sdata201635
  28. Marques, Filipe J and Moutinho, Alexandra and Vieira, Susana M and Sousa, João MC. Preprocessing of clinical databases to improve classification accuracy of patient diagnosis. IFAC Proceedings Volumes,  vol. 44 (1),  pp. 14121–14126, 2011. http://www.sciencedirect.com/science/article/pii/S1474667016458957
  29. J.P. Carvalho and S. Curto, Fuzzy Preprocessing of Medical Text Annotations of Intensive Care Units Patients, IEEE 2014 Conference on Norbert Wiener in the 21st Century, Jun. 2014, IEEE Xplorer http://www.inesc-id.pt/pt/indicadores/Ficheiros/10251.pdf
  30. L.F. Mendonça, S.M. Vieira, and J.M.C. Sousa, Decision tree search methods in fuzzy modeling and classification, International Journal of Approximate Reasoning, 44(2):106–123, 2007. http://www.sciencedirect.com/science/article/pii/S0888613X06000843
  31. Pacheco, Ricardo and Salgado, Cátia and Deliberato, Rodrigo and Celi, Leo Anthony and Sousa, João and Vieira, Susana. 128: MODELING TO INDIVIDUALIZE MEAN ARTERIAL PRESSURE THRESHOLD TO PREVENT ACUTE KIDNEY INJURY IN THE ICU, Critical Care Medicine, Vol. 44 (12), pp. 109, 2016, LWW. http://journals.lww.com/ccmjournal/Citation/2016/12001/128___MODELING_TO_INDIVIDUALIZE_MEAN_ARTERIAL.95.aspx
  32. Salgado, Catia M and Ferreira, Marta C and Vieira, Susana M. Mixed Fuzzy Clustering for Misaligned Time Series. IEEE Transactions on Fuzzy Systems, DOI: 10.1109/TFUZZ.2016.2633375, 2016, IEEE. http://ieeexplore.ieee.org/abstract/document/7762050/
  33. Salgado, Catia Matos and Viegas, Joaquim Laurens and Azevedo, Carlos Santos and Ferreira, Marta Costa and Vieira, Susana M and da Costa Sousa, Joao Miguel. Takagi-Sugeno fuzzy modeling using mixed fuzzy clustering.IEEE Transactions on Fuzzy Systems, DOI: 10.1109/TFUZZ.2016.2639565,  2016, IEEE. http://ieeexplore.ieee.org/abstract/document/7782753/
  34. Viegas, Rita and Salgado, Cátia M and Curto, Sérgio and Carvalho, João P and Vieira, Susana M and Finkelstein, Stan N. Daily prediction of ICU readmissions using feature engineering and ensemble fuzzy modelling. Expert Systems with Applications, Vol. 79, pp. 244–253, 2017, Pergamon. http://www.sciencedirect.com/science/article/pii/S0957417417301276


The five most representative publications from the team in this area.

[a] Vieira, S.M., Mendonça, L.F., Farinha, G.J. and Sousa, J.M.C.. Modified binary PSO for feature selection using SVM applied to mortality prediction of septic patients. Applied Soft Computing, Volume 13, Issue 8, pp. 3494–3504, August 2013.


[b] J.M.C. Sousa and U. Kaymak. Fuzzy Decision Making in Modeling and Control. World Scientific Series in Robotics & Intelligent Systems. World Scientific Pub. Co., Singapore, December 2002.


[c] F. Cismondi, L.A. Celi, A.S. Fialho, S.M. Vieira, S.R. Reti, J.M.C. Sousa and S. N. Finkelstein. Reducing unnecessary lab testing in the ICU with artificial intelligence. International Journal of Medical Informatics, 82(5):345-358, May 2013.


[d] R Henriques, SC Madeira, BicPAM: Pattern-based biclustering for biomedical data analysis. Algorithms for Molecular Biology 9 (1), 27, 2014.


[e] Nuno Homem and Joao P. Carvalho, Finding top-k elements in data streams, Information Sciences, 180(24), pp. 4958-4974, Dec. 2010, Elsevier.



Contact Person

Susana Vieira