Robust parameter extraction for decision support using multimodal intensive care data

Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences

Volumn 367, Issue 1887, 2009, Pages 411-429

  Clifford, G D ^a   Long, W J ^b   Moody, G B ^a   Szolovits, P ^b  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^b MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Clinical errors; Data fusion; Decision support; Intensive care unit; Noise; Signal quality

Indexed keywords

BIOINFORMATICS; DATA FUSION; DECISION SUPPORT SYSTEMS; ERRORS; INFORMATION FUSION; PARAMETER EXTRACTION; PHYSIOLOGICAL MODELS;

CLASSIFICATION ACCURACY; CLINICAL DECISION SUPPORT; CLINICAL ERRORS; CLINICAL STAFF; COMPUTATIONAL BIOLOGY; DATA ANALYSIS; DECISION SUPPORT; DECISION SUPPORTS; DIGITAL INFORMATION; ERROR PRONE; EXISTING CONDITIONS; EXOGENOUS PERTURBATION; HIGH-DIMENSIONAL; INTENSIVE CARE; KEY PROBLEMS; MEDICAL TREATMENT; MULTI-MODAL; NEW OPPORTUNITIES; NOISE; NONSTATIONARY; PHYSIOLOGICAL PARAMETERS; PRIOR PROBABILITY; SIGNAL QUALITY;

INTENSIVE CARE UNITS;

ALGORITHM; ARTICLE; ARTIFACT; COMPUTER NETWORK; DECISION SUPPORT SYSTEM; HEALTH SERVICE; HUMAN; INTENSIVE CARE; INTENSIVE CARE UNIT; METHODOLOGY; MONITORING; REPRODUCIBILITY; SIGNAL PROCESSING; STATISTICAL ANALYSIS; STATISTICAL MODEL;

ALGORITHMS; ARTIFACTS; COMPUTER COMMUNICATION NETWORKS; DATA INTERPRETATION, STATISTICAL; DECISION SUPPORT TECHNIQUES; HEALTH SERVICES NEEDS AND DEMAND; HUMANS; INTENSIVE CARE; INTENSIVE CARE UNITS; MODELS, STATISTICAL; MONITORING, PHYSIOLOGIC; REPRODUCIBILITY OF RESULTS; SIGNAL PROCESSING, COMPUTER-ASSISTED;

EID: 65849090400     PISSN: 1364503X     EISSN: None     Source Type: Journal    
DOI: 10.1098/rsta.2008.0157     Document Type: Article

References (73)

1. Abdala, O. T. and Saeed, M. 2004 Estimation of missing values in clinical laboratory measurements of ICU patients using a weighted K-nearest neighbors algorithm. Comput. Cardiol. 31, 693-696. (doi:10.1109/CIC.2004. 1443033)
2. Aboukhalil, A., Nielsen, L., Saeed, M., Mark, R. G. and Clifford, G. D. 2008 Reducing false alarm rates for critical arrhythmias using the arterial blood pressure waveform. J. Biomed. Inform. 41, 442-451. (doi:10.1016/j.jbi.2008.03.003)
3. Addison, P. S. 2005 Wavelet transforms and the ECG: a review. IOP Phys. Meas. 26, R155-R199. (doi:10.1088/0967-3334/26/5/R01)
4. Alsafadi, Y., Sheng, O. R. L. and Martinez, R. 1994 Comparison of communication protocols in medical information exchange standards. In IEEE Seventh Symp. on Computer-Based Medical Systems, pp. 258-263. (doi:10.1109/CBMS.1994.316022)
5. Baker, C. F. 1992 Discomfort to environmental noise: heart rate responses of SICU patients. Crit. Care Nurs. Q. 15, 75-90.
6. Bellomo, R., Ronco, C., Kellum, J. A., Mehta, R. L., Palevsky, P. and The ADQI Workgroup 2004 Acute renal failure-definition, outcome measures, animal models, fluid therapy and information technology needs. In Second Int. Consensus Conf. of the Acute Dialysis Quality Initiative (ADQI) Group. Crit. Care 8, R204-R212. See related letter by Lopes et al. http://ccforum.com/content/11/1/401.
7. Cassidy, M. J. and Penny, W. D. 2002 Bayesian nonstationary autoregressive models for biomedical signal analysis. Biomed. Eng. IEEE Trans. 49, 1142-1152. (doi:10.1109/TBME.2002.803511)
8. Chambrin, M.-C. 2001 Review: alarms in the intensive care unit: how can the number of false alarms be reduced? Crit. Care 5, 184-188. (doi:10.1186/cc1021)
9. Chen, Y., Perl, Y., Geller, J. and Cimino, J. J. 2007 Analysis of a study of the users, uses, and future agenda of the UMLS. J. Am. Med. Inform. Assoc. 14, 221-231. (doi:10.1197/jamia. M2202)
10. Chin, T. 2001 On Kalman filter solution of space-time interpolation. Image Process. IEEE Trans. 10, 663-666. (doi:10.1109/83.913601)
11. Clifford, G. D. 2006 A novel framework for signal representation and source separation. J. Biol. Syst. 14, 169-183. (doi:10.1142/S0218339006001830)
12. Clifford, G. D. and McSharry, P. E. 2004 Generating 24-hour ECG, BP and respiratory signals with realistic linear and nonlinear clinical characteristics using a nonlinear model. Comput. Cardiol. 31, 709-712. (doi:10.1109/CIC.2004.1443037)
13. Clifford, G. D. and Oefinger, M. B. 2006 ECG acquisition, storage, transmission, and representation. Advanced methods and tools for ECG analysis. Engineering in medicine and biology, pp. 27-53, vol. 1, 1st edn. Norwood, MA: Artech House.
14. Clifford, G. D., McSharry, P. E. and Tarassenko, L. 2002 Characterizing abnormal beats in the normal human 24-hour RR tachogram to aid identification and artificial replication of circadian variations in human beat to beat heart rate. Comput. Cardiol. 29, 129-132.
15. Clifford, G. D., Shoeb, A., McSharry, P. E. and Janz, B. A. 2005 Model-based filtering, compression and classification of the ECG. Int. J. Bioelectromag. 7, 158-161.
16. Clifford, G. D., Aboukhalil, A. and Mark, R. G. 2006 Using the blood pressure waveform to reduce critical false ECG alarms. Comput. Cardiol. 33, 829-832.
17. Clifford, G. D., Blaya, J. A., Hall-Clifford, R. and Fraser, H. S. F. 2008 Medical information systems: a foundation for healthcare technologies in developing countries. Biomed. Eng. Online 7, 18. (doi:10.1186/1475-925X-7-18)
18. Dean, B. S., Allan, E. L., Barber, N. D. and Barker, K. N. 1995 Comparison of medication errors in an American and a British hospital. Am. J. Health Syst. Pharm. 52, 2543-2549.
19. Donchin, Y. and Jacob, S. 2002 The hostile environment of the intensive care unit. Curr. Opin. Crit. Care 8, 316-320. (doi:10.1097/ 00075198-200208000-00008)
20. Douglass, M., Clifford, G. D., Reisner, A., Moody, G. B. and Mark, R. G. 2004 Computer-assisted de-identification of free text in the MIMIC II database. Comput. Cardiol. 31, 341-344. (doi:10. 1109/CIC.2004.1442942)
21. Fessler, J. A. and Sutton, B. P. 2003 Nonuniform fast Fourier transforms using min-max interpolation. Signal Process. IEEE Trans. 51, 560-574. (doi:10.1109/TSP.2002.807005)
22. Goldberger, A. L. et al. 2000 PHYSIO BANK, PHYSIO TOOLKIT, and PHYSIO NET: components of a new research resource for complex physiologic signals. Circulation 101, e215. (doi:10.1109/TSP. 2002.807005)
23. Gu, H., Perl, Y., Geller, J., Halper, M., Liu, L.-M. and Cimino, J. J. 2000 Representing the UMLS as an object-oriented database: modeling issues and advantages. J. Am. Med. Inform. Assoc. 7, 66-80.
24. Hagerman, I., Rasmanis, G., Blomkvist, V., Ulrich, R., Eriksen, C. A. and Theorell, T. 2005 Influence of intensive coronary care acoustics on the quality of care and physiological state of patients. Int. J. Cardiol. 98, 267-270. (doi:10.1016/j.ijcard.2003.11.006)
25. He, T., Clifford, G. D. and Tarassenko, L. 2006 Application of ICA in removing artefacts from the ECG. Neural Comput. Appl. 15, 105-116. (doi:10.1007/s00521-005-0013-y)
26. Hug, C. and Clifford, G. D. 2007 An analysis of the errors in recorded heart rate and blood pressure in the ICU using a complex set of signal quality metrics. Comput. Cardiol. 34, 641-645.
27. Husoy, J., Eilevstjonn, J., Eftestol, T., Aase, S. O., Myklebust, H. and Steen, P. A. 2002 Removal of cardiopulmonary resuscitation artifacts from human ECG using an efficient matching pursuitlike algorithm. Biomed. Eng. IEEE Trans. 49, 1287-1298. (doi:10.1109/TBME.2002.804591)
28. Imhoff, M. and Kuhls, S. 2006 Alarm algorithms in critical care monitoring. Anesth. Analg. 102, 1525-1537. (doi:10.1213/01.ane. 0000204385.01983.61)
29. Jager, F., Moody, G. B. and Mark, R. G. 2004 Protocol to assess robustness of ST analysers: a case study. IOP Phys. Meas. 25, 629-643. (doi:10.1088/0967-3334/25/3/004)
30. Laguna, P., Moody, G. B. and Mark, R. G. 1998 Power spectral density of unevenly sampled data by least-square analysis: performance and application to heart rate signals. IEEE Trans. Biomed. Eng. 45, 698-715. (doi:10.1109/10.678605)
31. LCP, T. 2008 Physiobank: the MIMIC II database. See www.physionet.org/ physiobank/database/mimic2db.
32. Li, Q., Mark, R. G. and Clifford, G. D. 2008 Robust heart rate estimation from multiple asynchronous noisy sources using signal quality indices and a Kalman filter. IOP Physiol. Meas. 29, 15-32. (doi:10.1088/0967- 3334/29/1/002)
33. Lisby, M., Nielsen, L. P. and Mainz, J. 2005 Errors in the medication process: frequency, type, and potential clinical consequences. Int. J. Qual. Health Care 17, 15-22. (doi:10.1093/intqhc/mzi015)
34. Lomb, N. 1976 Least-squares frequency analysis of unequally spaced data. Astrophys. Space Sci. 39, 447-462. (doi:10.1007/BF00648343)
35. Long, W. J. 2001 Medical informatics: reasoning methods. Art. Intel. Med. 23, 71-87. (doi:10.1016/S0933-3657(01)00076-8)
36. Long, W. J. 2007 Lessons extracting diseases from discharge summaries. In AMIA Annu. Symp. Proc., pp. 478-482.
37. Mäkivirta, A., Koski, E., Kari, A. and Sukuvaara, T. 1991 The median filter as a preprocessor for a patient monitor limit alarm system in intensive care. Comput. Methods Programs Biomed. 34, 139-144. (doi:10.1016/0169-2607(91)90039-V)
38. Martinez, M., Soria, E., Calpe, J., Guerrero, J. and Magdalena, J. R. 1997 Application of the adaptive impulse correlated filter for recovering fetal electrocardiogram. Comput. Cardiol. 24, 9-12. (doi:10.1109/CIC. 1997.647814)
39. McSharry, P. E. and Clifford, G. D. 2004 A comparison of nonlinear noise reduction and independent component analysis using a realistic dynamical model of the electrocardiogram. Proc. SPIE Int. Symp. on Fluctuations Noise 5467, 78-88. (doi:10.1117/12.548726)
40. Meyer, T., Eveloff, S. E., Bauer, M. S., Schwartz, W. A., Hill, N. S. and Millman, R. P. 1994 Adverse environmental conditions in the respiratory and medical ICU settings. Chest 105, 1211-1216. (doi:10.1378/chest. 105.4.1211)
41. Moody, G. B. 1993 Spectral analysis of heart rate without resampling. Comput. Cardiol. 20, 715-718. (doi:10.1109/CIC.1993.378302)
42. Moody, G. B. and Jager, F. 2003 Distinguishing ischemic from non-ischemic ST changes: the PHYSIONET/Computers in Cardiology Challenge 2003. Comput. Cardiol. 30, 235-237. (doi:10. 1109/CIC.2003.1291134)
43. Moody, G. B. and Mark, R. G. 1989 QRS morphology representation and noise estimation using the Karhunen-Loève transform. Comput. Cardiol. 16, 269-272.
44. Nairac, A., Corbett-Clark, T., Ripley, R., Townsend, N. and Tarassenko, L. 1997 Choosing an appropriate model for novelty detection. In Artificial Neural Networks, Fifth Int. Conference (Conf. Publ. no. 440), pp. 117-122.
45. Neamatullah, I. et al. 2008 Automated de-identification of free-text medical records. BMC Med. Inform. Decis. Mak. 8, 32. (doi:10.1186/1472-6947-8-32)
46. Nelson, N. C., Evans, R. S., Samore, M. H. and Gardner, R. M. 2005 Detection and prevention of medication errors using real-time bedside nurse charting. J. Am. Med. Inform. Assoc. 12, 390-397. (doi:10.1197/jamia. M1692)
47. Novaes, M. A., Aronovich, A., Ferraz, M. B. and Knobel, E. 1997 Stressors in ICU: patients' evaluation. Intensive Care Med. 23, 1282-1285. (doi:10.1007/s001340050500)
48. Okin, P. M., Devereux, R. B., Fabsitz, R. R., Lee, E. T., Galloway, J. M. and Howard, B. V. 2002 Principal component analysis of the T wave and prediction of cardiovascular mortality in American Indians: the strong heart study. Circulation 105, 714-719. (doi:10.1161/hc0602. 103585)
49. Parlikar, T., Heldt, T. and Verghese, G. C. 2006 Cycle-averaged models of cardiovascular dynamics. IEEE Trans. Circuits Syst. I 53, 2459-2468. (doi:10.1109/TCSI.2006.884457)
50. Parlikar, T. A., Heldt, T., Ranade, G. V. and Verghese, G. C. 2007 Model-based estimation of cardiac output and total peripheral resistance. Comput. Cardiol. 34, 379-382.
51. Parthasarathy, S. and Tobin, M. J. 2004 Sleep in the intensive care unit. Intensive Care Med. 30, 197-206. (doi:10.1007/s00134-003-2030-6)
52. Pueyo, E., Malik, M. and Laguna, P. 2008 A dynamic model to characterize beat-to-beat adaptation of repolarization to heart rate changes. Biomed. Signal Proc. Control 3, 29-43. (doi:10.1016/j.bspc.2007.09.005)
53. Rajan, J. J., Rayner, P. J. W. and Godsill, S. J. 1997 Bayesian approach to parameter estimation and interpolation of time-varying autoregressive processes using the Gibbs sampler. Vision Image Signal Process. IEE Proc. 144, 249-256. (doi:10.1049/ip-vis:19971305)
54. Roberts, J. M., Parlikar, T. A., Heldt, T. and Verghese, G. C. 2006 Bayesian networks for cardiovascular monitoring. In Proc. 28th IEEE Engineering in Medicine and Biology Conference, pp. 205-209.
55. Saeed, M., Lieu, C., Raber, G. and Mark, R. 2002 MIMIC II: a massive temporal ICU patient database to support research in intelligent patient monitoring. Comput. Cardiol. 29, 641-644.
56. Sameni, R., Shamsollahi, M. B., Jutten, C. and Clifford, G. D. 2007 A nonlinear Bayesian filtering framework for ECG denoising. IEEE Trans. Biomed. Eng. 54, 2172-2185. (doi:10.1109/TBME. 2007.897817)
57. Scargle, J. 1982 Studies in astronomical time series analysis. II. Statistical aspects of spectral analysis of unevenly spaced data. Astrophys. J. 263, 835-853. (doi:10.1086/160554)
58. Shu, J., Clifford, G. D., Long, W. J., Moody, G. B., Szolovits, P. and Mark, R. G. 2004 An opensource, interactive java-based system for rapid encoding of significant events in the ICU using the unified medical language system. Comput. Cardiol. 31, 197-200. (doi:10.1109/CIC.2004. 1442906)
59. Sun, J. X., Reisner, A. T. and Mark, R. G. 2006 A signal abnormality index for arterial blood pressure waveforms. Comput. Cardiol. 33, 13-16.
60. Takla, G., Petre, J. H., Doyle, D. J., Horibe, M. and Gopakumaran, B. 2006 The problem of artifacts in patient monitor data during surgery: a clinical and methodological review. Anesth. Analg. 103, 1196-1204. (doi:10.1213/01.ane.0000247964.47706.5d)
61. Tarassenko, L., Townsend, N., Clifford, G., Mason, L., Burton J. and Price, J. 2001 Medical signal processing using the software monitor. In DERA/IEE Workshop Intelligent Sensor Processing, no. 3 in 140, pp. 1-4. IEE: London, UK.
62. Tarassenko, L., Mason, L. and Townsend, N. 2002a Multi-sensor fusion for robust computation of breathing rate. Electron. Lett. 38, 1314-1316. (doi:10.1049/el:20020773)
63. Tarassenko, L., Hann, A., Patterson, A., Braithwaite, E., Davidson, K., Barber, V. and Young, D. 2002b Multi-parameter monitoring for early warning of patient deterioration. In IEE Conf. on Medical Applications of Signal Processing, pp. 71-76.
64. Tarassenko, L., Townsend, N. and Price, J. D. 2003 Combining measurements from different sensors. Technical report, United States Patent, application no. 311250. See http://www.freepatentsonline.com/20030187337.html.
65. Tarassenko, L., Hann, A. and Young, D. 2006 Integrated monitoring and analysis for early warning of patient deterioration. Br. J. Anaesth. 97, 64-68. (doi:10.1093/bja/ael113)
66. Tsien, C. and Fackler, J. 1997 Poor prognosis for existing monitors in the intensive care unit. Crit. Care Med. 25, 614-619. (doi:10.1097/00003246-199704000-00010)
67. Vawdrey, D. K., Gardner, R. M., Evans, R. S., Orme, J. F., Clemmer, T. P., Greenway, L. and Drews, F. A. 2007 Assessing data quality in manual entry of ventilator settings. J. Am. Med. Inform. Assoc. 14, 295-303. (doi:10.1197/jamia. M2219)
68. Yarita, M., Kobayashi, N., Takeda, S. and Tamura, T. 2007 Compensation for two specific types of artifact in pulse wave using a Kalman filter. In Information Technology Applications in Biomedicine 2007. ITAB 2007. Sixth Int. Special Topic Conference, pp. 269-272.
69. Zhang, Y. 2007 Real-time development of patient-specific alarm algorithms for critical care. In Twenty-ninth Annual International Conference of the IEEE on Engineering in Medicine and Biology Society, pp. 4351-4354.
70. Zhang, Y. and Szolovits, P. 2008 Patient-specific learning in real time for adaptive monitoring in critical care. J. Biomed. Inform 41, 452-460. (doi:10.1016/j.jbi.2008.03.011)
71. Zhang, L., Halper, M., Perl, Y., Geller, J. and Cimino, J. J. 2005 Relationship structures and semantic type assignments of the UMLS enriched semantic network. J. Am. Med. Inform. Assoc. 12, 657-666. (doi:10.1197/jamia. M1605)
72. Zhang, Y., Silvers, C. T. and Randolph, A. G. 2007 Real-time evaluation of patient monitoring algorithms for critical care at the bedside. In Twenty-ninth Annual International Conference of the IEEE on Engineering in Medicine and Biology Society, pp. 2783-2786.
73. Zong, W., Moody, G. B. and Mark, R. G. 2004 Reduction of false arterial blood pressure alarms using signal quality assessment and relationships between the electrocardiogram and arterial blood pressure. Med. Biol. Eng. Comput. 42, 698-706. (doi:10.1007/BF02347553)