@article{CliffordPT08, Author = {Clifford, G. D. and Long, W. J. and Moody, G. B. and Szolovits, P.}, Title = {Robust parameter extraction for decision support using multimodal intensive care data}, Journal = {Phil Trans Royal Soc A}, Volume = {}, Number = {}, Pages = {}, Month = {}, Year = {2008}, Note = {Special issue on {Signal Processing in Vital Rhythms and Signs}. In Press}} @article{CliffordBMEO08, Author = {Clifford, G. D. and Blaya, J. A. and Hall-Clifford, R. and Fraser, H. S. F.}, Title = {Medical information systems: {A} foundation for healthcare technologies in developing countries}, Journal = {BMC Biomed Eng Online}, VOLUME = {7}, YEAR = {2008}, NUMBER = {1}, PAGES = {18}, URL = {http://www.biomedical-engineering-online.com/content/7/1/18}, DOI = {10.1186/1475-925X-7-18}, PubMedID = {18547411}, ISSN = {1475-925X}, } @article{LehmanMIDM08, Author = {Neamatullah, I. and Douglass, M. and Lehman, L. H. and Reisner, A. amd Villarroel, M. and Long W. J. and Szolovits, P. amd Moody, G. B. and Mark, R. G. and Clifford, G. D.}, Title = {Automated De-Identification of Free-Text Medical Records}, Journal = {BMC Med Inform Decis Mak}, Volume = {8}, Number = {32}, Pages = {}, Month = {}, Year = {2008}, URL = {http://www.biomedcentral.com/1472-6947/8/32/}, doi = {doi:10.1186/1472-6947-8-32}, Note = {}} @article{Aboukhalil08, Author = {Aboukhalil, A. and Nielsen, L. and Saeed, M. and Mark, R. G. and Clifford, G. D.}, Title = {Reducing false alarm rates for critical arrhythmias using the arterial blood pressure waveform}, Journal = {J Biomed Inform}, Volume = {41}, Number = {3}, Pages = {442--451}, Month = {June}, URL = {http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6WHD-4S3S2HJ-1&_user=501045&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000022659&_version=1&_urlVersion=0&_userid=501045&md5=0c9567e62bc4c7cba5250ee4b728740a}, issn = {1532-0464}, pages = {442--451}, doi = {http://dx.doi.org/10.1016/j.jbi.2008.03.003}, publisher = {Elsevier Science}, address = {San Diego, USA}, Note = {Available online March 21st 2008} } @ARTICLE{ZhangJBI08, title={Patient-specific learning in real time for adaptive monitoring in critical care}, author={Zhang, Y. and Szolovits, P.}, journal={J Biomed Inform}, year={2008}, month = {June}, volume = {41}, number = {3}, year = {2008}, issn = {1532-0464}, pages = {452--460}, doi = {http://dx.doi.org/10.1016/j.jbi.2008.03.011}, publisher = {Elsevier Science}, address = {San Diego, USA}, } @article{JiaCHEST08, author = {Jia, X. and Malhotra, A. and Saeed, M. and Mark, R. G. and Talmor, D.}, title = {Risk Factors for {Acute Respiratory Distress Syndrome} in Patients Mechanically Ventilated for Greater Than 48 Hours.}, journal = {Chest}, volume = {133}, month = {April}, number = {4}, pages = {853-861}, doi = {10.1378/chest.07-1121}, year = {2008}, abstract = {Background: Low tidal volume ventilation for Acute Respiratory Distress Syndrome (ARDS) is a well accepted concept. However, controversy persists regarding the optimal ventilator settings for ventilated patients without ARDS. This study tested the hypothesis that ventilator settings influence the development of new ARDS. MethodsRetrospective analysis of patients from the MIMIC-II database who were mechanically ventilated for [≥] 48 hours between 2001 and 2005. Results: 2583 patients required greater than 48 hrs of ventilation. Of 789 patients who did not have ARDS at admission, 152 (19%) went on to develop ARDS. Univariate analysis revealed high peak inspiratory pressure (PIP) (OR 1.53 per standard deviation, 95% confidence interval 1.28 - 1.84), increasing PEEP (OR 1.35 per SD, 95%CI 1.15 - 1.58) and tidal volume (OR 1.36 per SD, 95%CI 1.12 - 1.64) to be significant risk factors. Major non-ventilator risk factors for ARDS included sepsis, low pH, elevated lactate, low albumin, transfusion of packed red blood cells, transfusion of plasma, high net fluid balance, and low respiratory compliance. Multivariable logistic regression showed that peak pressure (OR 1.31 per SD, 95%CI 1.08 - 1.59), high net fluid balance (OR 1.3 per SD, 95%CI 1.09 - 1.56), transfusion of plasma (OR 1.26 per SD, 95%CI 1.07 - 1.49), sepsis (OR 1.57, 95%CI 1.00 - 2.45) and tidal volume (OR 1.29 per SD, 95%CI 1.02 - 1.52) were significantly associated with the development of ARDS. Conclusions: The associations between the development of ARDS and clinical interventions, including high airway pressures, high tidal volume, positive fluid balance and transfusion of blood products, suggests that ARDS may be a preventable complication in some cases. }, URL = {http://www.chestjournal.org/cgi/content/abstract/chest.07-1121v1}, eprint = {http://www.chestjournal.org/cgi/reprint/chest.07-1121v1.pdf} } @article{LiPM08, Author = {Li, Q. and Mark, R. G. and Clifford, G. D.}, Title = {Robust heart rate estimation from multiple asynchronous noisy sources using signal quality indices and a {K}alman Filter}, Journal = {IOP Physiol Meas}, Volume = {29}, Number = {1}, Pages = {15-32}, Month = {Jan}, Year = {2008}, Note = {}} @Article{HeldtCEP05, author = {Heldt, T. and Chang, J. L. and Chen, J. J. S. and Verghese, G. C. and Mark, R. G.}, title = {Cycle-averaged dynamics of a periodically driven, closed loop circulation model}, journal = {Control Engineering Practice}, year = {2005}, volume = {13}, pages = {1163--1171}, } @Article{HeldtJAP06, author = {Heldt, T.}, title = {Continuous blood pressure-derived cardiac output monitoring -- should we be thinking long term?}, journal = {J Appl Physiol}, year = {2006}, volume = {101}, number = {2}, pages = {373--374}, note = {Invited editorial.}, } @Article{ParlikarTCS06, author = {Parlikar, T.A. and Heldt, T. and Verghese, G.C.}, title = {Cycle-averaged models of cardiovascular dynamics}, journal = {IEEE Trans Circuits Systems {I}}, year = {2006}, volume = {53}, number = {11}, pages = {2459--2468}, OPTnote = {IEEE Trans Circuits Systems {I}: Fundamental Theory and Applications}, } @Article{MukkamalaTBE05, author = {Mukkamala, R. and Reisner, T. A. and Hojman, H. and Mark, R. G. and Cohen, R. J.}, title = {Continuous cardiac output monitoring by peripheral blood pressure waveform analysis}, journal = {IEEE Trans Biomed Eng}, year = {2005}, volume = {53}, number = {3}, pages = {459--467}, } @article{SameniTBE07, Author = {Sameni, R. and Shamsollahi, M. B. and Jutten, C. and Clifford, G. D.}, Title = {A nonlinear {B}ayesian filtering framework for {ECG} denoising}, Journal = {IEEE Trans Biomed Eng}, Volume = {54}, Number = {12}, Pages = {2172-2185}, Month = {December}, Year = {2007}, Note = {}} @article{SameniJASP07, Author = {Sameni, R. and Clifford, G. D. and Shamsollahi, M. B. and Jutten, C.}, Title = {Multi-channel {ECG} and noise modeling: application to maternal and fetal {ECG} signals}, Journal = {EURASIP Journal on Advances in Signal Processing}, Volume = {2007}, Number = {43407}, Pages = {1-14}, Year = {2007}, doi = {10.1155/2007/43407}, } @article{LianBMEOL07, Author = {Lian, J. and Clifford, G. D. and M\"uessig, D. and Lang, V.}, Title = {Open source model for generating {RR} intervals in atrial fibrillation and beyond}, Journal = {BioMedical Engineering OnLine }, Volume = {6}, Number = {9}, Pages = {1-16}, Month = {March}, Year = {2007}, Note = {doi:10.1186/1475-925X-6-9}} @article{CliffordJBS06, Author = {Clifford, G. D.}, Title = {A novel framework for signal representation and source separation}, Journal = {Journal of Biological Systems}, Volume = {14}, Number = {2}, Pages = {169-183}, Month = {June}, Year = {2006}, Note = {}} @Article{CliffordTBE05, author = {Clifford, G. D. and Tarassenko, L.}, title = {Quantifying errors in spectral estimates of {HRV} due to beat replacement and resampling}, journal = {IEEE Trans Biomed Eng}, year = {2005}, OPTkey = {}, volume = {52}, number = {4}, pages = {630--638}, OPTnote = {}, OPTannote = {} } @article{HeNCA06, author = {He, T. and Clifford, G. D. and Tarassenko, L.}, title = {Application of {ICA} in removing artefacts from the {ECG}}, journal = {Neural Comput and Applic}, year = {2006}, OPTkey = {}, volume = {15}, number = {2}, pages = {105-116}, OPTmonth = {}, OPTannote = {} } @Article{CliffordIJB05, author = {Clifford, G. D. and Shoeb, A. and McSharry, P. E. and Janz, B. A.}, title = {Model-based Filtering, Compression and Classification of the {ECG}}, journal = {International Journal of Bioelectromagnetism}, year = {2005}, OPTkey = {}, volume = {7}, number = {1}, pages = {158-161}, OPTnote = {}, OPTannote = {} } @Article{CliffordPM04, author = {Clifford, G. D. and Tarassenko, L.}, title = {Segmenting cardiac-related data using sleep stages increases separation between normal subjects and apnoeic patients}, journal = {IOP Physiol Meas}, year = {2004}, OPTkey = {}, OPTvolume = {}, number = {25}, pages = {N27-N35}, annote = {http://www.iop.org/EJ/abstract/0967-3334/25/6/N03/} } @article{McSharryTBE03, Author = {McSharry, P. E. and Clifford, G. D. and Tarassenko, L.}, Title = {A dynamical model for generating synthetic electrocardiogram signals}, Journal = {IEEE Trans Biomed Eng}, Volume = {50}, Number = {3}, Pages = {289-294}, Month = {}, Year = {2003}, Note = {}} @Article{ZongMBEC04, author = {Zong, W. and Moody, G. B. and Mark, R. G.}, title = {Reduction of false arterial blood pressure alarms using signal quality assessment and relationships between the electrocardiogram and arterial blood pressure}, journal = {Med Biol Eng Comput}, year = {2004}, volume = {42}, pages = {698--706}, } @article{UzunerJAMIA07, author = {Uzuner, \"{O}. and Luo, Y. and Szolovits, P.}, title = {Evaluating the state-of-the-art in automatic de-identification}, journal = {J Am Med Inform Assoc}, volume = {14}, number = {5}, pages = {550--563}, doi = {10.1197/jamia.M2444}, year = {2007}, abstract = {As a part of the i2b2 (Informatics for Integrating Biology to the Bedside) project, authors orga-nized a Natural Language Processing (NLP) challenge on automatically removing private health information (PHI) from medical discharge records. This manuscript provides an overview of this "de-identification challenge", describes the data and the annotation process, explains the evalua-tion metrics, discusses the nature of the systems that addressed the challenge, and analyzes the results of received system runs. The challenge data consisted of discharge summaries drawn from the Partners Healthcare system. Authors prepared this data for the challenge by replacing authentic PHI with synthe-sized surrogates. To focus the challenge on non-dictionary-based de-identification methods, the data was enriched with out-of-vocabulary PHI surrogates, i.e., made up names. The data also included some PHI surrogates that were ambiguous with medical non-PHI terms. A total of seven teams participated in the challenge. Each team submitted up to three system runs, for a total of sixteen submissions. The authors used precision, recall, and F-measure to evaluate the submitted system runs based on their token-level and instance-level performance on the ground truth. The systems with the best performance scored above 98\% in F-measure for all categories of identifiers. Most out-of-vocabulary PHI could be identified accurately. However, identifying ambiguous PHI proved challenging. The performance of systems on the test data set is encouraging. Future evaluations of these systems will involve larger data sets from more heterogeneous sources. }, eprint = {http://www.jamia.org/cgi/reprint/M2444v1.pdf} } @article{UzunerAIM08, author = {Uzuner, \"{O}. and Sibanda, T. C. and Luo, Y. and Szolovits, P.}, title = {A de-identifier for medical discharge summaries}, journal = {Artif. Intell. Med.}, volume = {42}, number = {1}, year = {2008}, issn = {0933-3657}, pages = {13--35}, doi = {http://dx.doi.org/10.1016/j.artmed.2007.10.001}, publisher = {Elsevier Science Publishers Ltd.}, address = {Essex, UK}, } @article{JagerPM04, author={Jager, F. and Moody, G. B. and Mark, R. G.}, title={Protocol to assess robustness of {ST} analysers: a case study}, journal={IOP Phys Meas}, volume={25}, number={3}, pages={629-643}, year={2004}, abstract={This paper proposes principles and methods for assessing the robustness of ST segment analysers and algorithms. We describe an evaluation protocol, procedures and performance measures suitable for assessing the robustness. An ST analyser is robust if its performance is not critically dependent on the variation of the noise content of input signals and on the choice of the database used for testing, and if its analysis parameters are not critically tuned to the database used for testing. The protocol to assess the robustness includes: (1) a noise stress test addressing the aspect of variation of input signals; (2) a bootstrap evaluation of algorithm performance addressing the aspect of distribution of input signals and (3) a sensitivity analysis addressing the aspect of variation of analyser's architecture parameters. An ST analyser is considered to be robust if the performance measurements obtained during these procedures remain above the predefined critical performance boundaries. We illustrate the use of the robustness protocol and robustness measures by a case study in which we assessed the robustness of our Karhunen-Lo\`{e}ve transform based ischaemic ST episode detection and quantification algorithm using the European Society of Cardiology ST-T database.} } @article{WolfbergJMNM08, Author = {Wolfberg, A. J. and DeRosier, D. J. and Roberts, T. and Syed, Z. and Clifford, G. D. and Acker, D. and du Plessis, A. J.}, title = {A comparison of subjective and mathematical estimations of fetal heart rate variability.}, Journal = {Journal of Maternal-Fetal and Neonatal Medicine}, volume={21}, number={2}, pages={101-4}, year={2008}, doi = {**10.1080/14767050701836792}, abstract={Objectives. To develop a computerized algorithm to quantify fetal heart rate (FHR) variability and compare it to perinatologists' interpretation of FHR variability. Methods. FHR variability was calculated using data from 30 women who had a fetal scalp electrode placed for a clinical indication, and compared to the assessment of FHR variability from four perinatologists who interpreted paper tracings of the same data. Inter-rater reliability was calculated and receiver-operator curve analysis was done. Results. Correlation between the computer algorithm's assessment of variability and the perinatologists' assessment (0.27-0.68) was similar to the inter-rater reliability between perinatologists (0.33-0.72). Conclusions. A computer-based algorithm can assess FHR variability as well as expert clinicians.} } @article{Moody08, Author = {Moody, G. B.}, Title = {The {P}hysioNet / {C}omputers in {C}ardiology {C}hallenge 2008: {T}-Wave Alternans}, Journal = {Computers in Cardiology}, Volume = {35}, Number = {}, Pages = {}, Month = {September}, Year = {2008}, Note = {In Press}} @article{Clifford08, Author = {Clifford, G. D. and Sameni, R.}, Title = {An Artificial Multi-Channel Model for Generating Abnormal Electrocardiographic Rhythms}, Journal = {Computers in Cardiology}, Volume = {35}, Number = {}, Pages = {}, Month = {September}, Year = {2008}, Note = {In Press}} @article{Khaustov08, Author = {Khaustov, A. and Nemati, S. and Clifford, G. D.}, Title = {An Open-Source Standard {T}-Wave Alternans Detector for Benchmarking}, Journal = {Computers in Cardiology}, Volume = {35}, Number = {}, Pages = {}, Month = {September}, Year = {2008}, Note = {In Press}} @article{LiICBBE08, Author = {Li, Q. and Clifford, G. D.}, Title = {Suppression of false arrhythmia alarms from {ICU} monitors using heart rate estimation based on combined arterial blood pressure and {ECG} analysis}, Journal = {2nd International Conference on Bioinformatics (ICBBE)}, Volume = {2}, Number = {}, Pages = {2185-2187}, Month = {May}, Year = {2008}, Note = {Shanghai, China}} @article{Wolfberg07, Author = {Wolfberg, A. J. and Syed, Z. and Clifford, G. D. and Tin, A. and Guttag, J. and du Plessis, A. J.}, Title = {Entropy of fetal {EKG} associated with intrapartum fever}, Journal = {New England Conference on Perinatal Research}, Volume = {}, Number = {}, Pages = {}, Month = {October}, Year = {2007}, Note = {}} @ARTICLE{Zhang07a, title={Real-Time Evaluation of Patient Monitoring Algorithms for Critical Care at the Bedside}, author={Zhang, Y. and Silvers, C. T. and Randolph, A. G.}, journal={29th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society}, year={2007}, month = {Aug}, volume={}, number={}, pages={2783-2786}, keywords={artificial intelligence, data acquisition, medical computing, paediatrics, patient care, patient monitoring, time seriesICU, alarm algorithms, artificial intelligence techniques, bedside monitor, clinical event annotations, critical care, data acquisition system, frequency 1 Hz, patient monitoring algorithms, pediatric intensive care unit, physiological time-series, real-time evaluation, time 196 hour}, doi={10.1109/IEMBS.2007.4352906}, ISSN={1557-170X}, } @ARTICLE{Zhang07b, title={Real-Time Development of Patient-Specific Alarm Algorithms for Critical Care}, author={Zhang, Y.}, journal={29th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society}, year={2007}, month = {Aug}, volume={}, number={}, pages={4351-4354}, keywords={learning (artificial intelligence), medical computing, neural nets, patient care, patient monitoringclassification trees, clinical alarms, critical care, machine learning technique, neural networks, patient monitoring, patient population models, patient specific alarm algorithms, pediatric intensive care unit}, doi={10.1109/IEMBS.2007.4353300}, ISSN={1557-170X}, } @ARTICLE{Moody06, title={The {PhysioNet/Computers in Cardiology Challenge} 2006: {QT} interval measurement}, author={Moody, G. B. and Koch, H. and Steinhoff, U.}, journal={Computers in Cardiology}, year={2006}, volume={33}, number={}, pages={313-316}, abstract={}, doi={10.1109/CIC.2004.1442881}, ISSN={ }, } @ARTICLE{Moody04, title={Spontaneous termination of atrial fibrillation: a challenge from {PhysioNet and Computers in Cardiology} 2004}, author={Moody, G. B.}, journal={Computers in Cardiology}, year={19-22 Sept. 2004}, volume={31}, number={}, pages={101-104}, abstract={}, doi={10.1109/CIC.2004.1442881}, ISSN={ }, } @ARTICLE{Moody03, title={Distinguishing ischemic from non-ischemic {ST} changes: the {P}hysio{N}et/{Computers in Cardiology Challenge} 2003}, author={Moody, G. B. and Jager, F.}, journal={Computers in Cardiology}, year={2003}, volume={30}, number={}, pages={235-237}, abstract={Accurate diagnosis of myocardial ischemia during activities of daily living, if possible, would provide immediate and substantial benefits to affected subjects, by reducing the time needed to determine and evaluate therapeutic interventions intended to reduce or eliminate transient ischemia. Although ST changes provide a sensitive indicator of ischemia, a variety of non-ischemic mechanisms can also result in ST changes, so that ECG-based diagnosis of ischemia is regarded as non-specific and unreliable. It may be possible, by study of the dynamics of ST changes, to improve the specificity of ECG criteria consistent with ischemia. The fourth annual PhysioNet/Computers in Cardiology Challenge encouraged participants to develop and evaluate methods for distinguishing ischemic and non-ischemic ST changes using a standard, meticulously annotated data set. The training data provided to participants, and the algorithms they developed, are available at http://-www.physionet.org/challenge/2003/.}, keywords={ electrocardiography, medical diagnostic computing, medical information systems ECG-based diagnosis, Physionet/Computers in Cardiology Challenge 2003, ischemic ST changes, myocardial ischemia, nonischemic ST changes}, doi={10.1109/CIC.2003.1291134}, ISSN={0276-6547 }, } @article{Parlikar07, Author = {Parlikar, T. A. and Heldt, T. and Ranade, G. V. and Verghese, G. C.}, Title = {Model-based estimation of cardiac output and total peripheral resistance}, Journal = {Computers in Cardiology}, Volume = {34}, Number = {}, Pages = {379-382}, Year = {2007}, Note = {}} @article{Janz05c, author={Janz, B. A. and Frassica, J. and Baker, C. and Clifford, G. D. and Mark, R. G.}, title = {A new paradigm for managing information in the {ICU} in response to the 80 hour work week}, journal={New England Surgical Society}, volume={86}, pages={118-119}, year={2005}, abstract={} } @article{Heldt06b, Author = {Heldt, T. and Long, W. and Verghese, G. C. and Szolovits, P. and Mark, R. G.}, Title = {Integrating data, models, and reasoning in critical care}, Journal = {Proceedings of the 28th IEEE EMBS International Conference}, Volume = {28}, Number = {}, Pages = {350-353}, Month = {September}, Year = {2006}, Note = {}} @article{Samar05, Author = {Samar, Z. and Heldt, T. and Verghese, G.C. and Mark, R.G.}, Title = {Model-based cardiovascular parameter estimation in the intensive care unit}, Journal = {Computers in Cardiology}, Volume = {32}, Number = {}, Pages = {635-638}, Year = {2005}, Note = {}} @article{Long03, Author = {Long, W. J.}, Title = {Parsing free text nursing notes}, Journal = {AMIA Annu Symp Proc.}, Volume = {}, Number = {}, Pages = {917}, Month = {November 8-12}, Year = {2003}, Note = {}} @article{Saeed06, Author = {Saeed, M. and Mark, R. G.}, Title = {A novel method for the efficient retrieval of similar multiparameter physiologic time series using {W}avelet-based symbolic representations}, Journal = {AMIA Annu Symp Proc}, Volume = {}, Number = {}, Pages = {679-683}, Year = {2006}, abstract={An important challenge in data mining is in identifying "similar" temporal patterns that may illuminate hidden information in a database of time series. We are actively engaged in the development of a temporal database of several thousand ICU patient records that contains time-varying physiologic measurements recorded over each patient's ICU stay. The discovery of multiparameter temporal patterns that are predictive of physiologic instability may aid clinicians in optimizing care for critically-ill patients.In this paper, we introduce a novel temporal similarity metric based on a transformation of time series data into an intuitive symbolic representation. The symbolic transform is based on a wavelet decomposition to characterize time series dynamics at multiple time scales. The symbolic transformation allows us to utilize classical information retrieval algorithms based on a vector-space model. Our algorithm is capable of assessing the similarity between multi-dim! ensional time series and is computationally efficient.We utilized our algorithm to identify similar physiologic patterns in hemodynamic time series from ICU patients. The results of this study demonstrate that similarities between different patient time series may have meaningful physiologic interpretations in the detection of impending hemodynamic deterioration. Thus, our framework may be of potential use in clinical decision-support systems. As a generalized time series similarity metric, the algorithms that are described have applications in several other domains as well.}, Note = {}} @article{Ali04, Author = {Ali, W. and Eshelman, L. and Saeed, M.}, Title = {Identifying artifacts in arterial blood pressure using morphogram variability}, Journal = {Computers in Cardiology}, Volume = {31}, Number = {}, Pages = {697-700}, Month = {September}, Year = {2004}, Note = {}} @article{Abdala04b, Author = {Abdala, O. T. and Saeed, M.}, Title = {Estimation of missing values in clinical laboratory measurements of {ICU} patients using a weighted {K}-nearest neighbors algorithm}, Journal = {Computers in Cardiology}, Volume = {31}, Number = {}, Pages = {693-696}, Year = {2004}, Abstract = {Abstract: In the modern intensive care unit (ICU), the physiologic state of critically-ill patients is monitored through a diverse array of biosensors and laboratory measurements. The sheer volume of data that is collected has overwhelmed clinicians charged with assimilating and transforming the data into clinical hypotheses. The development of automated algorithms with vigilant monitoring and clinical decision-support capabilities would help to alleviate this "information-overload" challenge. The inherent noise and measurement error is an added level of complication to the real-time analysis and interpretation of medical data. One class of "noise" in medical data can be characterized by the absence or unavailability of a desired measurement. We have analyzed a large collection of clinical laboratory data (blood chemistry, blood gasses, complete blood counts) from over 600 ICU/CCU patients in the MIMIC II database. An analysis of the frequency of missing ! data values across patient records for each measurement was completed. Furthermore, we have developed a novel method to estimate the values of missing data by the use of a weighted K-nearest neighbors algorithm. We propose a weighting scheme that exploits the correlation between a "missing" dimension and available data values from other fields. We compare our technique with several popular missing value estimation techniques: principal components analysis, least squares estimation, mean imputation, and classical k-nearest neighbors. The mean standardized imputation error ranges from a minimum of 0.31 to a maximum, of 0.75 depending on the imputed dimension. The mean standardized imputation error over all dimensions is 0.45.}, Note = {}} @article{Parlikar05, Author = {Parlikar, T. A. and Verghese, G. C.}, Title = {A simple cycle-averaged model for cardiovascular dynamics}, Journal = {Proceedings of the 27th Annual IEEE Engineering in Medicine and Biology Society Conference}, Volume = {27}, Number = {}, Pages = {5490-5494}, Month = {}, Year = {2005}, Note = {}} @article{Roberts06, author = {Roberts, J. M. and Parlikar, T. A. and Heldt, T. and Verghese, G. C.}, title = {Bayesian networks for cardiovascular monitoring}, journal = {Proceedings of the 28th IEEE Engineering in Medicine and Biology Conference}, pages = {205--209}, year = {2006}, organization = {IEEE Engineering in Medicine and Biology Conference}, publisher = {IEEE Press}, } @article{Heldt03a, author = {Heldt, T. and Chang, J. L. and Verghese, G. C. and Mark, R. G.}, title = {Cycle-averaged models of cardiovascular dynamics}, journal = {Modelling and Control in Biomedical Systems 2003}, pages = {387--391}, year = {2003}, editor = {Feng, D.D. and Carson, E.R.}, address = {Oxford, UK}, organization = {International Federation of Automatic Control}, publisher = {Pergamon}, } @article{Heldt06a, Author = {Heldt, T. and Chernyak, Y. B.}, Title = {Analytical solution to minimal cardiovascular model}, Journal = {Computers in Cardiology}, Volume = {33}, Number = {}, Pages = {785-788}, Month = {September}, Year = {2006}, Note = {}} @article{Heldt03b, Author = {Heldt, T. and Oefinger, M. B. and Hoshiyama, M. and Mark, R. G.}, Title = {Circulatory response to passive and active changes in posture}, Journal = {Computers in Cardiology}, Volume = {30}, Number = {}, Pages = {263-266}, Month = {September}, Year = {2003}, Note = {}} @Article{Zong03a, author = {Zong, W. and Heldt, T. and Moody, G. B. and Mark, R. G.}, title = {An open-source algorithm to detect onset of arterial blood pressure pulses}, journal = {Computers in Cardiology}, year = {2003}, volume = {30}, pages = {259--262}, } @Article{Zong03b, author = {Zong, W. and Moody, G. B. and Jiang, D.}, title = {A robust open-source algorithm to detect onset and duration of {QRS} complexes}, journal = {Computers in Cardiology}, year = {2003}, volume = {30}, pages = {737--740}, } @Article{Zong06, author = {Zong, W. and Saeed, M. and Heldt, T.}, title = {A {QT} interval detection algorithm based on {ECG} curve length transform}, journal = {Computers in Cardiology}, year = {2006}, volume = {33}, pages = {377--380}, } @Article{Chen03, author = {Chen, J. J. S. and Heldt, T. and Verghese, G. C. and Mark, R. G.}, title = {Analytical solution to simplified circulatory model using piecewise linear elastance}, journal = {Computers in Cardiology}, year = {2003}, volume = {30}, pages = {45--48}, } @Article{Heldt05a, author = {Heldt, T. and Mark, R. G.}, title = {Understanding post-spaceflight orthostatic intolerance: a simulation study}, journal = {Computers in Cardiology}, year = {2005}, volume = {32}, pages = {631--634}, } @Article{Heldt04, author = {Heldt, T. and Mark, R. G.}, title = {Scaling cardiovascular parameters for population simulations}, journal = {Computers in Cardiology}, year = {2004}, volume = {31}, pages = {133--136}, } @article{Long05, Author = {Long, W. J.}, Title = {Extracting diagnoses from discharge summaries}, Journal = {AMIA Annu Symp Proc.}, Volume = {}, Number = {}, Pages = {470-474}, Month = {October 22-26}, Year = {2005}, Note = {}} @article{Long07, Author = {Long, W. J.}, Title = {Lessons extracting diseases from discharge summaries}, Journal = {AMIA Annu Symp Proc.}, Volume = {}, Number = {}, Pages = {478-482}, Month = {November 10-14}, Year = {2007}, Note = {}} @article{Szolovits03, Author = {Szolovits, P.}, Title = {Adding a medical lexicon to an {English} parser}, Journal = {AMIA Annu Symp Proc.}, Volume = {}, Number = {}, Pages = {639-643}, Month = {November 8-12}, Year = {2003}, Note = {}} @article{Villarroel07, Author = {Villarroel, M. and Saeed, A. and Clifford, G. D. and Moody, G. B. and Mark, R. G.}, Title = {Finding relevant cases in large databases of signals, time series, and clinical data}, Journal = {Computers in Cardiology}, Volume = {34}, Number = {}, Pages = {265-268}, Month = {September}, Year = {2007}, Note = {}} @article{Lehman07, Author = {Lehman, L. H. and Kyaw, T. H. and Clifford, G. D. and Mark, R. G.}, Title = {A temporal search engine for a massive multi-parameter clinical information database}, Journal = {Computers in Cardiology}, Volume = {34}, Pages = {637-640}, Month = {September}, Year = {2007}, Note = {}} @article{Hug07, Author = {Hug, C. and Clifford, G. D.}, Title = {An analysis of the errors in recorded heart rate and blood pressure in the {ICU} using a complex set of signal quality metrics}, Journal = {Computers in Cardiology}, Volume = {34}, Number = {}, Pages = {641-645}, Month = {September}, Year = {2007}, Note = {}} @article{Clifford06a, Author = {Clifford, G. D. and Villarroel, M.}, Title = {Model-based determination of {QT} intervals}, Journal = {Computers in Cardiology}, Volume = {33}, Number = {}, Pages = {357-360}, Year = {2006}, Note = {}} @article{Clifford06b, Author = {Clifford, G. D. and Aboukhalil, A. and Zong, W. and Sun, J. X. and Janz, B.A. and Moody, G. B. and Mark, R. G.}, Title = {Using the blood pressure waveform to reduce critical false {ECG} alarms}, Journal = {Computers in Cardiology}, Volume = {33}, Number = {}, Pages = {829-832}, Year = {2006}, Note = {}} @article{Sun06, Author = {Sun, J. X. and Reisner, A. T. and Mark, R. G.}, Title = {A signal abnormality index for arterial blood pressure waveforms}, Journal = {Computers in Cardiology}, Volume = {33}, Number = {}, Pages = {13-16}, Month = {September}, Year = {2006}, Note = {}} @article{Sun05, Author = {Sun, J. X. and Reisner, A. T. and Saeed, M. and Mark, R. G.}, Title = {Estimating cardiac output from arterial blood pressure waveforms: a critical evaluation using the {MIMIC II} database}, Journal = {Computers in Cardiology}, Volume = {32}, Number = {}, Pages = {295-298}, Month = {September}, Year = {2005}, Note = {}} @article{Clifford05a, Author = {Clifford, G. D. and McSharry, P. E.}, Title = {Method to filter {ECG}s and evaluate clinical parameter distortion using realistic {ECG} model parameter fitting}, Journal = {Computers in Cardiology}, Volume = {32}, Number = {}, Pages = {715--718}, Month = {}, Year = {2005}, Note = {}} @article{Clifford05b, Author = {Clifford, G. D. and Zapanta, L. and Janz, B. A. and Mietus, J. and Mark, R. G.}, Title = {Segmentation of 24-hour cardiovascular activity using {ECG}-based sleep/sedation and noise metrics}, Journal = {Computers in Cardiology}, Volume = {32}, Number = {}, Pages = {595--598}, Month = {}, Year = {2005}, Note = {}} @article{Janz05a, title = {Development and optimization of a critical care alert and display ({CCAD}) system using retrospective {ICU} databases.}, author={Janz, B. A. and Saeed, M. and Frassica, J. and Clifford, G. D. and Mark, R. G.}, journal={AMIA Annu Symp Proc}, year={2005}, abstract={Introduction The goal of this research project is to design and optimize a novel critical care alert and display (CCAD) system to assist decision support in the ICU using a massive temporal ICU patient research database [1]. The CCAD system will generate and display abnormal clinical values (Alerts) to the clinician through a user interface designed to allow for the efficient display of data. Background Patients admitted to ICUs are generally physiologically labile and require close monitoring, which results in the accumulation of a large amount of physiologic data. This accumulation of data can lead to an overload of information especially for young physicians caring for these patients. It is essential to have the ability to view and display this information in a concise manner to optimize patient care. Being able to review a large amount of chronological information in a short period of time might help the clinician better evaluate the state of a patient in the ICU. System Design The CCAD system was designed using the MIMIC II database which is a robust fully de-identified temporal ICU research database recorded from patients in the MICU, SICU, and CCU at Beth Israel Deaconess Medical Center, Boston, MA [1]. The software program was written using C-sharp and compiled in the Microsoft Visual Studio .NET(tm) environment. The search engine accesses a set of relational databases and sends abnormal values to a Microsoft ACCESS(tm) database. The graphical user interface imports data from the ACCESS(tm) database and displays the abnormal values to the clinician. The clinician can then select an abnormal value and display the trend using a variety of different graphical tools. Results The search engine and the clinician GUI were both created off-line using the MIMIC II research database [1], which allowed clinicians to assist with the design of the system without altering real-time data or viewing protected health information. Histograms were generated to evaluate the frequency of abnormal values per ICU patient day. 2000 patients were selected from the MIMIC II database. Sixty different common ICU parameters were specified for analysis. For these parameters, there were a total of 56 abnormal values (alerts) generated per patient ICU day. For a 20 bed ICU, that would equate to 1127 total alerts per ICU patient day. When looking specifically at the complete blood count (CBC), 2.9 alerts were generated per ICU patient day.} } @article{McSharry05, Author = {McSharry, P. E. and Clifford, G. D.}, Title = {A Statistical model of the sleep-wake dynamics of the cardiac Rhythm}, Journal = {Computers in Cardiology}, Volume = {32}, Number = {}, Pages = {591-594}, Month = {}, Year = {2005}, Note = {}} @article{Janz05b, Author = {Janz, B. A. and Clifford, G. D. and Mark, R. G.}, Title = {A multivariable analysis of sedation, activity and agitation in critically ill patients using the {R}iker scale, {ECG}, blood pressure and respiratory rate}, Journal = {Computers in Cardiology}, Volume = {32}, Number = {}, Pages = {735--738}, Month = {}, Year = {2005}, Note = {}} @article{Douglass05, Author = {Douglass, M. and Clifford, G. D. and Reisner, A. and Long, W. J. and Moody, G. B. and Mark, R. G.}, Title = {De-identification algorithm for free-text nursing notes }, Journal = {Computers in Cardiology}, Volume = {32}, Number = {}, Pages = {341--344}, Month = {}, Year = {2005}, Note = {}} @article{Clifford04a, Author = {Clifford, G. D. and McSharry, P. E.}, Title = {A realistic coupled nonlinear artificial {ECG}, {BP}, and respiratory signal generator for assessing noise performance of biomedical signal processing algorithms}, Journal = {Proc of SPIE Int Symp on Fluctuations and Noise}, Volume = {5467}, Number = {34}, Pages = {290-301}, Month = {}, Year = {2004}, Note = {}} @article{McSharry04a, Author = {McSharry, P. E. and Clifford, G. D.}, Title = {A comparison of nonlinear noise reduction and independent component analysis using a realistic dynamical model of the electrocardiogram}, Journal = {Proc of SPIE Int Symp on Fluctuations and Noise}, Volume = {5467}, Number = {09}, Pages = {78-88}, Month = {}, Year = {2004}, Note = {}} @article{McSharry04b, Author = {McSharry, P. E. and Clifford, G. D.}, Title = {Open-source software for generating electrocardiogram signals}, Journal = {ARXIV preprints}, Volume = {}, Number = {}, Pages = {0406017}, Year = {2004}, Note = {}} @article{Wang04, Author = {Wang, H. and Azuaje, F. and Clifford, G. D. and Jung, B. and Black, N.}, Title = {Methods and tools for generating and managing ecg{ML}-based information}, Journal = {Computers in Cardiology}, Volume = {31}, Number = {}, Pages = {573-576}, Month = {}, Year = {2004}, Note = {}} @article{Clifford04c, Author = {Clifford, G. D. and McSharry, P. E.}, Title = {A nonlinear artificial model for generating realistic correlated {ECG}, {BP} and respiration}, Journal = {$17^{th}$ international EURASIP conference}, Volume = {}, Number = {}, Pages = {358-360}, Month = {June}, Year = {2004}, Note = {Biosignal2004, Brno, Czech Republic}} @article{Clifford04d, Author = {Clifford, G. D. and McSharry, P. E.}, Title = {Generating 24-hour {ECG}, {BP} and respiratory signals with realistic linear and nonlinear clinical characteristics using a nonlinear model}, Journal = {Computers in Cardiology}, Volume = {31}, Number = {}, Pages = {709-712}, Month = {}, Year = {2004}, Note = {}} @article{Healey04, Author = {Healey, J. and Clifford, G. D. and Kontothanassis, L. and McSharry, P. E.}, Title = {An open-source method for simulating atrial fibrillation using {ECGSYN} }, Journal = {Computers in Cardiology}, Volume = {31}, Number = {}, Pages = {425-427}, Month = {}, Year = {2004}, Note = {}} @article{Nam04, Author = {Nam, D. S. and Youn, C. H. and Lee, B. H. and Clifford, G. D. and Healey, J}, Title = {{QoS}-constrained resource allocation for a {Grid}-based multiple source electrocardiogram application}, Journal = {Lecture Notes in Computer Science}, Volume = {3043}, Number = {}, Pages = {352-359}, Year = {2004}, Note = {Information Systems and Information Technologies (ISIT) Workshop, (Grid Session)}} @article{Youn04a, Author = {Youn, C. H. and Nam, D. S. and Kim, B. and An, E-S and Lee, B. H. and Shim, E. B. and Clifford, G. D.}, Title = {{QoS} quorum-constrained resource management in wireless grid}, Journal = {Lecture Notes in Computer Science}, Volume = {3222}, Number = {}, Pages = {65-72}, Year = {2004}, Note = {Network and Parallel Computing, (NPC 2004), IFIP International Conference, Wuhan, China, October 18-20}} @article{Youn04b, Author = {Youn, C. H. and Kim, B. and Nam, D. S. and Shim, E. B. and Clifford, G. D. and Healey, J}, Title = {Resource reconfiguration scheme based on temporal quorum status estimation in computational grids}, Journal = {Lecture Notes in Computer Science}, Volume = {}, Number = {}, Pages = {699-707}, Month = {}, Year = {2004}, Note = {}} @article{Abdala04a, Author = {Abdala, O. T. and Clifford, G. D. and Saeed, M. and Reisner, A. and Moody, G. B. and Henry, I. and Mark, R. G.}, Title = {The {A}nnotation {S}tation: an open-source technology for annotating large biomedical databases}, Journal = {Computers in Cardiology}, Volume = {31}, Number = {}, Pages = {681-685}, Month = {}, Year = {2004}, Note = {}} @article{Shu04, Author = {Shu, J. and Clifford, G. D. and Saeed, M. and Long, W. J. and Moody, G. B. and Szolovits, P. and Mark, R. G.}, Title = {An open-source, interactive {J}ava-based system for rapid encoding of significant events in the {ICU} using the {Unified Medical Language System}}, Journal = {Computers in Cardiology}, Volume = {31}, Number = {}, Pages = {197-200}, Month = {}, Year = {2004}, Note = {}} @article{Douglass04, Author = {Douglass, M. and Clifford, G. D. and Reisner, A. and Moody, G. B. and Mark, R. G.}, Title = {Computer-assisted de-identification of free text in the {MIMIC II} database}, Journal = {Computers in Cardiology}, Volume = {31}, Number = {}, Pages = {341-344}, Month = {}, Year = {2004}, Note = {}} @article{Sibanda06a, author = {Sibanda, T. and He, T. and Szolovits, P. and and Uzuner, \"O.}, title = {Syntactically-informed semantic category recognizer for discharge summaries}, pages = {714-718}, year = {2006}, address = {Washington, DC}, month = {November}, Journal = {Proceedings of the Fall Symposium of the American Medical Informatics Association (AMIA)}, } @article{Clifford02, Author = {Clifford, G. D. and McSharry, P. E. and Tarassenko, L.}, Title = {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}, Journal = {Computers in Cardiology}, Volume = {29}, Number = {}, Pages = {129-132}, Month = {September}, Year = {2002}, Note = {}} @InProceedings{Tarassenko01, author = {Tarassenko, L. and Townsend, N. and Clifford, G. D. and Mason, L. and Burton, J. and Price, J.}, title = {Medical Signal Processing Using The Software Monitor}, booktitle = {DERA/IEE Workshop Intelligent Sensor Processing}, OPTcrossref = {}, OPTkey = {}, pages = {1-4}, year = {2001}, OPTeditor = {}, OPTvolume = {}, number = {3}, series = {140}, address = {London, U.K.}, OPTmonth = {}, organization = {IEE}, OPTpublisher = {}, OPTnote = {(Ref.No.01/050)}, annote = {pp. p.3/1-4.} } @article{Tarassenko02, Author = {Tarassenko, L. and Townsend, N. and Clifford, G. D. and Burton J. and Price, J. and Cove S. and Braithwaite E.}, Title = {Multi-parameter monitoring for early warning of patient deterioration}, Journal = {IEE Conference on Medical Applications of Signal Processing}, Volume = {}, Number = {}, Pages = {}, Month = {October}, Year = {2002}, Note = {}} @article{Saeed;2002, Author = {Saeed, M. and Lieu, C.and Raber, G. and Mark, R. G.}, Title = {{MIMIC II}: a massive temporal {ICU} patient database to support research in intelligent patient monitoring}, Journal = {Computers in Cardiology}, Volume = {29}, Number = {}, Pages = {641-644}, Month = {September}, Year = {2002}, Abstract = {Abstract: Development and evaluation of intensive care unit (ICU) decision-support systems would be greatly facilitated by the availability of a large-scale ICU patient database. Following our previous efforts with the MIMIC (Multi-parameter Intelligent Monitoring for Intensive Care) Database, we have leveraged advances in networking and storage technologies to develop a far more massive temporal database, MIMIC II. MIMIC II is an ongoing effort: data is continuously and prospectively archived from all ICU patients in our hospital. MIMIC II now consists of over 800 ICU patient records including over 120 gigabytes of data and is growing. A customized archiving system was used to store continuously up to four waveforms and 30 different parameters from ICU patient monitors. An integrated user-friendly relational database was developed for browsing of patients' clinical information (lab results, fluid balance, medications, nurses' progress notes). Based upon its unprecedented size and scope, MIMIC II will prove to be an important resource for intelligent patient monitoring research, and will support efforts in medical data mining and knowledge-discovery.}, Note = {}} @Book{CliffordECGTools06, ALTauthor = {}, editor = {Clifford, G. D. and Azuaje, F. and McSharry, P. E.}, title = {{Advanced Methods and Tools for ECG Analysis}}, publisher = {Artech House}, year = {2006}, OPTkey = {}, volume = {1}, OPTnumber = {}, series = {Engineering in Medicine and Biology}, address = {Norwood, MA, USA}, edition = {1}, month = {October}, note = {ISBN 1-58053-966-1}, OPTannote = {} } @InBook{ReisnerECGTools06Ch1, author = {Resiner, A. T. and Clifford, G. D. and Mark, R. G.}, editor = {Clifford, G. D. and Azuaje, F. and McSharry, P. E.}, title = {{Ch 1: The Physiological Basis of the Electrocardiogram in Advanced Methods and Tools for ECG Analysis}}, publisher = {Artech House}, year = {2006}, OPTkey = {}, volume = {1}, OPTnumber = {}, series = {Engineering in Medicine and Biology}, address = {Norwood, MA, USA}, edition = {1}, month = {October}, pages = {1-25}, note = {ISBN 1-58053-966-1}, OPTannote = {} } @InBook{CliffordECGTools06Ch2, author = {Clifford, G. D. and Oefinger, M. B.}, editor = {Clifford, G. D. and Azuaje, F. and McSharry, P. E.}, title = {{Ch 2: ECG Acquisition, Storage, Transmission, and Representation in Advanced Methods and Tools for ECG Analysis}}, publisher = {Artech House}, year = {2006}, OPTkey = {}, volume = {1}, OPTnumber = {}, series = {Engineering in Medicine and Biology}, address = {Norwood, MA, USA}, edition = {1}, month = {October}, pages = {27-53}, note = {ISBN 1-58053-966-1}, OPTannote = {} } @InBook{CliffordECGTools06Ch3, author = {Clifford, G. D.}, editor = {Clifford, G. D. and Azuaje, F. and McSharry, P. E.}, title = {{Ch 3: ECG Statistics, Noise, Artifacts, and Missing Data in Advanced Methods and Tools for ECG Analysis}}, publisher = {Artech House}, year = {2006}, OPTkey = {}, volume = {1}, OPTnumber = {}, series = {Engineering in Medicine and Biology}, address = {Norwood, MA, USA}, edition = {1}, month = {October}, pages = {55-99}, note = {ISBN 1-58053-966-1}, OPTannote = {} } @InBook{McSharryECGTools06Ch4, author = {McSharry, P. E. and Clifford, G. D.}, editor = {Clifford, G. D. and Azuaje, F. and McSharry, P. E.}, title = {{Ch 4: Models for ECG and RR interval Processes in Advanced Methods and Tools for ECG Analysis}}, publisher = {Artech House}, year = {2006}, OPTkey = {}, volume = {1}, OPTnumber = {}, series = {Engineering in Medicine and Biology}, address = {Norwood, MA, USA}, edition = {1}, month = {October}, pages = {101-133}, note = {ISBN 1-58053-966-1}, OPTannote = {} } @InBook{CliffordECGTools06Ch5, author = {Clifford, G. D.}, editor = {Clifford, G. D. and Azuaje, F. and McSharry, P. E.}, title = {{Ch 5: Linear Filtering MethodsAdvanced Methods and Tools for ECG Analysis}}, publisher = {Artech House}, year = {2006}, OPTkey = {}, volume = {1}, OPTnumber = {}, series = {Engineering in Medicine and Biology}, address = {Norwood, MA, USA}, edition = {1}, month = {October}, pages = {135-170}, note = {ISBN 1-58053-966-1}, OPTannote = {} } @InBook{McSharryECGTools06Ch6, author = {McSharry, P. E. and Clifford, G. D.}, editor = {Clifford, G. D. and Azuaje, F. and McSharry, P. E.}, title = {{Ch 6: Nonlinear Filtering Methods in Advanced Methods and Tools for ECG Analysis}}, publisher = {Artech House}, year = {2006}, OPTkey = {}, volume = {1}, OPTnumber = {}, series = {Engineering in Medicine and Biology}, address = {Norwood, MA, USA}, edition = {1}, month = {October}, pages = {171-196}, note = {ISBN 1-58053-966-1}, OPTannote = {} } @article{AG-00, author = "Goldberger, A. L. and Amaral, L. A. N. and Glass, L. and Hausdorff, J. M. and Ivanov, P. Ch. and Mark, R. G. and Mietus, J. E. and Moody, G. B. and Peng, C.-K. and Stanley, H. E.", title = "{PhysioBank, PhysioToolkit, and PhysioNet}: Components of a New Research Resource for Complex Physiologic Signals", journal = "Circulation", year = 2000, volume = 101, pages = "e215", note = "[http://circ.ahajournals.org/cgi/content/full/101/23/e215]"}