Publications

1999
Cao C, McIntosh N, Kohane IS, Wang K. Artifact detection in the PO2 and PCO2 time series monitoring data from preterm infants. J Clin Monit ComputJ Clin Monit Comput. 1999;15 :369-78.Abstract
BACKGROUND: Artifacts in clinical intensive care monitoring lead to false alarms and complicate later data analysis. Artifacts must be identified and processed to obtain clear information. In this paper, we present a method for detecting artifacts in PCO2 and PO2 physiological monitoring data from preterm infants. PATIENTS AND DATA: Monitored PO2 and PCO2 data (1 value per minute) from 10 preterm infants requiring intensive care were used for these experiments. A domain expert was used to review and confirm the detected artifact. METHODS: Three different classes of artifact detectors (i.e., limit-based detectors, deviation-based detectors, and correlation-based detectors) were designed and used. Each identified artifacts from a different perspective. Integrating the individual detectors, we developed a parametric artifact detector, called ArtiDetect. By an exhaustive search in the space of ArtiDetect instances, we successfully discovered an optimal instance, denoted as ArtiDetector. RESULTS: The sensitivity and specificity of ArtiDetector for PO2 artifacts is 95.0% (SD = 4.5%) and 94.2% (SD = 4.5%), respectively. The sensitivity and specificity of ArtiDetector for PCO2 artifacts is 97.2% (SD = 3.6%) and 94.1% (SD = 4.2%), respectively. Moreover, 97.0% and 98.0% of the artifactual episodes in the PO2 and PCO2 channels respectively are confirmed by ArtiDetector. CONCLUSIONS: Based on the judgement of the expert, our detection method detects most PO2 and PCO2 artifacts and artifactual episodes in the 10 randomly selected preterm infants. The method makes little use of domain knowledge, and can be easily extended to detect artifacts in other monitoring channels.
1998
Mandl KD, Katz SB, Kohane IS. Social equity and access to the World Wide Web and E-mail: implications for design and implementation of medical applications. Proc AMIA SympProc AMIA Symp. 1998 :215-9.Abstract
INTRODUCTION: The distribution and types of Internet connectivity will determine the equity of access by patient populations to emerging health technologies. We sought to measure the rates, types, and predictors of access in a patient population targeted for Web-based medical services. METHODS: Design. Cross sectional in-person interview. Setting. Emergency department of a large urban pediatric teaching hospital. Subjects. Primary caretakers of patients or patients at least 16 years old. Procedure and measures. Subjects were asked about access to e-mail and the Internet as well as about willingness to use and concerns about Web-based services. Views of equity and access and sociodemographic data were also elicited. RESULTS: 132 subjects were enrolled in the study. Of respondents, 67.2% use a computer and 36.4% can access the Internet or e-mail from home. Including Internet connections and/or e-mail accounts at work, school and public libraries, 50.7% of the sample has access. Forty percent of families have e-mail accounts. The rate at which families have connectivity is primarily correlated with income (r = 0.6, p < 0.01). At all income levels, rates of access to the World Wide Web are higher than to e-mail. White patients are much more likely to have e-mail (OR 5.0, 95% CI 2.4-10.8) and Web access (OR 3.6, 95% CI 1.7-7.5). CONCLUSIONS: Connectivity is directly correlated with income and distributed unevenly across racial and ethnic groups. World Wide Web access is more prevalent than e-mail accounts, and both are often obtained outside the home. Design of health applications should account for these attributes of patient access.
1997
Wang K, van Wingerde FJ, Bradshaw K, Szolovits P, Kohane I. A Java-based multi-institutional medical information retrieval system. Proceedings, Annual Fall Symposium of the American Medical Informatics AssociationProceedings, Annual Fall Symposium of the American Medical Informatics Association. 1997 :538-42.Abstract
JAMI (Java-based Agglutination of Medical Information) is designed as a framework for integrating heterogeneous information systems used in healthcare related institutions. It is one of the implementations under the W3-EMRS project 1 aimed at using the World Wide Web (Web) to unify different hospital information systems. JAMI inherited several design decisions from the first W3-EMRS implementation described in, including using the Web as the communication infrastructure and HL7 as the communication protocol between the heterogeneous systems and the W3- EMRS systems. In addition, JAMI incorporates the growing Java technologies and has a more flexible and efficient architecture. This paper describes JAMI's architecture and implementation. It also present two instances of JAMI, one for the integration of different hospital information systems and another for the integration of two heterogeneous systems within a single hospital. Some important issues for the further development of JAMI, including security and confidentiality, data input and decision support are discussed.
1996
Cimino C, Nhan N, Schindler J, Szolovits P, Kohane I. A model for distributed vocabulary translation Cimino JJ. Proceedings, Annual Fall Symposium of the American Medical Informatics AssociationProceedings, Annual Fall Symposium of the American Medical Informatics Association. 1996 :637.
1995
Kohane IS, Greenspun P, Fackler J, Szolovits P. Accessing Pediatric Electronic Medical Record Systems via the World Wide Web. Pediatric ResearchPediatric Research. 1995;37 :139A.
Waisel DB, Fackler JC, Brunner JX, Kohane I. PEFIOS: an expert closed-loop oxygenation algorithm. MEDINFOMedinfo. 1995;8 :1132-6.
Kohane I. Special Issue: Interpreting Clinical Data. 1995.Abstract
Papers based on works presented at the Spring Symposium entitled 'Interpreting Clinical Data', held Spring 1994 in Palo Alto, California.
Kohane I, Greenspun P, Fackler J, Cimino C, Szolovits P. W3-EMRS: Access to Multi-Institutional Electronic Medical Records via with World Wide Web Hripsak G. Spring Congress of the American Medical Informatics Association.Spring Congress of the American Medical Informatics Association. 1995.
1990
McCallie, David P. J, Margulies DM, Kohane IS, Stahlhut R, Bergeron B. The Children's Hospital Workstation Miller RA. Proceedings, Annual Fall Symposium of the American Medical Informatics AssociationProceedings, Annual Fall Symposium of the American Medical Informatics Association. 1990.
1986
Kohane IS. Temporal reasoning in medical expert systems Salomon, R, Blum B, Jørgensen M. MEDINFO 86/Fifth World Congress on Medical InformaticsMEDINFO 86/Fifth World Congress on Medical Informatics. 1986;1 :170-174.

Pages