Patient-perceived usefulness of an emergency medical card and a continuity-of-care report in enhancing the quality of care.

OBJECTIVE: To evaluate the patients' opinion on the usefulness of the electronic medical card (EMC) and continuity-of-care report in enhancing quality of care, and to assess the effects of the patient-entered data on the quality of data in the electronic medical record (EMR). DESIGN: A structured survey assessed patients' opinion on the usefulness of the EMC and continuity-of-care report. The accuracy of EMR data involved comparing the patient-entered data in the continuity-of-care report with the healthcare-provider-entered data in the EMR. The analysis assessed whether the EMR information was consistent with the patient-entered data. A data completeness evaluation compared data entries in the EMR collected before and after the use of continuity-of-care record application. RESULTS: One hundred and thirty-three patients used the application, of which 76% who had actually used the EMC and continuity-of-care report to seek medical care and/or update EMR information were surveyed. Age was associated with the reported usefulness of the documents. Few users (16%) printed the continuity-of-care reports to take to their healthcare providers for data updates and fewer (9%) to correct errors in the EMR. Overall, 68% of patients found the documents to be useful. CONCLUSIONS: Patients reported that the EMC and continuity-of-care report were useful in enhancing quality of care. They were able to identify missing or erroneous data in the EMR data, making them an important source of quality control for their information in the healthcare-provider-maintained EMR.

Countering imbalanced datasets to improve adverse drug event predictive models in labor and delivery.

BACKGROUND: The IOM report, Preventing Medication Errors, emphasizes the overall lack of knowledge of the incidence of adverse drug events (ADE). Operating rooms, emergency departments and intensive care units are known to have a higher incidence of ADE. Labor and delivery (L&D) is an emergency care unit that could have an increased risk of ADE, where reported rates remain low and under-reporting is suspected. Risk factor identification with electronic pattern recognition techniques could improve ADE detection rates. OBJECTIVE: The objective of the present study is to apply Synthetic Minority Over Sampling Technique (SMOTE) as an enhanced sampling method in a sparse dataset to generate prediction models to identify ADE in women admitted for labor and delivery based on patient risk factors and comorbidities. RESULTS: By creating synthetic cases with the SMOTE algorithm and using a 10-fold cross-validation technique, we demonstrated improved performance of the Naïve Bayes and the decision tree algorithms. The true positive rate (TPR) of 0.32 in the raw dataset increased to 0.67 in the 800% over-sampled dataset. CONCLUSION: Enhanced performance from classification algorithms can be attained with the use of synthetic minority class oversampling techniques in sparse clinical datasets. Predictive models created in this manner can be used to develop evidence based ADE monitoring systems.

Chronic hemolytic anemia due to cold agglutinins: the mechanism of resistance of red cells to C' hemolysis by cold agglutinins.

The red cells of patients with chronic hemolytic anemia due to cold agglutinins are agglutinated by antiglobulin serum in a nongamma reaction due to the coating of beta-globulins, C'4 and C'3. The red cells of such patients are abnormally resistant to C' hemolysis by cold agglutinin. Normal red cells can be made equally resistant to C' hemolysis by incubation with cold agglutinin and normal serum at temperatures which allow transient reactions between the red cells and cold agglutinins. The development of resistance to C' hemolysis was related to increasing susceptibility to agglutination in anti-beta(1c)- and anti-beta(1e)-sera and by increasing uptake of (131)I activity from labeled anti-beta-globulin serum containing antibodies for both globulins. There was decrease in the adsorption of (131)I-labeled cold agglutinin during the development of resistance to C' hemolysis and reduced susceptibility to agglutination by cold agglutinins. Since cold agglutinins have been demonstrated to dissociate from the red cell, leaving fractions of C' globulin attached, it is postulated that repeated transient reactions produce the accumulation of incomplete C' complexes. Steric hindrance by the adsorbed C' complexes is probably responsible for the inhibition of the reaction with cold agglutinin. There is evidence that the adsorbed C' complexes also interfere with the hemolytic action of C' even when cold agglutinin has become reattached to the red cells. The accumulation of C' complexes by cold agglutinins appears to be the most important factor in the abnormal resistance to C' hemolysis exhibited by the patient's red cells. Other factors, such as the heterogeneity within a population of normal cells, appear to be of minor significance.

Chronic hemolytic anemia due to cold agglutinins. II. The role of C' in red cell destruction.

The sera of four patients with chronic hemolytic anemia due to cold agglutinins deposited C' globulins on normal red cells at 37 degrees C. The circulating cells of the patients were heavily coated with C' complex and were relatively resistant to C' hemolysis by cold agglutinin. Such red cells were removed from the patients' circulation at an exponential rate with (51)Cr t((1/2)) that varied from 7 to 19 days. Normal red cells were removed rapidly by hepatic sequestration during the first hours in the patients' circulation. Thereafter, a slower rate of abnormal destruction occurred which was associated with the accumulation of C' complexes on the red cell and the development of resistance to C' hemolysis by cold agglutinin. Normal red cells coated with sufficient C' complex by action of cold agglutinins in vitro to produce resistance to C' hemolysis by cold agglutinins demonstrated varying degrees of improved survival during the first hours in the circulation of three of the patients. The levels of serum C' were reduced in all four patients with chronic hemolytic anemia due to cold agglutinins. Transfusion of large volumes of normal red cells into two patients further reduced serum C'. (51)Cr-labeled normal red cells survived longer after red cell transfusions than before, because of less rapid destruction during the first hours in the circulation. The reduction in serum C' levels appeared responsible for the improved survival. In subjects without cold agglutinins, the presence of the spleen decreased the survival of red cells from a patient who had previously undergone splenectomy. Splenic removal also predominated in the reduced survival of autologous red cells in one patient. Neither hepatic nor splenic mechanisms predominated in removing autologous C'-coated cells in the other two patients.

An international summer school on health informatics: a collaborative effort of the Amsterdam Medical Informatics Program and IPhiE--the International Partnership for Health Informatics Education.

PURPOSE: Today, the need for health informatics training for health care professionals is acknowledged and educational opportunities for these professionals are increasing. To contribute to these efforts, a new initiative was undertaken by the Medical Informatics Program of the University of Amsterdam-Academic Medical Center and IPHIE (IPhiE)-the International Partnership for Health Informatics Education. In the year 2004, a summer school on health informatics was organized for advanced medical students from all over the world. METHODS: We elaborate on the goals and the program for this summer school. In developing the course, we followed the international guidelines of the International Medical Informatics Association-IMIA. Students provided feedback for the course through both summative and formative evaluations. As a result of these evaluations, we outline the lessons we have learned and what consequences these results have had in revising the course. RESULTS: Overall the results of both the summative and formative evaluation of the summer school showed that we succeeded in the goals we set at the beginning of the course. Students highly appreciated the course content and indicated that the course fulfilled their educational needs. The decision support and image processing computer practicums however proved too high level. We therefore will redesign these practicums to competence requirements of medical doctors as defined by IMIA. All participants recommended the summer school event to other students. CONCLUSIONS: Our experiences demonstrated a true need for health informatics education among medical students and that even a 2 weeks course can fulfill health informatics educational needs of these future physicians. Further establishment of health informatics courses for other health professions is recommended.

Electronic Health Records: Then, Now, and in the Future.

OBJECTIVES: Describe the state of Electronic Health Records (EHRs) in 1992 and their evolution by 2015 and where EHRs are expected to be in 25 years. Further to discuss the expectations for EHRs in 1992 and explore which of them were realized and what events accelerated or disrupted/derailed how EHRs evolved. METHODS: Literature search based on "Electronic Health Record", "Medical Record", and "Medical Chart" using Medline, Google, Wikipedia Medical, and Cochrane Libraries resulted in an initial review of 2,356 abstracts and other information in papers and books. Additional papers and books were identified through the review of references cited in the initial review. RESULTS: By 1992, hardware had become more affordable, powerful, and compact and the use of personal computers, local area networks, and the Internet provided faster and easier access to medical information. EHRs were initially developed and used at academic medical facilities but since most have been replaced by large vendor EHRs. While EHR use has increased and clinicians are being prepared to practice in an EHR-mediated world, technical issues have been overshadowed by procedural, professional, social, political, and especially ethical issues as well as the need for compliance with standards and information security. There have been enormous advancements that have taken place, but many of the early expectations for EHRs have not been realized and current EHRs still do not meet the needs of today's rapidly changing healthcare environment. CONCLUSION: The current use of EHRs initiated by new technology would have been hard to foresee. Current and new EHR technology will help to provide international standards for interoperable applications that use health, social, economic, behavioral, and environmental data to communicate, interpret, and act intelligently upon complex healthcare information to foster precision medicine and a learning health system.

Improving empiric antibiotic selection using computer decision support.

BACKGROUND: Physicians frequently need to start antibiotic therapy before the results of bacterial cultures and antibiotic susceptibility tests are available. We developed and evaluated a computerized antibiotic consultant to assist physicians in the selection of appropriate empiric antibiotics. METHODS: We used a two-stage random-selection study to compare antibiotics suggested by the antibiotic consultant with 482 associated antibiotic susceptibility results and the concurrent antibiotics ordered by physicians. The antibiotics ordered by randomized physicians were then compared between crossover periods of antibiotic consultant use. RESULTS: The antibiotic consultant suggested an antibiotic regimen to which all isolated pathogens were shown to be susceptible for 453 (94%) of 482 culture results, while physicians ordered an antibiotic regimen to which all isolated pathogens were susceptible for 369 culture results (77%) (P < .001). The physicians who prescribed antibiotics to which all pathogens were susceptible did so a mean of 21 hours after the culture specimens were collected. Physicians ordered appropriate antibiotics within 12 hours of the culture collection significantly more often when they had use of the antibiotic consultant than during the period before use (P < .035). Moreover, 88% of the physicians stated they would recommend the program to other physicians, 85% said the program improved their antibiotic selection, and 81% said they felt use of the program improved patient care. CONCLUSIONS: Information from computer-based medical records can be used to help improve physicians' selection of empiric antibiotics for infections.

Use of computer decision support in an antimicrobial stewardship program (ASP).

OBJECTIVE: Document information needs, gaps within the current electronic applications and reports, and workflow interruptions requiring manual information searches that decreased the ability of our antimicrobial stewardship program (ASP) at Intermountain Healthcare (IH) to prospectively audit and provide feedback to clinicians to improve antimicrobial use. METHODS: A framework was used to provide access to patient information contained in the electronic medical record, the enterprise-wide data warehouse, the data-driven alert file and the enterprise-wide encounter file to generate alerts and reports via pagers, emails and through the Centers for Diseases and Control's National Healthcare Surveillance Network. RESULTS: Four new applications were developed and used by ASPs at Intermountain Medical Center (IMC) and Primary Children's Hospital (PCH) based on the design and input from the pharmacists and infectious diseases physicians and the new Center for Diseases Control and Prevention/National Healthcare Safety Network (NHSN) antibiotic utilization specifications. Data from IMC and PCH now show a general decrease in the use of drugs initially targeted by the ASP at both facilities. CONCLUSIONS: To be effective, ASPs need an enormous amount of "timely" information. Members of the ASP at IH report these new applications help them improve antibiotic use by allowing efficient, timely review and effective prioritization of patients receiving antimicrobials in order to optimize patient care.

Serious Pseudomonas infections associated with endoscopic retrograde cholangiopancreatography.

After observing a single case of Pseudomonas aeruginosa bacteremia following endoscopic retrograde cholangiopancreatography (ERCP), six other P. aeruginosa infections that were temporally related to ERCP were retrospectively found over one year (August 1985 through July 1986) at LDS Hospital. In all seven patients, infection developed within five days after an ERCP. Five patients had bacteremia and two had cholangitis. All five of the Pseudomonas isolates available for testing were serotype 010. Cultures from the ERCP endoscope and several other endoscopes also yielded P. aeruginosa serotype 10, as did environmental cultures from equipment used to clean endoscopes. Among 167 ERCPs performed during the outbreak period, no other patient acquired P. aeruginosa infection. Each of the patients in the outbreak received the first scheduled ERCP of the day. The mean duration between the cleaning of the ERCP endoscope and its subsequent use was significantly longer in cases than in matched controls, a factor that may have permitted contaminating organisms to achieve high inocula in the inadequately cleaned endoscope. Epidemic control measures included improved disinfection of endoscopes, ongoing surveillance, and appropriate antimicrobial prophylaxis. This experience suggests that exogenous infection with Pseudomonas is associated with ERCP, that protracted and insidious outbreaks may occur, and that the occurrence of even a single case of Pseudomonas infection after ERCP should stimulate an epidemiologic investigation.

Therapeutic antibiotic monitoring: surveillance using a computerized expert system.

STUDY OBJECTIVE: To develop and evaluate a computerized system to monitor therapeutic antibiotics in a hospital setting. MATERIAL AND METHODS: From November 1986 through October 1987, we prospectively monitored 1,632 hospitalized patients who had 2,157 microbiology specimens sent for culture and sensitivity testing. During the study period, computer algorithms were used to identify patients whose antibiotic therapy was inappropriate in relation to microbiology culture and sensitivity data. When inconsistencies occurred between antibiotic therapy and in vitro sensitivity data, computer algorithms generated therapeutic antibiotic monitor (TAM) alerts. A clinical pharmacist then notified the attending physician of the alert. RESULTS: Antibiotic therapy was identified by the computer as inappropriate in 696 instances (32%). After we eliminated false-positive alerts, 420 evaluable TAM alerts remained. Physicians responded to the TAM alerts by either changing or starting antimicrobial therapy in 125 cases (30%). Moreover, physicians were previously unaware of the relevant susceptibility test results in 49% of the alerts. CONCLUSION: Computer-assisted monitoring is an efficient and promising method to identify and correct errors in antimicrobial prescribing and to assure the appropriate use of therapeutic antibiotics.

Surveillance for quality assessment: IV. Surveillance using a hospital information system.

Hospital surveillance for infection control purposes is a well-accepted method of following nosocomial infections in U.S. hospitals. However, hospital surveillance is being increasingly performed for nosocomial events in noninfectious areas, such as quality assurance and other areas of outcomes research. For the continued development of hospital surveillance in all these areas, dramatic growth in the amount of information collected will occur. To accommodate this growth and to validate new approaches in these areas, large amounts of data collection will be necessary. Collection of these data will be quite difficult without the creation of clinical hospital data bases in which large amounts of information are collected as a routine part of patient care, not as an elaborate addition to patient care. Automated hospital information systems, such as the HELP system, can facilitate the conduct of ongoing hospital surveillance not only in infection control but also in a broad range of areas, such as quality improvement outcomes research and cost-containment areas.

Improved perioperative antibiotic use and reduced surgical wound infections through use of computer decision analysis.

A prospective study was performed over a two-year period to determine whether computer-generated reminders of perioperative antibiotic use could improve prescribing habits and reduce postoperative wound infections. During the first year, baseline patterns of antibiotic use and postoperative infection rates were established. During the second year, computer-generated reminders regarding perioperative antibiotic use were placed in the patient's medical record prior to surgery and patterns of antibiotic use and postoperative wound infections monitored. Hospitalized patients undergoing non-emergency surgery from June to November 1985 (3,263 patients), and from June to November 1986 (3,568) were monitored with respect to indications for perioperative antibiotic use, timing of antibiotic use and postoperative infectious complications. Perioperative antibiotic use was considered advisable for 1,621 (50%) patients in the 1985 sample and for 1,830 (51%) patients in the 1986 sample. Among these patients, antibiotics were given within two hours before the surgical incision in 638 (40%) of the 1985 sample and 1,070 (58%) of the 1986 sample (p less than 0.001). Overall, postoperative wound infections were detected in 28 (1.8%) of 1,621 patients in 1985 compared with 16 (0.9%) of 1,830 such patients in 1986 (p less than 0.03). We conclude that computer-generated reminders of perioperative antibiotic use improved prescribing habits with a concurrent decline in postoperative wound infections.

Computerized identification of patients at high risk for hospital-acquired infection.

Surveillance for hospital-acquired infections is required in U.S. hospitals, and statistical methods have been used to predict the risk of infection. We used the HELP (Health Evaluation through Logical Processing) Hospital Information System at LDS Hospital to develop computerized methods to identify and verify hospital-acquired infections. The criteria for hospital-acquired infection are standardized and based on the guidelines of the Study of the Efficacy of Nosocomial Infection Control and the Centers for Disease Control. The computer algorithms are automatically activated when key items of information, such as microbiology results, are reported. Computer surveillance identified more hospital-acquired infections than did traditional methods and has replaced manual surveillance in our 520-bed hospital. Data on verified hospital-acquired infections are electronically transferred to a microcomputer to facilitate outbreak investigation and the generation of reports on infection rates. Recently, we used the HELP system to employ statistical methods to automatically identify high-risk patients. Patient data from more than 6000 patients were used to develop a high-risk equation. Stepwise logistic regression identified 10 risk factors for nosocomial infection. The HELP system now uses this logistic-regression equation to monitor and determine the risk status for all hospitalized patients each day. The computer notifies infection control practitioners each morning of patients who are newly classified as being at high risk. Of 605 hospital-acquired infections during a 6-month period, 472 (78%) occurred in high-risk patients, and 380 (63%) were predicted before the onset of infection. Computerized regression equations to identify patients at risk of having hospital-acquired infections can help focus prevention efforts.

Clinicians' response to computerized detection of infections.

OBJECTIVE: To analyze whether computer-generated reminders about infections could influence clinicians' practice patterns and consequently improve the detection and management of nosocomial infections. DESIGN: The conclusions produced by an expert system developed to detect and manage infections were presented to the attending clinicians in a pediatric hospital to determine whether this information could improve detection and management. Clinician interventions were compared before and after the implementation of the system. MEASUREMENTS: The responses of the clinicians (staff physicians, physician assistants, and nurse practitioners) to the reminders were determined by review of paper medical charts. Main outcome measures were the number of suggestions to treat and manage infections that were followed before and after the implementation of COMPISS (Computerized Pediatric Infection Surveillance System). The clinicians' opinions about the system were assessed by means of a paper questionnaire distributed following the experiment. RESULTS: The results failed to show a statistical difference between the clinicians' treatment strategies before and after implementation of the system (P: > 0.33 for clinicians working in the emergency room and P: > 0.45 for clinicians working in the pediatric intensive care unit). The questionnaire results showed that the respondents appreciated the information presented by the system. CONCLUSION: The computer-generated reminders about infections were unable to influence the practice patterns of clinicians. The methodologic problems that may have contributed to this negative result are discussed.

Automatic detection of acute bacterial pneumonia from chest X-ray reports.

OBJECTIVE: To evaluate the performance of a natural language processing system in extracting pneumonia-related concepts from chest x-ray reports. DESIGN: Four physicians, three lay persons, a natural language processing system, and two keyword searches (designated AAKS and KS) detected the presence or absence of three pneumonia-related concepts and inferred the presence or absence of acute bacterial pneumonia from 292 chest x-ray reports. Gold standard: Majority vote of three independent physicians. Reliability of the gold standard was measured. OUTCOME MEASURES: Recall, precision, specificity, and agreement (using Finn's R: statistic) with respect to the gold standard. Differences between the physicians and the other subjects were tested using the McNemar test for each pneumonia concept and for the disease inference of acute bacterial pneumonia. RESULTS: Reliability of the reference standard ranged from 0.86 to 0.96. Recall, precision, specificity, and agreement (Finn R:) for the inference on acute bacterial pneumonia were, respectively, 0.94, 0.87, 0.91, and 0.84 for physicians; 0.95, 0.78, 0.85, and 0.75 for natural language processing system; 0.46, 0.89, 0.95, and 0.54 for lay persons; 0.79, 0.63, 0.71, and 0.49 for AAKS; and 0.87, 0.70, 0.77, and 0.62 for KS. The McNemar pairwise comparisons showed differences between one physician and the natural language processing system for the infiltrate concept and between another physician and the natural language processing system for the inference on acute bacterial pneumonia. The comparisons also showed that most physicians were significantly different from the other subjects in all pneumonia concepts and the disease inference. CONCLUSION: In extracting pneumonia related concepts from chest x-ray reports, the performance of the natural language processing system was similar to that of physicians and better than that of lay persons and keyword searches. The encoded pneumonia information has the potential to support several pneumonia-related applications used in our institution. The applications include a decision support system called the antibiotic assistant, a computerized clinical protocol for pneumonia, and a quality assurance application in the radiology department.

The HELP system and its application to infection control.

The HELP system is a comprehensive hospital information system that is linked to an allied financial data base. The clinical data base integrates information from areas such as admitting, pharmacy, radiology, surgery, pathology, nursing, respiratory therapy, and the clinical laboratories, including microbiology. This allows for the creation of an electronic medical record that contains all the clinical and financial data for each patient. The HELP system combines both communication and advice features through the use of data- and time-driven algorithms. We have used the HELP system to automate the surveillance and analysis of hospital-acquired infections and to identify patients at high risk for nosocomial infection. The expert system features have also been used to suggest alternatives for patients receiving inappropriate antimicrobial therapy, to improve the timing of antibiotic prophylaxis in surgery, and to curtail unnecessarily prolonged prophylaxis. Automated hospital information systems such as HELP can facilitate the investigation of a broad range of infection control, quality improvement, and cost-containment issues.

Intensive surveillance of midazolam use in hospitalized patients and the occurrence of cardiorespiratory arrest.

Midazolam, a benzodiazepine used extensively as a sedative and a hypnotic for patients undergoing inpatient and outpatient medical procedures, has been associated with several side effects, the most serious of which are cardiac and respiratory arrest. We studied the use of midazolam and its association with cardiac and respiratory arrest among hospital patients at our institution. From 1988 through 1990 we identified 5439 patients exposed to midazolam, representing 8% of all patients admitted; 3031 (55.7%) received midazolam while not on mechanical ventilation. In the majority of patients the drug was given as a one-time dose, and the total dose was less than or equal to 5 mg in more than 70%. Three patients (0.099%) experienced respiratory arrest. All three events occurred within 2 hours after the last dose of midazolam had been given. All patients were elderly and all survived. The rate of respiratory arrest appears low at our institution and was associated with high doses of midazolam, concurrent use of opiates, and use in elderly patients.

Bringing HELP to the clinical laboratory--use of an expert system to provide automatic interpretation of laboratory data.

In domains where the types of data which are to be interpreted are relatively constrained (as in the case of specific laboratory test results), our modular data-driven approach can be very productive and well received by the clinical recipient of the data. The computer rarely surpasses the knowledge of an experts result from lack of communication, imperfect memory, oversight or multiple decision-makers caring for the same patient. In such cases, most of the alerts are immediately recognized as valid, so the need for elaborate explanations is not a high priority. On the other hand, a non-specialist is alerted to the need for additional investigation, tests or collaborative support, by the fact that a reminder or diagnosis that s/he had not previously considered, appears. In other words, for the expert, a data-driven system provides unceasing oversight in high-volume low-yielded situations where a small number of mistakes may uncommonly occur for reasons which are not related to the lack of knowledge of the provider. For the non-specialist the system suggests that the patient may have problems in a domain for which the physician needs additional support. In the present state of the art, we do not think that total reliance on the computer-contained knowledge is the ultimate source of this additional support; providing the awareness of the need may be the most important contribution. Once you know that you need help, it is usually obtainable. In a discussion about how computer systems have failed, Friedman and Gustafson made the following observation.(ABSTRACT TRUNCATED AT 250 WORDS)

Building a comprehensive clinical information system from components. The approach at Intermountain Health Care.

OBJECTIVES: To discuss the advantages and disadvantages of an interfaced approach to clinical information systems architecture. METHODS: After many years of internally building almost all components of a hospital clinical information system (HELP) at Intermountain Health Care, we changed our architectural approach as we chose to encompass ambulatory as well as acute care. We now seek to interface applications from a variety of sources (including some that we build ourselves) to a clinical data repository that contains a longitudinal electronic patient record. RESULTS: We have a total of 820 instances of interfaces to 51 different applications. We process nearly 2 million transactions per day via our interface engine and feel that the reliability of the approach is acceptable. Interface costs constitute about four percent of our total information systems budget. The clinical database currently contains records for 1.45 m patients and the response time for a query is 0.19 sec. DISCUSSION: Based upon our experience with both integrated (monolithic) and interfaced approaches, we conclude that for those with the expertise and resources to do so, the interfaced approach offers an attractive alternative to systems provided by a single vendor. We expect the advantages of this approach to increase as the costs of interfaces are reduced in the future as standards for vocabulary and messaging become increasingly mature and functional.

Applications of medical informatics in antibiotic therapy.

The Infectious Disease Society of America is concerned about the excessive and inappropriate use of antibiotics in U.S. hospitals. Applications of Medical Informatics can help improve the use of antibiotics and help improve patient care by monitoring and managing enormous amounts of patient information. Monitoring the duration of every antibiotic ordered in the hospital or keeping tract of the antibiotic susceptibilities for five years are examples of tasks better performed by computers. The impact of computers in medicine is seen by some as disappointing. The computer revolution has not had the impact in medicine experienced by other areas. The acceptance and use of computers by medicine will be evolutionary rather than revolutionary. In 1979, the MYCIN project demonstrated that the computer could aid physicians in the selection of antibiotics. However, MYCIN was never clinically used because physicians were require to enter all patient information into the computer. The development of computerized medical records is an essential step to further the development and implementation of computer-aided decision support. The science of Medical Informatics is still relatively new but is emerging as a distinct academic field. A few hospitals are now installing information systems and have determined that these systems will play an essential role in their ability to survive into the next century. The telephone and the automobile have been recognized as two of the most important tools for improving medical care during the past 100 years. People could more readily get medical care and the time to transmit medical information was greatly reduced through physician use of the telephone and automobile. The computer is a tool that can be used to help physicians manage the great amount of medical information being generated every day. The computer can also alert the physician of patient conditions that need attention. However, it is the physician who must use and apply the computer provided information. Thus, the computer will assist but not replace physicians in providing medical care.