The article by van der Lei and colleagues in this issue of Annals [3], which describes the introduction of computer-based records in the Netherlands, is encouraging. The authors report that more than one fourth of the 6400 Dutch general practitioners have instituted a computer-based clinical record system in their offices. We discuss the status and issues involved with the use of computer-based records in the United States in the context of the Dutch experience.

The diverse and heterogenous patterns of care and the various medical provider and institutional environments characteristic of U.S. health care have resulted in a fragmented patient medical record, with no single provider, institution, or third-party payer responsible for maintaining a comprehensive record. Consequently, the major thrust of the successful computer-supported medical information systems in the United States has been to support the financial, administrative, and communication functions of individual institutions. The primary emphasis of these computer systems has not been the clinical record but functions such as billing, admission and discharge, scheduling, and laboratory reporting. Some systems have incorporated the retrieval of previously transcribed clinical data such as radiology reports, discharge summaries, problem lists, and visit notes. Once stored in the computer-based clinical record system, the data can be viewed simultaneously by multiple persons at different sites.

Impressive examples of such systems are in place both in U.S. hospitals [4-7] and in some ambulatory practices [4, 7-10]. For example, several hundred ambulatory care sites use COSTAR, a public domain computer-based ambulatory medical record system developed at Massachusetts General Hospital [8, 9]. In COSTAR, the medical data for a patient visit are recorded on a paper-based encounter form and then transcribed into the computer system by clerical personnel. Other examples of computer-based systems include the electronic record developed at the Regenstrief Institute at Indiana University [4], where a clinician can view a patient's problem list and laboratory data interactively as flowsheets, allowing easier detection of trends. An ambulatory computer-based record at Boston's Brigham and Women's Hospital [10] also provides a summary screen displaying a "patient-at-a-glance" with a problem list, allergies, and medications. In these systems, like many similar systems, the patient information is accessed either through direct inquiry at a computer terminal or through computer-generated summaries and reports.

A major impediment to the development of a computer-based clinical record system has been the lack of agreement in standards both for the clinical terminology to be used and for the computer technology. The American Society for Testing and Materials (ASTM) recently promulgated a standard to describe the content and structure of a computer-based system [11], but it is not widely reflected in currently used systems. A consortium of vendors and hospitals, Health Level Seven, is developing standards for transmitting billing; admission, discharge, and transfer; order entry; and the reporting of results between a network of computers [12]. Health Level Seven collaborates closely with ASTM and has defined a standard for the protocol to be used in the communication of laboratory data in an electronic format; this standard has been adopted by many vendors. The absence of standards for the other sections of the clinical record and the lack of support for standards by the government and professional organizations has resulted in the use of many competing computer operating systems, hardware platforms, user interfaces, and software tools, making every computer-based record system implementation almost hopelessly proprietary. Little attention has been focused on establishing a standard for a system with an "open architecture," a standard that would allow computer hardware and software products of many different manufacturers to function together. Given the diversity of computer technology, such an open architecture will be essential for the dissemination and national adoption of a common computer-based system.

The successful development of the automated medical record in the Dutch system is based largely on the country's progress in four crucial areas [9, 13, 14]. These are the development of a standard clinical vocabulary, effective methods for direct physician interaction with the computer-based system, support of key professional societies, and judicious use of government funding.

Standard Clinical Vocabulary

One clear advantage of computer-based medical records is that clinical information can be retrieved almost instantaneously and simultaneously from many different sites. Simply recording and storing the medical information in a narrative format in a computer system would accomplish this and would improve the legibility of previously handwritten notes. However, using the computer as nothing more than a large word-processing program would make analysis of the nature, extent, and time-course of the disease processes, therapies, and outcomes difficult and time consuming. Without a more structured method of data collection using a standard controlled vocabulary, it will be impossible to make rational decisions about which treatments are cost-effective and how patient outcomes are affected by our clinical decisions.

A controlled vocabulary implies a standard set of common terms (including accepted synonyms and abbreviations) for recording clinical information. A controlled vocabulary would allow the computer to search and sort data quickly, summarize the information (for example, the active problems and active medications), identify important clinical manifestations (such as a drug allergy), and retrieve selectively (for example, the last visit note discussing the problem of congestive heart failure). In addition, a structured clinical record with a controlled vocabulary would enable the computer to identify and retrieve relevant medical knowledge (such as the contraindications of a particular drug), to provide problem-specific guidelines, to alert the provider to the need for indicated preventive medicine interventions, and to highlight an anomalous test result. Most commercial medical record systems (as well as the Elias system described in the article by van der Lei and colleagues) do not require a controlled vocabulary. The development and national adoption of a controlled vocabulary is a prerequisite for a computer-based clinical record to achieve its full potential [15].

Direct Physician Interaction with the Computer System

For maximum effectiveness, the computer-based record system must completely replace the paper record, and the clinician responsible must interact directly with the computer to enter and retrieve medical information. This would reduce transcription errors as well as personnel costs and minimize delay in the availability of clinical information. An additional advantage of direct physician use of the computer-based system would be the provision of reminders and warnings when a clinical decision is being made. For example, a physician writing a prescription interactively can be warned of an adverse drug-drug interaction before the medication is given to the patient and possible harm ensues. This capability, which cannot be provided in a paper-based record, is a key advantage of a computer-based record and is supported by some hospital information systems in the United States. Changing from narrative text recording (either written or dictated) to interacting with a computer requires modification of longstanding traditions of medical recordkeeping. Although many medical students and young physicians have extensive experience using computer technology, there is little continuation of this in their training years. In addition, many older physicians, unfamiliar with the technology, are reluctant to enter data directly into the computer. Again, it is encouraging to note the progress toward this goal in the Dutch system.

System designers continue to improve computer interfaces to permit rapid direct entry of narrative data into the computer while still maintaining the flexibility of the dictated note. For example, PEN&PAD, a prototype workstation being developed at the University of Manchester [16] in the United Kingdom, uses a graphic interface, user-defined templates for common clinical problems, and "point-and-click" technology to permit the user to enter rapidly a description of a patient's symptoms and physical findings. In another example, interactive encoding of diagnoses by physicians has been a part of the electronic medical record at the University of Geneva Hospital in Switzerland since 1985 [17]. Despite such advances, the design of interfaces for direct entry of clinical information by physicians remains one of the most difficult challenges in the development of a computer-based system.

Role of Professional Societies

The formulation of specific requirements for the computer systems by professional organizations was one of the important factors that led to the successful development and dissemination of the computer-based system in the Netherlands. Most busy physicians lack both the expertise in information management and the time to evaluate the relative merits of the many commercially available computer-based systems. The promulgation of guidelines for computer-based records by the Dutch College of General Practitioners and the Dutch Association of General Practitioners is an important lesson for this country. The creation of de facto standards and training programs in the use of representative computer systems by national organizations improves the acceptance of a computer-based system. This leadership is especially needed in the United States, where many different computer-based medical record systems are being marketed. Without professionally defined requirements for the functional capabilities for the system, a standard clinical vocabulary, and national standards for patient identification, record security, and electronic transmission of data, the existing Tower of Babel will persist.

Role of Government Funding

The initial costs of replacing a paper-based patient record with computer-based technology can be substantial because of the investment in hardware, software, and personnel training necessary to use the system. In an uncertain environment of impending health care reform in which the level of reimbursement for services provided to patients may be reduced, many physicians will be reluctant to spend the necessary thousands of dollars, despite the potential advantage of computer-based records in improving efficiency through better organization and availability of patient data. For similar reasons, institutions are often loathe to commit resources to the development and implementation of computer-based solutions that may be outmoded in a few years. The financial incentives provided by the Dutch government, specifically the 60% reimbursement to the general practitioner for the expenses of office automation, offer a lesson for how the United States can encourage dissemination of the technology.

In summary, we believe that the widespread implementation of computer-based medical records will result in significant improvement in the health care system in the United States. The current attention to health-care reform provides a stimulus and an opportunity for the development of an effective computer-based system. The escalating need for medical record access by diverse groups in the managed care climate offers a unique opportunity for cooperation between all the interested parties in this country. A major effort will be needed to develop a standard medical vocabulary, to encourage direct physician-computer interaction, to involve professional societies in the setting of standards and in training, and to provide financial incentives to aid the transition from a paper-based record. However, if we are willing to meet these challenges, we will go a long way toward satisfying Florence Nightingale's desire for medical records that better fulfill our information needs.

Grant support: In part by grants R18 HS06575 and R01 LM05200 and contract LM-1-3538 to the Massachusetts General Hospital.