Definition, structure, content, use and impacts of electronic health records: A review of the research literature

This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Statistical Pattern Recognition

The invention concerns medical diagnosis and monitoring equipment with wireless electrodes (2a...2f) designed to be secured to the skin of the patient (3). The electrodes (2a...2f) include, as well as microsensors, a digital transmitter (31) and receiver (30) unit and an antenna (36a). The electrodes (2a...2f) can be used, for instance, to detect EEG and ECG signals or to monitor body/berathing movements, temperature or perspiration. A preferred embodiment has an electrode which incorporates all functions in a semiconductor chip designed as an integrated circuit with the appropriate sensor, sensor-control, frequency-generation, transmitter and receiver units plus a switching control unit. The antenna (36a) can be mounted either in the flexible electrode covering or directly on the chip.

Wireless medical diagnosis and monitoring equipment

Systems and methods for controlling the power supplied to an electrosurgical probe. The systems and methods may be used to monitor electrode-tissue contact, adjust power in response to a loss of contact, and apply power in such a manner that charring, coagulum formation and tissue popping are less likely to occur.

Systems and methods for controlling power in an electrosurgical probe

A medical sensor may be adapted to account for factors that cause irregularities in pulse oximetry measurements or other spectrophotemetric measurements. Sensors are provided with surface features that reduce the amount of outside light or shunted light that impinge the detecting elements of the sensor. The sensor is adapted to reduce the effect of outside light or shunted light on pulse oximetry measurements.

Medical sensor and technique for using the same

Described here are a novel means and device for noninvasively quantifying important blood constituents. Total hemoglobin, arterial oxygen content, hematocrit, and other parameters can all be determined quickly and easily without the need for skin puncture or lengthy laboratory analysis. The invention described here concerns the simultaneous measurement of volume changes and changes in the mass of either oxyhemoglobin, total hemoglobin, or reduced hemoglobin. The data obtained by these measurements is used to quantity the parameters of interest.

Method for noninvasive intermittent and/or continuous hemoglobin, arterial oxygen content, and hematocrit determination

The heating of blood or other medical fluids supplied to a patient is provided by a system and method of feedback control. The temperature of the blood is sensed by receiving infrared energy from the medical fluid as it flows within a sterile and disposable tube from a fluid source to the patient. Feedback control stabilizes the temperature at a desired value. A second sensor may optionally be used to determine if the fluid is too hot within the microwave device itself. The disposable tube has at least one window or thin membrane portion which allows infrared radiation to pass therethrough in order to be sensed by the sensor. One arrangement of the present invention uses a microprocessor with adaptive control to provide precise and accurate control of the temperature of the medical fluid.

System and method for in-line heating of medical fluid

Objective. Despite efforts to develop electronic access to medical records, there are few data on availability of past evaluations. Typical analyses assess only availability of paper charts. We studied the availability of prior internal and external medical documentation in the preanesthetic clinic of our tertiary teaching institution, which has had access to hospital-wide electronic records for five years. Methods. Residents and clerks answered questions on availability of desired pre-existing records either in a physical chart delivered to our clinic by computer terminal, at the start of the physician interview, and on later success in obtaining desired records not available at start of interview. Patient interview lengths were calculated. Results. 397 responses from 19-9-96 through 25-10-96 were available after 718 patient encounters. The surgeon's history & physical was unavailable in 11%. For 114/397 patients (29%) the anesthesiologist desired more pre-existing information than was available in either paper or electronic format. For 32/397 patients (8%), the desired information resided outside the institution (“MISSING EXTERNAL”); for 89/397 (22%), it was within the institution (“MISSING INTERNAL”). Additional information was desired for 41% of ASA 3/4 patients, and for 23% of ASA 1/2 patients. Some or all of desired information was not found for 45% of MISSING INTERNAL, and for 78% (p = 0.12 NS) of MISSING EXTERNAL. MISSING EXTERNAL of any ASA status required significantly longer evaluations (70 ± 39 min) than even ASA 3/4 patients missing no information (51.4 ± 35.7 min, p 0.03). The surgeries of only eight patients (2%) were postponed in the preanesthetic evaluation clinic; half of the postponements were to obtain pre-existing records. Conclusions. Anesthesiologists retrieved, and added to the perioperative evaluation, information from previous encounters for 16% of patients. Despite our hospital-wide electronic records, internal information was missing for 22% of patients. Uneven deployment, and reliance on transcription may contribute to failures. A national electronic medical records system would benefit the 8% (one out of twelve) of outpatients missing external records identified in this study. For many patients, optimal medical understanding was not achieved during the planned preanesthetic evaluation.

Availability of Records in an Outpatient Preanesthetic Evaluation Clinic

Anesthesia information-management systems: their role in risk-versus cost assessment and outcomes research.

Objective. To review, from a legal perspective, the potential for using the Internet for inter-institutional transfer of patient medical records. Methods. Basic issues and recent legislation that relate to protection of both medical data, and those transferring that data over public network systems is reviewed. Results. Many laws already in existence can be applied to Internet transmission, but questions of jurisdiction remain. Providing signatures on requests for information, which are in essence contracts, is a problem. Signatures must both prove the identity of the participants and provide for non-repudiation of the agreement. Cryptographic digital signatures appear secure and effective, but their use is difficult to implement. Simpler methods are fraught with risks, yet are more easily accomplished. The patient's rights of privacy must be balanced against the need for access by government, physician, or healthcare institutions to confidential information. In general, information holders must put forth reasonable efforts to keep information confidential. The development of acknowledged standards will provide guidance. Multiple laws provide some deterrence and hence some reassurance to healthcare institutions, for example, by criminalizing acts of electronic interception of patient records in transit. Conclusion. Some believe the expense of secure transfer of medical records by electronic means is a major obstacle; this is false: such transfers are now technologically quite easy. The greatest obstacle to electronic transfer of medical records at this point is the development of workable standards for signing agreements and protecting transmissions, but the perceived advantages will likely drive the necessary developments.

Gordon L. Gibby

Papers

Method for noninvasive intermittent and/or continuous hemoglobin, arterial oxygen content, and hematocrit determination

System and method for in-line heating of medical fluid

Availability of Records in an Outpatient Preanesthetic Evaluation Clinic

Anesthesia information-management systems: their role in risk-versus cost assessment and outcomes research.

The Internet and electronic transmission of medical records.