Search PubMedSearch

Biomedical subjects

W A Yasnoff

Publications and source records attributed to W A Yasnoff.

At least 19 recordsLinked to original sources

Combining tabular, rule-based, and procedural knowledge in computer-based guidelines for childhood immunization.

IMM/Serve is a computer program which implements the clinical guidelines for childhood immunization. IMM/Serve accepts as input a child's immunization history. It then indicates which vaccinations are due and which vaccinations should be scheduled next. The clinical guidelines for immunization are quite complex and are modified quite frequently. As a result, it is important that IMM/Serve's knowledge be represented in a format that facilitates the maintenance of that knowledge as the field evolves over time. To achieve this goal, IMM/Serve uses four representations for different parts of its knowledge base: (1) Immunization forecasting parameters that specify the minimum ages and wait-intervals for each dose are stored in tabular form. (2) The clinical logic that determines which set of forecasting parameters applies for a particular patient in each vaccine series is represented using if-then rules. (3) The temporal logic that combines dates, ages, and intervals to calculate recommended dates, is expressed procedurally. (4) The screening logic that checks each previous dose for validity is performed using a decision table that combines minimum ages and wait intervals with a small amount of clinical logic. A knowledge maintenance tool, IMM/Def, has been developed to help maintain the rule-based logic. The paper describes the design of IMM/Serve and the rationale and role of the different forms of knowledge used.

Age Factors

IMM/Serve: a rule-based program for childhood immunization.

A rule-based program, IMM/Serve, is being developed to help guide childhood immunization for initial use, within Oregon. The program is designed primarily for automated use with an online immunization registry, but can also be used interactively by a single user. The paper describes IMM/Serve and discusses 1) the sources of complexity in immunization logic, 2) the potential advantages of a rule-based approach for representing that logic, and 3) the potential advantage of such a program evolving to become the standard of care. Related projects include 1) a computer-based tool to help verify the completeness of the logic, 2) a tool that allows a central part of the logic to be generated automatically, and 3) an approach that allows visualization of the logic graphically.

Child

US HealthLink: a national information resource for health care professionals.

US HealthLink is a new, comprehensive online medical information system designed specifically for health care professionals. Available to individuals for a fixed fee, it includes literature, news, diagnostic decision support, drug interactions, electronic mail, and bulletin boards. It also provides user-specific current awareness via clipping service, and fax delivery of both clipping and electronic mail information. US HealthLink can now be utilized to access a wide variety of medical information sources inexpensively.

Health Personnel

Alterations in left ventricular diastolic function with doxorubicin therapy.

To determine whether impaired diastolic function may be an early sign of doxorubicin cardiotoxicity, a retrospective study was performed in 12 patients who had undergone serial radionuclide angiography and were found to have a left ventricular ejection fraction of 55% or more before doxorubicin (Adriamycin) treatment and during follow-up. Average rapid filling velocity and slow filling velocity were both significantly reduced after doxorubicin treatment. Rapid filling velocity decreased from 5.17 +/- 1.52 to 4.18 +/- 0.96 units/s (p less than 0.01), and slow filling velocity decreased from 2.20 +/- 1.32 to 1.42 +/- 0.62 units/s (p less than 0.05). There were no significant changes in filling volume ratio, total diastolic time or diastolic time ratio. Because a change in left ventricular diastolic function can occur before ejection fraction falls to subnormal levels, diastolic function as well as systolic function should be examined for the early detection of doxorubicin cardiotoxicity. The clinical implications of our observations can only be established by a longer-term prospective analysis of left ventricular function in patients receiving doxorubicin therapy.

Adolescent

Scene-segmentation algorithm development using error measures.

Development of scene-segmentation algorithms has generally been an ad hoc process. This paper presents a systematic technique for developing these algorithms using error-measure minimization. If scene segmentation is regarded as a problem of pixel classification whereby each pixel of a scene is assigned to a particular object class, development of a scene-segmentation algorithm becomes primarily a process of feature selection. In this study, four methods of feature selection were used to develop segmentation techniques for cervical cytology images: (1) random selection, (2) manual selection (best features in the subjective judgment of the investigator), (3) eigenvector selection (ranking features according to the largest contribution to each eigenvector of the feature covariance matrix) and (4) selection using the scene-segmentation error measure A2. Four features were selected by each method from a universe of 35 features consisting of gray level, color, texture and special pixel neighborhood features in 40 cervical cytology images . Evaluation of the results was done with a composite of the scene-segmentation error measure A2, which depends on the percentage of scenes with measurable error, the agreement of pixel class proportions, the agreement of number of objects for each pixel class and the distance of each misclassified pixel to the nearest pixel of the misclassified class. Results indicate that random and eigenvector feature selection were the poorest methods, manual feature selection somewhat better and error-measure feature selection best. The error-measure feature selection method provides a useful, systematic method of developing and evaluating scene-segmentation algorithms.

Computers

Computers in medicine.

Explore the source record for details and available documents.

Attitude of Health Personnel

Automated scene analysis of CT scans.

Since the advent of computed tomography, there has been an increasing realization that CT scans contain quantitative as well as qualitative information useful in the diagnostic process. Often however, the use of this information is impeded by the tedious manual outlining of the areas of interest in the scan. To alleviate this problem, we have developed a scene segmentation algorithm which will automatically delineate areas of interest in a CT scan. This procedure uses known information about the expected objects in the scan in conjuction with an algorithm to label those objects. The resultant scene segmentation divides the scan into four anatomical areas: skull, normal brain, high density lesions and CSF. After an area of interest is interactively selected by the clinician, volume, density or other quantitative measures may be computed. Limitations of the algorithm and its clinical applications are discussed.

Absorptiometry, Photon

Ventricular volume in man computed from CAT scans.

A new interactive computers has been developed to measure ventricular volume from CAT scans. Testing this system on phantoms demonstrated an accuracy to within 16%. Then a series of scans of patients with obstructive hydrocephalus was analyzed using both tradional linear measures and the computer method. None of the traditional measures were directly proportional to the calculated volume. The area measure of ventricular volume correlated well with the computer-generated values. Clinical studies which attempt to quantitate ventricular volume should use a computerized or planigraphic measure.

Cerebral Ventricles

Stereotactic surgery with image processing of computerized tomographic scans.

The three-dimensional information from computerized tomographic scans has been transformed by image processing for use in stereotactic surgery. A lateral image of the target and calvarium can be superimposed on the lateral x-ray film taken at operation. Computer processing also eliminates extraneous data on the scan and gives the precise distance of the target from the midline. Testing the technique on a phantom shows it to be accurate to better than 0.5 cm. Application of the method for the stereotactic biopsy of a deep tumor is illustrated.

Adenocarcinoma