Expert learning system network for diagnosis of breast calcifications.

Breast calcification diagnosis was studied by using clinical findings and computerized image processing of a mammogram in a network of trained expert learning systems (Outcome Advisor [OA]). The system was tested with records not used for training and performance was compared with radiologist. The network was 72% accurate in classifying clusters of calcifications as malignant or benign over a set of test cases radiologists had considered "hard-to-diagnose calcifications," and referred for biopsy. The radiologists had decided to conduct biopsy by selecting an equal number of positive and negative cases for the test group; thus the radiologists' performance with respect to categories of benign versus malignant was constrained to be 50/50. Statistical analysis shows only a 2% probability that the observed accuracy of 72% was a chance performance in recognizing whether a cluster is benign or malignant. The feasibility of developing a network of OAs for diagnosing breast cancer integrating digital image processing of mammograms is promising.

The Heimlich maneuver. Best technique for saving any choking victim's life.

The American Red Cross (ARC) and the American Heart Association (AHA) advocated backslaps, chest thrusts, and abdominal thrusts for 10 years after the Heimlich maneuver was introduced in 1974. Even after the Surgeon General in 1985 declared these methods to be "hazardous, even lethal," the ARC and the AHA continue to recommend backslaps and chest thrusts for infants under 1 year of age. ARC and AHA instructional materials that advocate use of these methods have not been recalled, and the public has not been warned of the dangers. One cause of the confusion about backslaps is the flawed belief that gas pressure alone removes a foreign body. In addition, there is lack of understanding that, compared with the Heimlich maneuver, the backslap produces an insignificant amount of the energy required to expel an object from the airway. In fact, the energy produced by the backslap drives the foreign object in the wrong direction, toward the lungs, while the energy produced by the Heimlich maneuver drives the object away from the lungs, toward the mouth. Backslaps and chest thrusts should be publicly recalled as a treatment for choking infants before further deaths and injuries occur. The Heimlich maneuver is the best rescue technique for treating choking victims of all ages.

Using the Heimlich maneuver to save near-drowning victims.

Flooding of the lungs occurs routinely in drowning victims. The cause of death in 90% of them is hypoxemia caused by water in the lungs. Mouth-to-mouth ventilation is ineffective until the water is removed. The Heimlich maneuver expels aspirated water, vomitus, debris, and other foreign matter. In treating near-drowning victims, place the victim in the supine position with head turned to the side and perform the Heimlich maneuver to evacuate water from the lungs, unless you know water is not in the respiratory tract. The Heimlich maneuver is a form of artificial respiration. It elevates the diaphragm, increasing intrathoracic pressure and compressing the lungs, and should be performed intermittently until all water is expelled. It is an especially useful technique because fear of contagion sometimes deters rescuers from using mouth-to-mouth ventilation . Further treatment has not been necessary in most instances. If the victim does not recover after water ceases to flow from the mouth, ventilation techniques, cardiopulmonary resuscitation, and other measures as indicated should be used.

The use of an expert system in the clinical laboratory as an aid in the diagnosis of anemia.

Experience with an expert system developed for the purpose of classification of anemias is presented. Input for this system consists of limited demographic information on each patient and the results of the complete blood count, with the incorporation of the results of further chemical testing (serum iron/total iron binding capacity/ferritin and serum B12/serum folate/red blood cell folate), if indicated. Performance of this system is demonstrated using data from 84 patients seen in the authors' laboratory selected either because of a request for evaluation by the attending physician or because of significant anemias. Using this limited input, the system was able to accurately classify 74 of 84 (88%) of cases according to previously established criteria. The output from the system is overread by a pathologist. Future directions are also discussed.

Evaluation of a new classification system for anemias using Consult Learning System.

Since the advent of electronic particle counting, anemias have customarily been classified by evaluating cell size (MCV) and hemoglobin content (MCH). Recently a new parameter estimating red cell size heterogeneity (the 'red cell distribution width' or 'RDW') has been introduced. We have evaluated a proposed classification of anemias based upon this new parameter in a large group of hospitalized patients utilizing an expert system based upon statistical pattern recognition and compared our results to other studies. The potential advantages of using such a system over currently existing uni-dimensional classification systems to evaluate clinical problems are discussed.

Thyroid disorders: automatic diagnosis in CONSULT I.

Automatic diagnosis of thyroid diseases is implemented on CONSULT I, a microcomputer system based on the Patrick model for computer-assisted diagnosis in medicine. The thyroid 'subsystem' consists of 19 classes (diseases) and 16 features (signs, symptoms, laboratory tests). For 76 test cases obtained from patient records (recognition samples), the 'true' class (disease) is decided in the highest 'probability' number in 89% of cases and in the differential diagnosis in 100% of cases. Performance is compared to physicians. Estimation of class-conditional probability densities utilizing equivalence regions in the feature space is discussed.