A voice-enabled, structured medical reporting system.

Kurzweil Applied Intelligence received a research grant from the National Institute of Standards and Technology (NIST) Advanced Technology Program to develop a prototype voice-enabled, structured medical reporting system. In typical usage, the physician dictates to the system, which then uses automatic speech recognition and medical knowledge bases to produce a structured report. This report can then be formatted and viewed on a computer screen, stored in databases of patient information, transmitted to other systems, used to support outcome studies, or viewed on a Web browser. The output reports are structured according to two standard, platform-independent formats: SGML and CORBA. These formats represent the data in a way that can be read by both computers and humans, and efficiently communicated to a wide range of databases and communications protocols.

Hospital-acquired morbidity on a neurology service.

Clinical services must monitor hospital-acquired morbidity, but what rates are expected specifically for neurology inpatients is not evident from published studies. We studied prospectively 1317 consecutive admissions to a neurology service in a university-affiliated city hospital from 1987 to 1990 and recorded all nosocomial infections, nosocomial pneumonia, and decubitus ulcers of stage III or IV. Over the 3-year period, 6.8% of patients had > or = 1 nosocomial infection (and almost half of these had a nosocomial bloodstream infection); 3.1% had > or = 1 case of nosocomial pneumonia; 1.2% developed severe decubitus ulcers, and 8.4% had one or more of the three complications. The incidence of nosocomial infection exceeds that expected from multihospital studies. How much of the excess is peculiar to neurology patients and how much can be attributed to factors in our community and at our hospital cannot be determined from this study. Furthermore, our statistics are not meant as norms, but as initial estimates for quality assurance.

Examination of Pseudomonas aeruginosa-gentamicin discrepancies encountered in an Autobac I-disk diffusion comparison.

Seven Pseudomonas aeruginosa strains found to be susceptible to gentamicin by the Autobac I system and resistant by the Bauer-Kirby disk diffusion method were tested for the presence of mixed populations of cells. Double zones of inhibition randomly appeared on gentamicin disk diffusion plates, and susceptible and resistant subpopulations were isolated from these plates. Growth kinetic studies of separated strains and mixed subpopulations indicated that the susceptible organisms grew rapidly and were read as susceptible at 5 h with the Autobac I system. Resistant organisms entered a sustained lag phase and did not achieve sufficient turbidity to be read as resistant with the Autobac I system before 6 h. Thus, a false reading of susceptible could be obtained with the Autobac I system, depending on the ratio of susceptible organisms to resistant organisms selected for testing. A mixed susceptible and resistant population could be recognized by extending the incubation time of the Autobac I cuvette or by using other susceptibility methods to test isolates with light-scattering indexes of less than 1.0.

Comparative recovery of fungi from biphasic and conventional blood culture media.

A brain heart infusion broth and agar biphasic bottle was compared with a vented broth brain heart infusion bottle for the recovery of fungi from blood. A total of 40 fungi, all yeasts, were recovered from 5,000 blood cultures. The biphasic bottle slightly increased the overall recovery of six species of yeasts. In addition, yeasts were first detected more often in the biphasic bottle (73%) than in the vented broth bottle (38%). A routine early (6- to 24-h) or late (5-day) subculture of macroscopically negative cultures may not be required for yeast isolation when a biphasic medium is used. Of the yeasts initially detected in the biphasic medium, 83% were seen to be growing on the agar slant. Only four were detected from a 24-h subculture, a Candida glabrata of questionable clinical significance, was recovered after our routine blood culture period of 7 days; however, other fungi, not recovered in this study, require extended incubation periods.

Comparison of a commercial identification kit and conventional biochemical tests used for the identification of enteric gram-negative rods.

A comparison between 11 Minitek biochemical tests and corresponding conventional tubed media was undertaken with 1,089 isolates of enteric gram-negative rods. Overall correlation between Minitek and conventional biochemicals was 97.4%. Minitek proved to be a time- and space-saving miniaturized biochemical system that can be used effectively for the identification of enteric gram-negative rods.

Antimicrobial susceptibility of Haemophilus parainfluenzae.

Fifty random clinical isolates of Haemophilus parainfluenzae were tested for their susceptibility to 10 antibiotics by a microtiter broth dilution method. Three of the strains tested were resistant to ampicillin, whereas eight were resistant to tetracycline. All strains tested were susceptible to chloramphenicol, kanamycin, gentamicin, cephalothin, and colistin. The ranges of minimal inhibitory concentrations for the three remaining antibiotics were: 0.5 to >/=128 mug of penicillin G per ml, 0.03 to 4 mug of carbenicillin per ml, and 1 to 16 mug of erythromycin per ml. Elevated minimal inhibitory concentrations for penicillin and carbenicillin were noted for the three ampicillin-resistant strains. Tests for beta-lactamase production demonstrated the presence of this enzyme in each of the three ampicillin-resistant strains.

Recurrent Aeromonas sepsis in a patient with leukemia.

A case of recurrent sepsis due to Aeromonas hydrophila in a patient with acute myelogenous leukemia is reported. The patient's first infection leading to bacteremia followed contamination of a mosquito bite by stagnant water. After recovery from the first bacteremia, the patient again became septic with a second strain of Aeromonas hydrophila, which again responded to antimicrobial therapy. It is hypothesized that contamination of the local water supply may have led to the establishment of a gastrointestinal carrier state that produced the second bout of Aeromonas sepsis when the patient was markedly leukopenic. The importance of the oxidase test to differentiate Aeromonas species from members of the family Enterobacteriaceae is re-emphasized.