Search PubMed⌕ Search

Biomedical subjects

S J Darmoni

Publications and source records attributed to S J Darmoni.

14 recordsLinked to original sources
PubMed1995

HOROPLAN: computer-assisted nurse scheduling using constraint-based programming.

Nurse scheduling is a difficult and time consuming task. The schedule has to determine the day to day shift assignments of each nurse for a specified period of time in a way that satisfies the given requirements as much as possible, taking into account the wishes of nurses as closely as possible. This paper presents a constraint-based, artificial intelligence approach by describing a prototype implementation developed with the Charme language and the first results of its use in the Rouen University Hospital. Horoplan implements a non-cyclical constraint-based scheduling, using some heuristics. Four levels of constraints were defined to give a maximum of flexibility: French level (e.g. number of worked hours in a year), hospital level (e.g. specific day-off), department level (e.g. specific shift) and care unit level (e.g. specific pattern for week-ends). Some constraints must always be verified and can not be overruled and some constraints can be overruled at a certain cost. Rescheduling is possible at any time specially in case of an unscheduled absence.

France↗
PubMed1994

SETH: an expert system for the management on acute drug poisoning in adults.

The aim of SETH is to give end-users specific advice concerning treatment and monitoring of adult drug poisoning. SETH is developed with an off the shelf expert system shell (KBMS) and runs on a microcomputer. Technical choices were done according to this analysis, financial considerations and portability. Currently, the database contains 1000 French drugs from 75 different toxicological classes. The SETH expert system simulates the expert reasoning, taking into account for each toxicological class delay, signs and dose. Two phases of evaluation were performed. The experimental implementation of Seth began in April 1992 in our Poison Control Centre. Since then, 1100 cases inputted by residents were analysed by SETH. The extension of the knowledge base to child poisoning began in March 1993.

Acute Disease↗
PubMed1993

[HERETAIN: a computer-assisted diagnosis system for hereditary retinal syndromes].

The diagnosis of hereditary retinal syndromes may be difficult for a physician because of their number and variability. A computer assisted diagnosis of these syndromes can be useful in such cases. We used an identification software (XPER) for this purpose. The data base contains more than 67,000 elementary data that enable us to define 115 hereditary retinal syndromes. The knowledge is not represented by description of typical cases or diagnostic procedure rules but by structured description of syndromes defined by the group of experts. This CAI software is characterised by specific optimising procedures, deductive algorithms and dissimilarities calculus and enables very fast diagnoses by limiting the number of complementary analyses and thus the cost of this research. This system is extensible and justifies all its conclusions, its user-friendly data representation makes it accessible for any physician even if he does not master computers. The selected pathology field seems very suitable to developing a computer assisted diagnosis system: many low frequency syndromes, meaningful precise diagnosis for genetic and professional counseling, therapeutic expectations due to progress in molecular genetics. According to the authors, HERETAIN is one of the largest computer assisted decision support systems in ophthalmology.

Diagnosis, Computer-Assisted↗
PubMed1992

Computer-aided decision support in hepatology.

The aim of this study was to describe and to evaluate the publications of the last 30 years devoted to computer-aided decision support in clinical hepatology. The search used Medlars and references of articles. Computer-aided decision support (CADS) was classified in two categories: statistical systems and knowledge-based systems. Two specific questionnaires were used for methodologic evaluation, one for statistical systems and one for knowledge-based systems. They were filled out independently by two observers. A total of 31 papers were selected among 55 identified between 1960 and 1991. The maximum possible for the two scores was 24. The methodologic quality ranged from 4 to 22 (median, 12) for statistical systems and from 8 to 12 (median, 9) for knowledge-based systems. The poor level of methodology could explain in part the lack of utilization of computer-aided decision support in the daily clinical practice of hepatologists.

Bayes Theorem↗
PubMed1991

[System of decision support in obstetrics. The computerization of prenatal consultations].

The aim of this study was to realize a prototype of a computer-aided decision support for prenatal visits. He has been developped on a microcomputer. We used procedural programming to represent the medical knowledge. This prototype has several interfaced units: a computerized prenatal record, the computing of quantitative variables (term, fetal biometry, uterine height) and the two computer-aided units (preterm births and modelization of weight gain during pregnancy). The next step will be the medical evaluation of this computer-aided decision support in obstetrics.

Anthropometry↗
PubMed1990

[What to expect from expert systems for the diagnosis of functional bowel disorders].

The goal of this study was to evaluate the computer-aided diagnosis systems used for functional intestinal disorders published between 1970 and 1989. The methodology of all prospective studies published was evaluated using a score system of 12 items, filled in by two independent observers. A total of 10 studies were identified. None of the systems studied could truly be considered as an expert system. Most systems were not methodologically sound and the median score was 11 of a possible total of 24. The two principal characteristics of functional intestinal disorders are their high prevalence and the absence of objective diagnostic criteria. Taking these two facts into consideration when elaborating a diagnostic method, expert systems should be useful for teaching purposes and for conducting prospective epidemiologic or therapeutic studies. It seems too early, however, to consider the use of veritable expert systems as an aid to the practitioner in daily practice.

Algorithms↗
PubMed1987

[Development of an expert system as a teaching aid in the serological diagnosis of acute viral hepatitis].

The serological diagnosis of acute viral hepatitis is complex for both practitioners and students. We have developed an expert system to teach the serological diagnosis of acute viral hepatitis in order to help non-specialists in deciding on the diagnosis. Three levels of increasing difficulty have been devised. The procedure consists of the following steps: choice of first-line examinations; discontinuation of the examinations in cases where the diagnosis is ascertained; choice of the most discriminant examination in cases where the diagnosis is doubtful. The value of this computer-assisted teaching must be confirmed by randomized studies involving a group of students trained by "classical" methods and a group of students trained by a computer-assisted method.

Diagnosis, Computer-Assisted↗
PubMedDate not supplied

[Computer-assisted model of weight gain during pregnancy].

The goal of this study was to modelize the evolution of "ideal" weight gain during pregnancy and to generate automatically the appropriate diet. This computerized model has been developed on a microcomputer and has two units: the first unit calculates the "ideal" weight gain during pregnancy, based on the curves of Rosso which show that weight gain is not linear with term and depends of the prepregnancy weight. The second unit calculates the appropriate diet which is depending for the first visit on height, prepregnancy weight and weight gain and for the followed visits on weight gain and the diet situation of the previous visit. The next step will be the medical evaluation of this computer-aided modelization of weight gain during pregnancy.

Computer Simulation↗
PubMedDate not supplied

[Value of digestive endoscopic examination in acquired immunodeficiency syndrome (45 cases)].

45 patients with acquired immunodeficiency syndrome (AIDS) were studied with gastrointestinal endoscopy (42 upper endoscopies and 12 colonoscopies). 28 patients had skin or buccal Kaposi's sarcoma with or without opportunistic infections and 17 had opportunistic infections. 12 patients out of 45 (27 per cent) had 1 or several Kaposi's sarcoma macroscopic gastrointestinal localisations, 12 documented by upper endoscopy and 4 by colonoscopy. Endoscopic biopsies confirmed the diagnosis 5 times out of 16 (31 per cent). 16 patients (38 per cent) had candidosis oesophagitis, 1 had ulcerative antritis, 2 had a erythematosus duodenitis, 6 had diffuse inflammatory mucosal colonic changes. The specific abnormalities documented by histology were 1 case of total villous atrophy and 2 cases of cytomegalovirus colitis. The patients with cutaneous Kaposi's sarcoma have more often shown gastrointestinal Kaposi's sarcoma than the patients without Kaposi's sarcoma. The prevalence of tumoral or major (diffuse candidosis oesophagitis, ulcerative antritis, active colitis) endoscopic abnormalities documented by upper endoscopy was 40 per cent (10 cases out of 25) in asymptomatic patients, 43 per cent in diarrheic patients (3 cases out of 7) and 60 per cent (6 cases out of 10) in patients with dysphagia, epigastralgic pain or vomiting and that of documented by colonoscopy was 75 per cent (3 cases out of 4) in patients with mucus or bloody stools and 14 per cent (1 case out of 7) in diarrheic patients. The main result of the endoscopy on AIDS patients has therefore been the diagnosis of visceral localisations of Kaposi's sarcoma. The appearance of the secondary major lesions related to opportunistic infections is unusual, especially in asymptomatic patients. A systematic endoscopy on these patients remains a disputed question.

Acquired Immunodeficiency Syndrome↗