PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 8289535

Limits to diagnostic accuracy.

B S Todd·R Stamper
View original source ↗Export metadata ↓

Abstract

This paper explores the limits to computer-aided medical diagnosis. A specific application area (the diagnosis of abdominal pain of suspected gynaecological origin) is chosen, and the factors limiting the accuracy of computer programs are investigated by means of a simulation model which has been shown previously to generate realistic cases. The model is used to generate arbitrarily large training and test sets. The results suggest that, while statistical dependencies exist amongst symptoms and signs, there is little to be gained by taking interactions into account. However, failure to record all possible observations does limit diagnostic accuracy significantly. The results suggest that near-optimal diagnostic accuracy (75-80%) can be obtained with a training set size of 10(5) cases simply by applying Bayes' theorem with the usual assumption of conditional independence.

Explore related subjects

Abdominal PainBayes TheoremComputer SimulationDiagnosis, Computer-AssistedFemaleGenital Diseases, FemaleHumansModels, BiologicalSensitivity and SpecificityJournal ArticleResearch Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

B S Todd, R Stamper. Limits to diagnostic accuracy.. https://doi.org/10.3109/14639239309025314

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed1997

[Esophago-gastro-duodenoscopy of pediatric patients].

In total 199 oesophago-gastro-duodenoscopies (OGD) were performed in 71 female and 71 male paediatric patients (three months-15 years, median 8 years 2 months). The endoscopy was performed in general anaesthesia in children less than five years old, and in an intravenous sedation in older patients. The indications for OGD were: recurrent abdominal pain and concomitant positive antibodies against Helicobacter pylori as a part of a scientific project, upper dyspepsia, upper gastrointestinal bleeding, failure to thrive, coeliac disease, suspicion of chronic inflammatory bowel disease and a percutaneous gastrostomy. Seventy-two OGD were carried out in general anaesthesia, 86 in intravenous sedation with midazolam and pethidine and 41 in intravenous midazolam sedation. Complications related to the sedation or to the endoscopy were not observed. Amnesia was reported in 94/95 children who were sedated intravenously with midazolam and pethidine or midazolam alone. Six endoscopies could not be carried out in intravenous sedation because of agitation. In the primary OGD endoscopy revealed a normal mucosa in 121/142 (85%), oesophagitis in four (3%), nodular mucosa in six (4%), gastritis in four (3%) and a duodenal ulcer in one (0.7%). Histology disclosed active or inactive chronic gastritis at the primary endoscopy in 35/69 (51%) of the children with recurrent abdominal pain and antibodies against H. pylori. In children with failure to thrive an avillous duodenal mucosa was seen in 3/32 (9%). A comparison between histological and stereomicroscopical evaluation of the duodenal biopsies revealed agreement in 41/47 (87%). We conclude that OGD is a safe and tolerable procedure in paediatric patients, in whom possible morphological changes are suspected. The indications for an OGD need further evaluation.

Abdominal Pain↗