PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 1505701

Evaluating patients with chest pain using classification and regression trees.

F Buntinx·J Truyen·P Embrechts·G Moreel·R Peeters
View original source ↗Export metadata ↓

Abstract

We collected data on 320 patients complaining to their general practitioner of a new episode of chest pain, discomfort or oppression. Relationships were examined between initial signs and symptoms and a follow-up diagnosis after a period of 2 weeks to 2 months. The data were analysed with CART, a statistical decision theory software package. In our first run, the number of misclassifications by CART was 56%. After regrouping of the data and diagnostic categories, there were 37% misclassifications. The most discriminating variable turned out to be pain on palpation. When comparing each of five diagnostic groups to all others, we found a positive predictive value of 27% for gastrointestinal diseases, 72% for cardiovascular disorders, 69% for respiratory diseases, 58% for psychopathology and 73% for chest wall pathology. The CART methodology needs further investigation and testing before any clinical application will be possible in general practice.

Explore related subjects

Chest PainDecision Support TechniquesDecision TreesFamily PracticeHumansPredictive Value of TestsProspective StudiesRegression AnalysisJournal ArticleResearch Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

F Buntinx, J Truyen, P Embrechts, G Moreel, R Peeters. 1992. Evaluating patients with chest pain using classification and regression trees.. https://doi.org/10.1093/fampra%2F9.2.149

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

KEEP EXPLORING

Related citations

PubMed2007

Impact of a negative prior stress test on emergency physician disposition decision in ED patients with chest pain syndromes.

OBJECTIVE: Many emergency department (ED) patients with potential acute coronary syndromes (ACS) have prior visits and prior cardiac testing; however, the effect of knowledge of prior testing on the emergency physician disposition decision making is not known. We studied the impact of prior noninvasive testing (ie, stress testing) for myocardial ischemia on disposition decision making in ED patients with potential ACS. METHODS: We performed a prospective cohort study of ED patients with chest pain who received an electrocardiogram for potential ACS. Data included demographics, medical history, stress test history, and TIMI risk score. Patients were followed in-house; 30-day telephone interviews were performed for follow-up. Main outcomes were ED disposition (admit/discharge) and a composite of 30-day death, acute myocardial infarction, and revascularization stratified on the basis of prior stress testing known at the time of presentation. Standard statistical techniques were used with 95% confidence intervals (CI). RESULTS: There were 1853 patients enrolled and 97% had follow-up. Patients had a mean age of 53 +/- 14 years; 60% were women, 67% were black. There were 1491 (79%) patients without a prior stress test, 291 (16%) had a normal prior stress test result, and 89 (5%) had an abnormal prior stress test result. Admission rates were 92% (95% CI, 87%-98%) for patients with a prior abnormal stress test, 73% (95% CI, 67%-78%) for patients with a normal prior stress test, and 70% (95% CI, 67%-72%) for patients without a prior stress test. Adverse outcomes were the highest among patients with prior abnormal stress test but did not differ significantly between patients with no prior stress test and patients with prior normal stress test (10.1% [95% CI, 3.6-16.7%] vs 5.2% [95% CI, 4.1-6.4%] vs 4.8% [95% CI, 2.4-7.3%]). CONCLUSION: Patients without prior stress tests and patients with prior normal stress tests were admitted for potential ACS at the same rate and had the same 30-day cardiovascular event rates. This suggests that prior stress testing does not affect subsequent disposition decisions. Perhaps cardiac catheterization or computed tomography coronary angiograms would have more of an impact on subsequent visits, making them potentially more cost-effective in the low-risk patient.

Chest Pain↗
PubMed2007

Hypothesis: chest pain in primary spontaneous pneumothorax.

The mechanism of chest pain in spontaneous pneumothorax has never been discussed in the literature. It is proposed that this is due to acute parietal pleural irritation secondary to leakage of inflammatory material following bleb rupture, rather than the presence of interpleural air.

Chest Pain↗