AI Article Synopsis
- The study aimed to evaluate a Bayesian network for improving the diagnosis accuracy of pyloric stenosis in infants, given that many ultrasounds have negative results despite clinical suspicion.
- Researchers analyzed records of 118 infants, training the network on 88 cases and testing its predictions against two groups of physicians - one using the Bayesian tool and the other relying on standard records.
- Results showed that the Bayesian network improved diagnostic accuracy (ROC 0.973 vs 0.882) and could potentially reduce unnecessary ultrasounds by 22% without missing any cases of pyloric stenosis.
Article Abstract
Purpose: Most infants undergoing an ultrasound to rule out pyloric stenosis will have a negative study, suggesting the low accuracy of clinical assessment. The purpose of this study was to evaluate the feasibility of using a Bayesian network to improve the accuracy of diagnosing pyloric stenosis.
Methods: Records of 118 infants undergoing an ultrasound to rule out pyloric stenosis were reviewed. Data from 88 (75%) infants were used to train a Bayesian decision network that predicted the probability of pyloric stenosis using risk factors, signs, and symptoms of the disease. The emergency department records of the remaining 28 (25%) infants were used to test the network. Two groups of pediatric surgeons and pediatric emergency medicine physicians were asked to predict the probability of pyloric stenosis in the testing set: (1) physicians using the network and (2) physicians using only emergency department records. Accuracy was evaluated using area under the ROC curve (discrimination) and Hosmer-Lemeshow (H-L) c-statistic (calibration).
Results: Physicians using the Bayesian decision network better predicted the probability of pyloric stenosis among infants in the testing set than those not using the network (ROC 0.973 vs 0.882; H-L c-statistic 3.9 [P > .05] vs 24.3 [P < .05]). Physicians using the network would have ordered 22% fewer ultrasounds and missed no cases of pyloric stenosis.
Conclusions: The use of a Bayesian decision network may improve the accuracy of physicians diagnosing infants with possible pyloric stenosis. Use of this decision tool may safely reduce the need for imaging among infants with suspected pyloric stenosis.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jpedsurg.2005.10.019 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The safety profile of azithromycin in pediatrics: a pharmacovigilance disproportionality analysis.
Expert Opin Drug Saf
December 2024
Department of Pharmacy, DaLi University First Affiliated Hospital, DaLi City, Yunnan Province, China.
Aim: To mine and analyze adverse drug events (ADEs) signals of azithromycin use in children in the real world to inform the safety assessment of azithromycin use in children.
Methods: ADE reports from the FDA Adverse Event Reporting System (FAERS) involving children (0-17 years) with azithromycin as the primary suspected drug from 2004 to early 2024 were extracted. ADEs were categorized using MedDRA, and signal detection was conducted using Reporting Odds Ratio (ROR) and Proportional Reporting Ratio (PRR).
Failure to thrive in infant secondary to congenital colonic stenosis: a case report.
J Surg Case Rep
December 2024
Department of Surgery, University of Miami, PO Box 016960 (C203), Miami, FL 33101, United States.
Congenital colonic stenosis (CCS) is a rare cause of intestinal obstruction, most commonly presenting in the neonatal period. We present a case of delayed CCS and describe the diagnostic challenges experienced. A 16-week-old female patient presented with persistent failure to thrive associated with signs of intestinal obstruction.
View Article and Find Full Text PDFArticle Synopsis
- A 60s male patient diagnosed with advanced gastric cancer (with pyloric stenosis and enlarged lymph nodes) experienced significant tumor reduction after two courses of chemotherapy before surgery.
- He underwent laparoscopic gastric jejunal bypass followed by distal gastrectomy and para-aortic lymph node dissection, with positive surgical results and no further tumor growth observed.
- After the operation, he received a year of adjuvant chemotherapy and has remained recurrence-free for 1.5 years, highlighting the effectiveness of preoperative treatment for this condition.
Recurrent Hypertrophic Pyloric Stenosis: Neonatal age and pyloric canal length as risk factors.
Pediatr Neonatol
November 2024
Department of Pediatric Surgery, Bab Al Hawa Hospital, Edlib, Syria; Department of Pediatric Surgery, DEVA Hospital, Aleppo, Syria; Scientific Committee of Pediatric Surgery in Syrian Board of Medical Specialities (SBOMS), Syria. Electronic address:
Long-term Gastrointestinal Sequelae in Children who Underwent Pyloromyotomy for Infantile Hypertrophic Pyloric Stenosis.
J Pediatr Surg
November 2024
Department of Pediatric Surgery, Emma Children's Hospital, Amsterdam UMC, University of Amsterdam and Vrije Universiteit Amsterdam, the Netherlands; Amsterdam Gastroenterology Endocrinology Metabolism, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam UMC, Amsterdam Reproduction and Development Research Institute, University of Amsterdam, Meibergdreef 9, Amsterdam, the Netherlands.
Article Synopsis
- The study aimed to assess the long-term gastrointestinal effects of pyloromyotomy in children who had undergone this surgery for infantile hypertrophic pyloric stenosis (IHPS) from 2007 to 2017.
- A questionnaire, including the Pediatric Quality of Life Inventory™ Gastrointestinal symptoms module, was completed by 199 participants, revealing that their GI symptoms scores were similar to those of healthy peers.
- The results suggest that long-term GI issues after pyloromyotomy are rare, indicating no significant difference in health outcomes between these children and healthy controls, which can help inform parents and lessen the need for extensive follow-up care.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!