Specific imaging features of intestinal perforation on supine abdominal X-ray evaluation in infants with necrotizing enterocolitis

Zhang, Han; Ling, Ke-Ran; Hu, Xiaoyu; Li, Wei; Li, Lu‐Quan

doi:10.1136/wjps-2020-000255

Cited by 5 publications

(4 citation statements)

References 25 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their follow-up NEC study, Lin et al reported that 77.8% of NEC patients were late preterm or term infants, and 90.3% of the infants had a birth weight of more than 1500 g based on a 10 years retrospective study [31]. Another study involving 598 NEC patients showed that the gestational age and birth weight of NEC perforated group were 36.57 (33.43-38.86) weeks and 2500 (2020-3200) g, respectively, and the gestational age and birth weight of NEC non-perforated group were 37.86 (35.14-39.21) weeks and 2800 (2250-3250) g, respectively [32]. In addition, a multicenter study that eventually included 449 NEC patients showed that 238 premature infants (53.0%) and 211 fullterm infants (47.0%) had intestinal perforation, importantly, 47 full-term infants also had intestinal perforation [33].…”

Section: Discussionmentioning

confidence: 99%

Risk factor analysis and nomogram prediction model construction for NEC complicated by intestinal perforation

Huang

Luo

Shi

et al. 2023

Preprint

View full text Add to dashboard Cite

Objective To investigate the clinical characteristics of neonatal necrotizing enterocolitis (NEC) complicated by intestinal perforation and predict the incidence of intestinal perforation in NEC. Methods Neonates diagnosed with NEC at the Affiliated Hospital of Zunyi Medical University from January 2012 to May 2022 were enrolled, and the clinical data were collected and analyzed retrospectively. The patients were divided into two groups based on intestinal perforation occurrence or not. Mann-Whitney U tests, t-tests, chi-square tests, and fisher's exact tests were performed between-group comparisons. Logistic and lasso regressions were applied to screen independent risk factors for concomitant bowel perforation, and R software (RMS package) was used to formulate the nomogram prediction model. In addition, the receiver operating curve (ROC) and the calibration curve were drawn to verify the predictive power, while decision curve analysis (DCA) was constructed to evaluate the clinical applicability of the nomogram model. Results 180 neonates with NEC were included, of which 48 had intestinal perforations, and 132 did not; the overall incidence of intestinal perforation was 26.67% (48/180). Bloody stool (OR = 5.60), APTT ≥ 50s (OR = 3.22), thrombocytopenia (OR = 4.74), and hypoalbuminemia (OR = 5.56) were identified as independent risk variables for NEC intestinal perforation (P < 0.05) through multivariate logistic regression analysis. These factors were then applied to develop a nomogram prediction model (C-index = 0.838) by using the R software. The area under the curve (AUC) for the nomogram in the training and validation cohorts were 0.838 (95% Cl: 0.768, 0.908) and 0.802 (95% CI: 0.659, 0.944), respectively. The calibration curve shown that the nomogram has a good predictive ability for predicting the risk of intestinal perforation occurrence. And the decision curve and clinical impact curve analyses demonstrated good clinical utility of the nomogram model. Conclusion We found that Bloody stool, APTT ≥ 50s, Thrombocytopenia, and hypoalbuminemia could be used as independent risk factors for predicting intestinal perforation in neonates with NEC. The nomogram model based on these variables had high predictive values to identify NEC patients with intestinal perforation.

show abstract

Section: Discussionmentioning

confidence: 99%

Risk factor analysis and nomogram prediction model construction for NEC complicated by intestinal perforation

Huang

Luo

Shi

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In their follow-up NEC study, Lin et al reported that 77.8% of NEC patients were late preterm or term infants, and 90.3% of the infants had a birth weight of more than 1500 g based on a 10 years retrospective study [ 28 ]. Another study involving 598 NEC patients showed that the gestational age and birth weight of NEC perforated group were 36.57 (33.43–38.86) weeks and 2500 (2020–3200) g, respectively, and the gestational age and birth weight of NEC non-perforated group were 37.86 (35.14–39.21) weeks and 2800 (2250–3250) g, respectively [ 29 ]. In addition, a multicenter study that eventually included 449 NEC patients showed that 238 premature infants (53.0%) and 211 full-term infants (47.0%) had intestinal perforation, importantly, 47 full-term infants also had intestinal perforation [ 30 ].…”

Section: Discussionmentioning

confidence: 99%

Risk factor analysis and nomogram prediction model construction for NEC complicated by intestinal perforation

Huang,

Luo,

Shi

et al. 2024

BMC Pediatr

View full text Add to dashboard Cite

Objective To investigate the clinical characteristics of neonatal necrotizing enterocolitis (NEC) complicated by intestinal perforation and predict the incidence of intestinal perforation in NEC. Methods Neonates diagnosed with NEC at the Affiliated Hospital of Zunyi Medical University from January 2012 to May 2022 were enrolled, and the clinical data were collected and analyzed retrospectively. The patients were divided into two groups based on intestinal perforation occurrence or not. Mann-Whitney U tests, t-tests, chi-square tests, and fisher’s exact tests were performed between-group comparisons. Logistic and lasso regressions were applied to screen independent risk factors for concomitant bowel perforation, and R software (RMS package) was used to formulate the nomogram prediction model. In addition, the receiver operating curve (ROC) and the calibration curve were drawn to verify the predictive power, while decision curve analysis (DCA) was constructed to evaluate the clinical applicability of the nomogram model. Results One hundred eighty neonates with NEC were included, of which 48 had intestinal perforations, and 132 did not; the overall incidence of intestinal perforation was 26.67% (48/180). Bloody stool (OR = 5.60), APTT ≥ 50 s (OR = 3.22), thrombocytopenia (OR = 4.74), and hypoalbuminemia (OR = 5.56) were identified as independent risk variables for NEC intestinal perforation (P < 0.05) through multivariate logistic regression analysis. These factors were then applied to develop a nomogram prediction model (C-index = 0.838) by using the R software. The area under the curve (AUC) for the nomogram in the training and validation cohorts were 0.838 (95% Cl: 0.768, 0.908) and 0.802 (95% CI: 0.659, 0.944), respectively. The calibration curve shown that the nomogram has a good predictive ability for predicting the risk of intestinal perforation occurrence. And the decision curve and clinical impact curve analyses demonstrated good clinical utility of the nomogram model. Conclusion We found that Bloody stool, APTT ≥ 50 s, Thrombocytopenia, and hypoalbuminemia could be used as independent risk factors for predicting intestinal perforation in neonates with NEC. The nomogram model based on these variables had high predictive values to identify NEC patients with intestinal perforation.

show abstract

“…In recent years, deep learning has seen extensive application in diagnosing traumatic bone fractures (10), pulmonary nodules (11), COVID-19 (12), and in classifying pneumonia as well as in image segmentation (13,14). Deep learning neural networks, by mimicking the human brain, automatically learn and recognize patterns in images, offering an edge in processing complex image data (15).…”

Section: Introductionmentioning

confidence: 99%

Enhancing surgical decision-making in NEC with ResNet18: a deep learning approach to predict the need for surgery through x-ray image analysis

Wu,

Zhuo,

Liu

et al. 2024

Front. Pediatr.

View full text Add to dashboard Cite

BackgroundNecrotizing enterocolitis (NEC) is a severe neonatal intestinal disease, often occurring in preterm infants following the administration of hyperosmolar formula. It is one of the leading causes of neonatal mortality in the NICU, and currently, there are no clear standards for surgical intervention, which typically depends on the joint discretion of surgeons and neonatologists. In recent years, deep learning has been extensively applied in areas such as image segmentation, fracture and pneumonia classification, drug development, and pathological diagnosis.ObjectiveInvestigating deep learning applications using bedside x-rays to help optimizing surgical decision-making in neonatal NEC.MethodsThrough a retrospective analysis of anteroposterior bedside chest and abdominal x-rays from 263 infants diagnosed with NEC between January 2015 and April 2023, including a surgery group (94 cases) and a non-surgery group (169 cases), the infants were divided into a training set and a validation set in a 7:3 ratio. Models were built based on Resnet18, Densenet121, and SimpleViT to predict whether NEC patients required surgical intervention. Finally, the model's performance was tested using an additional 40 cases, including both surgical and non-surgical NEC cases, as a test group. To enhance the interpretability of the models, the study employed 2D-Grad-CAM technology to describe the models’ focus on significant areas within the x-ray images.ResultsResnet18 demonstrated outstanding performance in binary diagnostic capability, achieving an accuracy of 0.919 with its precise lesion imaging and interpretability particularly highlighted. Its precision, specificity, sensitivity, and F1 score were significantly high, proving its advantages in optimizing surgical decision-making for neonatal NEC.ConclusionThe Resnet18 deep learning model, constructed using bedside chest and abdominal imaging, effectively assists clinical physicians in determining whether infants with NEC require surgical intervention.

show abstract

Specific imaging features of intestinal perforation on supine abdominal X-ray evaluation in infants with necrotizing enterocolitis

Cited by 5 publications

References 25 publications

Risk factor analysis and nomogram prediction model construction for NEC complicated by intestinal perforation

Risk factor analysis and nomogram prediction model construction for NEC complicated by intestinal perforation

Risk factor analysis and nomogram prediction model construction for NEC complicated by intestinal perforation

Enhancing surgical decision-making in NEC with ResNet18: a deep learning approach to predict the need for surgery through x-ray image analysis

Contact Info

Product

Resources

About