Understanding risk factors for postoperative mortality in neonates based on explainable machine learning technology

Hu, Yinan; Gong, Xiaojue; Shu, Liqi; Zeng, Xian; Duan, Huilong; Luo, Qinyu; Zhang, Baihui; Ji, Yongming; Shu, Qiang; Li, Haomin

doi:10.1016/j.jpedsurg.2021.03.057

Cited by 10 publications

(22 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although some prediction techniques like decision trees are transparent, the vast majority of artificial intelligence applications in medicine using deep learning techniques are black box in essence and have therefore no explanation for their prediction. This has led to the creation of several explainable AI methods in the past few years [ [70] , [71] , [72] ]. Accordingly, a new research area called Explainable AI aims to increase the explainability of black box models.…”

Section: Introductionmentioning

confidence: 99%

A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest

Rostami

Oussalah

2022

Informatics in Medicine Unlocked

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest

Rostami

Oussalah

2022

Informatics in Medicine Unlocked

View full text Add to dashboard Cite

“…Twenty-three articles9,19,21,23–25,27,29,30,32–34,36,37,39,41,42,44–46,48–50 (63.9%) reported precision metrics (area under the precision-recall curve, positive predictive value, or F1 score). Twenty-five articles9,20,21,23–28,31,33,34,36,38,40,42–50 (69.4%) included explainability mechanisms to convey the relative importance of input features in determining outputs. Thirteen articles9,16,17,20,25,27,29,30,35,38,45,46,50 (36.1%) presented a framework that could be used for clinical implementation; none of the articles assessed the efficacy of clinical implementation.…”

Section: Resultsmentioning

confidence: 99%

“…Table 1 summarizes study populations, model architecture, performance, validation type, and explainability, and whether precision and implementation frameworks were reported. The overall sample size range was 163-2,882,526, with 8 22,23,[26][27][28]31,35,37 of 36 articles (22.2%) featuring sample sizes of less than 2000. The average AUROC for the best model across all 36 articles was 0.83; of the 8 articles with sample sizes of less than 2000 (ie, less than 1000 samples per class), 7 22,[26][27][28]31,35,37 (87.5%) had below-average (ie, less than 0.83) AUROC or accuracy.…”

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence–enabled Decision Support in Surgery

et al. 2023

View full text Add to dashboard Cite

Objective: To summarize state-of-the-art artificial intelligence-enabled decision support in surgery and to quantify deficiencies in scientific rigor and reporting. Background: To positively affect surgical care, decision-support models must exceed current reporting guideline requirements by performing external and real-time validation, enrolling adequate sample sizes, reporting model precision, assessing performance across vulnerable populations, and achieving clinical implementation; the degree to which published models meet these criteria is unknown. Methods: Embase, PubMed, and MEDLINE databases were searched from their inception to September 21, 2022 for articles describing artificial intelligence-enabled decision support in surgery that uses preoperative or intraoperative data elements to predict complications within 90 days of surgery. Scientific rigor and reporting criteria were assessed and reported according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines. Results: Sample size ranged from 163-2,882,526, with 8/36 articles (22.2%) featuring sample sizes of less than 2000; 7 of these 8 articles (87.5%) had below-average (< 0.83) area under the receiver operating characteristic or accuracy. Overall, 29 articles (80.6%) performed internal validation only, 5 (13.8%) performed external validation, and 2 (5.6%) performed real-time validation. Twenty-three articles (63.9%) reported precision. No articles reported performance across sociodemographic categories. Thirteen articles (36.1%) presented a framework that could be used for clinical implementation; none assessed clinical implementation efficacy. Conclusions: Artificial intelligence-enabled decision support in surgery is limited by reliance on internal validation, small sample sizes that risk overfitting and sacrifice predictive performance, and failure to report confidence intervals, precision, equity analyses, and clinical implementation. Researchers should strive to improve scientific quality.

show abstract

“…Still, these models also have several shortcomings. For one, they are all black box algorithms [52][53][54] . Although RF can be used to evaluate the relative importance of each variable, it is di cult to solve the relationship between variables in the model.…”

Section: Discussionmentioning

confidence: 99%

Risk prediction of gestational diabetes mellitus with four machine learning models

Yue

Pan

zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Purpose To construct and compare machine learning models for predicting the risk of gestational diabetes mellitus (GDM). Method The clinical data of 2048 pregnant women who gave birth at Shunde Women’s and Children’s Hospital of Guangdong Medical University between June 2019 and June 2021 were retrospectively collected. Logistic regression, backpropagation neural networks, random forests, and support vector machines were constructed with the R studio and Python software programs. The logistic regression and random forest models were used to identify significant influencing factors. The area under the receiver operating characteristic curve (AUC) was used to evaluate the predictive performance and discriminative ability of the models, and the Hosmer-Lemeshow test was used to determine goodness of fit. Results Age, glycated hemoglobin, fasting blood glucose, white blood cell count, hemoglobin, and activated partial prothrombin time were identified as significant factors associated with GDM. The random forest model had the best prediction effect (accuracy, 78.07%; Youden index, 1.56). In all four models, AUC was greater than 78%. The Hosmer–Lemeshow fit test showed that all four models were a good fit. Conclusion It was concluded that age, GHB, FBG, WBC, HB, and APTT are the more important related influencing factors or early predictors of gestational diabetes. Among the tested models, random forest was the best one for predicting the risk of GDM in early pregnancy.

show abstract

Understanding risk factors for postoperative mortality in neonates based on explainable machine learning technology

Cited by 10 publications

References 11 publications

A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest

A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest

Artificial Intelligence–enabled Decision Support in Surgery

Risk prediction of gestational diabetes mellitus with four machine learning models

Contact Info

Product

Resources

About