Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
February 5, 2026CIN Computers Informatics Nursing

Development of a Machine-Learning Model for Predicting Postoperative Complication Occurrence After Radical Gastrectomy Using Electronic Medical Records

View Full Paper
Ask AI
Bookmark
Share

Authors

SLSuyeon LimUniversity of MichiganJCJa Yun ChoiChonnam National University

Discussion

Loading...

Member takes

Implication

Develops a machine-learning model predicting postoperative complications in gastric cancer patients, suggesting earlier interventions for high-risk individuals.

Key Points

  • The aim is to create a machine-learning model that can accurately predict complications following radical gastrectomy.
  • Analyzed electronic medical records from 4892 patients who underwent radical gastrectomy between January 2012 and March 2022.
  • Identified 32 predictors related to postoperative outcomes and matched them to the records.
  • Developed 5 machine-learning models: logistic regression, random forest, extreme gradient boosting, CatBoost, and multilayer perceptron.
  • Assessed model performance using F1 score, accuracy, and area under the precision-recall curve.
  • Identified key predictors through permutation-based feature importance.
  • The random forest model achieved an F1 score of 0.86, accuracy of 0.95, and an area under the precision-recall curve of 0.90.
  • Key predictors included late fever on postoperative days 4-7, pain management, operating time, age, and blood transfusions.
  • The model showed strong potential in helping nurses identify high-risk patients for early intervention.

Cite This Study

Lim et al. (2026) studied this question.

synapsesocial.com/papers/69843405f1d9ada3c1fb1a2bhttps://doi.org/10.1097/cin.0000000000001486
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Development and validation of an interpretable Markov-embedded multilabel model for predicting risks of multiple postoperative complications among surgical inpatients: a multicenter prospective cohort study2023 · 8 citations
  2. 2Exploring the Interplay of Dataset Size and Imbalance on CNN Performance in Healthcare: Using X-rays to Identify COVID-19 Patients2024 · 21 citations
  3. 3ECOG and BMI as preoperative risk factors for severe postoperative complications in ovarian cancer patients: results of a prospective study (RISC-GYN—trial)2021 · 35 citations
  4. 4Short-term outcomes of distal gastrectomy versus total gastrectomy for gastric cancer under enhanced recovery after surgery: a propensity score-matched analysis2024 · 5 citations
  5. 5The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression2022 · 369 citations