Post

New research · AI in Medicine
Pediatric surgery international · 1w
Cohort studyPediatric surgery international · 2026

Transfer learning prediction of 2-year native liver survival in biliary atresia following Kasai portoenterostomy using early perioperative biochemical data up to 3 months postoperatively.

Chuanping Xie, Wenqing Yan, Yong Zhao … Jinshi Huang
Read paper
AI in MedicineCohort study

Transfer-learning model predicted 2-year native liver survival after Kasai portoenterostomy for biliary atresia

Transfer learning prediction of 2-year native liver survival in biliary atresia following Kasai portoenterostomy using early perioperative biochemical data up to 3 months postoperatively.

Chuanping Xie … Jinshi Huang
Pediatric surgery international · 2026
Background

Biliary atresia (biliary atresia), a rare but life-threatening neonatal cholestatic disorder, necessitates Kasai portoenterostomy (kasai portoenterostomy) as the primary surgical intervention.

Methods

The study subjects were biliary atresia patients treated by a senior kasai portoenterostomy surgeon at our center (93 cases) and another senior kasai portoenterostomy surgeon at Jiangxi Children's Hospital (61 cases) from January 2017 to December 2022.

n = 154 patients
Results

how well the model separated infants whose own liver survived 2 years from those who needed a transplant; higher means b

AUC 0.86 (95% CI 0.74 to 0.95)
null 0
0.74
0.95
CI excludes the null - significant
More results

The five traditional machine learning models showed varying performance, with RF demonstrating the highest average AUC in the training set (AUC = 0.795, 95% CI 0.709-0.881).

GGT_3M, ALB_3M, DBIL_3M, DBIL_1M and GLO_1W were identified as the most critical predictive features.

More results

A transfer learning-based clinical decision support system was deployed, providing dynamic visualization of individualized 24-month native liver survival trajectories.

“
Conclusion · 1 of 2

Early perioperative biochemical data-driven machine learning models, enhanced by transfer learning, enable accurate prediction of 2-year native liver survival in biliary atresia.

Conclusion · 2 of 2

GGT_3M, ALB_3M, DBIL_3M, DBIL_1M, and GLO_1W are among the most influential predictors for 2-year native liver survival after kasai portoenterostomy procedure.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
AI / Informatics
88.5%
Top-5 genetic diagnoses were more accurate with Retina4IRD-assisted specialists.
Randomized Trial
88.2%
Model correctly classified 88.2% of children as achieving remission or not
Cohort Study
75.7%
This is the percentage of people with dementia that the sleep model correctly identified
Guideline
first 5 years
annual eye screening for damage can be delayed for this long if no risk factors
AI / Informatics
0.80
the AI's calls on who was at high psychosis risk were mostly correct
AI / Informatics
89%
Artificial intelligence/machine learning models correctly identified 89% of high-grade glioma recurrences and non-recurrences.
Cohort Study
4 percentage points
the new method improved the accuracy of survival prediction for rare cancers
Cohort Study
0.80
Model's accuracy score (AUROC) for spotting long COVID; 1.0 is perfect, 0.80 is good