loading page

Prediction of Clinical Outcomes in Women with Placenta Accreta Spectrum Using Machine Learning Models: An International Multicenter Study
  • +37
  • Sherif Shazly,
  • Ismet Hortu,
  • Jin-chung Shih,
  • Rauf Melekoglu,
  • Shangrong Fan,
  • Farhatulain ahmed,
  • Erbil Karaman,
  • Ildar Fatkullin,
  • Pedro Pinto,
  • Setyorini Irianti,
  • Joel Tochie,
  • Amr Abdelbadie,
  • A. Mete Ergenoglu,
  • Ahmet Yeniel,
  • Sermet Sagol,
  • Ismail Itil,
  • Jessica Kang,
  • KUAN-YING HUANG,
  • Ercan Yilmaz,
  • Yiheng Liang,
  • Hijab Aziz,
  • Tayyiba Akhter,
  • Afshan Ambreen,
  • Çağrı Ateş,
  • Yasemin Karaman,
  • Albir Khasanov ,
  • Larisa Fatkullina ,
  • Nariman Akhmadeev,
  • Adelina Vatanina ,
  • Ana Machado,
  • Nuno Montenegro,
  • Jusuf Effendi,
  • Dodi Suardi,
  • Ahmad Pramatirta,
  • Muhamad Aziz,
  • Amillia Siddiq,
  • Ingrid Ofakem,
  • Julius Dohbit,
  • Mohamed Fahmy,
  • Mohamed Anan
Sherif Shazly

Corresponding Author:sherify2k2@gmail.com

Author Profile
Ismet Hortu
Ege University
Author Profile
Jin-chung Shih
National Taiwan University Hospital, National Taiwan University College of Medicine
Author Profile
Rauf Melekoglu
Author Profile
Shangrong Fan
Peking University Shenzhen Hospital
Author Profile
Farhatulain ahmed
Department of Obstetrics and Gynaecology, Fatima Memorial Hospital, Punjab, Pakistan
Author Profile
Erbil Karaman
Yuzuncu Yil University Faculty of Medicine
Author Profile
Ildar Fatkullin
Kazan State Medical University
Author Profile
Pedro Pinto
Centro Hospitalar de São João EPE
Author Profile
Setyorini Irianti
Universitas Padjadjaran
Author Profile
Joel Tochie
Faculty of Medicine and Biomedical Sciences, University of Yaoundé I, Yaoundé, Cameroon
Author Profile
Amr Abdelbadie
Department of Obstetrics and Gynaecology, Aswan University Hospital, Aswan, Egypt
Author Profile
A. Mete Ergenoglu
Ege University
Author Profile
Ahmet Yeniel
Ege Universitesi
Author Profile
Sermet Sagol
Ege Universitesi
Author Profile
Ismail Itil
Ege Universitesi
Author Profile
Jessica Kang
National Taiwan University Hospital, National Taiwan University College of Medicine
Author Profile
KUAN-YING HUANG
National Taiwan University Hospital
Author Profile
Ercan Yilmaz
Inonu University School of Medicine
Author Profile
Yiheng Liang
Peking University
Author Profile
Hijab Aziz
Fatima Memorial Hospital
Author Profile
Tayyiba Akhter
Fatima Memorial Hospital
Author Profile
Afshan Ambreen
Fatima Memorial Hospital
Author Profile
Çağrı Ateş
Yuzuncu Yil University Faculty of Medicine
Author Profile
Yasemin Karaman
Van Lokman Hekim Hayat Hospital
Author Profile
Albir Khasanov
Kazan State Medical University
Author Profile
Larisa Fatkullina
Kazan State Medical University
Author Profile
Nariman Akhmadeev
Kazan State Medical University
Author Profile
Adelina Vatanina
Kazan State Medical University
Author Profile
Ana Machado
Centro Hospitalar de São João EPE
Author Profile
Nuno Montenegro
Centro Hospitalar de São João EPE
Author Profile
Jusuf Effendi
Universitas Padjadjaran
Author Profile
Dodi Suardi
Universitas Padjadjaran
Author Profile
Ahmad Pramatirta
Universitas Padjadjaran
Author Profile
Muhamad Aziz
Universitas Padjadjaran
Author Profile
Amillia Siddiq
Universitas Padjadjaran
Author Profile
Ingrid Ofakem
University of Yaounde I
Author Profile
Julius Dohbit
University of Yaounde I
Author Profile
Mohamed Fahmy
Aswan University
Author Profile
Mohamed Anan
Aswan University
Author Profile

Abstract

Objective: To establish a prediction model of clinical outcomes in women with placenta accreta spectrum (PAS) Design: Retrospective cohort study Setting: International multicenter study (PAS-ID); 11 centers from 9 countries Population: Women who were diagnosed with PAS and were managed in recruiting centers between January 1st, 2010 and December 31st, 2019. Methods: Data were collected using a standardized sheet, which included baseline information, medical and obstetric history, diagnosis, disease characteristics, management, and outcomes. Analysis of association between these variables and primary outcome was first conducted using conventional logistic regression. Data were reanalyzed using machine learning (ML) models, and 2 models were created to predict outcomes using antepartum and perioperative features. Main Outcome Measures: Massive PAS-associated perioperative blood loss (intraoperative blood loss ≥ 2500 ml, triggering massive transfusion protocol, or complicated by disseminated intravascular coagulopathy). Other outcomes include prolonged hospitalization > 7 days and admission to intensive care unit (ICU). Results: 727 women with PAS were included. Area under curve (AUC) for ML antepartum prediction model was 0.84, 0.81, and 0.82 for massive blood loss, prolonged hospitalization, and admission to ICU, respectively. Significant contributors to this model were parity, placental site, method of diagnosis and antepartum hemoglobin. Combing baseline and perioperative variables, ML model performed at 0.86, 0.90, and 0.86 for study outcomes, respectively. This model was most contributed by ethnicity, pelvic invasion, and uterine incision. Conclusions: ML models may be used to calculate individualized risk of morbidity in women with PAS, which may assist to outline management plan in priori
12 Dec 2022Published in The Journal of Maternal-Fetal & Neonatal Medicine volume 35 issue 25 on pages 6644-6653. 10.1080/14767058.2021.1918670