Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review

Abstract Introduction There was limited evidence on the quality of reporting and methodological quality of prediction models using machine learning methods in preterm birth. This systematic review aimed to assess the reporting quality and risk of bias of a machine learning‐based prediction model in...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiuyu Yang, Xia Fan, Xiao Cao, Weijie Hao, Jiale Lu, Jia Wei, Jinhui Tian, Min Yin, Long Ge
Format: Article
Language:English
Published: Wiley 2023-01-01
Series:Acta Obstetricia et Gynecologica Scandinavica
Subjects:
Online Access:https://doi.org/10.1111/aogs.14475
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849422837501132800
author Qiuyu Yang
Xia Fan
Xiao Cao
Weijie Hao
Jiale Lu
Jia Wei
Jinhui Tian
Min Yin
Long Ge
author_facet Qiuyu Yang
Xia Fan
Xiao Cao
Weijie Hao
Jiale Lu
Jia Wei
Jinhui Tian
Min Yin
Long Ge
author_sort Qiuyu Yang
collection DOAJ
description Abstract Introduction There was limited evidence on the quality of reporting and methodological quality of prediction models using machine learning methods in preterm birth. This systematic review aimed to assess the reporting quality and risk of bias of a machine learning‐based prediction model in preterm birth. Material and methods We conducted a systematic review, searching the PubMed, Embase, the Cochrane Library, China National Knowledge Infrastructure, China Biology Medicine disk, VIP Database, and WanFang Data from inception to September 27, 2021. Studies that developed (validated) a prediction model using machine learning methods in preterm birth were included. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement and Prediction model Risk of Bias Assessment Tool (PROBAST) to evaluate the reporting quality and the risk of bias of included studies, respectively. Findings were summarized using descriptive statistics and visual plots. The protocol was registered in PROSPERO (no. CRD 42022301623). Results Twenty‐nine studies met the inclusion criteria, with 24 development‐only studies and 5 development‐with‐validation studies. Overall, TRIPOD adherence per study ranged from 17% to 79%, with a median adherence of 49%. The reporting of title, abstract, blinding of predictors, sample size justification, explanation of model, and model performance were mostly poor, with TRIPOD adherence ranging from 4% to 17%. For all included studies, 79% had a high overall risk of bias, and 21% had an unclear overall risk of bias. The analysis domain was most commonly rated as high risk of bias in included studies, mainly as a result of small effective sample size, selection of predictors based on univariable analysis, and lack of calibration evaluation. Conclusions Reporting and methodological quality of machine learning‐based prediction models in preterm birth were poor. It is urgent to improve the design, conduct, and reporting of such studies to boost the application of machine learning‐based prediction models in preterm birth in clinical practice.
format Article
id doaj-art-ca68e1ccd433462cb8314b06ade3cc25
institution Kabale University
issn 0001-6349
1600-0412
language English
publishDate 2023-01-01
publisher Wiley
record_format Article
series Acta Obstetricia et Gynecologica Scandinavica
spelling doaj-art-ca68e1ccd433462cb8314b06ade3cc252025-08-20T03:30:53ZengWileyActa Obstetricia et Gynecologica Scandinavica0001-63491600-04122023-01-01102171410.1111/aogs.14475Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic reviewQiuyu Yang0Xia Fan1Xiao Cao2Weijie Hao3Jiale Lu4Jia Wei5Jinhui Tian6Min Yin7Long Ge8Evidence‐Based Nursing Center, School of Nursing Lanzhou University Lanzhou ChinaDepartment of Obstetrics and Gynecology, The Second School of Clinical Medicine Shanxi University of Chinese Medicine Shanxi ChinaEvidence‐Based Nursing Center, School of Nursing Lanzhou University Lanzhou ChinaEvidence‐Based Social Science Research Center, School of Public Health Lanzhou University Lanzhou ChinaEvidence‐Based Social Science Research Center, School of Public Health Lanzhou University Lanzhou ChinaEvidence‐Based Social Science Research Center, School of Public Health Lanzhou University Lanzhou ChinaKey Laboratory of Evidence Based Medicine and Knowledge Translation of Gansu Province Lanzhou ChinaHealth Examination Center The First Hospital of Lanzhou University Lanzhou ChinaEvidence‐Based Social Science Research Center, School of Public Health Lanzhou University Lanzhou ChinaAbstract Introduction There was limited evidence on the quality of reporting and methodological quality of prediction models using machine learning methods in preterm birth. This systematic review aimed to assess the reporting quality and risk of bias of a machine learning‐based prediction model in preterm birth. Material and methods We conducted a systematic review, searching the PubMed, Embase, the Cochrane Library, China National Knowledge Infrastructure, China Biology Medicine disk, VIP Database, and WanFang Data from inception to September 27, 2021. Studies that developed (validated) a prediction model using machine learning methods in preterm birth were included. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement and Prediction model Risk of Bias Assessment Tool (PROBAST) to evaluate the reporting quality and the risk of bias of included studies, respectively. Findings were summarized using descriptive statistics and visual plots. The protocol was registered in PROSPERO (no. CRD 42022301623). Results Twenty‐nine studies met the inclusion criteria, with 24 development‐only studies and 5 development‐with‐validation studies. Overall, TRIPOD adherence per study ranged from 17% to 79%, with a median adherence of 49%. The reporting of title, abstract, blinding of predictors, sample size justification, explanation of model, and model performance were mostly poor, with TRIPOD adherence ranging from 4% to 17%. For all included studies, 79% had a high overall risk of bias, and 21% had an unclear overall risk of bias. The analysis domain was most commonly rated as high risk of bias in included studies, mainly as a result of small effective sample size, selection of predictors based on univariable analysis, and lack of calibration evaluation. Conclusions Reporting and methodological quality of machine learning‐based prediction models in preterm birth were poor. It is urgent to improve the design, conduct, and reporting of such studies to boost the application of machine learning‐based prediction models in preterm birth in clinical practice.https://doi.org/10.1111/aogs.14475machine learningprediction modelpreterm birthquality of reportingrisk of biassystematic review
spellingShingle Qiuyu Yang
Xia Fan
Xiao Cao
Weijie Hao
Jiale Lu
Jia Wei
Jinhui Tian
Min Yin
Long Ge
Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review
Acta Obstetricia et Gynecologica Scandinavica
machine learning
prediction model
preterm birth
quality of reporting
risk of bias
systematic review
title Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review
title_full Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review
title_fullStr Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review
title_full_unstemmed Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review
title_short Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review
title_sort reporting and risk of bias of prediction models based on machine learning methods in preterm birth a systematic review
topic machine learning
prediction model
preterm birth
quality of reporting
risk of bias
systematic review
url https://doi.org/10.1111/aogs.14475
work_keys_str_mv AT qiuyuyang reportingandriskofbiasofpredictionmodelsbasedonmachinelearningmethodsinpretermbirthasystematicreview
AT xiafan reportingandriskofbiasofpredictionmodelsbasedonmachinelearningmethodsinpretermbirthasystematicreview
AT xiaocao reportingandriskofbiasofpredictionmodelsbasedonmachinelearningmethodsinpretermbirthasystematicreview
AT weijiehao reportingandriskofbiasofpredictionmodelsbasedonmachinelearningmethodsinpretermbirthasystematicreview
AT jialelu reportingandriskofbiasofpredictionmodelsbasedonmachinelearningmethodsinpretermbirthasystematicreview
AT jiawei reportingandriskofbiasofpredictionmodelsbasedonmachinelearningmethodsinpretermbirthasystematicreview
AT jinhuitian reportingandriskofbiasofpredictionmodelsbasedonmachinelearningmethodsinpretermbirthasystematicreview
AT minyin reportingandriskofbiasofpredictionmodelsbasedonmachinelearningmethodsinpretermbirthasystematicreview
AT longge reportingandriskofbiasofpredictionmodelsbasedonmachinelearningmethodsinpretermbirthasystematicreview